Development and optimization of an Artificial Neural Network (ANN) model for predicting the cadmium fixation efficiency of biochar in soil

Abstract

This study addresses the issue of soil cadmium pollution and the common problem of data missing during the training of artificial neural network models. A substantial amount of characteristic data regarding the immobilization of cadmium in soil through biochar was collected from the literature. Subsequently, data was organized and analyzed using correlation matrix analysis and feature importance analysis. The results revealed that the feature importance of biochar (52%) was relatively significant. A novel approach is introduced, involving a non-deterministic optimization technique based on linear interpolation to supplement the missing data within the dataset. The completed dataset effectively preserves the distributional characteristics of the original data, thereby enhancing the training performance of the neural network model. Through three phases, namely data incompleteness, data supplementation, and genetic algorithm optimization, the neural network model was progressively refined. The outcome of this iterative process is a high-performance artificial neural network model capable of predicting the efficiency of biochar in immobilizing cadmium in soil. The significance of these findings lies in their potential to advance the application of machine learning in environmental science, particularly in addressing complex pollution scenarios.