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.

Fine particulate matter (PM_2.5) can carry numerous substances and penetrate deep into the respiratory tract due to its small particle size; associated harmful microorganisms are suspected to increase health risks for humans and animals. To find out the microbial compositions of PM_2.5 in piggeries, their interaction and traceability, we collected PM_2.5 samples from a piggery while continuously monitoring the environmental indicators. We also identified pathogenic bacteria and allergens in the samples using high-throughput sequencing technology. We analyzed the microbial differences of PM_2.5 samples at different heights and during different times of day and investigated the microbial dynamics among the PM_2.5 samples. To better understand the interaction between microorganisms and environmental factors among different microbial communities, we applied the network analysis method to identify the correlation among various variables. Finally, SourceTracker, a commonly used microbial traceability tool, was used to predict the source of airborne microorganisms in the pig house. We identified 14 potential pathogenic bacteria and 5 allergens from PM_2.5 in the pig houses, of which Acinetobacter was the dominant bacterium in all samples (relative abundance > 1%), which warrants attention. We found that bacteria and fungi directly affected the the microbial community. The bacterial community mainly played a positive role in the microbial community. Environmental variables mainly indirectly and positively affected microbial abundance. In the SourceTracker analysis using fecal matter and feed as sources and PM_2.5 sample as sink, we found that fecal matter made the greatest contribution to both bacterial and fungal components of PM_2.5. Our findings provide important insights into the potential risks of pathogens in PM_2.5 to human and animal health and their main sources.