Optimization of the Tomato Drying Process through Artificial Neural Networks: A Focus on Food Sustainability

Fruit dehydration is a widely used technique to extend shelf life, minimize waste, and preserve nutritional quality by reducing moisture content, which inhibits enzymatic activity and microbial growth. However, traditional dehydration methods are often inconsistent due to subjective assessments, environmental factors, and prolonged drying times. This study introduces an artificial intelligence (AI) approach to optimize tomato dehydration, employing a simple neural network model to predict relative humidity levels during drying. The goal is to enhance product quality, automate the process, and potentially reduce energy consumption. Experimental dehydration at different temperatures and thicknesses provided insights into organoleptic and nutritional effects, with sensory analysis identifying an optimal drying temperature of 50°C. The results support AI integration in food dehydration for enhanced control, quality, and sustainability. Future research may focus on integrating real-time energy consumption data and multidimensional variables into AI models to optimize this process further.