A novel method for predicting cadmium concentration in rice grain using genetic algorithm and back-propagation neural network based on soil properties
Heavy metal pollution is a global ecological safety issue, especially in crops, where it directly threatens regional ecological security and human health. In this study, the back-propagation (BP) neural network optimized by the genetic algorithm (GA) was used to predict the concentration of cadmium (Cd) in rice grain based on influencing factors. As an intelligent information processing system, the GA-BP neural network could learn the laws of Cd movement in the soil-crop system through its own training and use the soil properties to predict the concentration of Cd in grain with high accuracy. The total soil Cd concentration, clay content, Ni concentration, cation exchange capacity (CEC), organic matter (OM), and pH have important impacts and interactions on Cd concentration in rice grain were selected as input factors of the prediction model based on Pearson’s correlation analysis and GeoDetector. By using GA to optimize the initial weight, the prediction accuracy of the GA-BP neural network model was optimal compared with the BP neural network model and multiple regression analysis. Based on the Cd concentration predicted in grain by the model, human exposure and health risk can be assessed quickly, enabling measures to be taken in time to reduce the transfer of Cd from soil to the food chain.
KeywordsPrediction model Cadmium Rice grain Soil-rice system GA-BP neural network Soil properties
We thank the International Science Editing (http://www.internationalscienceediting.com) for editing this manuscript.
This study was financially supported by the national key R&D program of China (No. 2017YFD0800305) and special funds for scientific research on public causes of ministry of land and resources of China (No. 201511082).
Compliance with ethical standards
Conflict of interest
The authors declare that there is no conflict of interest.
- Barber S.A., Cushman J.H (1981) Nitrogen uptake model for agronomic crops, in modeling waste water renovation- land treatmentGoogle Scholar
- Jiang J, Liu X, Xu Z, Jin M, Liu F (2016) An improved BP neural network model for estimating cd stress in rice using remote sensing data. In: International conference on fuzzy systems and knowledge discoveryGoogle Scholar
- Martin I, Jeffries J (2008) Updated technical background to the CLEA modelGoogle Scholar
- Pang NS, Shi YL (2008) Research on short-term load forecasting based on adaptive hybrid genetic optimization BP neural network algorithm. Int C Manage Sci Eng 1563–1568. https://doi.org/10.1109/Icmse.2008.4669113
- Peng HY (2013) The BP neural network’s GA optimization and its realization on MATLAB. In: Chinese Control and Decision Conference. IEEE, 2013:536–539. https://doi.org/10.1109/CCDC.2013.6560982
- Rizwan M, Ali S, Adrees M, Rizvi H, Zia-ur-Rehman M, Hannan F, Qayyum MF, Hafeez F, Ok YS (2016b) Cadmium stress in rice: toxic effects, tolerance mechanisms, and management: a critical review. Environ Sci Pollut Res Int 23:17859–17879. https://doi.org/10.1007/s11356-016-6436-4 CrossRefGoogle Scholar
- Sterckeman T, Perriguey J, Caël M, Schwartz C, Morel JL (2004) Applying a mechanistic model to cadmium uptake by Zea mays and Thlaspi caerulescens: consequences for the assessment of the soil quantity and capacity factors. Plant Soil 262:289–302. https://doi.org/10.1023/B:PLSO.0000037049.07963.ab CrossRefGoogle Scholar
- Wang JF, Li XH, Christakos G, Liao YL, Zhang T, Gu X, Zheng XY (2010) Geographical detectors-based health risk assessment and its application in the neural tube defects study of the Heshun region, China. Int J Geogr Inf Sci 24:107–127. https://doi.org/10.1080/13658810802443457 CrossRefGoogle Scholar