Performance estimation of a mini-passive solar still

---

Mini-passive polystyrene (PS)-based single-slope solar still is designed for brackish water desalination. Supervised machine learning are applied to create trained models from experimental results. The proposed method aims to develop accurate predictive models via dimensional analysis and datasets expansion from in-between randomization.

We correlated the water-glass temperature and evaporative coefficients  to the still outputs. A good agreement between theoretical, numerical, and experimental results is observed. Polyurethane (PU) and Silica are found to be promising wall-insulating candidates for maximizing outputs.

This work opens a new avenue towards further downscaling solar stills to ease experimentation, considering that excess heat loss needs to be yet investigated in future works via creating a unified machine learning model.