University of Isfahan Journal of Stratigraphy and Sedimentology Researches 2008-7888 41 2 2025 06 22 Sedimentary environment analysis of the Asmari Formation (Upper Rupelian) based on microfossils in Bandar Abbas Hinterland, south Iran Sedimentary environment analysis of the Asmari Formation (Upper Rupelian) based on microfossils in Bandar Abbas Hinterland, south Iran 1 20 29378 10.22108/jssr.2025.142715.1295 FA Jahanbakhsh Daneshian Professor in Geology, Department of Geology, Faculty of Earth Science, Kharazmi University, Tehran, Iran Mahboobeh Sadat Tabatabaei Ph.D. in Geology, Department of Geology, Faculty of Earth Science, Kharazmi University, Tehran, Iran Alireza Tahmasbi Paleontology and Geochemistry Research and Studies, Exploration Directorate, National Iranian Oil Company, Tehran, Iran Journal Article 2024 09 07 Abstract In this research, facies distribution and sedimentary environment of the Asmari Formation have been studied in Bandar Abbas Hinterland, located in southern Iran. For this purpose, two outcrop sections including Khamir and Gachestan have been selected in this area. The study of thin sections of Khamir (160 m-thick) and Gachestan sections (220 m-thick) and their components led us to identify nine microfacies. In this research, the role of microfossils, especially foraminifera is investigated in the detection of microfacies and sedimentary environment. Based on the sedimentary texture and the type of fossils, the depositional environments were identified. The components are mostly larger benthic foraminifera and red algae, which indicate the middle ramp, and also the accumulation of imperforate foraminifera, which indicates the inner ramp. Based on this, the sedimentary model for the Asmari Formation in the study area was attributed to a carbonate ramp, which can be divided into three sub-environments: inner, middle and outer ramp. Keywords: Asmari Formation, Rupelian, depositional environments, Bandar Abbas Hinterland Introduction The carbonates of the Asmari Formation are the main petroleum reservoir rock in the Zagros Basin. Primary works concerning the Asmari Formation are attributed to Busk and Mayo (1918), Richardson (1924 and Thomas (1948). The age of this rock unit is Oligocene to Early Miocene (Burdigalian). In Fars province, this formation belongs to the Oligocene, while in Khuzestan, the age is Oligocene to Early Miocene and towards the basin center, this rock unit belongs to Early Miocene (Aquitanian–Burdigalian). Considering the importance of the Asmari Formation in the Zagros Basin and the fact that studies conducted on this formation have been mostly in the Fars and Izeh zones, this study focuses on depositional environment reconstruction of the Asmari Formation in Bandar Abbas hinterland in southern Iran. Materials & Methods The study is based on two outcrops in Bandar Abbas hinterland in southern Iran. Kuh-e Khamir section with coordinates of 27°, 00ʹ, 35ʹʹ N and 55°, 35ʹ, 13ʹʹ E, and Gachestan section with coordinates of 26°, 54ʹ, 04ʹʹ N and 54°, 05ʹ, 22ʹʹ E. The microfacies studies are based on 250 thin sections of the examined sections. All thin sections were analyzed under the microscope for biostratigraphy and facies. The classification of carbonate rocks followed the nomenclature of Dunham (1962) as well as the modified scheme of Embry and Klovan (1971). In addition, microfacies were determined based on Flügel (2020). Discussion of Results & Conclusions Facies analysis of the Asmari Formation in study outcrops including Khamir (160 m-thick) and Gachestan (220 m-thick) sections resulted in the definition of nine microfacies types as follows: Bioclastic planktonic foraminifera wackestone/packstone (MF1): The presence of planktonic foraminifera, muddy matrix and lack of sedimentary structures suggest that this facies were deposited in calm and deep, normal-salinity seawater below the storm wave base. Bioclastic Nummulitid packstone/grainstone (MF2): Abundance of larger and flat nummulitids with some planktonic foraminifera suggest low-medium energy, open-marine environment, and between the storm and fair-weather wave base. Bioclastic nummulitid red algae floatstone/packstone (MF3): The presence of corallinacean algae and larger benthic foraminifera suggest a distal part of inner to mid-ramp sub-environments and indicate an oligophotic zone. Bioclastic coral- red algae floatstone/rudstone (MF4): This facies is interpreted to have been deposited under shallow water with moderate energy below the fair-weather wave base in the middle ramp sub-environment. Bioclastic imperforate foraminifera nummulitid packstone (MF5): The faunal composition indicates that sedimentation took place in the lagoon with normal circulation and well-oxygenated waters. The presence of large porcelaneous foraminifers associated with Nummulitid suggests deposition in the euphotic zone in an open-lagoonal environment. Bioclastic imperforate foraminifera packstone (MF6): This facies represents a high-energy, shallow-water setting influenced by wave and tide processes. In addition, the presence of Peneroplis and Archaias in this facies indicates a sea grass-dominated environment. Bioclastic small benthic foraminifera echinoid wackestone/packstone (MF7): The low diversity of fauna (small rotaliids and echinoid debris) suggests a low-energy environment in the shallow water of the inner ramp sub-environment. Bioclastic miliolids wackestone/packstone (MF8): This microfacies is interpreted as the restricted shallow inner ramp sub-environment. Low diversity and abundance of imperforate foraminifera and mud-rich facies indicate deposition in a low-energy, restricted shallow lagoon. Mudstone (MF9): Accumulation of carbonate mud suggests the low energy conditions in the lagoonal-peritidal and proximal inner ramp sub-environment. A detail study of the Asmari Formation in two outcrop sections represents the development of a carbonate ramp as a sedimentary model during the Rupelian. The Carbonate ramp can be divided into three inner, middle and outer ramp sub-environments their boundary can be distinct based on the water depth of fair-weather wave and storm wave base. In this study outer ramp represents with microfacies MF1 and the dominant fauna is planktonic foraminifera. The middle ramp is shown with the presence of microfacies 2–4 (MF2–4). This environment is dominant in large benthic foraminifera, red algae and coral. The inner ramp setting is represented by an abundance of imperforate foraminifera, so microfacies 5 to 9 (MF5–9) are deposited in this sub-environment. Abstract In this research, facies distribution and sedimentary environment of the Asmari Formation have been studied in Bandar Abbas Hinterland, located in southern Iran. For this purpose, two outcrop sections including Khamir and Gachestan have been selected in this area. The study of thin sections of Khamir (160 m-thick) and Gachestan sections (220 m-thick) and their components led us to identify nine microfacies. In this research, the role of microfossils, especially foraminifera is investigated in the detection of microfacies and sedimentary environment. Based on the sedimentary texture and the type of fossils, the depositional environments were identified. The components are mostly larger benthic foraminifera and red algae, which indicate the middle ramp, and also the accumulation of imperforate foraminifera, which indicates the inner ramp. Based on this, the sedimentary model for the Asmari Formation in the study area was attributed to a carbonate ramp, which can be divided into three sub-environments: inner, middle and outer ramp. Keywords: Asmari Formation, Rupelian, depositional environments, Bandar Abbas Hinterland Introduction The carbonates of the Asmari Formation are the main petroleum reservoir rock in the Zagros Basin. Primary works concerning the Asmari Formation are attributed to Busk and Mayo (1918), Richardson (1924 and Thomas (1948). The age of this rock unit is Oligocene to Early Miocene (Burdigalian). In Fars province, this formation belongs to the Oligocene, while in Khuzestan, the age is Oligocene to Early Miocene and towards the basin center, this rock unit belongs to Early Miocene (Aquitanian–Burdigalian). Considering the importance of the Asmari Formation in the Zagros Basin and the fact that studies conducted on this formation have been mostly in the Fars and Izeh zones, this study focuses on depositional environment reconstruction of the Asmari Formation in Bandar Abbas hinterland in southern Iran. Materials & Methods The study is based on two outcrops in Bandar Abbas hinterland in southern Iran. Kuh-e Khamir section with coordinates of 27°, 00ʹ, 35ʹʹ N and 55°, 35ʹ, 13ʹʹ E, and Gachestan section with coordinates of 26°, 54ʹ, 04ʹʹ N and 54°, 05ʹ, 22ʹʹ E. The microfacies studies are based on 250 thin sections of the examined sections. All thin sections were analyzed under the microscope for biostratigraphy and facies. The classification of carbonate rocks followed the nomenclature of Dunham (1962) as well as the modified scheme of Embry and Klovan (1971). In addition, microfacies were determined based on Flügel (2020). Discussion of Results & Conclusions Facies analysis of the Asmari Formation in study outcrops including Khamir (160 m-thick) and Gachestan (220 m-thick) sections resulted in the definition of nine microfacies types as follows: Bioclastic planktonic foraminifera wackestone/packstone (MF1): The presence of planktonic foraminifera, muddy matrix and lack of sedimentary structures suggest that this facies were deposited in calm and deep, normal-salinity seawater below the storm wave base. Bioclastic Nummulitid packstone/grainstone (MF2): Abundance of larger and flat nummulitids with some planktonic foraminifera suggest low-medium energy, open-marine environment, and between the storm and fair-weather wave base. Bioclastic nummulitid red algae floatstone/packstone (MF3): The presence of corallinacean algae and larger benthic foraminifera suggest a distal part of inner to mid-ramp sub-environments and indicate an oligophotic zone. Bioclastic coral- red algae floatstone/rudstone (MF4): This facies is interpreted to have been deposited under shallow water with moderate energy below the fair-weather wave base in the middle ramp sub-environment. Bioclastic imperforate foraminifera nummulitid packstone (MF5): The faunal composition indicates that sedimentation took place in the lagoon with normal circulation and well-oxygenated waters. The presence of large porcelaneous foraminifers associated with Nummulitid suggests deposition in the euphotic zone in an open-lagoonal environment. Bioclastic imperforate foraminifera packstone (MF6): This facies represents a high-energy, shallow-water setting influenced by wave and tide processes. In addition, the presence of Peneroplis and Archaias in this facies indicates a sea grass-dominated environment. Bioclastic small benthic foraminifera echinoid wackestone/packstone (MF7): The low diversity of fauna (small rotaliids and echinoid debris) suggests a low-energy environment in the shallow water of the inner ramp sub-environment. Bioclastic miliolids wackestone/packstone (MF8): This microfacies is interpreted as the restricted shallow inner ramp sub-environment. Low diversity and abundance of imperforate foraminifera and mud-rich facies indicate deposition in a low-energy, restricted shallow lagoon. Mudstone (MF9): Accumulation of carbonate mud suggests the low energy conditions in the lagoonal-peritidal and proximal inner ramp sub-environment. A detail study of the Asmari Formation in two outcrop sections represents the development of a carbonate ramp as a sedimentary model during the Rupelian. The Carbonate ramp can be divided into three inner, middle and outer ramp sub-environments their boundary can be distinct based on the water depth of fair-weather wave and storm wave base. In this study outer ramp represents with microfacies MF1 and the dominant fauna is planktonic foraminifera. The middle ramp is shown with the presence of microfacies 2–4 (MF2–4). This environment is dominant in large benthic foraminifera, red algae and coral. The inner ramp setting is represented by an abundance of imperforate foraminifera, so microfacies 5 to 9 (MF5–9) are deposited in this sub-environment.

https://jssr.ui.ac.ir/article_29378_6ed74ec10547c0ef0e56176a4acc544e.pdf

University of Isfahan Journal of Stratigraphy and Sedimentology Researches 2008-7888 41 2 2025 06 22 Mineralogy and fluid inclusions investigation of the conglomerate-hosted Gharmorvarid occurrence, Southwest Arak, Iran Mineralogy and fluid inclusions investigation of the conglomerate-hosted Gharmorvarid occurrence, Southwest Arak, Iran 21 46 28752 10.22108/jssr.2024.141393.1287 FA Zahra Alaminia Associate Professor, Department of Geology, Faculty of Sciences, Ferdowsi University of Mashhad, Mashhad, Iran Journal Article 2024 05 06 Abstract The Gharmorvarid ore occurrence in southwest Arak, Iran, is located within the Malayer–Isfahan metallogenic province, which is hosted by a basal conglomerate of the Early Cretaceous sedimentary strata. Mineralization consists of galena and pyrite with trace amounts of chalcopyrite and sphalerite. Ore occurs as disseminated, replacement, mottled, and space-filling style. The gangue is dominated by quartz, ankerite, siderite, Fe-dolomite, calcite, sericite, biotite, chlorite, and minor barite. Our findings indicate a sequence of events during ore formation: euhedral quartz and fine-grained sulfide minerals are hosted within earlier diagenetic carbonate, galena with pervasive Fe-Mg-Mn-carbonate alteration occurred after them, leading to the dissolution (replacement) reaction in contact with quartz. Later minerals are characterized by coarse-grained quartz, galena, sericite, biotite, and chlorite. Primary fluid inclusions trapped in quartz and dolomite reveal that ore-forming fluid was intermediate saline, with a range from 3.7 to 16.2 wt % NaCl equiv. and had a medium to high temperature ranging from 151 to 330 ºC. The mineralization is controlled by a fault-fold structure. The Gharmorvarid mineralization is very similar to the sandstone-hosted Pb-Zn deposits along the margin of the Scandinavian Caledonides and in particular the Laisvall deposit in Sweden. Keywords: Conglomerate, Lead mineralization, SEM, Fluid inclusions, Arak. Introduction In comparison to lead-zinc deposits hosted by shales and limestones, few are located in sandstones and conglomerates. As a result, global demand for imbalanced mineral resources, such as conglomerate-hosted Pb-Zn deposits, has gradually increased. Recently, a large Pb-Zn deposit (Uragen) was discovered in China hosted by sandstones and conglomerates (Gao et al., 2022). In Iran, a notable concentration of lead and zinc deposits, along with mineral occurrences, is observed in the Lower Cretaceous sediments south of Arak. From a stratigraphic perspective, ore-bearing horizons are deposited in shale-carbonate units of the Cretaceous except for two mineral occurrences, Dokhaharan and Gharmorvarid, which are hosted in the Cretaceous basal conglomerates (Momenzadeh, 1976; Mahmoodi et al., 2021). Although numerous economic, geological studies have been conducted on the Arak deposits, no investigation has thus far focused specifically on the conglomerate-hosted Gharmorvarid deposit. This presents a promising opportunity for us to explore further. Material & Methods After examining the geological map, samples were collected from the mineralized outcrops and the host rock. Thin sections of all samples were studied by transmitted and reflected microscopy in the Economic Geology laboratory at the University of Isfahan. To identify the surface morphology and chemical composition, the samples were carbon-coated and examined with a Scanning Electron Microscope (SEM). Microthermometric measurements were carried out at the University of Isfahan using the Linkam THM600. The samples used all drive from the two host mineral phases of carbonate and quartz from the Gharmorvarid. Discussion of Results & Conclusions The Gharmorvarid anticline is situated approximately 7 kilometeres northeast of the Emarat. The stratigraphic successions of Gharmorvarid consist of two sedimentary strata including the Jurassic and the Cretaceous. The oldest rocks consist of medium-bedded sandstones, which has been overlain by the basal conglomerates of the Early Cretaceous. These sedimentary rocks are tectonically folded. Mineralization was controlled by the thrust systems and occurred within the conglomerates. The Conglomerate ranges from quartz arenite to subgreywacke, composed of grains consisting mainly of quartz, chert, lesser carbonates, opaque, and accessory minerals. This unit preserves evidence of two types of alteration: diagenetic and hydrothermal. Diagenetic processes have increased porosity and permeability, providing a suitable structure for the ore-bearing fluid flows. The major ore types of the Gharmorvarid are disseminated, replacement, semi-massive, and open space filling. The ore mineral is mainly coarse-grained galena. The common gangue minerals are quartz, Fe-Mg-Mn carbonates, pyrite, minor chlorite, sericite, and biotite. A number of fluid inclusions in quartz and carbonate minerals were measured for Th, which was found to range from 133 to 323 ºC. The salinity calculated from the final ice melting temperature was observed in the range of -2.2 to -12.3 ºC. These temperatures correspond to salinities ranging from 5.1 to 39.5 eq. wt.%. The Gharmorvarid ore occurrence is controlled by a fault-fold structure. The sedimentary succession of Gharmorvarid indicates that from the onset of deposition of the Early Cretaceous strata, the sedimentary basin exhibited a tendency towards subsidence and deepening. Mineralogical observations of the host rock suggest that the succession was deposited in a shallow coastal environment, which was influenced by diagenesis. However, in the upper horizons, which predominantly consist of carbonate sediments containing outlined features, there is evidence of basin deepening and the activity of syn-sedimentary faults. The results of this study align with the tectonic events of the Sanandaj–Sirjan zone and clearly demonstrate the transition in the tectonic regime from extensional to compressional. Therefore, it is proposed that, alongside basin subsidence during diagenesis, conditions were favorable for the mineralization in Gharmorvarid. During the orogeny in the Late Cretaceous, the faults were reactivated, and ore-bearing fluids migrated from deeper parts to shallow zones within the conglomerate unit through steep reverse faults. Consequently, the main mineralization was deposited between the particles of the host rock in Gharmorvarid due to mixing with seawater and intraformational fluids. Abstract The Gharmorvarid ore occurrence in southwest Arak, Iran, is located within the Malayer–Isfahan metallogenic province, which is hosted by a basal conglomerate of the Early Cretaceous sedimentary strata. Mineralization consists of galena and pyrite with trace amounts of chalcopyrite and sphalerite. Ore occurs as disseminated, replacement, mottled, and space-filling style. The gangue is dominated by quartz, ankerite, siderite, Fe-dolomite, calcite, sericite, biotite, chlorite, and minor barite. Our findings indicate a sequence of events during ore formation: euhedral quartz and fine-grained sulfide minerals are hosted within earlier diagenetic carbonate, galena with pervasive Fe-Mg-Mn-carbonate alteration occurred after them, leading to the dissolution (replacement) reaction in contact with quartz. Later minerals are characterized by coarse-grained quartz, galena, sericite, biotite, and chlorite. Primary fluid inclusions trapped in quartz and dolomite reveal that ore-forming fluid was intermediate saline, with a range from 3.7 to 16.2 wt % NaCl equiv. and had a medium to high temperature ranging from 151 to 330 ºC. The mineralization is controlled by a fault-fold structure. The Gharmorvarid mineralization is very similar to the sandstone-hosted Pb-Zn deposits along the margin of the Scandinavian Caledonides and in particular the Laisvall deposit in Sweden. Keywords: Conglomerate, Lead mineralization, SEM, Fluid inclusions, Arak. Introduction In comparison to lead-zinc deposits hosted by shales and limestones, few are located in sandstones and conglomerates. As a result, global demand for imbalanced mineral resources, such as conglomerate-hosted Pb-Zn deposits, has gradually increased. Recently, a large Pb-Zn deposit (Uragen) was discovered in China hosted by sandstones and conglomerates (Gao et al., 2022). In Iran, a notable concentration of lead and zinc deposits, along with mineral occurrences, is observed in the Lower Cretaceous sediments south of Arak. From a stratigraphic perspective, ore-bearing horizons are deposited in shale-carbonate units of the Cretaceous except for two mineral occurrences, Dokhaharan and Gharmorvarid, which are hosted in the Cretaceous basal conglomerates (Momenzadeh, 1976; Mahmoodi et al., 2021). Although numerous economic, geological studies have been conducted on the Arak deposits, no investigation has thus far focused specifically on the conglomerate-hosted Gharmorvarid deposit. This presents a promising opportunity for us to explore further. Material & Methods After examining the geological map, samples were collected from the mineralized outcrops and the host rock. Thin sections of all samples were studied by transmitted and reflected microscopy in the Economic Geology laboratory at the University of Isfahan. To identify the surface morphology and chemical composition, the samples were carbon-coated and examined with a Scanning Electron Microscope (SEM). Microthermometric measurements were carried out at the University of Isfahan using the Linkam THM600. The samples used all drive from the two host mineral phases of carbonate and quartz from the Gharmorvarid. Discussion of Results & Conclusions The Gharmorvarid anticline is situated approximately 7 kilometeres northeast of the Emarat. The stratigraphic successions of Gharmorvarid consist of two sedimentary strata including the Jurassic and the Cretaceous. The oldest rocks consist of medium-bedded sandstones, which has been overlain by the basal conglomerates of the Early Cretaceous. These sedimentary rocks are tectonically folded. Mineralization was controlled by the thrust systems and occurred within the conglomerates. The Conglomerate ranges from quartz arenite to subgreywacke, composed of grains consisting mainly of quartz, chert, lesser carbonates, opaque, and accessory minerals. This unit preserves evidence of two types of alteration: diagenetic and hydrothermal. Diagenetic processes have increased porosity and permeability, providing a suitable structure for the ore-bearing fluid flows. The major ore types of the Gharmorvarid are disseminated, replacement, semi-massive, and open space filling. The ore mineral is mainly coarse-grained galena. The common gangue minerals are quartz, Fe-Mg-Mn carbonates, pyrite, minor chlorite, sericite, and biotite. A number of fluid inclusions in quartz and carbonate minerals were measured for Th, which was found to range from 133 to 323 ºC. The salinity calculated from the final ice melting temperature was observed in the range of -2.2 to -12.3 ºC. These temperatures correspond to salinities ranging from 5.1 to 39.5 eq. wt.%. The Gharmorvarid ore occurrence is controlled by a fault-fold structure. The sedimentary succession of Gharmorvarid indicates that from the onset of deposition of the Early Cretaceous strata, the sedimentary basin exhibited a tendency towards subsidence and deepening. Mineralogical observations of the host rock suggest that the succession was deposited in a shallow coastal environment, which was influenced by diagenesis. However, in the upper horizons, which predominantly consist of carbonate sediments containing outlined features, there is evidence of basin deepening and the activity of syn-sedimentary faults. The results of this study align with the tectonic events of the Sanandaj–Sirjan zone and clearly demonstrate the transition in the tectonic regime from extensional to compressional. Therefore, it is proposed that, alongside basin subsidence during diagenesis, conditions were favorable for the mineralization in Gharmorvarid. During the orogeny in the Late Cretaceous, the faults were reactivated, and ore-bearing fluids migrated from deeper parts to shallow zones within the conglomerate unit through steep reverse faults. Consequently, the main mineralization was deposited between the particles of the host rock in Gharmorvarid due to mixing with seawater and intraformational fluids.

https://jssr.ui.ac.ir/article_28752_4babdef18e39abd2530f461d6912472b.pdf

University of Isfahan Journal of Stratigraphy and Sedimentology Researches 2008-7888 41 2 2025 06 22 Foraminiferal morphogroups of the Early–Middle Cretaceous succession in northeastern Rafsanjan and their significance as palaeoenvironmental bioindicators Foraminiferal morphogroups of the Early–Middle Cretaceous succession in northeastern Rafsanjan and their significance as palaeoenvironmental bioindicators 47 78 29376 10.22108/jssr.2025.144230.1307 FA Tayebeh Ahmadi Assistant professor, Department of Geology, Payame Noor University (PNU), Tehran, Iran Journal Article 2025 02 02 Abstract Foraminiferal morphogroups reveal their responses to palaeoenvironmental and palaeoecological changes. The foraminiferal morphogroups of the early-mid Cretaceous in northeastern Rafsanjan have been investigated with an interest in palaeoenvironmental changes. According to the shell forms, coiling modes, and life positions linked to the lifestyles and feeding strategies, eleven morphogroups, including one planktonic and ten benthic foraminiferal morphogroups, were identified. The planktonic morphogroup includes various species of the genus Hedbergella, showing an open marine eutrophic environment in the lower part of the section. In the upper part of the section, the bioclasts are characterized by the dominance of conical and discoidal orbitolinids. Their distribution patterns reflect changes in environmental conditions. In the initial and final intervals of the upper part, conical orbitolinids are dominated and associated with micro-encrusters (Lithocodium-Bacinella). The peloidal packstones to wackestones facies in these succession, demonstrate the low-energy conditions. This association suggests an oxygenated and shallow water lagoonal environment. However, a few numbers of planktonic foraminifera and oligosteginids in the final layers suggest a minor increase in depositional water depth. Discoidal orbitolinids and calcareous algae associated with skeletal fragments of invertebrates, ooids and detrital particles are the most common constituents of the middle intervals. Complete to partial micritization and micrite envelope around bioclasts are common. These suggest unstable, fluctuating environmental conditions with higher energy currents, resulting in the reworking of skeletal grains. The diverse fossil fauna, larger benthic foraminifera, and the predominance of epifaunal relative to infaunal foraminifera in most horizons of the upper part reflect a well-oxygenated and good trophic level environment. Keywords: Morphogroup, Foraminifera, Cretaceous, Palaeoecology. Introduction Foraminifera are good indicators of the ecological factors of ancient water environments, including palaeobathymetry, bottomwater dissolved oxygen, and primary productivity. In recent decades, some studies have been done to reconstruct the palaeoenvironment by using morphological (test form, life position, and feeding strategy) characteristics (Nagy et al. 2009). In this study, foraminifera fossils in the Earlt to Middle Cretaceous marine carbonate succession of northeastern Rafsanjan were analyzed to interpreting palaeoenvironmental conditions. Material & Methods A total of 65 benthic and planktonic foraminiferal genera were extracted from the 100 limestone samples in the Gezeresh section, 40 km northeastern Rafsanjan city, Kerman Province, Iran. Foraminifera were classified into morphological groups according to morphological features (general shape, mode of coiling, chamber arrangement, feeding strategy and life habitat). In this study, the morphogroups classification were modified from the planktonic morphogroup schemes of Premoli Silva and Sliter (1999), Lowery et al. (2014), Price and Hart (2002) as well as benthonic morphogroup schemes of Bernhard (1986); Jones and Charnock (1985), Koutsoukos and Hart (1990), Nagy (1992), Tyszka (1994), Szydlo (2004), Nagy et al. (2009), Reolid et al. (2008a,b), Reolid et al. (2012a,b) and Smolen (2012). Discussion of Results & Conclusions The microfaunal content of the Gezeresh section is dominated by foraminifera, but calcareous algal and vertebrate particles are also abundant in some horizons. Both benthic and planktonic foraminifera are present. Eleven morphogroups including, one planktonic and ten benthic foraminiferal morphogroups were identified according to morphological features (general shell morphology, aperture position, mode of coiling and number of chambers). Morphogroup MPA includes non-keeled, small-sized and simple morphotypes of trochospiral Hedbergella planktonic foraminiferal species. Most of the benthic tests are distributed within the following morphogroups: 1- Agglutinated foraminiferal morphogroups with a general dominance include AG-A to AG-G morphotypes. 2- Calcareous foraminiferal morphogroups comprising: porcelaneous (CP-A) and hyaline tests (CH-A and CH-B). Morphogroup AG-A includes rounded to plano-convex and biconvex multilocular shells with spiral chamber arrangement, planispiral and trochospiral coiled tests (Haplophragmoides, Nezzazata, Nezzazatinella Trochaminoides and Debarina). Morphogroup AG-B comprises flattened and discoidal forms (Glomospira, Glomospirella). Morphogroup AG-C includes elongated, subcylindric multilocular forms with infaunal habitats and it was divided into three subgroups: AG-C1 comprises uniserial tests (Reophax), AG-C2 consists of forms with a planispiral or streptospiral initial stage, later uniserial (Ammobaculites, Novalesia, Feurtillia, Turriglomina, Pseudolituonella) and AG-C3 consists of elongated biserial and triserial forms (Gaudryina, Textularia, Arenobulimina, etc.). Morphogroup AG-D comprises conical forms with a short early trochospiral initial stage followed by a more prominent biserial final stage (Cuneolina, Sabaudia Vercorsella and Akcaya). Morphogroup AG-E is represented by subspherical to flattened tests with early stages planispirally coiled and later uncoiled tests (Pseudocyclammina and Torremiroella). Morphogroup AG-F comprises finely agglutinated lenticular to subglobular forms and uncoiled tests in the last one or two chamber tests (Charentia, Mayncina and Nautiloculina). Morphogroup AG-G comprises larger benthic foraminifera with low to high conical tests and apically situated embryonal apparatus. The porcelaneous CP-A morphogroup was characterized by a discoidal flattened spiral and elongated test shape. The hyaline tests are distributed within the following morphogroups: Morphogroup CH-A consists of calcareous discoidal to flattened shapes (planispiral) and plano-convex (trochospiral) forms (Trocholina, Concospirillina, Neotrocnholina) and Morphogroup CH-B is composed of biconvex (lenticular), planispiral and multilocular forms (Lenticulina). The foraminiferal morphogroups identified in this study occur with different percentages throughout the analyzed succession. The distribution of foraminiferal assemblages in two lithostratigraphic units of the Gezeresh section shows the dominance of planktonic and benthic foraminifera (mainly orbitolinids) in the lower and upper parts of the section, respectively. The dominant planktonic taxa are Hedbergellidae (r-strategists) which reflects meso- to eutrophic conditions (Premoli Silva and Sliter 1999). The upper part of the studied section is characterized by mixed, diverse biota including various foraminifera, echinoderms, bivalves, corals and gastropods. Orbitolinids (mainly conical forms) are common. These levels indicate more favorable conditions for agglutinated foraminifera, including taxa represented, mainly by larger benthonic Orbitolina. While, the calcareous forms are minor ones, including taxa represented mainly by miliolids. The distribution patterns of the diverse biota (especially orbitolinids) suggest shallow water marine, oxygenated and rich trophic resource conditions for most levels of the upper part of the succession. However, locally invertebrate floatstones and rudstones and a high amount of reworked bioclasts suggest unstable, fluctuating environmental conditions with higher energy currents for some middle horizons (Pittet et al. 2002). Abstract Foraminiferal morphogroups reveal their responses to palaeoenvironmental and palaeoecological changes. The foraminiferal morphogroups of the early-mid Cretaceous in northeastern Rafsanjan have been investigated with an interest in palaeoenvironmental changes. According to the shell forms, coiling modes, and life positions linked to the lifestyles and feeding strategies, eleven morphogroups, including one planktonic and ten benthic foraminiferal morphogroups, were identified. The planktonic morphogroup includes various species of the genus Hedbergella, showing an open marine eutrophic environment in the lower part of the section. In the upper part of the section, the bioclasts are characterized by the dominance of conical and discoidal orbitolinids. Their distribution patterns reflect changes in environmental conditions. In the initial and final intervals of the upper part, conical orbitolinids are dominated and associated with micro-encrusters (Lithocodium-Bacinella). The peloidal packstones to wackestones facies in these succession, demonstrate the low-energy conditions. This association suggests an oxygenated and shallow water lagoonal environment. However, a few numbers of planktonic foraminifera and oligosteginids in the final layers suggest a minor increase in depositional water depth. Discoidal orbitolinids and calcareous algae associated with skeletal fragments of invertebrates, ooids and detrital particles are the most common constituents of the middle intervals. Complete to partial micritization and micrite envelope around bioclasts are common. These suggest unstable, fluctuating environmental conditions with higher energy currents, resulting in the reworking of skeletal grains. The diverse fossil fauna, larger benthic foraminifera, and the predominance of epifaunal relative to infaunal foraminifera in most horizons of the upper part reflect a well-oxygenated and good trophic level environment. Keywords: Morphogroup, Foraminifera, Cretaceous, Palaeoecology. Introduction Foraminifera are good indicators of the ecological factors of ancient water environments, including palaeobathymetry, bottomwater dissolved oxygen, and primary productivity. In recent decades, some studies have been done to reconstruct the palaeoenvironment by using morphological (test form, life position, and feeding strategy) characteristics (Nagy et al. 2009). In this study, foraminifera fossils in the Earlt to Middle Cretaceous marine carbonate succession of northeastern Rafsanjan were analyzed to interpreting palaeoenvironmental conditions. Material & Methods A total of 65 benthic and planktonic foraminiferal genera were extracted from the 100 limestone samples in the Gezeresh section, 40 km northeastern Rafsanjan city, Kerman Province, Iran. Foraminifera were classified into morphological groups according to morphological features (general shape, mode of coiling, chamber arrangement, feeding strategy and life habitat). In this study, the morphogroups classification were modified from the planktonic morphogroup schemes of Premoli Silva and Sliter (1999), Lowery et al. (2014), Price and Hart (2002) as well as benthonic morphogroup schemes of Bernhard (1986); Jones and Charnock (1985), Koutsoukos and Hart (1990), Nagy (1992), Tyszka (1994), Szydlo (2004), Nagy et al. (2009), Reolid et al. (2008a,b), Reolid et al. (2012a,b) and Smolen (2012). Discussion of Results & Conclusions The microfaunal content of the Gezeresh section is dominated by foraminifera, but calcareous algal and vertebrate particles are also abundant in some horizons. Both benthic and planktonic foraminifera are present. Eleven morphogroups including, one planktonic and ten benthic foraminiferal morphogroups were identified according to morphological features (general shell morphology, aperture position, mode of coiling and number of chambers). Morphogroup MPA includes non-keeled, small-sized and simple morphotypes of trochospiral Hedbergella planktonic foraminiferal species. Most of the benthic tests are distributed within the following morphogroups: 1- Agglutinated foraminiferal morphogroups with a general dominance include AG-A to AG-G morphotypes. 2- Calcareous foraminiferal morphogroups comprising: porcelaneous (CP-A) and hyaline tests (CH-A and CH-B). Morphogroup AG-A includes rounded to plano-convex and biconvex multilocular shells with spiral chamber arrangement, planispiral and trochospiral coiled tests (Haplophragmoides, Nezzazata, Nezzazatinella Trochaminoides and Debarina). Morphogroup AG-B comprises flattened and discoidal forms (Glomospira, Glomospirella). Morphogroup AG-C includes elongated, subcylindric multilocular forms with infaunal habitats and it was divided into three subgroups: AG-C1 comprises uniserial tests (Reophax), AG-C2 consists of forms with a planispiral or streptospiral initial stage, later uniserial (Ammobaculites, Novalesia, Feurtillia, Turriglomina, Pseudolituonella) and AG-C3 consists of elongated biserial and triserial forms (Gaudryina, Textularia, Arenobulimina, etc.). Morphogroup AG-D comprises conical forms with a short early trochospiral initial stage followed by a more prominent biserial final stage (Cuneolina, Sabaudia Vercorsella and Akcaya). Morphogroup AG-E is represented by subspherical to flattened tests with early stages planispirally coiled and later uncoiled tests (Pseudocyclammina and Torremiroella). Morphogroup AG-F comprises finely agglutinated lenticular to subglobular forms and uncoiled tests in the last one or two chamber tests (Charentia, Mayncina and Nautiloculina). Morphogroup AG-G comprises larger benthic foraminifera with low to high conical tests and apically situated embryonal apparatus. The porcelaneous CP-A morphogroup was characterized by a discoidal flattened spiral and elongated test shape. The hyaline tests are distributed within the following morphogroups: Morphogroup CH-A consists of calcareous discoidal to flattened shapes (planispiral) and plano-convex (trochospiral) forms (Trocholina, Concospirillina, Neotrocnholina) and Morphogroup CH-B is composed of biconvex (lenticular), planispiral and multilocular forms (Lenticulina). The foraminiferal morphogroups identified in this study occur with different percentages throughout the analyzed succession. The distribution of foraminiferal assemblages in two lithostratigraphic units of the Gezeresh section shows the dominance of planktonic and benthic foraminifera (mainly orbitolinids) in the lower and upper parts of the section, respectively. The dominant planktonic taxa are Hedbergellidae (r-strategists) which reflects meso- to eutrophic conditions (Premoli Silva and Sliter 1999). The upper part of the studied section is characterized by mixed, diverse biota including various foraminifera, echinoderms, bivalves, corals and gastropods. Orbitolinids (mainly conical forms) are common. These levels indicate more favorable conditions for agglutinated foraminifera, including taxa represented, mainly by larger benthonic Orbitolina. While, the calcareous forms are minor ones, including taxa represented mainly by miliolids. The distribution patterns of the diverse biota (especially orbitolinids) suggest shallow water marine, oxygenated and rich trophic resource conditions for most levels of the upper part of the succession. However, locally invertebrate floatstones and rudstones and a high amount of reworked bioclasts suggest unstable, fluctuating environmental conditions with higher energy currents for some middle horizons (Pittet et al. 2002).

https://jssr.ui.ac.ir/article_29376_7349bd27379a8fa47bcb461b9b7e2cfc.pdf

University of Isfahan Journal of Stratigraphy and Sedimentology Researches 2008-7888 41 2 2025 06 22 An artificial intelligence approach to palaeogeographic studies: a case study of the Late Ordovician brachiopods of Laurentia An artificial intelligence approach to palaeogeographic studies: a case study of the Late Ordovician brachiopods of Laurentia 79 99 29319 10.22108/jssr.2025.143190.1300 FA Akbar Sohrabi Assistant Professor, Department of Geology, University of Tabriz, Tabriz, Iran 0000-0002-5320-7238 Journal Article 2024 10 28 Abstract According to the earliest hypothesis which was based on qualitative studies of the Late Ordovician brachiopod fauna, the younger and larger species of Hiscobeccus, which was one of the epicontinental brachiopod fauna of North America, evolved from the older and smaller species of Rhynchotrema, which lived in precratonic regions. The results of quantitative studies and multivariate analyses based on the morphological characteristics of the brachiopods support this hypothesis. In this study, an artificial intelligence model based on neural networks was conducted in order to determine the relationship between the morphological characteristics of the Late Ordovician brachiopods of the Laurentia and their geographical localities. This neural network model estimates the palaeogeographic localities of the brachiopods by generating a mathematical formula between the morphometric characteristics of brachiopods and their geographical distribution. Based on the results of this study, the neural network can estimate the geographical localities of the test samples of brachiopod with a high accuracy of 82%. By creating a more comprehensive dataset based on the morphometric parameters of the brachiopods of Laurentia and other regions of the world and using the neural network model, the palaeogeographic localities of brachiopods can be estimated with high accuracy. Keywords: Brachiopods, Neural network, Morphometrics, Palaeogeography, Late Ordovician Introduction Traditionally, paleontology has been a descriptive science, and much of the previous research has been based on qualitative approaches. In recent years, more quantitative methods have been used by paleontologists, in order to have a more comprehensive understanding of the relationships between fossils and their palaeogeography, palaeoecology, palaeobiology, and evolutionary history. Based on the previous studies, which have been largely qualitative, Hiscobeccus evolved from Rhynchotrema, probably in the late Chatfieldian (middle Caradoc), and developed into a large, spherical, and highly lamellated shell (Amsden 1983; Jin 2001). Despite these early studies, there are still many questions regarding the evolutionary lineage of Rhynchotrema-Hiscobeccus. For example, what was the rate of morphological transformation from Rhynchotrema to Hiscobeccus? Did morphological changes occur similarly in different regions with different palaeoenvironments on the Laurentian plate? What was the palaeoecological position of different species of the Rhynchotrema-Hiscobeccus lineage in different palaeogeographic environments? How did sea-level changes affect the evolution of the Rhynchotrema-Hiscobeccus lineage? In a study by Sohrabi and Jin (2013), a dataset was conducted based on morphological features of Rhynchotrema and Hiscobeccus specimens from North America and they used multivariate analysis to distinguish morphological trends from Rhynchotrema to Hiscobeccus. Based on the primary measurements, they extracted secondary parameters in order to examine morphological changes (e.g. increase in shell size, lamellosity, and globosity) from Rhynchotrema to Hiscobeccus. Based on these secondary parameters such as shell size index (SSI), shell convexity index (SCI), shell lamellosity index (SLI), and shell lamella density (SLD), they studied the differences between younger and older forms of Rhynchotrema and early forms of Hiscobeccus during the Late Ordovician time. In their study, based on the morphological changes, the relationships between different forms of Rhynchotrema and Hiscobeccus in different regions and with different palaeogeographic distribution patterns of species were investigated. In previous studies, the Late Ordovician brachiopods from different regions of North America have been qualitatively and quantitatively examined, and also a detailed dataset related to the morphological characteristics of brachiopod fossils from different regions of North America has been previously collected. Therefore, a dataset based on the North American brachiopods was used in this study. The fact that most of the studies on the Late Ordovician brachiopods from different regions of Iran have been qualitative, and also the quantitative data related to the morphological characteristics of Iranian brachiopods are very limited, the Late Ordovician brachiopods of Iran were not used in this study. For the present study, an artificial intelligence approach was used to investigate and analyze the palaeogeography and evolutionary process of the Rhynchotrema-Hiscobeccus lineage during the Late Ordovician in North America (Laurentia). Artificial intelligence has the ability to learn from any pattern between a set of input and output data and involves various techniques including neural networks. In this study, a neural network method was used to estimate the location of the Rhynchotrema-Hiscobeccus lineage and also their palaeogeographical analysis. The use of neural network-based artificial intelligence allows paleontologists to have a better and more comprehensive understanding of the palaeogeographic distribution of the brachiopods. By adding more brachiopods data from other geographical locations around the world to the current dataset, a more inclusive dataset can be created for future studies, which would enhance the predictivity power of the neural network model to cover wider geographic locations. Materials & Methods The data used in this study are based on a morphometric dataset of Rhynchotrema and Hiscobeccus specimens collected by previous studies (see Sohrabi and Jin 2013). This dataset includes biometric measurements of the Upper Ordovician (upper Sandbian–upper Katian) rhynchonellid brachiopods from nine localities in North America (Brett et al. 2004; Bergstrom 1971; Mitchell & Bergstrom 1991) (Figs. 1 and 3). The Rhynchotrema specimens in this study are as follows: Mn-10 from the Platteville Formation, Upper Sandbian, Minnesota; W (NAPC-9) from the Lexington Formation, lower Katian, Kentucky; Mara-1 (0–2) from the Verulam Formation, lower Katian, Lake Simcoe Region, Ontario; Ottawa-1 from the Verulam Formation, lower Katian, Ottawa Region; GSC Loc. 1603 specimens from the Verulam Formation, lower Katian, Bay of Quinte, southern Ontario. The specimens of Hiscobeccus in this study are as follows: GSC Loc. 205924 from the Advance Formation, Trentonian age, northern Rocky Mountains, British Columbia; GSC Loc. 113531 from the Amadjuak Formation, Edenian–Maysvilian age, Baffin Island; GSC Loc. C-205929 from the Stony Mountain Formation, Richmondian age, southern Manitoba; W (C-7a-77) specimens from the Waynesville and Liberty formations, Richmondian age, Ohio (Figs. 1 and 2). Discussion of Results & Conclusions In this study, a neural network model was developed based on palaeogeography and evolutionary analysis of brachiopods in North America, and a back-propagation neural network model was created to estimate the location of the Rhynchotrema and Hiscobeccus specimens, based on a set of nine morphometric data (Nouri-Taleghani et al. 2015; Abdizadeh et al. 2017; Farzi et al. 2017) (Fig. 4). In this method, after entering the dataset, an artificial intelligence model learns the morphological features of brachiopods related to each geographical region and then estimates the geographical location of the brachiopods for new specimens. The neural network tries to relate these morphometric data to their location in order to predict their initial location by providing new morphometric measures to the neural network model. If the initial location of the brachiopods has been displaced by various factors, neural networks can estimate the initial location of those brachiopods with high accuracy. In this method, the input (morphometric data) and output (brachiopod location) are divided into a training set (to learn the input and output patterns), a validation set (for overtraining prevention), and a test set (for reliability measurement of the neural network). Localities identified based on laboratory measurements of Rhynchotrema-Hiscobeccus brachiopods are: 15862 (Baffin); 0–104507 (Baffin); 0–104517 (Baffin); GSC 113531–113541 (Baffin); GSC 205924 (Advance Formation, Rocky Mountains), GSC 1603 (Bay of Quinte, Ontario), NAPC-Pre Stop 1B (Bromley Member, Lexington limestone, Kentucky), Ottawa-1 (Ottawa), Mara 1(0–2) (Lake Simcoe area, Ontario), MN-10 (Minnesota), GSC Loc. C-205929 (Stony Mountain, Manitoba), C-7a- 77 (Waynesville and Liberty, Ohio). Codes 1 to 12 were assigned to the 12 locations, in order to be identified by the neural network program in MATLAB software. Two-thirds of the data were used for training and one-third of the data were used for validating and testing in the neural network model. From a total of 160 brachiopod samples, 52 samples (33%) were randomly selected as test samples, and 108 samples were used for training the neural network model. The morphometric data including L, L1, W, W1, W2, T, T1, AA and LN were used as the input data (Fig. 3). The matrix diagram indicates the interrelationships of morphometric data measured on 160 brachiopod samples and there is a good correlation between the input data of the neural network model (Figs. 4 and 5). Twelve neurons in the input layer, and one neuron in the output layer were used. Figure (6) shows the TANSIG and PURLIN transfer functions which were considered from layers one to two and from layers two to three. In order to measure the reliability of the neural network model, the mean square error performance function was used. For training the neural network model, the Bayesian training function (trainbr) was used. Based on the training algorithm and after 146 periods, the training error decreased, but the validation error increased (Fig. 7). The optimized weights and bias values were obtained when the network training was stopped when a period was at 146. The graphical images showing the gradient, mu, Gamk, ssX, and validation failure of the neural network model (Fig. 8). The comparison between the actual and estimated locations of the Rhynchotrema-Hiscobeccus lineage in the training and testing datasets of the neural network model is shown (Figs 9 and 10). The correspondence of the neural network model training samples and their associated locations for the real samples (left graph) and the training samples (right graph) are shown (Fig. 9). There is a good correspondence between the real locations (left graph) and the estimated locations (right graph) of the brachiopods using the back-propagation neural network model. Figure (10) shows the correspondence of the neural network model for the testing samples and their associated locations for the actual samples (left graph) and the training samples (right graph). There is a very high correspondence between the left graph (real localities) and the right graph (estimated localities). Among 52 locations in the testing dataset, the neural network predicted 46 locations correctly with an accuracy of 82%. Based on morphometric analysis of Rhynchotrema and Hiscobeccus specimens from nine geographic localities in North America, Hiscobeccus diversified during the Late Katian (Richmondian and Maysvillian) by developing a larger, more spherical, and more strongly lamellose shell in the epicontinental seas of Laurentia. In contrast to Hiscobeccus, which was common in the palaeo-equatorial epicontinental seas, Rhynchotrema species were common and diverse in the continental margins and platforms of the pericratonic region of Laurentia. The increase in shell sphericity can be interpreted as an adaptation of brachiopods to high-energy tropical environments such as the Cincinnati region during the Late Ordovician (Richmondian) (Jin 2001; Sohrabi & Jin 2013). Assuming that there are some reworked brachiopods that have moved from their original location, the neural network is able to identify the original location of the brachiopods. Since the neural network has not seen the brachiopod locations in the test samples, it is able to predict the locations of the test samples based on the pattern learned in the training dataset. If there is an area with a poor fossil record and no reliable data, artificial intelligence methods can be used to identify mathematical relationships between the morphometric data of the fossils and their geographical distribution. The dataset used in this study and the developed models are freely available to other researchers around the world, so that with the addition of more data, a more comprehensive dataset can be provided for the future studies. By completing the dataset used in this study, the capabilities of the neural network models can be increased to estimate the original location of the fossils. The model can be updated by adding more fossil samples from other geographical regions around the world, such as Iran and other regions of Gondwana, and accordingly, the neural network model can be retrained to include a wider range of localities. By increasing fossil data from other parts of the world and creating a more complete dataset, this AI model can have a larger test dataset to learn from and, as a result, be used with much higher accuracy in predicting the geographical locations of fossils and other palaeogeographic studies. Abstract According to the earliest hypothesis which was based on qualitative studies of the Late Ordovician brachiopod fauna, the younger and larger species of Hiscobeccus, which was one of the epicontinental brachiopod fauna of North America, evolved from the older and smaller species of Rhynchotrema, which lived in precratonic regions. The results of quantitative studies and multivariate analyses based on the morphological characteristics of the brachiopods support this hypothesis. In this study, an artificial intelligence model based on neural networks was conducted in order to determine the relationship between the morphological characteristics of the Late Ordovician brachiopods of the Laurentia and their geographical localities. This neural network model estimates the palaeogeographic localities of the brachiopods by generating a mathematical formula between the morphometric characteristics of brachiopods and their geographical distribution. Based on the results of this study, the neural network can estimate the geographical localities of the test samples of brachiopod with a high accuracy of 82%. By creating a more comprehensive dataset based on the morphometric parameters of the brachiopods of Laurentia and other regions of the world and using the neural network model, the palaeogeographic localities of brachiopods can be estimated with high accuracy. Keywords: Brachiopods, Neural network, Morphometrics, Palaeogeography, Late Ordovician Introduction Traditionally, paleontology has been a descriptive science, and much of the previous research has been based on qualitative approaches. In recent years, more quantitative methods have been used by paleontologists, in order to have a more comprehensive understanding of the relationships between fossils and their palaeogeography, palaeoecology, palaeobiology, and evolutionary history. Based on the previous studies, which have been largely qualitative, Hiscobeccus evolved from Rhynchotrema, probably in the late Chatfieldian (middle Caradoc), and developed into a large, spherical, and highly lamellated shell (Amsden 1983; Jin 2001). Despite these early studies, there are still many questions regarding the evolutionary lineage of Rhynchotrema-Hiscobeccus. For example, what was the rate of morphological transformation from Rhynchotrema to Hiscobeccus? Did morphological changes occur similarly in different regions with different palaeoenvironments on the Laurentian plate? What was the palaeoecological position of different species of the Rhynchotrema-Hiscobeccus lineage in different palaeogeographic environments? How did sea-level changes affect the evolution of the Rhynchotrema-Hiscobeccus lineage? In a study by Sohrabi and Jin (2013), a dataset was conducted based on morphological features of Rhynchotrema and Hiscobeccus specimens from North America and they used multivariate analysis to distinguish morphological trends from Rhynchotrema to Hiscobeccus. Based on the primary measurements, they extracted secondary parameters in order to examine morphological changes (e.g. increase in shell size, lamellosity, and globosity) from Rhynchotrema to Hiscobeccus. Based on these secondary parameters such as shell size index (SSI), shell convexity index (SCI), shell lamellosity index (SLI), and shell lamella density (SLD), they studied the differences between younger and older forms of Rhynchotrema and early forms of Hiscobeccus during the Late Ordovician time. In their study, based on the morphological changes, the relationships between different forms of Rhynchotrema and Hiscobeccus in different regions and with different palaeogeographic distribution patterns of species were investigated. In previous studies, the Late Ordovician brachiopods from different regions of North America have been qualitatively and quantitatively examined, and also a detailed dataset related to the morphological characteristics of brachiopod fossils from different regions of North America has been previously collected. Therefore, a dataset based on the North American brachiopods was used in this study. The fact that most of the studies on the Late Ordovician brachiopods from different regions of Iran have been qualitative, and also the quantitative data related to the morphological characteristics of Iranian brachiopods are very limited, the Late Ordovician brachiopods of Iran were not used in this study. For the present study, an artificial intelligence approach was used to investigate and analyze the palaeogeography and evolutionary process of the Rhynchotrema-Hiscobeccus lineage during the Late Ordovician in North America (Laurentia). Artificial intelligence has the ability to learn from any pattern between a set of input and output data and involves various techniques including neural networks. In this study, a neural network method was used to estimate the location of the Rhynchotrema-Hiscobeccus lineage and also their palaeogeographical analysis. The use of neural network-based artificial intelligence allows paleontologists to have a better and more comprehensive understanding of the palaeogeographic distribution of the brachiopods. By adding more brachiopods data from other geographical locations around the world to the current dataset, a more inclusive dataset can be created for future studies, which would enhance the predictivity power of the neural network model to cover wider geographic locations. Materials & Methods The data used in this study are based on a morphometric dataset of Rhynchotrema and Hiscobeccus specimens collected by previous studies (see Sohrabi and Jin 2013). This dataset includes biometric measurements of the Upper Ordovician (upper Sandbian–upper Katian) rhynchonellid brachiopods from nine localities in North America (Brett et al. 2004; Bergstrom 1971; Mitchell & Bergstrom 1991) (Figs. 1 and 3). The Rhynchotrema specimens in this study are as follows: Mn-10 from the Platteville Formation, Upper Sandbian, Minnesota; W (NAPC-9) from the Lexington Formation, lower Katian, Kentucky; Mara-1 (0–2) from the Verulam Formation, lower Katian, Lake Simcoe Region, Ontario; Ottawa-1 from the Verulam Formation, lower Katian, Ottawa Region; GSC Loc. 1603 specimens from the Verulam Formation, lower Katian, Bay of Quinte, southern Ontario. The specimens of Hiscobeccus in this study are as follows: GSC Loc. 205924 from the Advance Formation, Trentonian age, northern Rocky Mountains, British Columbia; GSC Loc. 113531 from the Amadjuak Formation, Edenian–Maysvilian age, Baffin Island; GSC Loc. C-205929 from the Stony Mountain Formation, Richmondian age, southern Manitoba; W (C-7a-77) specimens from the Waynesville and Liberty formations, Richmondian age, Ohio (Figs. 1 and 2). Discussion of Results & Conclusions In this study, a neural network model was developed based on palaeogeography and evolutionary analysis of brachiopods in North America, and a back-propagation neural network model was created to estimate the location of the Rhynchotrema and Hiscobeccus specimens, based on a set of nine morphometric data (Nouri-Taleghani et al. 2015; Abdizadeh et al. 2017; Farzi et al. 2017) (Fig. 4). In this method, after entering the dataset, an artificial intelligence model learns the morphological features of brachiopods related to each geographical region and then estimates the geographical location of the brachiopods for new specimens. The neural network tries to relate these morphometric data to their location in order to predict their initial location by providing new morphometric measures to the neural network model. If the initial location of the brachiopods has been displaced by various factors, neural networks can estimate the initial location of those brachiopods with high accuracy. In this method, the input (morphometric data) and output (brachiopod location) are divided into a training set (to learn the input and output patterns), a validation set (for overtraining prevention), and a test set (for reliability measurement of the neural network). Localities identified based on laboratory measurements of Rhynchotrema-Hiscobeccus brachiopods are: 15862 (Baffin); 0–104507 (Baffin); 0–104517 (Baffin); GSC 113531–113541 (Baffin); GSC 205924 (Advance Formation, Rocky Mountains), GSC 1603 (Bay of Quinte, Ontario), NAPC-Pre Stop 1B (Bromley Member, Lexington limestone, Kentucky), Ottawa-1 (Ottawa), Mara 1(0–2) (Lake Simcoe area, Ontario), MN-10 (Minnesota), GSC Loc. C-205929 (Stony Mountain, Manitoba), C-7a- 77 (Waynesville and Liberty, Ohio). Codes 1 to 12 were assigned to the 12 locations, in order to be identified by the neural network program in MATLAB software. Two-thirds of the data were used for training and one-third of the data were used for validating and testing in the neural network model. From a total of 160 brachiopod samples, 52 samples (33%) were randomly selected as test samples, and 108 samples were used for training the neural network model. The morphometric data including L, L1, W, W1, W2, T, T1, AA and LN were used as the input data (Fig. 3). The matrix diagram indicates the interrelationships of morphometric data measured on 160 brachiopod samples and there is a good correlation between the input data of the neural network model (Figs. 4 and 5). Twelve neurons in the input layer, and one neuron in the output layer were used. Figure (6) shows the TANSIG and PURLIN transfer functions which were considered from layers one to two and from layers two to three. In order to measure the reliability of the neural network model, the mean square error performance function was used. For training the neural network model, the Bayesian training function (trainbr) was used. Based on the training algorithm and after 146 periods, the training error decreased, but the validation error increased (Fig. 7). The optimized weights and bias values were obtained when the network training was stopped when a period was at 146. The graphical images showing the gradient, mu, Gamk, ssX, and validation failure of the neural network model (Fig. 8). The comparison between the actual and estimated locations of the Rhynchotrema-Hiscobeccus lineage in the training and testing datasets of the neural network model is shown (Figs 9 and 10). The correspondence of the neural network model training samples and their associated locations for the real samples (left graph) and the training samples (right graph) are shown (Fig. 9). There is a good correspondence between the real locations (left graph) and the estimated locations (right graph) of the brachiopods using the back-propagation neural network model. Figure (10) shows the correspondence of the neural network model for the testing samples and their associated locations for the actual samples (left graph) and the training samples (right graph). There is a very high correspondence between the left graph (real localities) and the right graph (estimated localities). Among 52 locations in the testing dataset, the neural network predicted 46 locations correctly with an accuracy of 82%. Based on morphometric analysis of Rhynchotrema and Hiscobeccus specimens from nine geographic localities in North America, Hiscobeccus diversified during the Late Katian (Richmondian and Maysvillian) by developing a larger, more spherical, and more strongly lamellose shell in the epicontinental seas of Laurentia. In contrast to Hiscobeccus, which was common in the palaeo-equatorial epicontinental seas, Rhynchotrema species were common and diverse in the continental margins and platforms of the pericratonic region of Laurentia. The increase in shell sphericity can be interpreted as an adaptation of brachiopods to high-energy tropical environments such as the Cincinnati region during the Late Ordovician (Richmondian) (Jin 2001; Sohrabi & Jin 2013). Assuming that there are some reworked brachiopods that have moved from their original location, the neural network is able to identify the original location of the brachiopods. Since the neural network has not seen the brachiopod locations in the test samples, it is able to predict the locations of the test samples based on the pattern learned in the training dataset. If there is an area with a poor fossil record and no reliable data, artificial intelligence methods can be used to identify mathematical relationships between the morphometric data of the fossils and their geographical distribution. The dataset used in this study and the developed models are freely available to other researchers around the world, so that with the addition of more data, a more comprehensive dataset can be provided for the future studies. By completing the dataset used in this study, the capabilities of the neural network models can be increased to estimate the original location of the fossils. The model can be updated by adding more fossil samples from other geographical regions around the world, such as Iran and other regions of Gondwana, and accordingly, the neural network model can be retrained to include a wider range of localities. By increasing fossil data from other parts of the world and creating a more complete dataset, this AI model can have a larger test dataset to learn from and, as a result, be used with much higher accuracy in predicting the geographical locations of fossils and other palaeogeographic studies.

https://jssr.ui.ac.ir/article_29319_221013a29d2f2c52e66268c7e0effd9f.pdf