Machine Learning-Based Microclimate Model for Indoor Air Temperature and Relative Humidity Prediction in a Swine Building.

Jaesung Park,Elanchezhian Arulmozhi,Thavisack Sihalath,Hyeon Tae Kim,Byeong Eun Moon,Jayanta Kumar Basak

doi:10.3390/ani11010222

Jaesung Park, Elanchezhian Arulmozhi + Show 4 more

Open Access

https://doi.org/10.3390/ani11010222

Copy DOI

Abstract

Simple SummaryIndoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables. Among other livestock animals, pigs are more sensitive to environmental equilibrium; a lack of favorable environment in barns affects the productivity parameters such as voluntary feed intake, feed conversion, heat stress, etc. Machine learning (ML) based prediction models are utilized for solving various nonlinear problems in the current decade. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. Typically, most of the available IAT and IRH models are limited to feed the animal biological data as the input. Since the biological factors of the internal animals are challenging to acquire, this study used accessible factors such as external environmental data to simulate the models. Three different input datasets named S1 (weather station parameters), S2 (weather station parameters and indoor attributes), and S3 (Highly correlated values) were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available.Indoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables; still, potential contributors that influence the homeostasis of livestock animals reared in closed barns. Further, predicting IAT and IRH encourages farmers to think ahead actively and to prepare the optimum solutions. Therefore, the primary objective of the current literature is to build and investigate extensive performance analysis between popular ML models in practice used for IAT and IRH predictions. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. This study used accessible factors such as external environmental data to simulate the models. In addition, three different input datasets named S1, S2, and S3 were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction among other models particularly with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available. Overall, the current study demonstrates a better model among other models to predict IAT and IRH of a naturally ventilated swine building containing animals with fewer input attributes.

Highlights

The current study considers the use of different datasets as a useful method to ascertain the appropriate data that may have fewer variables and significant implications for predictions [20,21,36,37]
The current study successfully predicts Indoor air temperature (IAT) and indoor relative humidity (IRH) using simple and powerful Machine learning (ML) models. This literature attempts to conclude with the following key points
The random forest regression (RFR) models performed the most well among all the forecasting models used in this research most probably

Summary

Introduction

Climate change has intensified the impacts against agriculture production over the past few decades that makes bewilderment on the livelihoods of farmers and consumers. In the current scenario, producing high quality agricultural products using traditional farming methodologies is becoming arduous for the farmers. In 2030, the world would have to feed more than 8 billion people, whereas maintaining sustainable farming methodologies is an enormous challenge for food security [1]. Extreme weather conditions directly affect the livestock sector in several ways, such as productivity losses, biological changes, and welfare issues [2]. There is a demand to adopt modern farming methods such as smart livestock farming (SLF), which are alternatives to conventional farming methods to address these challenges. The significance of well-managed animal welfare is not narrow to ethical aspects; it is vital to realize an effective action of provoking animal commodities

Results

Discussion

Conclusion