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

TL;DR

This paper presents a novel spatio-temporal graph neural network framework for forecasting sustainability indices at the county level in dairy farms, integrating data augmentation and a new scoring system for comprehensive policy analysis.

Contribution

It introduces the first county-scale application of STGNNs for dairy farm sustainability forecasting, combining VAE-based data augmentation and a new pillar-based scoring method.

Findings

Effective multi-year forecasts for 2026-2030 generated.

Novel STGNN architecture encodes geographic and temporal dependencies.

Augmented datasets improve model robustness and accuracy.

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.