多尺度多模态建模提升物种分布预测精度
Multi-Scale and Multimodal Species Distribution Modeling
- 模块化设计支持单/多尺度测试，灵活处理不同数据尺度
- 融合多模态数据与多尺度特征，GeoLifeCLEF 2023 上表现更优
- 适合关注生态建模、遥感与深度学习交叉研究的读者
物种分布模型（SDMs）通过关联观测数据与环境变量来预测物种分布。近年来，深度学习在SDMs中的应用使空间数据（如环境栅格、卫星图像）可作为预测因子，让模型考虑物种观测点周围的空问上下文。然而，图像的空间范围难以确定，且尺度对模型性能有显著影响。本文提出一种模块化结构，可在单尺度与多尺度设置下测试尺度效应，并支持不同模态采用不同尺度，采用后期融合策略。在GeoLifeCLEF 2023基准测试中，融合多模态数据并学习多尺度表示，显著提升了模型准确性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。