Geoinformatics-Guided Machine Learning for Power Plant Classification

TL;DR

This paper introduces a novel geoinformatics-guided machine learning framework combining CNN, ViT, and GIS spatial masks to improve power plant classification accuracy from satellite imagery, advancing AI applications in energy and environmental management.

Contribution

It presents an integrated KGML framework that effectively incorporates geoinformatics spatial knowledge into deep learning models for power plant classification.

Findings

Enhanced classification accuracy over baseline CNN and ViT models

Effective integration of GIS spatial masks improves model performance

Potential applications in smart city and environmental monitoring

Abstract

This paper proposes an approach in the area of Knowledge-Guided Machine Learning (KGML) via a novel integrated framework comprising CNN (Convolutional Neural Networks) and ViT (Vision Transformers) along with GIS (Geographic Information Systems) to enhance power plant classification in the context of energy management. Knowledge from geoinformatics derived through Spatial Masks (SM) in GIS is infused into an architecture of CNN and ViT, in this proposed KGML approach. It is found to provide much better performance compared to the baseline of CNN and ViT only in the classification of multiple types of power plants from real satellite imagery, hence emphasizing the vital role of the geoinformatics-guided approach. This work makes a contribution to the main theme of KGML that can be beneficial in many AI systems today. It makes broader impacts on AI in Smart Cities, and Environmental Computing.