@misc{jones1956introduction2, author = "Jones, D. J", title = "Introduction to Microfossils", year = "1956", howpublished = "New York, Harper, 406 p", note = "talkorigins\_source = {true}; raw\_reference = {Jones, D. J., 1956, Introduction to Microfossils: New York, Harper, 406 p.}" } @article{rexroad1958the6, author = "Rexroad, C. B", title = "The conodont homeomorphs Taphrognathus and Streptognathodus", year = "1958", journal = "Journal of Paleontology, v. 32, p. 1158-1159", note = "talkorigins\_source = {true}; raw\_reference = {Rexroad, C. B., 1958, The conodont homeomorphs Taphrognathus and Streptognathodus: Journal of Paleontology, v. 32, p. 1158-1159.}" } @misc{pokorny1963principles4, author = "Pokorny, V", title = "Principles of Zoological Micropaleontology", year = "1963", howpublished = "New York, Macmillan, 652 p.; Translated by Allen, K.A", note = "talkorigins\_source = {true}; raw\_reference = {Pokorny, V., 1963, Principles of Zoological Micropaleontology: New York, Macmillan, 652 p.; Translated by Allen, K.A.}" } @book{rauzerchernousova1963einige5, author = "Rauzer-Chernousova, D. M", title = "Einige Fragen zur Evolution der Fusulinideen, in von Koenigswald, G. H. R., ed., Evolutionary Trends in Foraminifera", year = "1963", publisher = "Amsterdam, Elsevier, p. 45-65; 355 p", note = "talkorigins\_source = {true}; raw\_reference = {Rauzer-Chernousova, D. M., 1963, Einige Fragen zur Evolution der Fusulinideen, in von Koenigswald, G. H. R., ed., Evolutionary Trends in Foraminifera: Amsterdam, Elsevier, p. 45-65; 355 p.}" } @article{doi104319lo19731840647, author = "Battarbee, Richard W.", title = "A new method for the estimation of absolute microfossil numbers, with reference especially to diatoms", year = "1973", journal = "Limnology and Oceanography", abstract = "A new method for obtaining permanent quantitative slides of microfossils involves the use of an evaporation tray in which microfossil suspensions can be sedimented randomly onto cover slips on the tray floor. Slides are made after evaporation. The technique is statistically reliable.", url = "https://doi.org/10.4319/lo.1973.18.4.0647", doi = "10.4319/lo.1973.18.4.0647", openalex = "W2030835188" } @article{doi101007bf01731491, author = "Kenyon, D H and Nissenbaum, A", title = "Melanoidin and aldocyanoin microspheres: implications for chemical evolution and early precambrian micropaleontology.", year = "1976", journal = "Journal of molecular evolution", abstract = {Two new classes of organic microspheres are described. One of them (melanoidin) is synthesized from amino acids and sugars in heated aqueous solutions. The other (aldocyanoin) is formed in aqueous solutions of ammonium cyanide and formaldehyde at room temperature. The general properties of these microspheres, including conditions of synthesis, size and shape, mechanical and pH stability, and solubility, are compared with corresponding properties of other "protocell" model systems. It is concluded that melanoidin and aldocyanoin microsphreres are plausible candidates for precellular units in the primitive hydrosphere. Since the bulk of the organic carbon in early Precambrian sediments is insoluble kerogen-melanoidin, it is suggested that some Precambrian "microfossils" may be abiotic melanoidin microspheres of the type described herein.}, url = "https://pubmed.ncbi.nlm.nih.gov/778393/", doi = "10.1007/BF01731491", openalex = "W1997527155", pmid = "778393", references = "doi1010160026265x73901124, doi1010160304416566901978, doi101016s0022283667800378, doi101016s0047248478800529, doi101016s0096533208602234, doi101016s0096533208603835, doi101021ja01503a072, doi101038199219a0, doi101038248121a0, doi101146annurevea03050175001241" } @article{doi1023071485325, author = "Kennedy, Casiana and Zeidler, Wolfgang", title = "The Preparation of Oriented Thin Sections in Micropaleontology: An Improved Method for Revealing the Internal Morphology of Foraminifera and Other Microfossils", year = "1976", journal = "Micropaleontology", abstract = "C. Kennedy, W. Zeidler, The Preparation of Oriented Thin Sections in Micropaleontology: An Improved Method for Revealing the Internal Morphology of Foraminifera and Other Microfossils, Micropaleontology, Vol. 22, No. 1 (Jan., 1976), pp. 104-107", url = "https://doi.org/10.2307/1485325", doi = "10.2307/1485325", openalex = "W2327834123", references = "doi1023071484559" } @article{doi1023071485444, author = "Olsson, Richard K. and Haq, Bilal U. and Boersma, Anne", title = "Introduction to Marine Micropaleontology", year = "1980", journal = "Micropaleontology", abstract = "Marine micropaleontology: an introduction (W.A. Berggren). Calcareous Microfossils. Foraminifera (A. Boersma). Calcareous nannoplankton (B.U. Haq). Ostracodes (V. Pokomy). Pteropods (Y. Herman). Calpionellids (J. Remane). Calcareous algae (J.L. Wray). Bryozoa (K. Brood). Siliceous Microfossils. Radiolaria (S.A. Kling). Marine diatoms (L.H. Burckle). Silicoflagellates and ebridians (B.U. Haq). Phosphatic Microfossils. Conodonts and other phosphatic microfossils (K.J. Muller). Organic-Walled Microfossils. Dinoflagellates, acritarchs and tasmanitids (G.L. Williams). Spores and pollen in the marine realm (L. Heusser). Chitinozoa (A. Jansonius, W.A.M. Jenkins).", url = "https://doi.org/10.2307/1485444", doi = "10.2307/1485444", openalex = "W1976402450" } @article{mendelson1982proterozoic3, author = "Mendelson, C. V. and Schopf, J. W", title = "Proterozoic microfossils from the Sukhaya Tunguska, Shorikha and Yudoma formations of the Siberian Platform, USSR", year = "1982", journal = "Journal of Paleontology, v. 56, p. 42-83", note = "talkorigins\_source = {true}; raw\_reference = {Mendelson, C. V., and Schopf, J. W., 1982, Proterozoic microfossils from the Sukhaya Tunguska, Shorikha and Yudoma formations of the Siberian Platform, USSR: Journal of Paleontology, v. 56, p. 42-83.}" } @misc{golovenok1985riphean1, author = "Golovenok, V. K. and Belova, M. Y", title = "Riphean microbiotas in cherts of the Yenesei Ridge [in Russian]", year = "1985", howpublished = "Paleontol. Zh., v. 2, p. 94-103", note = "talkorigins\_source = {true}; raw\_reference = {Golovenok, V. K., and Belova, M. Y., 1985, Riphean microbiotas in cherts of the Yenesei Ridge [in Russian]: Paleontol. Zh., v. 2, p. 94-103.}" } @book{doi1010079781461541677, author = "Martin, Ronald E.", title = "Environmental Micropaleontology: The Application Of Microfossils To Environmental Geology", year = "2000", url = "https://doi.org/10.1007/978-1-4615-4167-7", doi = "10.1007/978-1-4615-4167-7", openalex = "W573684887" } @incollection{doi101007978940170581320, author = "Green, Owen R.", title = "Thin Section and Slide Preparation Techniques of Macro- and Microfossil Specimens and Residues", year = "2001", url = "https://doi.org/10.1007/978-94-017-0581-3\_20", doi = "10.1007/978-94-017-0581-3\_20", openalex = "W205555987", references = "doi1010079781349053971, doi1010160025322771900533, doi101029eo064i042p0059801, doi10130674d728ba2b2111d78648000102c1865d, doi102113gsjfr144309, doi1023071485325, doi1023071485964, doi104319lo19731840647, doi10577261531, openalexw2241437853, openalexw2612667057, openalexw37418461" } @article{doi102110palo2019102, author = "de Lima, Rafael Pires and Welch, Katie F. and Barrick, James E. and Marfurt, Kurt J. and Burkhalter, Roger and Cassel, Murphy and Soreghan, Gerilyn S.", title = "CONVOLUTIONAL NEURAL NETWORKS AS AN AID TO BIOSTRATIGRAPHY AND MICROPALEONTOLOGY: A TEST ON LATE PALEOZOIC MICROFOSSILS", year = "2020", journal = "Palaios", abstract = "ABSTRACT Accurate taxonomic classification of microfossils in thin-sections is an important biostratigraphic procedure. As paleontological expertise is typically restricted to specific taxonomic groups and experts are not present in all institutions, geoscience researchers often suffer from lack of quick access to critical taxonomic knowledge for biostratigraphic analyses. Moreover, diminishing emphasis on education and training in systematics poses a major challenge for the future of biostratigraphy, and on associated endeavors reliant on systematics. Here we present a machine learning approach to classify and organize fusulinids—microscopic index fossils for the late Paleozoic. The technique we employ has the potential to use such important taxonomic knowledge in models that can be applied to recognize and categorize fossil specimens. Our results demonstrate that, given adequate images and training, convolutional neural network models can correctly identify fusulinids with high levels of accuracy. Continued efforts in digitization of biological and paleontological collections at numerous museums and adoption of machine learning by paleontologists can enable the development of highly accurate and easy-to-use classification tools and, thus, facilitate biostratigraphic analyses by non-experts as well as allow for cross-validation of disparate collections around the world. Automation of classification work would also enable expert paleontologists and others to focus efforts on exploration of more complex interpretations and concepts.", url = "https://doi.org/10.2110/palo.2019.102", doi = "10.2110/palo.2019.102", openalex = "W3095972551", references = "doi101007s112630150816y, doi101038nature14539, doi101038nature21056, doi101109cvpr20157298594, doi101109cvpr2016308, doi101109cvpr2017243, doi101109cvpr201800474, doi101109tkde2009191, doi1011453065386, openalexw2095705004" } @article{doi101007s11042022138102, author = "Özer, İlyas and Ozer, Caner Kaya and Karaca, Ali Can and Görür, Kutlucan and Koçak, İsmail and Çetin, Onursal", title = "Species-level microfossil identification for globotruncana genus using hybrid deep learning algorithms from the scratch via a low-cost light microscope imaging", year = "2022", journal = "Multimedia Tools and Applications", url = "https://doi.org/10.1007/s11042-022-13810-2", doi = "10.1007/s11042-022-13810-2", openalex = "W4297347739", references = "doi1010160031018288900302, doi101016jcompbiomed201806002, doi101016jimu2020100412, doi101016jmeasurement2021109094, doi101016jtree200807015, doi101016s0001299878800142, doi101017pab202214, doi101109access20213060654, doi1021037atm20200244, doi102110palo2019102, doi103390make1030048, doi105121ijdkp20155201" } @article{doi101016jacags2022100092, author = "Mimura, Kazuhide and Minabe, Shugo and Nakamura, Kentaro and Yasukawa, Kazutaka and Ohta, Junichiro and Kato, Yasuhiro", title = "Automated detection of microfossil fish teeth from slide images using combined deep learning models", year = "2022", journal = "Applied Computing and Geosciences", abstract = "Microfossil fish teeth, known as ichthyoliths, provide a key constraint on the depositional age and environment of deep-sea sediments, especially pelagic clays where siliceous and calcareous microfossils are rarely observed. However, traditional methods for the observation of ichthyoliths require considerable time and manual labor, which can hinder their wider application. In this study, we constructed a system to automatically detect ichthyoliths in microscopic images by combining two open source deep learning models. First, the regions for ichthyoliths within the microscopic images are predicted by the instance segmentation model Mask R–CNN. All the detected regions are then re-classified using the image classification model EfficientNet-V2 to determine the classes more accurately. Compared with only using the Mask R–CNN model, the combined system offers significantly higher performance (89.0\% precision, 78.6\% recall, and an F1 score of 83.5\%), demonstrating the utility of the system. Our system can also predict the lengths of the teeth that have been detected, with more than 90\% of the predicted lengths being within ±20\% of measured length. This system provides a novel, automated, and reliable approach for the detection and length measurement of ichthyoliths from microscope images that can be applied in a range of paleoceanographic and paleoecological contexts.", url = "https://doi.org/10.1016/j.acags.2022.100092", doi = "10.1016/j.acags.2022.100092", openalex = "W4292411406", references = "doi1010292018gc007584, doi10103824322, doi101038nature06588, doi101038ngeo1185, doi101038s41598018239485, doi101098rspb20181194, doi101109access20182874767, doi101109cvpr1994323798, doi101109tpami20182844175, doi101126scienceaba6853, doi102110palo2019102, doi102113gsjfr192164" } @article{doi103390biology12010016, author = "Wang, Bin and Sun, Ruyue and Yang, Xiaoguang and Niu, Ben and Zhang, Tao and Zhao, Yuandi and Zhang, Yuanhui and Zhang, Yiheng and Han, Jian", title = "Recognition of Rare Microfossils Using Transfer Learning and Deep Residual Networks.", year = "2022", journal = "Biology", abstract = "Various microfossils from the early Cambrian provide crucial clues for understanding the Cambrian explosion and the origin of animal phyla. However, specimens with important anatomical structures are extremely rare and the efficiency of retrieving such fossils by traditional manual selection under a microscope is quite low. Such a contradiction has hindered breakthroughs in micropaleontology for a long time. Here, we propose a solution for identifying specific taxa of Cambrian microfossils using only a few available specimens by transferring a model pre-trained on natural image datasets to the field of paleontological artificial intelligence. The method employs a 34-layer deep residual neural network as the underlying framework, migrates the ImageNet pre-trained model, freezes the low-layer network parameters and retrains the high-layer parameters to build a microfossil image recognition model. We built training sets with randomly selected images of varied number for each taxon. Our experiments show that the average recognition accuracy for specific taxa of Cambrian microfossils (50 images for each taxon) is higher than 0.97 and it can reach 0.85 with only three training samples per taxon. Comparative analyses indicate that our results are much better than those of various prevalent methods, such as the transpose convolutional neural network (TCNN). This demonstrates the feasibility of using natural images (ImageNet) for the training of microfossil recognition models and provides a promising tool for the discovery of rare fossils.", url = "https://pmc.ncbi.nlm.nih.gov/articles/PMC9854841/", doi = "10.3390/biology12010016", openalex = "W4312186694", pmcid = "PMC9854841", pmid = "36671708", references = "doi101007978303001424727, doi101007978354031865125, doi101007s112630150816y, doi1011095726791, doi101109cvpr20095206848, doi101109cvpr2014222, doi101109cvpr20157298594, doi101109cvpr2016308, doi101109cvpr201690, doi101109tkde2009191, doi102110palo2019102" } @article{doi101016jdib2023108940, author = "Mimura, Kazuhide and Nakamura, Kentaro", title = "Datasets for training and validating a deep learning-based system to detect microfossil fish teeth from slide images", year = "2023", journal = "Data in Brief", abstract = "In this paper, we describe the three datasets that were used to train, validate, and test deep learning models to detect microfossil fish teeth. The first dataset was created for training and validating a Mask R-CNN model to detect fish teeth in the images taken using the microscope. The training set contained 866 images and one annotation file; the validation set contained 92 images and one annotation file. The second dataset was created for training and validating EfficientNet-V2 models; it included 17,400 images of teeth and 15,036 images that contained only noise (particles other than teeth). The third dataset was created to evaluate the performance of a system that combines a Mask R-CNN model and an EfficientNet-V2 model; it contained 5177 images with annotation files for the locations of 431 teeth within the images.", url = "https://doi.org/10.1016/j.dib.2023.108940", doi = "10.1016/j.dib.2023.108940", openalex = "W4318612738", references = "doi101016jacags2022100092" } @article{doi101016jjestch2023101589, author = "Özer, İlyas and Koçak, İsmail and Çetin, Onursal and Karaca, Ali Can and Ozer, Caner Kaya and Görür, Kutlucan", title = "Towards investigation of transfer learning framework for Globotruncanita genus and Globotruncana genus microfossils in Genus-Level and Species-Level prediction", year = "2023", journal = "Engineering Science and Technology an International Journal", abstract = "The applicability of digital imaging techniques and machine learning models to paleontological datasets is exploring the possibility of predicting microfossils extracted from the rock samples instead of the traditional identifying methodologies under the microscope in a one-by-one way via a domain expert. However, these processes, including labeling, are carried out manually and take a high time-consuming, especially for many quantities and diversity of complex morphological microfossil specimens. In this work, we propose a transfer learning framework based on a custom model CNN (Convolutional Neural Network) and diverse pre-trained deep models (ResNet50, Xception, InceptionV3, VGG6, MobileNet) trained with the millions of images for Globotruncanita genus and Globotruncana genus in genus-level and species-level prediction. The second primary advantage of our framework is able to provide better and more robust decisions for a limited number of microfossil images captured by the low-cost light microscope imaging technology. The comparison of the diverse methods was evaluated with different performance metrics, and the observation of the framework was made to perform high prediction scores reaching up to the outcomes (>99 \% accuracy and > 0.99 AUC score for genus-level/>81 \% accuracy and > 0.89 AUC score for species-level). As far as we know, this research study is the first attempt to investigate a transfer learning framework to predict the Globotruncanita genus and Globotruncana genus families at the genus-level and species-level microfossils. Overall, it may extend the existing literature on paleontological science and automated/quick classification manner.", url = "https://doi.org/10.1016/j.jestch.2023.101589", doi = "10.1016/j.jestch.2023.101589", openalex = "W4389387865", references = "doi103390biology12010016" } @misc{doi1022541essoar16850034003413762v1, author = "Mimura, Kazuhide and Nakamura, Kentaro and Yasukawa, Kazutaka and Sibert, Elizabeth C and Ohta, Junichiro and Kitazawa, Takahiro and Kato, Yasuhiro", title = "Applicability of Object Detection to Microfossil Research: Implications from Deep Learning Models to Detect Microfossil Fish Teeth and Denticles Using YOLO-v7", year = "2023", abstract = "Microfossils of fish teeth and denticles, termed ichthyoliths, provide critical information for depositional ages, paleo-environments and marine ecosystems, especially in pelagic realms. However, owing to their small size and rarity, it is time-consuming and difficult to analyze large numbers of ichthyoliths from sediment samples, limiting their use in scientific studies. Here, we propose a method to detect ichthyoliths from microscopic images automatically using a deep learning technique of object detection. We applied YOLO-v7, one of the latest object detection architectures, and trained several models under different conditions. The model trained under appropriate conditions with an original dataset achieved an F1 score of 0.87. We then enhanced the dataset efficiently using the pre-trained model. We validated the practical applicability of the model by comparing the number of ichthyoliths detected by the model with those counted manually. This revealed that the best model can predict the number of triangular teeth without manual check, and those of denticles and irregularly shaped teeth with manual check. This object detection method can extend the applicability of deep learning to a wider array of microfossils, and has the potential to dramatically increase the spatiotemporal resolution of ichthyolith records for applications across disciplines.", url = "https://doi.org/10.22541/essoar.168500340.03413762/v1", doi = "10.22541/essoar.168500340.03413762/v1", openalex = "W4378226227", references = "doi101016jacags2022100092" } @article{doi1010292023ea003122, author = "Mimura, Kazuhide and Nakamura, Kentaro and Yasukawa, Kazutaka and Sibert, Elizabeth C and Ohta, Junichiro and Kitazawa, Taro and Kato, Yasuhiro", title = "Applicability of Object Detection to Microfossil Research: Implications From Deep Learning Models to Detect Microfossil Fish Teeth and Denticles Using YOLO‐v7", year = "2024", journal = "Earth and Space Science", abstract = "Abstract Microfossils of fish teeth and denticles, referred to as ichthyoliths, provide critical information for depositional ages, paleo‐environments, and marine ecosystems, especially in pelagic realms. However, owing to their small size and rarity, it is time‐consuming and difficult to analyze large numbers of ichthyoliths from sediment samples, limiting their use in scientific studies. Here, we propose a method to automatically detect ichthyoliths from microscopic images using a deep learning technique. We applied YOLO‐v7, one of the latest object detection architectures, and trained several models under different conditions. The model trained under appropriate conditions with an original data set achieved an F1 score of 0.87. We then enhanced the data set efficiently using the pre‐trained model. We validated the practical applicability of the model by comparing the number of ichthyoliths detected by the model with those counted manually. This revealed that the best model can predict the number of triangular teeth, denticles and irregularly shaped teeth with minimal human intervention. This object detection method can extend the applicability of deep learning to a wider array of microfossils and has the potential to dramatically increase the spatiotemporal resolution of ichthyolith records for applications across disciplines.", url = "https://doi.org/10.1029/2023ea003122", doi = "10.1029/2023ea003122", openalex = "W4391127389", references = "doi101016jacags2022100092" } @misc{doi1022541essoar17180494338756240v1, author = "Mimura, Kazuhide and Kitazawa, Takahiro and Nakamura, Kentaro and Yasukawa, Kazutaka and Kuwahara, Yusuke and Ohta, Junichiro and Kato, Yasuhiro", title = "Deep-sea rare-earth mineral resources formed in the early Eocene Hothouse ocean: Insights from deep learning-based microfossil observations", year = "2024", abstract = "Deep-sea mud enriched in rare-earth elements (REEs), termed REE-rich mud, is a promising seafloor mineral resource. A decade of surveys has revealed that the mud with the highest REE concentration occurs in the pelagic realm of the western North Pacific Ocean, with two layers of elevated REE concentration. Previous analyses of sediments have revealed multiple periods of significant REE enrichment, with the first (youngest) REE enrichment triggered by global cooling during the Eocene–Oligocene climate transition. However, the depositional mechanism of older REE peaks remains unclear. Fish debris is the major host of REE in deep-sea sediments. In this study, the microfossils of fish teeth and denticles, called ichthyoliths, were observed to constrain the depositional ages of REE-enriched layers with unknown genesis. Empowered by deep learning, more than 40,000 ichthyoliths were observed, and the second (older) REE enrichment was revealed to have occurred in the early Eocene, when the Earth’s climate was exceedingly warm. The warm ocean may have enhanced the efficiency of trophic transfer, leading to an increased supply of fish debris and thus REE, to the seafloor. Therefore, the Paleogene Hothouse might have been advantageous for producing valuable seafloor mineral resources.", url = "https://doi.org/10.22541/essoar.171804943.38756240/v1", doi = "10.22541/essoar.171804943.38756240/v1", openalex = "W4399480274", references = "doi101016jacags2022100092" } @article{doi1010292024pa004938, author = "Mimura, Kazuhide and Kitazawa, Taro and Nakamura, Kentaro and Yasukawa, Kazutaka and Kuwahara, Yusuke and Ohta, Junichiro and Kato, Yasuhiro", title = "Deep‐Sea Rare‐Earth Mineral Resources Formed in the Early Eocene Hothouse Ocean: Insights From Deep Learning‐Based Microfossil Observations", year = "2025", journal = "Paleoceanography and Paleoclimatology", abstract = "Abstract Deep‐sea mud enriched in rare‐earth elements (REE), termed REE‐rich mud, is a promising seafloor mineral resource. Data from a decade of surveys have revealed that the mud with the highest REE concentration occurs in the pelagic realm of the western North Pacific Ocean, with at least two layers of elevated REE concentration. Previous analyses of sediments have revealed multiple periods of significant REE enrichment, with the younger REE enrichment triggered by global cooling during the Eocene–Oligocene climate transition. However, the depositional mechanism of older REE peaks remains unclear. Fish debris is the major host of REE in deep‐sea sediments. In this study, ichthyoliths, the microfossils of fish teeth and denticles, were observed to constrain the depositional ages of REE‐enriched (e.g., total REE contents exceeding 2,000 ppm) layers with unknown genesis. Empowered by deep learning, more than 40,000 ichthyoliths were observed, and the older REE enrichment was revealed to have occurred in the early Eocene when the Earth's climate was exceedingly warm. The warm ocean may have enhanced trophic transfer efficiency, leading to an increased supply of fish debris and, thus, REE to the seafloor. Therefore, the Paleogene Hothouse might have been advantageous for producing valuable seafloor mineral resources.", url = "https://doi.org/10.1029/2024pa004938", doi = "10.1029/2024pa004938", openalex = "W4409647536", references = "doi101016jacags2022100092" } @article{doi101038s4159802590988z, author = "Mimura, Kazuhide and Itaki, Takuya and Kataoka, Hirokatsu and Miyakawa, Ayumu", title = "Classifying microfossil radiolarians on fractal pre-trained vision transformers", year = "2025", journal = "Scientific Reports", abstract = "While deep learning techniques, especially image classification using deep learning, continue to evolve, it has been noted that there is a large time gap in applying these techniques in geological studies. Recently, a new architecture called the vision transformer (ViT), which is an alternative to convolutional neural networks (CNN), has attracted considerable attention. In addition, it has been proposed that the pre-training of classification models using mathematically generated images instead of real images, called formula-driven supervised learning (FDSL), achieves a comparative or even higher performance in visual understanding. In this study, we applied these new techniques to the classification of microfossils (radiolarians). Compared with a previous CNN model, the ViT-based model achieved 6-8\% higher average precision. On average, the precision of the FDSL pre-trained models was slightly higher than that of the models pre-trained on real images. Therefore, we propose that these techniques may be suitable for image classification in geological tasks.", url = "https://doi.org/10.1038/s41598-025-90988-z", doi = "10.1038/s41598-025-90988-z", openalex = "W4408201266", references = "doi101016jacags2022100092" }