# A Patch and Attention Mechanism-Based Model for Multi-Parameter Prediction of Rabbit House Environmental Parameters

## TL;DR

A new model using patching and attention mechanisms accurately predicts rabbit house environmental conditions, improving farming efficiency and rabbit health.

## Contribution

A novel multi-parameter prediction model, PatchCrossFormer-RHP, is introduced with patching and cross-attention mechanisms for improved accuracy and generalization.

## Key findings

- PatchCrossFormer-RHP outperforms RNN, GRU, and LSTM in predicting temperature, humidity, and CO2 concentration in rabbit houses.
- The model achieves strong cross-regional generalization with limited target-domain data through transfer learning.
- High R2 values (up to 0.963) demonstrate the model's effectiveness in capturing environmental dynamics.

## Abstract

Accurate prediction of temperature, humidity, and carbon dioxide concentration inside rabbit houses makes it possible to regulate the environment more precisely, which improves housing conditions and ultimately enhances the health and productivity of rabbits. To improve prediction accuracy and cross-regional generalization, a multi-parameter prediction model for rabbit houses is proposed, integrating patching and attention mechanisms. The model employs differentiated encoding strategies for environmental and auxiliary parameters, substantially enhancing its multi-parameter modeling capabilities. Experimental results indicate that the model achieves superior predictive accuracy and strong cross-regional generalization, supporting intelligent environmental regulation in intensive rabbit farming.

The health and productivity of rabbits are highly sensitive to the environmental conditions within the rabbit house, particularly to fluctuations and deviations in temperature, relative humidity, and carbon dioxide (CO2) concentration. However, owing to the thermal inertia and residual evaporation effects inherent in ventilation and cooling systems, environmental changes often exhibit delayed responses, rendering real-time control inadequate. Accurate prediction of key environmental parameters is indispensable for formulating effective environmental control strategies, as it enables consideration of their future dynamics and thereby enhances the rationality of regulation in rabbit farming. Existing prediction models often exhibit unsatisfactory accuracy and weak generalization, which restricts the incorporation of prediction into effective environmental control strategies. To address these limitations, summer indoor and outdoor environmental data were collected from rabbit houses in Nanping, Fujian; Jiyuan, Henan; and Qingyang, Gansu, China—three climatically distinct regions—forming three datasets. Based on these datasets, a multi-parameter time-series prediction model, Patch and Cross-Attention Enhanced Transformer for Rabbit House Prediction (PatchCrossFormer-RHP), is introduced, integrating patching and attention mechanisms. The model partitions the sequences of rabbit house temperature, relative humidity, and CO2 concentration into patches and incorporates auxiliary parameters, such as indoor air velocity and outdoor temperature and humidity, to enhance feature representation. Furthermore, it applies cross-attention with differentiated encoding to disentangle multi-parameter relationships and improve predictive performance. This study used the Fujian dataset as the primary benchmark. On this dataset, PatchCrossFormer-RHP achieved root mean square error (RMSE) values of 0.290 °C, 1.554%, and 38.837 ppm for rabbit house temperature, humidity, and CO2 concentration, respectively, with corresponding R2 values of 0.963, 0.956, and 0.838, consistently outperforming RNN, GRU, and LSTM. Transfer experiments with single- and multi-source pretraining followed by fine-tuning on Fujian demonstrated that strong cross-regional generalization can be achieved with only limited target-domain data.