Neural Federated Learning for Livestock Growth Prediction

2026-03-30

AI Summary

This work addresses the challenges of limited data availability and poor model generalization in livestock growth prediction, which stem from data silos and privacy constraints across farms. To overcome these issues, the study proposes LivestockFL, the first federated learning framework tailored for livestock growth forecasting, along with its personalized variant, LivestockPFL. Without exchanging raw data, the approach enables multiple farms to collaboratively train a neural network that integrates GRU and MLP architectures, while employing customized prediction heads to balance shared global knowledge with farm-specific characteristics. Experimental results demonstrate that the proposed methods significantly enhance prediction accuracy and robustness, particularly excelling in data-scarce settings. This study marks the first successful application of federated learning to the domain of livestock growth prediction.

Abstract

Livestock growth prediction is essential for optimising farm management and improving the efficiency and sustainability of livestock production, yet it remains underexplored due to limited large-scale datasets and privacy concerns surrounding farm-level data. Existing biophysical models rely on fixed formulations, while most machine learning approaches are trained on small, isolated datasets, limiting their robustness and generalisability. To address these challenges, we propose LivestockFL, the first federated learning framework specifically designed for livestock growth prediction. LivestockFL enables collaborative model training across distributed farms without sharing raw data, thereby preserving data privacy while alleviating data sparsity, particularly for farms with limited historical records. The framework employs a neural architecture based on a Gated Recurrent Unit combined with a multilayer perceptron to model temporal growth patterns from historical weight records and auxiliary features. We further introduce LivestockPFL, a novel personalised federated learning framework that extends the above federated learning framework with a personalized prediction head trained on each farm's local data, producing farm-specific predictors. Experiments on a real-world dataset demonstrate the effectiveness and practicality of the proposed approaches.

Problem

• livestock growth prediction
• data privacy
• federated learning
• data sparsity
• generalisability

Innovation

• Federated Learning
• Livestock Growth Prediction
• Personalized Federated Learning
• GRU-based Neural Architecture
• Data Privacy