GeoAI Techniques for Detecting and Classifying Roofs-Included Solar Panels on Remote Sensing Imagery in Thai Urban Historical Heritage: The old moat of Nakhonratchasima City Municipality, Thailand
Yaowaret Jantakat, Pongpun Juntakut, Chomphak Jantakat

1. Rajamangala University of Technology Isan, Nakhon Ratchasima, Thailand
2. Royal Thai Armed Forces Headquarters, Bangkok, Thailand
3. Vongchavalitkul University, Nakhon Ratchasima, Thailand

Abstract

Presently, the utilization of solar panels on rooftop received a lot of attention because it helps save electricity and protect the environment. Therefore, this study have attention to promote using solar panels on rooftop especially city areas because there are a lot of buildings and impervious surfaces (where are mainly artificial structures). The aim of this study was to survey and support collecting data about the quantity of solar panels on building^ rooftops from using satellite imagery of Google Earth. Deep learning is one type of GeoAI (Geospatial Artificial Intelligence) techniques that was used for the roofs with the solar panels on classification of satellite imagery of Google Earth in this study. The old moat of Nakhonratchasima City Municipality (NCM) is selected as the case study or area-specific characteristics because it is ancient city mixed presently modern structure with a full of impervious building materials brick and concrete block. Deep learning-based Deepness panel in QGIS, was employed to analyze buildings and their solar panels on rooftops. This was a collection of pre-trained deep learning models in the ONNX format that was needed for this plugin in QGIS. This study used the Solar PV segmentation. As the results, this study found that deep learning technique can detect solar panels on rooftops of 12,888 of 53,559 buildings (22.83%) in the old moat of NCM. The output was investigation on true ground with accuracy assessment 82.08% so deep learning technique is suitable for detecting solar panels on building^ rooftops in the old moat of NCM.

Keywords: Deep learning, solar panel, Renewable energy source, Spatial tool, GeoAI

Topic: Topic B: Applications of Remote Sensing