Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks

TL;DR

This paper explores optimal methods for utilizing multi-spectral satellite data with CNNs for semantic segmentation, demonstrating that automatic band selection and Bayesian optimization improve accuracy over traditional expert-selected bands.

Contribution

The paper introduces Bayesian optimization for band selection in CNNs applied to satellite imagery, outperforming traditional expert-selected bands and other methods.

Findings

Using all available bands improves performance over expert-selected bands.

Bayesian optimization further enhances accuracy in band selection.

Automatic band selection methods outperform standard practices.

Abstract

The analysis of satellite imagery will prove a crucial tool in the pursuit of sustainable development. While Convolutional Neural Networks (CNNs) have made large gains in natural image analysis, their application to multi-spectral satellite images (wherein input images have a large number of channels) remains relatively unexplored. In this paper, we compare different methods of leveraging multi-band information with CNNs, demonstrating the performance of all compared methods on the task of semantic segmentation of agricultural vegetation (vineyards). We show that standard industry practice of using bands selected by a domain expert leads to a significantly worse test accuracy than the other methods compared. Specifically, we compare: using bands specified by an expert; using all available bands; learning attention maps over the input bands; and leveraging Bayesian optimisation to dictate band choice. We show that simply using all available band information already increases test time performance, and show that the Bayesian optimisation, first applied to band selection in this work, can be used to further boost accuracy.