All Earth

Artificial Intelligence in Paleontology

Paleontology is entering a data transition. Digital imaging, CT scanning, 3D reconstruction, geochemical and fossil occurrence datasets, and the vast legacy literature have created opportunities that exceed the capacity of traditional manual workflows.

As more data becomes available, artificial intelligence has begun to transform paleontology from a manual, expert-driven discipline into a more scalable, data-driven, and integrative earth science. Fossils, sediments, geochemical proxies, and stratigraphic records all contain information about how life and environment change through deep time, but much of it remains difficult to extract at scale. Recent work shows that AI is increasingly being applied to various paleontological problems. When combined with stratigraphy, sedimentology, geochemistry, and earth-system thinking, AI in paleontology can generate new insights into planetary change across biological, environmental, and geological timescales.

Paleontological records are essential to understanding planetary changes. Deep-time archives reveal how ecosystems and biodiversity responded to long-term warming, cooling, sea-level fluctuation, and extreme events. AI in paleontology is not merely a technical exercise in fossil classification, but a route toward better reconstruction of earth-system history and more integrated analysis of biosphere-lithosphere-hydrosphere interactions.

While the use of AI in paleontology is growing, it is still far from mainstream regarding methodological innovation, research scale, and broader adoption. Limited sample sizes, uneven preservation, and taxonomic and taphonomic bias are inherent to the fossilization process, and these challenges make paleontology an important test bed for interpretable, uncertainty-aware, and domain-informed AI.

This Article Collection aims to present how AI can help paleontological studies and subsequently its contribution to multidisciplinary earth sciences, motivated by the rapid growth of complex, heterogeneous datasets and the need for more powerful analytical tools across the geosciences.

We welcome original studies that apply artificial intelligence/machine learning/deep learning, and related data-driven methods to paleontological and deep-time earth system questions. We are particularly interested in work that used paleontological evidence to illuminate past changes in earth systems and processes, and that connects fossil, stratigraphy, sedimentology, geochemistry, and paleoenvironment. Suggested subtopics include, but are not limited to:

1. Fossil identification and classification using computer vision, deep learning, geometric morphometrics;
2. Automated extraction of paleontological data from legacy literature, museum archives, and other databases;
3. AI for phylogenetics, taxonomy, and morphological evolution;
4. Paleoecological and paleobiological prediction using AI;
5. Integration of fossils with geochemistry and sedimentology to investigate paleoclimate, environmental changes, and earth-life feedback;
6. Foundation datasets, benchmarks, and reproducible workflows for paleontological AI

Original research articles are preferred for this collection, and other article types listed in journal information will be considered.

Article Collection Guest Advisors

Professor Congyu Yu is a paleontologist interested in artificial intelligence application in fossil data and dinosaur evolution. His research uses various machine learning approaches to understand how much information can be preserved and extracted from accumulating fossil data. While AI is making rapid progress in both earth and life sciences, this work helps us alleviate cost in fossil data processing and explore the merits from multi-modal fossil data.

Dr Zichuan Qin uses multi-disciplinary methods from high-resolution CT scans, finite element analysis, and macroevolution analysis to understand the morphological and functional evolution in dinosaur and other organisms. He is interested in the theoretical morphospace built from fossil morphology and how different lineage evolved in it, and how organisms distribute in the inferred functional space. Recently, he has been working on major morphological changes in theropod dinosaur and its link to the origin of birds.

Further Information

­­All manuscripts submitted to this Article Collection will undergo a full peer-review; the Guest Advisor for this Collection will not be handling the manuscripts

Please review the journal scope and author submission instructions prior to submitting a manuscript

The deadline for submitting manuscripts is 31 March 2027

Please contact Alex Johnson at alex.johnson@tandf.co.uk if you have any questions about this Article Collection, or for information on available discounts

At submission:

• Please be sure to select the appropriate Article Collection from the drop-down menu in the submission system
• Please select Planetary Change & Paleosciences from the list of available sections during submission. Failure to select the appropriate Article Collection or Section name can result in delays

Article Collection Key Words:

1. Artificial intelligence
2. Machine learning
3. Deep learning
4. Paleontology
5. Fossil data