A new prediction model based on deep learning for pig house environment
Authors:
Open Access
- 28 December 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Abstract
A prediction model of the pig house environment based on Bayesian optimization (BO), squeeze and excitation block (SE), convolutional neural network (CNN) and gated recurrent unit (GRU) is proposed to improve the prediction accuracy and animal welfare and take control measures in advance. To ensure the optimal model configuration, the model uses a BO algorithm to fine-tune hyper-parameters, such as the number of GRUs, initial learning rate and L2 normal form regularization factor. The environmental data are fed into the SE-CNN block, which extracts the local features of the data through convolutional operations. The SE block further learns the weights of the feature channels, highlights the important features and suppresses the unimportant ones, improving the feature discrimination ability. The extracted local features are fed into the GRU network to capture the long-term dependency in the sequence, and this information is used to predict future values. The indoor environmental parameters of the pig house are predicted. The prediction performance is evaluated through comparative experiments. The model outperforms other models (e.g., CNN-LSTM, CNN-BiLSTM and CNN-GRU) in predicting temperature, humidity, CO2 and NH3 concentrations. It has higher coefficient of determination (R2), lower mean absolute error (MSE), and mean absolute percentage error (MAPE), especially in the prediction of ammonia, which reaches R2 of 0. 9883, MSE of 0.03243, and MAPE of 0.01536. These data demonstrate the significant advantages of the BO-SE-CNN-GRU model in prediction accuracy and stability. This model provides decision support for environmental control of pig houses.Keywords
Funding Information
- Key Projects of Qiqihar City Scientific and Technological Plan (ZDGG-202202)
- General Research Project on Higher Education Teaching Reform in Heilongjiang Province (SJGY20220410)
- Educational Science Research Project of Qiqihar University (GJQTYB202212)
- Collaborative Innovation Achievement Project of "Double First-class" Disciplines in Heilongjiang Province (LJGXCG2024-P25)
- The Basic Research Fund for State-owned Universities in Heilongjiang Province (145209311)
This publication has 38 references indexed in Scilit:
- Haze prediction method based on stacking learningStochastic Environmental Research and Risk Assessment, 2023
- High performance machine learning approach for reference evapotranspiration estimationStochastic Environmental Research and Risk Assessment, 2023
- Modeling and predicting mean indoor radon concentrations in Austria by generalized additive mixed modelsStochastic Environmental Research and Risk Assessment, 2023
- Review: What have we learned about the effects of heat stress on the pig industry?Animal, 2022
- Optimising the design of confined laying hen house insulation requirements in cold climates without using supplementary heatBiosystems Engineering, 2018
- Co-evolutionary multi-task learning for dynamic time series predictionApplied Soft Computing, 2018
- Review on greenhouse gas emissions from pig houses: Production of carbon dioxide, methane and nitrous oxide by animals and manureAgriculture, Ecosystems & Environment, 2015
- Modelling ventilation rate, balance temperature and supplemental heat need in alternative vs. conventional laying-hen housing systemsBiosystems Engineering, 2013
- Ammonia emissions from pig houses: Influencing factors and mitigation techniquesAgriculture, Ecosystems & Environment, 2011
- A Thermal Balance Model for Livestock Buildings for use in Climate Change StudiesJournal of Agricultural Engineering Research, 1998