Few-shot Species Range Estimation
Keywords: species distribution modeling, SDM, spatial implicit neural representation, SINR, low-shot learning, few-shot learning
TL;DR: A new low-shot method for estimating the spatial range of species
Abstract: Understanding where a particular species can or cannot be found is crucial for ecological research and conservation efforts. By mapping the spatial ranges of all species on Earth, we could obtain deeper insights into how global biodiversity is affected by climate change and habitat loss. However, accurate range estimates are available for a relatively small proportion of known species. For most species, we have only have a few prior observations indicating the locations where they have been previously recorded. In this work we address the challenge of training with limited observations by developing a new approach for few-shot species range estimation. During inference, our model takes a set of spatial coordinates as input, along with optional metadata such as text, and outputs a species encoding that can be used to predict the range of a previously unseen species in feed-forward manner. We validate our method on two challenging benchmarks, where we obtain state-of-the-art performance in predicting the ranges of unseen species, in a fraction of the compute time, compared to recent alternative approaches.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8203
Loading