Classifying Crop Types using Gaussian Bayesian Models and Neural Networks on GHISACONUS USGS data from NASA Hyperspectral Satellite Imagery

TL;DR

This paper compares Bayesian, LDA, QDA, and neural network methods for classifying crop types using hyperspectral satellite imagery, demonstrating Bayesian models' superior performance on USGS data.

Contribution

Introduces Bayesian classification methods tailored for hyperspectral crop data, outperforming traditional LDA, QDA, and neural networks in accuracy.

Findings

Bayesian models outperform non-Bayesian methods in crop classification.

Neural network performs comparably to LDA and QDA.

Bayesian approach effectively incorporates spectral and growth stage information.

Abstract

Hyperspectral Imagining is a type of digital imaging in which each pixel contains typically hundreds of wavelengths of light providing spectroscopic information about the materials present in the pixel. In this paper we provide classification methods for determining crop type in the USGS GHISACONUS data, which contains around 7,000 pixel spectra from the five major U.S. agricultural crops (winter wheat, rice, corn, soybeans, and cotton) collected by the NASA Hyperion satellite, and includes the spectrum, geolocation, crop type, and stage of growth for each pixel. We apply standard LDA and QDA as well as Bayesian custom versions that compute the joint probability of crop type and stage, and then the marginal probability for crop type, outperforming the non-Bayesian methods. We also test a single layer neural network with dropout on the data, which performs comparable to LDA and QDA but not as well as the Bayesian methods.