BioCube: A Multimodal Dataset for Biodiversity Research

2025-05-16

AI Summary

Current biodiversity research is hindered by the absence of large-scale, spatiotemporally aligned, and standardized multimodal datasets, limiting data-driven ecological modeling. To address this, we introduce BioCube—the first globally comprehensive (2000–2020), WGS84-georeferenced multimodal biodiversity dataset—integrating seven heterogeneous modalities: Sentinel satellite imagery, ERA5 meteorological data, environmental DNA (eDNA), soundscapes, photographic images, textual species descriptions, and land-use maps. We propose a geospatially driven multi-source fusion framework that enables fine-grained spatiotemporal alignment and semantic standardization across modalities for the first time. The dataset and end-to-end processing pipeline are fully open-sourced (Hugging Face / GitHub). Empirical evaluation demonstrates substantial improvements in generalizability and ecological interpretability for species distribution modeling and community dynamics prediction, establishing a foundational resource for scalable, multimodal biodiversity science.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Biodiversity research requires complete and detailed information to study ecosystem dynamics at different scales. Employing data-driven methods like Machine Learning is getting traction in ecology and more specific biodiversity, offering alternative modelling pathways. For these methods to deliver accurate results there is the need for large, curated and multimodal datasets that offer granular spatial and temporal resolutions. In this work, we introduce BioCube, a multimodal, fine-grained global dataset for ecology and biodiversity research. BioCube incorporates species observations through images, audio recordings and descriptions, environmental DNA, vegetation indices, agricultural, forest, land indicators, and high-resolution climate variables. All observations are geospatially aligned under the WGS84 geodetic system, spanning from 2000 to 2020. The dataset will become available at https://huggingface.co/datasets/BioDT/BioCube while the acquisition and processing code base at https://github.com/BioDT/bfm-data.

Problem

• Lack of large multimodal datasets for biodiversity research
• Need for granular spatial-temporal biodiversity data
• Absence of curated global species-environment datasets

Innovation

• Multimodal dataset with images, audio, and eDNA
• Geospatially aligned global biodiversity observations
• High-resolution climate and environmental variables