Multi-Scale and Multimodal Species Distribution Modeling
This work addresses a scale-related bottleneck in species distribution modeling for ecology and conservation, though it appears incremental as it builds on existing deep learning methods for SDMs.
The authors tackled the problem of determining the appropriate spatial scale for species distribution models (SDMs) when using deep learning with multimodal data, and found that their modular multi-scale and multimodal approach led to more accurate models on the GeoLifeCLEF 2023 benchmark.
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.