The current study aims to develop a non-intrusive Reduced Order Model (ROM) to reconstruct the full temperature field for a large-scale industrial application based on both numerical and experimental datasets. The proposed approach is validated against a domestic refrigerator. At the full order level, air circulation and heat transfer in fluid and between fluid and surrounding solids in the fridge were numerically studied using the Conjugate Heat Transfer (CHT) method to explore both the natural and forced convection-based fridge model, followed by a parametric study based on the ambient temperature, fridge fan angular velocity, and evaporator temperature. The main novelty of the current work is the introduction of a stable Artificial Neural Network (ANN) enhanced Gappy Proper Orthogonal Decomposition (GPOD) method, which shows better performance in terms of solution accuracy given a fixed number of sensor locations than the conventional GPOD approach in such large-scale industrial applications. In our current work, we show that a prediction error of 1 () and a computational speed-up of are achieved even with a very sparse training dataset using the proposed deep-learning-enhanced GPOD approach. In addition, the proposed methodology integrates Computational Fluid Dynamics (CFD) predictions with experimental data, which yields more accurate solution fields at new parametric points than CFD-only predictions.