A Physics-Informed, Behavior-Aware Digital Twin for Robust Multimodal Forecasting of Core Body Temperature in Precision Livestock Farming

TL;DR

This paper introduces a physics-informed digital twin combined with an ensemble learning approach for accurate, uncertainty-aware prediction of core body temperature in dairy cattle, enhancing heat stress management in livestock farming.

Contribution

It presents a novel integrated framework that fuses thermoregulation modeling, sensor data, and behavioral analysis with a stacked ensemble for improved temperature forecasting.

Findings

Achieved a cross-validated R2 of 0.783 for 2-hour ahead predictions.

Attained an F1 score of 84.25% and PICP of 92.38% in uncertainty quantification.

Demonstrated that multimodal data fusion improves predictive performance.

Abstract

Precision livestock farming requires accurate and timely heat stress prediction to ensure animal welfare and optimize farm management. This study presents a physics-informed digital twin (DT) framework combined with an uncertainty-aware, expert-weighted stacked ensemble for multimodal forecasting of Core Body Temperature (CBT) in dairy cattle. Using the high-frequency, heterogeneous MmCows dataset, the DT integrates an ordinary differential equation (ODE)-based thermoregulation model that simulates metabolic heat production and dissipation, a Gaussian process for capturing cow-specific deviations, a Kalman filter for aligning predictions with real-time sensor data, and a behavioral Markov chain that models activity-state transitions under varying environmental conditions. The DT outputs key physiological indicators, such as predicted CBT, heat stress probability, and behavioral state distributions are fused with raw sensor data and enriched through multi-scale temporal analysis and cross-modal feature engineering to form a comprehensive feature set. The predictive methodology is designed in a three-stage stacked ensemble, where stage 1 trains modality-specific LightGBM 'expert' models on distinct feature groups, stage 2 collects their predictions as meta-features, and at stage 3 Optuna-tuned LightGBM meta-model yields the final CBT forecast. Predictive uncertainty is quantified via bootstrapping and validated using Prediction Interval Coverage Probability (PICP). Ablation analysis confirms that incorporating DT-derived features and multimodal fusion substantially enhances performance. The proposed framework achieves a cross-validated R2 of 0.783, F1 score of 84.25% and PICP of 92.38% for 2-hour ahead forecasting, providing a robust, uncertainty-aware, and physically principled system for early heat stress detection and precision livestock management.