Visible and near-infrared reflectance spectroscopy offers a rapid, inexpensive, and environmentally friendly method for monitoring copper pollution in the soil. However, the application of this approach in vegetation-covered areas is still a challenge due to interference from plants, making it difficult to acquire soil reflectance spectra. To address this problem, this study assesses whether the reflectance spectrum of a widely distributed arid desert plant (Seriphidium terrae-albae) can be used to rapidly evaluate copper pollution in the soil. A pot experiment was conducted for five months from April to September 2019. The reflectance spectra of the plants were measured in June, July, and August 2019 using an ASD Fieldspec3 spectrometer. Each month, the five vegetation indexes with the highest correlation with the evaluation value of the copper pollution degree were input into an extreme learning machine (ELM) to build a model to monitor the degree of copper pollution in the soil. The results showed that the model could quickly evaluate the degree of copper pollution, but the accuracy varied widely among the calculated vegetation indexes depending on the month when the spectral data were extracted. The model constructed by selecting ten vegetation indexes composed of plant spectra collected in June and July provides high recognition accuracy, reaching 89.02%. Only seven bands were needed due to the model's low complexity, which means that it has great potential to be applied to remote sensing images to establish a real-time monitoring system to detect copper pollution in the soil. This study proposed a simple and rapid method for monitoring copper pollution in soil using plant spectra, and this method could provide extremely valuable for soil protection and management in arid desert areas.
Keywords: Arid desert plants; Copper pollution in soil; Extreme learning machine; Monitoring model; Vegetation index.
Copyright © 2021 Elsevier B.V. All rights reserved.