Multi-Scale and Multimodal Species Distribution Modeling

TL;DR

This paper introduces a modular deep learning framework for species distribution modeling that incorporates multi-scale and multimodal environmental data, improving prediction accuracy by optimizing spatial extent and modality fusion.

Contribution

It presents a novel multi-scale, multimodal SDM architecture with a late fusion approach, allowing flexible scale testing and improved ecological predictions.

Findings

Multi-scale modeling enhances SDM accuracy.

Multimodal data fusion improves prediction performance.

Results outperform existing benchmarks on GeoLifeCLEF 2023.

Abstract

Species distribution models (SDMs) aim to predict the distribution of species by relating occurrence data with environmental variables. Recent applications of deep learning to SDMs have enabled new avenues, specifically the inclusion of spatial data (environmental rasters, satellite images) as model predictors, allowing the model to consider the spatial context around each species' observations. However, the appropriate spatial extent of the images is not straightforward to determine and may affect the performance of the model, as scale is recognized as an important factor in SDMs. We develop a modular structure for SDMs that allows us to test the effect of scale in both single- and multi-scale settings. Furthermore, our model enables different scales to be considered for different modalities, using a late fusion approach. Results on the GeoLifeCLEF 2023 benchmark indicate that considering multimodal data and learning multi-scale representations leads to more accurate models.