Estimating Pasture Biomass from Top-View Images: A Dataset for Precision Agriculture

2025-10-26

AI Summary

This study addresses the low accuracy of pasture forage yield estimation, which hinders scientific stocking rate determination and grazing management. To this end, we construct the first large-scale top-view multimodal forage biomass dataset comprising 1,162 images, integrating RGB imagery, active optical sensor (AOS)-derived NDVI and vegetation height, and ground-truthed biomass measurements (dry and fresh weight). Unlike conventional remote sensing or single-modality approaches, our dataset systematically unifies visual, spectral, and structural information, with synchronized spatial–spectral–biophysical multi-dimensional annotations. The dataset is publicly released and has served as the foundation for an international Kaggle competition. It significantly advances deep learning–based automated forage biomass estimation, providing a reproducible, scalable data foundation and methodological paradigm for smart livestock farming.

Technology Category

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

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate estimation of pasture biomass is important for decision-making in livestock production systems. Estimates of pasture biomass can be used to manage stocking rates to maximise pasture utilisation, while minimising the risk of overgrazing and promoting overall system health. We present a comprehensive dataset of 1,162 annotated top-view images of pastures collected across 19 locations in Australia. The images were taken across multiple seasons and include a range of temperate pasture species. Each image captures a 70cm * 30cm quadrat and is paired with on-ground measurements including biomass sorted by component (green, dead, and legume fraction), vegetation height, and Normalized Difference Vegetation Index (NDVI) from Active Optical Sensors (AOS). The multidimensional nature of the data, which combines visual, spectral, and structural information, opens up new possibilities for advancing the use of precision grazing management. The dataset is released and hosted in a Kaggle competition that challenges the international Machine Learning community with the task of pasture biomass estimation. The dataset is available on the official Kaggle webpage: https://www.kaggle.com/competitions/csiro-biomass

Problem

• Estimating pasture biomass from top-view images for precision agriculture
• Managing livestock stocking rates to optimize pasture utilization
• Providing annotated dataset combining visual, spectral and structural information

Innovation

• Created annotated top-view pasture image dataset
• Combined visual spectral structural biomass measurements
• Hosted Kaggle competition for ML biomass estimation