Abstract—This study proposes and evaluates a hybrid Artificial Neural Network–Long Short-Term Memory (ANN-LSTM) model integrated into a Data Visualization Tool (DVT) for solar energy forecasting and management. Using meteorological data from the National Aeronautics and Space Administration Prediction of Worldwide Energy Resources (NASA POWER) Project in the Davao Region (1,956 daily records), the DVT combines a hybrid model with LSTM for sequential data and ANN for static feature analysis, which was further enhanced by attention mechanisms and normalization. The model achieves a Mean Absolute Error (MAE) of 0.82 and Root Mean Squared Error (RMSE) of 1.15, outperforming single-model baselines. Key contributions include demonstrating the effectiveness of the hybrid approach, incorporating data quality into training, and clarifying feature roles in temporal modeling. While the model performs well in tropical conditions, its applicability to low-irradiance regions remains a limitation, highlighting opportunities for future research, adaptation, and implementation.
 
Keywords—solar energy forecasting, hybrid deep learning, data visualization tool


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).