AI and paleontology: Effects of vertebrate fossil sample size on machine learning image classification

With the growing application of artificial intelligence (AI) and machine learning (ML), great potential exists to leverage these technologies in paleontology. Relative to many other scientific fields, a challenge of ML applied to paleontology is small sample sizes, particularly for fossil vertebrates. Shark teeth, abundant in the fossil record, provide a model system to use ML across varying sample sizes. Here we use six classes (taxa) of Neogene shark teeth for taxonomic identification, including a curated dataset of 3150 images. Each class was evaluated using an 80% training and 20% validation split, with a separate, external test set of 25 samples per class. Pretrained models perform well (accuracy > 90%), providing a strong baseline for classification. However, enabling fine-tuning of the ML model to identify fossil shark teeth improves performance considerably. Likewise, sample size per class also affects the accuracy of the models’ classifications. Smaller sample sizes (n = 50 ..., , # AI and paleontology: Effects of vertebrate fossil sample size on machine learning image classification

Dataset DOI: [10.5061/dryad.zpc866tpq](https://doi.org/10.5061/dryad.zpc866tpq)

## Description of the data and file structure

A complete README file, formatted as a .pdf is included in the file 1 README 1.28.26.pdf. The other files are listed as follows:

* 3c_Optimal_pixel_density_ML_model_results.csv
* 5b_Database_optimal_perf_ML_results_WO_fine_tuning.csv
* 5c_Database_optimal_perf_ML_results_W_fine_tuning.csv
* 5d_Variance_dataset.csv
* 6b_Data_Augmentation-FT_model__RG-HF.csv
* 9_SharkAI_R_code_2025_sections_356.R
* 1_README_1.29.2026.pdf
* 2_Complete_study_image_data_set.pdf
* 3ab_Optimal_pixel_density_context_and_statistical_results.pdf
* 4_Original_Python-Tensorflow_files_including_model_code.pdf
* 5a_Optimal_performance_statistical_results.pdf
* 6a_Data_augmentation_statisical_results_.pdf
* 7_Misidentification_analysis.pdf
* 8_GBIF_plots_of_fossil_Lamnidae_and_Carcharhin...,