Microfossil analysis allows us to map the subsurface and understand past geological times. In research labs all over the world geologists spend countless hours looking through the microscope identifying and counting microfossils extracted from sedimentary rock below the seabed.

The analysis is time-consuming but important, as the species distribution tell a great deal about the geological time period of sedimentary layers from the subsurface, as well as the climatic conditions at the earths surface at the time when these microfossils were formed.

In a recent study published in the KeAI journal Artificial Intelligence in Geosciences, researchers at the machine learning group at University of Tromsø (UiT) The Arctic University of Norway created an advanced method for automatically detecting and analyzing microfossils from microscope images using AI. The team, in collaboration with industry partner Equinor, presented a method for automatic microfossil detection and analysis.

“This work shows that there is great potential in utilizing AI in this field,” says researcher Iver Martinsen, first and co-corresponding author of the study. “By using AI to automatically detect and recognize fossils, geologists might have a tool that can help them better utilize the enormous amount of information that wellbore samples provide”.

Microfossils are found in vast amounts everywhere, but the time and expertise required to analyze the data means that only a fraction of the available fossils are analyzed. The method the researchers used are based on state-of-the-art AI methodology — training an AI model completely without annotations, utilizing the large pool of raw data provided by the Norwegian Offshore Directorate.

“We used AI to detect fossils from one selected well on the Norwegian continental shelf, and in turn use 100,000 of the detected fossils to train a model for image recognition,” shares Martinsen.

To evaluate how well the model performs, the researchers tested the model by classifying several hundreds labeled fossils from the same well.

“We are very happy with our results. Our model exceeds previous benchmarks available out there. We hope that the present work will be beneficial for geologists both in industry and academia,” adds Martinsen.

‍

Microfossil classification is an important discipline in subsurface exploration, for both oil & gas and Carbon Capture and Storage (CCS). The abundance and distribution of species found in sedimentary rocks provide valuable information about the age and depositional environment. However, the analysis is difficult and time-consuming, as it is based on manual work by human experts. Attempts to automate this process face two key challenges: (1) the input data are very large - our dataset is projected to grow to 3 billion microfossils, and (2) there are not enough labeled data to use the standard procedure of training a deep learning classifier. We propose an efficient pipeline for processing and grouping fossils by genus, or even species, from microscope slides using self-supervised learning. First we show how to efficiently extract crops from whole slide images by adapting previously trained object detection algorithms. Second, we provide a comparison of a range of self-supervised learning methods to classify and identify microfossils from very few labels. We obtain excellent results with both convolutional neural networks and vision transformers fine-tuned by self-supervision. Our approach is fast and computationally light, providing a handy tool for geologists working with microfossils.

‍