Hyperspectral monitor of soil chromium contaminant based on deep learning network model in the Eastern Junggar coalfield

In China, over 10% of cultivated land is polluted by heavy metals, which can affect crop growth, food safety and human health. Therefore, how to effectively quickly detect soil metal pollution has become a critical issue. This study provides novel data preprocessing method that extract vital information from hyperspectra uses different classification algorithms levels contamination in soil. this experiment, 160 samples the Eastern Junggar Coalfield Xinjiang were employed for verification, including 143 noncontaminated 17 contaminated samples. Because concentration chromium exists trace amounts, combined with fact spectral characteristics are easily influenced other types impurity soil, evaluation concentrations through hyperspectral analysis not satisfactory. To avoid phenomenon, pretreatment experiment includes combination second derivative enhancement (DA) approaches. Then, support vector machine (SVM), k-nearest neighbour (KNN) deep neural network (DNN) used create discriminant models. The accuracies DA-SVM, DA-KNN DA-DNN models 95.61%, 95.62% 96.25%, respectively. results demonstrate technology learning be instantly monitor on large scale. research management areas agricultural insurance applications.