Generalizability of Neural Network-based Identification of PV in Aerial Images

Identification of PV panels from aerial imagery is a potential strategy for building comprehensive behind-the-meter PV datasets. Several previous studies have utilized Convolutional Neural Networks with the goal of producing tools that can perform these identification tasks. Neural Network approaches rely on labelled data for training, with several aerial imagery datasets with labelled PV already available. This study aims to investigate generalizability of models trained on one set of labelled PV data to other datasets, to further understanding of how these models can be applied. Six different PV datasets were utilized, and test data results were compared. Overall, we find that generalizability suffers when models are presented with different data than they were trained on. We describe some dataset features that led to particularly poor generalization. This study highlights the need for further research to investigate strategies for improving generalizability of trained Neural Network models.

Files

  • Ranalli2023PVSCNN.pdf

    size: 642 KB | mime_type: application/pdf | date: 2023-07-03 | sha256: 07d26bd

Metadata

Work Title Generalizability of Neural Network-based Identification of PV in Aerial Images
Access
Open Access
Creators
  1. Joseph Ranalli
  2. Matthias Zech
License In Copyright (Rights Reserved)
Work Type Other
Publication Date June 16, 2023
Source
  1. 50th IEEE PV Specialists Conference
Deposited July 03, 2023

Versions

Analytics

Collections

This resource is currently not in any collection.

Work History

Version 1
published

  • Created
  • Added Ranalli2023PVSCNN.pdf
  • Added Creator Joseph Ranalli
  • Added Creator Matthias Zech
  • Published
  • Updated Source, Subtitle Show Changes
    Source
    • 50th IEEE PV Specialists Conference
    Subtitle
    • 50th IEEE PV Specialists Conference
  • Updated