Comparison of Neuro-Fuzzy and Neural Networks Techniques for Estimating Ammonia Concentration in Poultry Farms

Abstract

Ammonia (NH3) is a primary air pollutant in poultry farms that affects the ecosystem, environment, and birds and humans' health adversely. Therefore, estimating NH3 concentration is valuable in research on environmental protection, human and animal health, litter management, etc. The study's main objective was to develop a simple, accurate, rapid, and economic model that estimates NH3 concentration in poultry farms best. To do so, four different models-multilayer perceptron (MLP), integrated adaptive neuro-fuzzy inference systems with grid partitioning and subtractive clustering (ANFIS-GP and ANFIS-SC), and multiple linear regression analysis (MLR)-were performed to estimate NH3 concentration in poultry farms using climatic variables and litter quality properties that can be obtained easily. The root mean square error (RMSE), mean relative percentage absolute error (MRPE), and determination coefficient (R-2) were used to evaluate the applied models' performance. A comparison of the results indicated that the ANFIS-SC model, the inputs of which are air temperature, air relative humidity, and airspeed, was the most suitable estimation model with respect to RMSE, MRPE, and R-2 to predict NH3 concentration (1.130 ppm, 4.032%, and 0.858, respectively) for the validation dataset. The MLR model's results were the least accurate. In conclusion, this study recommends the neurocomputing model developed as an alternative approach to estimating NH3 concentration in poultry farms because it yields accurate estimations quickly.