Agro-environmental Protection Institute, Ministry of Agriculture, Tianjin 300071, China.
Department of Computer and Control Engineering, Nankai University, Tianjin 300071, China.
Environ Pollut. 2018 May;236:366-372. doi: 10.1016/j.envpol.2018.01.088.
In China, the cadmium (Cd) levels in paddy fields have increased, which has led to the excessive uptake of Cd into rice grains. In this study, we determined the physicochemical properties of soil samples, including the pH, soil organic matter (SOM) content, cation exchange capacity (CEC), and total Cd content (Cd) in order to establish a quadratic discriminant analysis (QDA) model for assessing the risk of Cd in rice and to calculate its prior probability. Decision tree and logistic regression models were also established for comparison. The results showed that the accuracy rate was 74% with QDA, which was significantly higher than that obtained using the decision tree (67%) and logistic regression (68%) models. The correlation coefficients between the soil pH and the other three factors (CEC, SOM, and Cd) were higher in the inaccurate set than the accurate set, whereas the correlation coefficients were smaller in the inaccurate set than the accurate set.
在中国，稻田中的镉 (Cd) 水平有所增加，这导致水稻对 Cd 的过度吸收。在这项研究中，我们确定了土壤样本的理化性质，包括 pH 值、土壤有机质 (SOM) 含量、阳离子交换能力 (CEC) 和总 Cd 含量 (Cd)，以便建立一个二次判别分析 (QDA) 模型来评估水稻中 Cd 的风险，并计算其先验概率。还建立了决策树和逻辑回归模型进行比较。结果表明，QDA 的准确率为 74%，明显高于决策树 (67%) 和逻辑回归 (68%) 模型。在不准确集，土壤 pH 值与其他三个因素（CEC、SOM 和 Cd）的相关系数高于准确集，而在不准确集，土壤 pH 值与其他三个因素（CEC、SOM 和 Cd）的相关系数则小于准确集。
