Premium
Two hyperspectral indices for detecting cadmium and lead contamination from arice canopy spectrum
Author(s) -
Zhang Shuangyin,
Fei Teng,
You Xiang,
Wan Yinkang,
Wang Yunjiang,
Bian Meng
Publication year - 2020
Publication title -
land degradation and development
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.403
H-Index - 81
eISSN - 1099-145X
pISSN - 1085-3278
DOI - 10.1002/ldr.3721
Subject(s) - hyperspectral imaging , cadmium , canopy , environmental science , environmental chemistry , remote sensing , chemistry , botany , geology , biology , organic chemistry
Neither Cadmium (Cd) nor lead (Pb) is necessary for crop growth, and they both cause severe soil pollution in many countries. A cross‐stress experiment was designed to investigate the feasibility of diagnosing the type and the level of Cd–Pb cross‐stress by observing rice canopy hyperspectral images. Two‐way analysis of variance and random forest algorithm were employed to select the sensitive indices for Cd–Pb cross‐stress diagnosing. Following the exploration of bandwidth expansion from 1 to 20 nm, the final sensitive indices were proposed. We proposed two indices for distinguishing the two heavy metals named: the cadmium stress vegetation index (CSVI) and the lead stress vegetation index (LSVI). The diagnostic accuracies of CSVI distinguishing the four different Cd‐stressed levels (0, 2, 5, 8 mg L −1 ) reached 0.85, 0.92, 0.96, and 0.92, respectively, while the precision for four Pb‐stressed levels (0, 50, 100, 500 mg L −1 ) based on the LSVI were 0.92, 0.94, 0.96, and 0.96, respectively. The two indices are CSVI = [( R 772 + R 773 + R 774 + … + R 789 ) ‐ ( R 754 + R 755 + R 756 + … + R 771 )]/18, LSVI = [( R 711 + R 712 + R 713 + … + R 718 ) – ( R 703 + R 704 + R 705 + … + R 710 )]/8, located in near‐infrared ranges with 18 and 8 nm bandwidth, respectively. Therefore, it was feasible to diagnose the type and the level of Cd–Pb cross‐stress by examining the hyperspectral dataset of the rice canopy. Finally, the experiment compared the diagnostic ability of the proposed indices with the typical spectral indices for the physiological characterization of rice. The results showed that the proposed indices had state‐of‐the‐art distinguishing accuracies.