Heterogeneous graph neural networks for species distribution modeling
This work addresses the problem of predicting species occurrences for ecologists and conservationists, representing an incremental improvement by applying a novel graph-based method to an established domain.
The authors tackled species distribution modeling by introducing a presence-only model using heterogeneous graph neural networks, which treats species and locations as distinct node sets to predict detection records as edges. The model performed comparably to or better than existing single-species models and a neural network baseline across six regions in a benchmark dataset.
Species distribution models (SDMs) are necessary for measuring and predicting occurrences and habitat suitability of species and their relationship with environmental factors. We introduce a novel presence-only SDM with graph neural networks (GNN). In our model, species and locations are treated as two distinct node sets, and the learning task is predicting detection records as the edges that connect locations to species. Using GNN for SDM allows us to model fine-grained interactions between species and the environment. We evaluate the potential of this methodology on the six-region dataset compiled by National Center for Ecological Analysis and Synthesis (NCEAS) for benchmarking SDMs. For each of the regions, the heterogeneous GNN model is comparable to or outperforms previously-benchmarked single-species SDMs as well as a feed-forward neural network baseline model.