Scholarlink

<p>Efficiently steering dairy production toward environmental viability requires models that jointly exploit spatial, temporal, and management information. This study introduces a novel data-driven framework and a county-scale application of Spatio-Temporal Graph Neural Networks (STGNN) to forecast composite sustainability indices from herd-level operational records derived from zootechnical indicators (e.g., calving interval, fertility, and herd management) as proxies for sustainability performance. The methodology employs an end-to-end pipeline utilizing a Variational Autoencoder (VAE) to augment Irish Cattle Breeding Federation (ICBF) datasets, preserving joint distributions while mitigating sparsity. A 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. The model achieves high predictive skill with a validation coefficient of determination above 0.90, significantly outperforming Temporal Graph Convolutional Network(T-GCN), Gaussian Kernel Regression (GKR), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Feedforward Neural Network (FFNN) baselines. Furthermore, scenario analyses show how modifying key management variables influence the projected composite sustainability scores in representative counties such as Monaghan and Kerry.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Spatio-temporal graph neural networks for dairy farm sustainability forecasting and strategic scenario analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月31日

查看全文
  • Surya Jayakumar,
  • Kieran Sullivan,
  • John McLaughlin,
  • Christine O’Meara,
  • Indrakshi Dey

摘要

Efficiently steering dairy production toward environmental viability requires models that jointly exploit spatial, temporal, and management information. This study introduces a novel data-driven framework and a county-scale application of Spatio-Temporal Graph Neural Networks (STGNN) to forecast composite sustainability indices from herd-level operational records derived from zootechnical indicators (e.g., calving interval, fertility, and herd management) as proxies for sustainability performance. The methodology employs an end-to-end pipeline utilizing a Variational Autoencoder (VAE) to augment Irish Cattle Breeding Federation (ICBF) datasets, preserving joint distributions while mitigating sparsity. A 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. The model achieves high predictive skill with a validation coefficient of determination above 0.90, significantly outperforming Temporal Graph Convolutional Network(T-GCN), Gaussian Kernel Regression (GKR), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Feedforward Neural Network (FFNN) baselines. Furthermore, scenario analyses show how modifying key management variables influence the projected composite sustainability scores in representative counties such as Monaghan and Kerry.