# Prediction of Ammonia Mitigation Efficiency in Sodium Bisulfate-Treated Broiler Litter Using Artificial Neural Networks

## TL;DR

This study uses artificial neural networks to predict how well sodium bisulfate reduces ammonia in broiler litter, offering a data-driven approach for managing emissions in poultry production.

## Contribution

The study introduces a novel application of artificial neural networks to estimate ammonia mitigation efficiency in sodium bisulfate-treated broiler litter.

## Key findings

- The Levenberg–Marquardt algorithm-based model achieved the highest predictive performance with R2 = 0.9777.
- ANN-based modeling is shown to be a reliable method for estimating ammonia removal efficiency in poultry litter.
- The LM algorithm outperformed other models in accuracy and generalization capability.

## Abstract

Intensive poultry production has intensified concerns regarding gaseous emissions, particularly ammonia, which can adversely affect animal welfare and occupational health if not adequately controlled. In recent years, artificial intelligence-based approaches have gained increasing attention as effective tools for predicting gaseous emissions and assessing mitigation performance. This study evaluates the predictive capability of artificial neural network models in estimating ammonia mitigation efficiency in broiler litter treated with sodium bisulfate under controlled laboratory-scale conditions. The findings indicate that AI-based modeling supports data-informed decision-making and contributes to the development of more effective environmental management strategies in intensive poultry production systems.

The increasing demand for poultry meat, driven by its favorable nutritional profile, including low cholesterol and high protein content, has resulted in intensified production volumes and, consequently, elevated ammonia (NH3) emissions. Artificial intelligence-based predictive approaches offer an effective alternative to conventional treatment-oriented methods by enabling faster and more accurate estimation of NH3 removal performance. This study aimed to predict the ammonia removal efficiency of broiler litter generated during a production cycle under controlled laboratory-scale conditions using artificial neural networks (ANNs) trained with different learning algorithms. Four ANN models were developed based on the Levenberg–Marquardt (LM), Fletcher–Reeves (FR), Scaled Conjugate Gradient (SCG), and Bayesian Regularization (BR) algorithms. The results showed that the LM-based model with 12 hidden neurons achieved the highest predictive performance (R2 = 0.9777; MSE = 0.0033; RMSE = 0.0574; MAPE = 0.0833), while the BR-based model with 10 neurons showed comparable accuracy. In comparison with the FR and SCG models, the LM algorithm demonstrated superior predictive accuracy and generalization capability. Overall, the findings suggest that ANN-based modeling is a reliable, data-informed approach for estimating NH3 removal efficiency, providing a potential decision-support framework for ammonia mitigation strategies in poultry production systems.