NTL-Unet: A Satellite-Based Approach for Non-Technical Loss Detection in Electricity Distribution Using Sentinel-2 Imagery and Machine Learning

Matheus Felipe Gremes, Renato Couto Gomes, Andressa Ullmann Duarte Heberle, Matheus Alan Bergmann, Luísa Treptow Ribeiro, Janice Adamski, Flávio Alves dos Santos, André Vinicius Rodrigues Moreira, Antonio Manoel Matta dos Santos Lameirão, Roberto Farias de Toledo, Antonio Oseas de C. Filho, Cid Marcos Gonçalves Andrade, Oswaldo Curty da Motta Lima

This study introduces an orbital monitoring system designed to quantify non-technical losses (NTLs) within electricity distribution networks. Leveraging Sentinel-2 satellite imagery alongside advanced techniques in computer vision and machine learning, this system focuses on accurately segmenting urban areas, facilitating the removal of clouds, and utilizing OpenStreetMap masks for pre-annotation. Through testing on two datasets, the method attained a Jaccard index (IoU) of 0.9210 on the training set, derived from the region of France, and 0.88 on the test set, obtained from the region of Brazil, underscoring its efficacy and resilience. The precise segmentation of urban zones enables the identification of areas beyond the electric distribution company’s coverage, thereby highlighting potential irregularities with heightened reliability. This approach holds promise for mitigating NTL, particularly through its ability to pinpoint potential irregular areas.