BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity

2024-06-25

AI Summary

Biodiversity AI models suffer from poor generalization to rare species and ecologically critical taxa due to insufficient large-scale, high-quality, and taxonomically comprehensive image data. Method: We introduce BioTrove—the largest publicly available research-grade biodiversity image dataset to date—comprising 161.9 million images spanning ~366,000 species across Animalia, Plantae, and Fungi, annotated with scientific names, taxonomic hierarchies, and common names. We further propose the first multi-level zero-shot evaluation benchmark tailored for biodiversity conservation and release BioTrove-Train—a curated subset focused on agriculturally and ecologically vital groups (e.g., insects, birds, fungi)—alongside a specialized CLIP-based model. Contribution/Results: Experiments demonstrate substantial improvements in zero-shot recognition of juveniles, rare species, and morphologically similar congeners. The framework shows strong practical utility in real-world applications such as pest and disease identification and crop monitoring.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Bio-inspired Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web search models and ranking

Abstract

We introduce BioTrove, the largest publicly accessible dataset designed to advance AI applications in biodiversity. Curated from the iNaturalist platform and vetted to include only research-grade data, BioTrove contains 161.9 million images, offering unprecedented scale and diversity from three primary kingdoms: Animalia ("animals"), Fungi ("fungi"), and Plantae ("plants"), spanning approximately 366.6K species. Each image is annotated with scientific names, taxonomic hierarchies, and common names, providing rich metadata to support accurate AI model development across diverse species and ecosystems. We demonstrate the value of BioTrove by releasing a suite of CLIP models trained using a subset of 40 million captioned images, known as BioTrove-Train. This subset focuses on seven categories within the dataset that are underrepresented in standard image recognition models, selected for their critical role in biodiversity and agriculture: Aves ("birds"), Arachnida ("spiders/ticks/mites"), Insecta ("insects"), Plantae ("plants"), Fungi ("fungi"), Mollusca ("snails"), and Reptilia ("snakes/lizards"). To support rigorous assessment, we introduce several new benchmarks and report model accuracy for zero-shot learning across life stages, rare species, confounding species, and multiple taxonomic levels. We anticipate that BioTrove will spur the development of AI models capable of supporting digital tools for pest control, crop monitoring, biodiversity assessment, and environmental conservation. These advancements are crucial for ensuring food security, preserving ecosystems, and mitigating the impacts of climate change. BioTrove is publicly available, easily accessible, and ready for immediate use.

Problem

• biodiversity
• AI models
• dataset diversity

Innovation

• BioTrove
• zero-shot learning
• biodiversity dataset