Spectral analysis and mapping of blackgrass weed by leveraging machine learning and UAV multispectral imagery

Abstract

Accurate weed mapping is a prerequisite for site-specific weed management to enable sustainable agriculture. This work aims to analyse (spectrally) and mapping blackgrass weed in wheat fields by integrating Unmanned Aerial Vehicle (UAV), multispectral imagery and machine learning techniques. 18 widely-used Spectral Indices (SIs) are generated from 5 raw spectral bands. Then various feature selection algorithms are adopted to improve model simplicity and empirical interpretability. Random Forest classifier with Bayesian hyperparameter optimization is preferred as the classification algorithm. Image spatial information is also incorporated into the classification map by Guided Filter. The developed framework is illustrated with an experimentation case in a naturally blackgrass infected wheat field in Nottinghamshire, United Kingdom, where multispectral images were captured by RedEdge on-board DJI S-1000 at an altitude of 20 m with a ground spatial resolution of 1.16 cm/pixel. Experimental results show that: (i) a good result (an average precision, recall and accuracy of 93.8%, 93.8%, 93.0%) is achieved by the developed system; (ii) the most discriminating SI is triangular greenness index (TGI) composed of Green-NIR, while wrapper feature selection can not only reduce feature number but also achieve a better result than using all 23 features; (iii) spatial information from Guided filter also helps improve the classification performance and reduce noises.