This research established an experimental database characterizing the solar drying behavior of seven distinct agricultural products (including fruits, vegetables, and meat) in a tunnel-type solar dryer. Based on this experimental data, a dual-model architecture using multilayer perceptron (MLP) neural network was developed to predict both the internal microclimate and the drying kinetics. The first network (ANN 1) mapped meteorological variables to the dryer’s internal conditions, while the second (ANN 2) predicted moisture loss. The results demonstrate distinct predictive capabilities for each physical phenomenon: the thermodynamic model (ANN 1) captured stochastic weather fluctuations, with an R² of 0.9878 and an MAPE of 4.64%. The kinetic model (ANN 2) achieved near-perfect linearity with an R² of 0.9997 and an MAPE of 0.49%, significantly outperforming baseline linear regression models (R² approx 0.78). These findings confirm the system’s capacity to generalize across diverse food types and variable weather conditions, providing a robust tool for future Model Predictive Control (MPC) applications.

The growing energy demand in the residential sector, driven by the extensive use of air conditioning systems, poses serious environmental and economic challenges. A sustainable alternative is the use of efficient insulating materials derived from waste resources. This study presents the synthesis of glass–ceramic foams produced from recycled glass (90 wt%), pumice (5 wt%), and limestone (5 wt%), sintered at 800 °C for 10 min. The resulting foams exhibited a low apparent density of 684 kg/${\mathrm{m}}^3$ and thermal conductivity of 0.09 W/m·K. These were incorporated into composite insulating panels composed of 70 wt% ceramic pellets and 30 wt% Portland cement, achieving a thermal conductivity of 0.18 W/m·K. The panels were evaluated in a 64.8 ${\mathrm{m}}^2$ social housing model located in Chihuahua, Mexico, using TRNSYS v.17 to simulate annual energy performance. Results showed that applying a 1.5-inch ceramic foam panel reduced the annual energy demand by 16.9% and the total energy cost by 14.7%, while increasing the panel thickness to 2 in improved savings to 18.4%. Compared with expanded polystyrene (EPS), which achieved 24.9% savings, the proposed ceramic panels offer advantages in fire resistance, durability, local availability, and environmental sustainability. This work demonstrates an effective, low-cost, and circular-economy-based solution for improving thermal comfort and energy efficiency in social housing.