Machine Learning Modelling of Anchovy Waste Treatment Using Solar Drying

Abstract This study aims to valorize co-products from the anchovy processing chain by obtaining compounds of interest through the implementation of environmentally friendly and energy-efficient techniques. These methods, which also apply to other fresh anchovy waste co-products, seek to minimize the environmental pollution associated with conventional systems. The investigation focused on the application of the solar drying as a treatment of anchovy waste. The resulting data were employed to model the drying behavior of anchovy waste using five machine learning algorithms. A thermo-kinetic study was conducted under both natural and forced convection solar drying to establish the optimal conditions for drying and storing sardine heads, which are a significant source of high-quality proteins for human and animal nutrition. Drying kinetics were examined at three temperatures (60°C, 70°C, and 90°C) and two airflow rates (150 m³/h and 300 m³/h). The study identified air drying temperature as the most critical factor affecting the drying kinetics of sardine heads. A machine learning modelling of Anchovy waste solar drying was conducted, evaluated models were RNN, LSTM, GRU, LightGBM, and CatBoost. CatBoost demonstrated superior performance in predicting moisture content. It achieved the lowest Mean Squared Error (MSE) of 1.1491e-06, the lowest Mean Absolute Error (MAE) of 0.0006265, and the highest coefficient of determination (R²) of 99.99%. The comparative analysis highlighted distinct differences in the predictive accuracy of the models, with CatBoost emerging as the most effective.