Prediction of Ammonia Concentration in a Pig House Based on Machine Learning Models and Environmental Parameters

Abstract

Accurately predicting the air quality in a piggery and taking control measures in advance are important issues for pig farm production and local environmental management. In this experiment, the NH3 concentration in a semi-automatic piggery was studied. First, the random forest algorithm (RF) and Pearson correlation analysis were combined to analyze the environmental parameters, and nine input schemes for the model feature parameters were identified. Three kinds of deep learning and three kinds of conventional machine learning algorithms were applied to the prediction of NH3 in the piggery. Through comparative experiments, appropriate environmental parameters (CO2, H2O, P, and outdoor temperature) and superior algorithms (LSTM and RNN) were selected. On this basis, the PSO algorithm was used to optimize the hyperparameters of the algorithms, and their prediction performance was also evaluated. The results showed that the R2 values of PSO-LSTM and PSO-RNN were 0.9487 and 0.9458, respectively. These models had good accuracy when predicting NH3 concentration in the piggery 0.5 h, 1 h, 1.5 h, and 2 h in advance. This study can provide a reference for the prediction of air concentrations in pig house environments.

Structure Optimization and Data Processing Method of Electronic Nose Bionic Chamber for Detecting Ammonia Emissions from Livestock Excrement Fermentation

“…Under the same gas concentration, the gas flow on the sensor surface varies, resulting in varied sensor responses. Previous studies [ 31 , 32 , 33 , 34 , 35 ] did not consider the electronic nose gas chamber’s effect on the output of the system. In this system, four groups of sensors with cross-sensitivity provide various response signals to the same gas concentration when activated via a bionic chamber.…”

“…In a different approach, researchers developed a livestock odor monitoring system incorporating information and communications technology (ICT) and ammonia sensors [ 34 ], enabling trend analysis of collected odor data. Furthermore, a study applied electronic nose technology [ 35 ] in pigsties by integrating a deep learning algorithm optimized using particle swarm optimization to enhance detection accuracy, achieving a determination coefficient R 2 over 0.94. However, most electronic nose methods employ passive sensor placement, resulting in poor real-time data and detection accuracy.…”

Potential of Organic Acids, Essential Oils and Their Blends in Pig Diets as Alternatives to Antibiotic Growth Promoters

“…Supplementing pigs with butyrate showed an effect on boar taint impacting pork sensory attributes. Butyrate has a regulatory effect on cell apoptosis and accumulation of androsterone in pigs, which causes boar taint [ 81 ]. However, there is a need for more research on the sensory effects of organic acids and essential oils in pork.…”

Research on Indoor Environment Prediction of Pig House Based on OTDBO–TCN–GRU Algorithm

“…In order to improve the prediction accuracy of complex and dynamically changing environmental factors in piggery environments, researchers have carried out a variety of studies that range from traditional statistical methods to modern machine learning techniques [ 10 , 11 , 12 ]. The high degree of non-linearity, rapid dynamic changes, and strong data dependence of the swine barn environment have led to the fact that existing prediction methods often face problems of insufficient prediction accuracy and poor adaptability to environmental changes [ 13 , 14 , 15 ].…”