Leveraging High-Resolution Satellite Imagery and Gradient Boosting for Invasive Weed Mapping

Abstract

An introduced pasture grass (Andropogon gayanus - gamba grass) is spreading through the tropical savannas of northern Australia, with detrimental ecosystem consequences including increased fire intensity. In order to monitor and manage the spread of gamba grass, a scalable solution for mapping its distribution over large areas is required. Recent developments in machine learning have proven useful for distinguishing vegetation types in satellite imagery in an automated manner. In this study, we collected field data for supervised learning of very high-resolution (0.3 m) WorldView-3 satellite imagery and tuned the hyperparameters of an extreme gradient boosting classifier to produce a viable solution for detecting the probability of gamba grass presence. To evaluate the performance of WorldView-3 imagery in discriminating gamba grass, we tested the utility of predictors derived from: 1) spectral bands; 2) textural features; 3) spectral indices; and 4) all predictors combined. Our results suggest that gamba grass presence can be mapped from space with an accuracy of up to 91% under optimal environmental conditions.

Keywords

• Extreme gradient boosting (XGBoost)
• gamba grass
• high resolution
• machine learning
• remote sensing
• weed