Feedforward Few-shot Species Range Estimation

Christian Lange, Max Hamilton, Elijah Cole, Alexander Shepard, Samuel Heinrich, Angela Zhu, Subhransu Maji, Grant Van Horn, Oisin Mac Aodha
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32523-32561, 2025.

Abstract

Knowing where a particular species can or cannot be found on Earth is crucial for ecological research and conservation efforts. By mapping the spatial ranges of all species, we would obtain deeper insights into how global biodiversity is affected by climate change and habitat loss. However, accurate range estimates are only available for a relatively small proportion of all known species. For the majority of the remaining species, we typically only have a small number of records denoting the spatial locations where they have previously been observed. We outline a new approach for few-shot species range estimation to address the challenge of accurately estimating the range of a species from limited data. During inference, our model takes a set of spatial locations as input, along with optional metadata such as text or an image, and outputs a species encoding that can be used to predict the range of a previously unseen species in a feedforward manner. We evaluate our approach on two challenging benchmarks, where we obtain state-of-the-art range estimation performance, in a fraction of the compute time, compared to recent alternative approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-lange25a, title = {Feedforward Few-shot Species Range Estimation}, author = {Lange, Christian and Hamilton, Max and Cole, Elijah and Shepard, Alexander and Heinrich, Samuel and Zhu, Angela and Maji, Subhransu and Horn, Grant Van and Mac Aodha, Oisin}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {32523--32561}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/lange25a/lange25a.pdf}, url = {https://proceedings.mlr.press/v267/lange25a.html}, abstract = {Knowing where a particular species can or cannot be found on Earth is crucial for ecological research and conservation efforts. By mapping the spatial ranges of all species, we would obtain deeper insights into how global biodiversity is affected by climate change and habitat loss. However, accurate range estimates are only available for a relatively small proportion of all known species. For the majority of the remaining species, we typically only have a small number of records denoting the spatial locations where they have previously been observed. We outline a new approach for few-shot species range estimation to address the challenge of accurately estimating the range of a species from limited data. During inference, our model takes a set of spatial locations as input, along with optional metadata such as text or an image, and outputs a species encoding that can be used to predict the range of a previously unseen species in a feedforward manner. We evaluate our approach on two challenging benchmarks, where we obtain state-of-the-art range estimation performance, in a fraction of the compute time, compared to recent alternative approaches.} }
Endnote
%0 Conference Paper %T Feedforward Few-shot Species Range Estimation %A Christian Lange %A Max Hamilton %A Elijah Cole %A Alexander Shepard %A Samuel Heinrich %A Angela Zhu %A Subhransu Maji %A Grant Van Horn %A Oisin Mac Aodha %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-lange25a %I PMLR %P 32523--32561 %U https://proceedings.mlr.press/v267/lange25a.html %V 267 %X Knowing where a particular species can or cannot be found on Earth is crucial for ecological research and conservation efforts. By mapping the spatial ranges of all species, we would obtain deeper insights into how global biodiversity is affected by climate change and habitat loss. However, accurate range estimates are only available for a relatively small proportion of all known species. For the majority of the remaining species, we typically only have a small number of records denoting the spatial locations where they have previously been observed. We outline a new approach for few-shot species range estimation to address the challenge of accurately estimating the range of a species from limited data. During inference, our model takes a set of spatial locations as input, along with optional metadata such as text or an image, and outputs a species encoding that can be used to predict the range of a previously unseen species in a feedforward manner. We evaluate our approach on two challenging benchmarks, where we obtain state-of-the-art range estimation performance, in a fraction of the compute time, compared to recent alternative approaches.
APA
Lange, C., Hamilton, M., Cole, E., Shepard, A., Heinrich, S., Zhu, A., Maji, S., Horn, G.V. & Mac Aodha, O.. (2025). Feedforward Few-shot Species Range Estimation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:32523-32561 Available from https://proceedings.mlr.press/v267/lange25a.html.

Related Material