Zhao Junyang, Zheng Fuhai, Yu Baoshan, Qin Guanchun, Meng Shunpiao, Qiu Yuhang, He Bing
Guangxi Key Laboratory of Agro-Environment and Agric-Products Safety, College of Agriculture, Guangxi University, Nanning 530004, China.
Agricultural Resources and Environmental Research Institute, Guangxi Academy of Agricultural Sciences/Guangxi Key Laboratory of Arable Land Conservation, Nanning 530004, China.
Toxics. 2025 Jul 30;13(8):645. doi: 10.3390/toxics13080645.
The translocation of cadmium (Cd) in the soil-rice system is complicated; therefore, most of the soil-plant models of Cd have not been extensively studied. Hence, we studied the back-propagation artificial neural network model (BP-ANN) and multiple regression model (MLR) to predict the cadmium (Cd) content in rice grain and soil through testing soil parameters. In this study, 486 pairs of rice grains and corresponding soil samples of 456 vectors were used for training + validation, and 30 vectors were collected from the southwestern karst area of Guangxi Province as a test data set. In this study, the Cd content in rice was successfully predicted by using the factors soil available cadmium (A), total soil cadmium (T), soil organic matter (SOM), and pH, which have a more significant impact on rice, as the main prediction variables. Root mean square error (RMSE), Relative Percent Difference (RPD), and correlation coefficient (R) were used to assess the models. The R, RPD, and RMSE values for R medium obtained by the MLR model with pH, T, and A as entered variables were 0.551, 2.398, and 0.049, respectively. The R and RMSE values for R medium obtained by the BP-ANN model with pH, T, and A as entered variables were 0.6846, 2.778, and 0.104, respectively. Therefore, it was concluded that BP-ANN was useful in predicting R and had better performance than MLR.
镉（Cd）在土壤-水稻系统中的迁移转化较为复杂，因此，大多数镉的土壤-植物模型尚未得到广泛研究。为此，我们研究了反向传播人工神经网络模型（BP-ANN）和多元回归模型（MLR），通过测试土壤参数来预测水稻籽粒和土壤中的镉（Cd）含量。本研究中，486对水稻籽粒及456个向量对应的土壤样本用于训练+验证，另外从广西西南部岩溶地区采集了30个向量作为测试数据集。本研究以对水稻影响更为显著的土壤有效镉（A）、土壤总镉（T）、土壤有机质（SOM）和pH值等因素作为主要预测变量，成功预测了水稻中的镉含量。采用均方根误差（RMSE）、相对百分比差异（RPD）和相关系数（R）对模型进行评估。以pH、T和A作为输入变量的MLR模型得到的R medium的R、RPD和RMSE值分别为0.551、2.398和0.049。以pH、T和A作为输入变量的BP-ANN模型得到的R medium的R和RMSE值分别为0.6846、2.778和0.104。因此，得出结论：BP-ANN在预测R方面是有用的，并且比MLR具有更好的性能。
