Machine Learning Approach to Predict Air Temperature and Relative Humidity inside Mechanically and Naturally Ventilated Duck Houses: Application of Recurrent Neural Network

Abstract

The duck industry ranks sixth as one of the fastest-growing major industries for livestock production in South Korea. However, there are few studies quantitatively predicting the internal thermal and moisture environment of duck houses. In this study, high-accuracy recurrent neural network (RNN) models were used to predict the internal air temperature and relative humidity of mechanically and naturally ventilated duck houses. The models were developed according to the type of duck houses, seasons, and environmental variables by learning the monitoring data of the internal and external environments. The optimal sequence length of learning data for the development of the RNN model was selected as 120 min. As a result of the validation, both air temperature and relative humidity could be accurately predicted within 1% error. In addition, simplified RNN models were additionally developed by learning only from the data of external air temperature, relative humidity, and duck weight, which are relatively easy to acquire at the farms. The accuracy of the simplified RNN models was similar to the basic model for predicting the internal air temperature and relative humidity of duck houses in real time. In the future, for the convergence of information and communications technologies (ICTs) and application of smart farms in duck houses, the RNN models of duck houses developed in this study can be applied to predict and control the internal environments of duck houses using the model predictive control (MPC) technique.

The Development Strategy of Chongqing Duck Industry Under the Background of Intelligent Breeding: Take Pingyalian Project as an Example

“…(6) Promoting comprehensive rural development By combining the duck industry with rural tourism, ecological agriculture, and other projects, the diversified development of the rural economy can be promoted, and the sustainability of the projects can be further enhanced by encouraging the community to participate in the management and operation of the breeding projects (Lee et al, 2022;Karunathilake et al, 2023). This comprehensive development strategy can create new economic growth fields in rural areas, promote cooperation and exchange between community members, jointly promote the prosperity of duck industry and related industries, and provide an effective way to realize the comprehensive development of the rural economy and society.…”

Performance Comparison Between Artificial Neural Network, Recurrent Neural Network and Long Short-Term Memory for Prediction of Extreme Climate Change

“…Research conducted by Arora et al, said the prediction results of the air quality index for various cities showed that the RNN produced higher accuracy with the smallest MAPE of 4,70% [6]. Another study was conducted by Lee and friends, that the RNN algorithm can accurately predict air temperature and relative humidity within 1% error [7]. Besides that.…”

Cabin air dynamics: Unraveling the patterns and drivers of volatile organic compound distribution in vehicles

“…Zhang et al made multiple attempts to apply artificial neural network models ( 43 ), single-feature LSTM model ( 44 ), and multifeature LSTM model ( 45 ) to forecast VOC concentrations emitted from furniture, classroom, and actual residence, with acceptable outcomes. Deep learning models, including RNN and LSTM models, have gained recognition for their efficacy in predicting indoor pollutant concentrations, and are also playing an important role in controlling the internal environment of smart farming facilities ( 46 , 47 ). As an inseparable component of human living environment, the in-cabin environment has also captured great attention recently.…”