Spectroscopic Diagnosis of Arsenic Contamination in Agricultural Soils
نویسندگان
چکیده
This study investigated the abilities of pre-processing, feature selection and machine-learning methods for the spectroscopic diagnosis of soil arsenic contamination. The spectral data were pre-processed by using Savitzky-Golay smoothing, first and second derivatives, multiplicative scatter correction, standard normal variate, and mean centering. Principle component analysis (PCA) and the RELIEF algorithm were used to extract spectral features. Machine-learning methods, including random forests (RF), artificial neural network (ANN), radial basis function- and linear function- based support vector machine (RBF- and LF-SVM) were employed for establishing diagnosis models. The model accuracies were evaluated and compared by using overall accuracies (OAs). The statistical significance of the difference between models was evaluated by using McNemar's test (Z value). The results showed that the OAs varied with the different combinations of pre-processing, feature selection, and classification methods. Feature selection methods could improve the modeling efficiencies and diagnosis accuracies, and RELIEF often outperformed PCA. The optimal models established by RF (OA = 86%), ANN (OA = 89%), RBF- (OA = 89%) and LF-SVM (OA = 87%) had no statistical difference in diagnosis accuracies (Z < 1.96, p < 0.05). These results indicated that it was feasible to diagnose soil arsenic contamination using reflectance spectroscopy. The appropriate combination of multivariate methods was important to improve diagnosis accuracies.
منابع مشابه
Recent advances in phytoremediation of arsenic-contaminated soils
Arsenic contamination in soils occurs widely in a range of ecosystems resulting from geological origins and anthropogenic activities. On average, arsenic concentration ranges from 5 to 10 mg kg−1 in uncontaminated soils and above 10 mg kg−1 in contaminated soils (Hossain, 2006). Increased buildup of arsenic in irrigated soils has been widely recognized in South and South-east Asia (Brammer and ...
متن کاملHeavy metal contamination and source in arid agricultural soil in central Gansu Province, China.
Concentrations of copper (Cu), lead (Pb), chromium (Cr), mercury (Hg), and arsenic (As) were measured in arid agricultural and irrigated agricultural soils collected in Daba Village, Shajiawuan Village, Gangou Village and Sifangwu Village, located in central Gansu Province, China. Concentrations except Hg and Pb were lower than the background values in grey calcareous soil in the selected arid ...
متن کاملSoil As contamination and its risk assessment in areas near the industrial districts of Chenzhou City, Southern China.
In order to assess soil As contamination and potential risk for human, soil, paddy rice, vegetable and human hair samples from the areas near the industrial districts in Chenzhou, southern China were sampled and analyzed. The results showed that the anthropogenic industrial activities have caused in local agricultural soils to be contaminated with As in a range of 11.0-1217 mg/kg. The GIS-based...
متن کاملAssessment of Potential Location of High Arsenic Contamination Using Fuzzy Overlay and Spatial Anisotropy Approach in Iron Mine Surrounding Area
Fuzzy overlay approach on three raster maps including land slope, soil type, and distance to stream can be used to identify the most potential locations of high arsenic contamination in soils. Verification of high arsenic contamination was made by collection samples and analysis of arsenic content and interpolation surface by spatial anisotropic method. A total of 51 soil samples were collected...
متن کاملSpectroscopic Based Quantitative Mapping of Contaminant Elements in Dumped Soils of a Copper Mine
Possibility of mapping the distribution of Arsenic and Chromium in a mining area was investigated using combination of (VNIR) reflectance spectroscopy and geostatistical analysis. Fifty five soil samples were gathered from a waste dump at Sarcheshmeh copper mine and VNIR reflectance spectra were measured in a laboratory. Savitzky- Golay first derivative was used as the main pre-processing metho...
متن کامل