Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping - Observation, Impacts, Energie Access content directly
Conference Papers Year : 2022

Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping

Abstract

Photovoltaic (PV) energy is rapidly growing and key to mitigating the energy crisis. However, distributed PV generation, which amounts to half of the PV installed capacity, is typically unavailable to transmission system operators (TSOs), making it increasingly difficult to balance the load and supply and avoid grid congestions. To assess distributed PV generation, TSOs need precise knowledge regarding the metadata of distributed PV installations. Many remote sensing-based approaches have been proposed to map these installations in recent years. However, to use these methods in industrial processes, assessing their accuracy over the mapping area, i.e., the area covered by the model during deployment, is necessary. We define the downstream task accuracy (DTA) as the accuracy over the mapping area, automatically computed using publicly available data sources and the model's outputs and expressed in an interpretable way for operators. We benchmark existing models for distributed PV mapping and show how they perform in terms of DTA. We show that the accuracy computed on the test set overestimates by about 30 percentage points the accuracy on the mapping area. Our approach paves the way for safer integration of deeplearning-based pipelines for remote PV mapping. Code is available at https://github.com/gabrielkasmi/dsfrance.
Fichier principal
Vignette du fichier
manuscript.pdf (512.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03778289 , version 1 (15-09-2022)

Identifiers

  • HAL Id : hal-03778289 , version 1

Cite

Gabriel Kasmi, Laurent Dubus, Philippe Blanc, Yves-Marie Saint-Drenan. Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping. Workshop on Machine Learning for Earth Observation (MACLEAN), in Conjunction with the ECML/PKDD 2022, Sep 2022, Grenoble, France. ⟨hal-03778289⟩
109 View
50 Download

Share

Gmail Facebook X LinkedIn More