Concentrations of Iron (Fe), As, and Cu in soil samples from the fields near the Baoshan Mine in Hunan Province, China, were analyzed and soil spectral reflectance was measured with an ASD FieldSpec FR spectroradiomet...Concentrations of Iron (Fe), As, and Cu in soil samples from the fields near the Baoshan Mine in Hunan Province, China, were analyzed and soil spectral reflectance was measured with an ASD FieldSpec FR spectroradiometer (Analytical Spectral Devices, Inc., USA) under laboratory condition. Partial least square regression (PLSR) models were constructed for predicting soil metal concentrations. The data pre-processing methods, first and second derivatives (FD and SD), baseline correction (BC), standard normal variate (SNV), multiplicative scatter correction (MSC), and continuum removal (CR), were used for the spectral reflectance data pretreatments. Then, the prediction results were evaluated by relative root mean square error (RRMSE) and coefficients of determination (R 2 ). According to the criteria of minimal RRMSE and maximal R 2 , the PLSR models with the FD pretreatment (RRMSE = 0.24, R 2 = 0.61), SNV pretreatment (RRMSE = 0.08, R 2 = 0.78), and BC-pretreatment (RRMSE = 0.20, R 2 = 0.41) were considered as the final models for predicting As, Fe, and Cu, respectively. Wavebands at around 460, 1 400, 1 900, and 2 200 nm were selected as important spectral variables to construct final models. In conclusion, concentrations of heavy metals in contaminated soils could be indirectly assessed by soil spectra according to the correlation between the spectrally featureless components and Fe; therefore, spectral reflectance would be an alternative tool for monitoring soil heavy metals contamination.展开更多
Soil salinization is a land degradation process that leads to reduced agricultural yields. This study investigated the method that can best predict electrical conductivity (EC) in dry soils using individual bands, a n...Soil salinization is a land degradation process that leads to reduced agricultural yields. This study investigated the method that can best predict electrical conductivity (EC) in dry soils using individual bands, a normalized difference salinity index (NDSI), partial least squares regression (PLSR), and bagging PLSR. Soil spectral reflectance of dried, ground, and sieved soil samples containing varying amounts of EC was measured using an ASD FieldSpec spectrometer in a darkroom. Predictive models were computed using a training dataset. An independent validation dataset was used to validate the models. The results showed that good predictions could be made based on bagging PLSR using first derivative reflectance (validation R2 = 0.85), PLSR using untransformed reflectance (validation R2 = 0.70), NDSI (validation R2 = 0.65), and the untransformed individual band at 2257 nm (validation R2 = 0.60) predictive models. These suggested the potential of mapping soil salinity using airborne and/or satellite hyperspectral data during dry seasons.展开更多
基金Project supported by the National Natural Science Foundation of China (No. 40571130)the Natural Science Foundation of Shanghai, China (No. 07ZR14032)
文摘Concentrations of Iron (Fe), As, and Cu in soil samples from the fields near the Baoshan Mine in Hunan Province, China, were analyzed and soil spectral reflectance was measured with an ASD FieldSpec FR spectroradiometer (Analytical Spectral Devices, Inc., USA) under laboratory condition. Partial least square regression (PLSR) models were constructed for predicting soil metal concentrations. The data pre-processing methods, first and second derivatives (FD and SD), baseline correction (BC), standard normal variate (SNV), multiplicative scatter correction (MSC), and continuum removal (CR), were used for the spectral reflectance data pretreatments. Then, the prediction results were evaluated by relative root mean square error (RRMSE) and coefficients of determination (R 2 ). According to the criteria of minimal RRMSE and maximal R 2 , the PLSR models with the FD pretreatment (RRMSE = 0.24, R 2 = 0.61), SNV pretreatment (RRMSE = 0.08, R 2 = 0.78), and BC-pretreatment (RRMSE = 0.20, R 2 = 0.41) were considered as the final models for predicting As, Fe, and Cu, respectively. Wavebands at around 460, 1 400, 1 900, and 2 200 nm were selected as important spectral variables to construct final models. In conclusion, concentrations of heavy metals in contaminated soils could be indirectly assessed by soil spectra according to the correlation between the spectrally featureless components and Fe; therefore, spectral reflectance would be an alternative tool for monitoring soil heavy metals contamination.
基金Project supported by the Agricultural Research Council-Institute for Soil, Climate and Water (ARC-ISCW) of South Africa (No.GW51/072)the National Research Foundation (NRF) of South Africa (No.GW 51/083/01)the Water Research Commission (WRC)of South Africa (No.K5/1849)
文摘Soil salinization is a land degradation process that leads to reduced agricultural yields. This study investigated the method that can best predict electrical conductivity (EC) in dry soils using individual bands, a normalized difference salinity index (NDSI), partial least squares regression (PLSR), and bagging PLSR. Soil spectral reflectance of dried, ground, and sieved soil samples containing varying amounts of EC was measured using an ASD FieldSpec spectrometer in a darkroom. Predictive models were computed using a training dataset. An independent validation dataset was used to validate the models. The results showed that good predictions could be made based on bagging PLSR using first derivative reflectance (validation R2 = 0.85), PLSR using untransformed reflectance (validation R2 = 0.70), NDSI (validation R2 = 0.65), and the untransformed individual band at 2257 nm (validation R2 = 0.60) predictive models. These suggested the potential of mapping soil salinity using airborne and/or satellite hyperspectral data during dry seasons.
