A novel method for predicting cadmium concentration in rice grain using genetic algorithm and back-propagation neural...

Area of Science:

• Environmental Science
• Agricultural Science
• Toxicology

Background:

• Heavy metal pollution, particularly cadmium (Cd), poses a significant global threat to ecological safety and human health through crop contamination.
• Understanding Cd accumulation in crops like rice is crucial for regional ecological security and public health.
• Existing methods for predicting Cd concentration in crops have limitations in accuracy and scope.

Purpose of the Study:

• To develop and validate an accurate prediction model for cadmium (Cd) concentration in rice grain.
• To identify key soil factors influencing Cd uptake and accumulation in rice.
• To enable rapid assessment of human exposure and health risks associated with Cd in rice.

Main Methods:

• Utilized a genetic algorithm-optimized back-propagation (GA-BP) neural network for predicting Cd concentration in rice grain.
• Selected input factors based on Pearson's correlation analysis and GeoDetector, including total soil Cd, clay content, Ni concentration, cation exchange capacity (CEC), organic matter (OM), and pH.
• Optimized the initial weights of the BP neural network using the genetic algorithm (GA) to enhance prediction accuracy.

Main Results:

• The GA-BP neural network model demonstrated superior prediction accuracy for Cd concentration in rice grain compared to the standard BP neural network and multiple regression analysis.
• Identified significant interactions between soil properties (e.g., total Cd, clay, Ni, CEC, OM, pH) and Cd concentration in rice grain.
• The model effectively learned the complex laws of Cd movement within the soil-crop system.

Conclusions:

• The GA-BP neural network is a highly accurate tool for predicting Cd concentration in rice grain, utilizing key soil properties.
• This predictive capability allows for timely assessment of human exposure and health risks, facilitating proactive risk management strategies.
• The study provides a robust method to mitigate Cd transfer from soil to the human food chain, enhancing food safety.