SPATIAL INVENTORY OF SOLAR PHOTOVOLTAIC (PV) INSTALLATIONS USING REMOTE SENSING AND MACHINE LEARNING: CASE OF PAMPANGA PROVINCE, PHILIPPINES

Abstract

In recent years, the cost of photovoltaic (PV) technologies significantly declined, boosting the expansion of solar PV installations in the country. This rapid development in solar PV utilization necessitates an effective detection method capable of delineating both utility-scale and distributed PV installations to generate a complete inventory of solar PV installations for status monitoring and implementation of appropriate programs of stakeholders and decision-makers. This study aims to detect and delineate solar PV installations in Pampanga, Philippines using different band combinations of Sentinel-2, Sentinel-1, and indices (NDVI, NDWI, and PVSI) through machine learning with the aid of open-source geographic information system and remote sensing software. Moreover, an alternative approach to identifying solar PVs using the combination of pixel-based classification (PBC) and object-based classification (OBC) was introduced. Training and validation data were acquired from the satellite images. The accuracy of each approach in PV detection was then compared using three classifiers: Support Vector Machine (SVM), Random Forest, and Naive Bayes. Results showed that SVM has the best performance for PBC while Random Forest demonstrated the highest accuracy for OBC. A post-processing procedure was also implemented using a set of spectral rules to further refine the results of image classification. The delineation accuracies of the post-processed data over the ground-truth data showed that the methodology is effective in delineating utility-scale installations for both Sentinel-2 and Planetscope. However, the detection of distributed PV systems showed limitations particularly when dealing with small solar PV installations (less than 45 pixels) due to Sentinel-2’s coarse spatial resolution.