Spatio-Temporal Graph Neural Networks for Dairy Farm Sustainability Forecasting and Counterfactual Policy Analysis

2025/12/23 by Surya Jayakumar, Kieran Sullivan, Jayakumar, Surya +7
Biochemistry, Genetics and Molecular Biology · Environmental Science · #Agriculture Sustainability and Environmental Impact #FOS: Computer and information sciences #FOS: Electrical engineering #Genetic and phenotypic traits in livestock #Machine Learning (cs.LG) #Sustainable Agricultural Systems Analysis #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2512.19970

openalex publication_date 2025/12/23 · openalex created_date 2025/12/25 · openalex updated_date 2026/07/28

Abstract

This study introduces a novel data-driven framework and the first-ever county-scale application of Spatio-Temporal Graph Neural Networks (STGNN) to forecast composite sustainability indices from herd-level operational records. The methodology employs a novel, end-to-end pipeline utilizing a Variational Autoencoder (VAE) to augment Irish Cattle Breeding Federation (ICBF) datasets, preserving joint distributions while mitigating sparsity. A first-ever pillar-based scoring formulation is derived via Principal Component Analysis, identifying Reproductive Efficiency, Genetic Management, Herd Health, and Herd Management, to construct weighted composite indices. These indices are modelled using a novel STGNN architecture that explicitly encodes geographic dependencies and non-linear temporal dynamics to generate multi-year forecasts for 2026-2030.

Citations

• Agri-GNN: A Novel Genotypic-Topological Graph Neural Network Framework Built on GraphSAGE for Optimized Yield Prediction
• Dynamic Structure Learning through Graph Neural Network for Forecasting Soil Moisture in Precision Agriculture

Related

• Applying Time Series Deep Learning Models to Forecast the Growth of Perennial Ryegrass in Ireland
• Prediction of Herd Life in Dairy Cows Using Multi-Head Attention Transformers
• Global distribution of cattle, goats, sheep and horses at 1-km resolution for 2000—2022 based on sub-national census data and spatiotemporal Machine Learning
• Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
• TRANSAE -Accompagner le développement de l'activité de travail des agricultrices et agriculteurs via la communauté d'apprentissage.