Research on prediction model of dewatering and solidification of river and lake sediment based on machine learning

In order to study the effects of mud moisture content, dosage and sludge specific resistance of river and lake sediment on dehydration and solidification of river and lake sediment, a prediction model between filter cake moisture content expressed by mud moisture content, dosage and sludge specific resistance was established by using machine learning (BP neural network and symbolic regression). The results showed that the prediction models obtained by the two machine learning methods had good correlation accuracy. Based on the comparison of four commonly used error evaluation indexes, the accuracy of BP neural network prediction results was better, and the contribution of mud moisture content and sludge specific resistance in the input parameters of the two models to the final filter cake moisture content was similar and large. The established correlation model provided a reliable prediction and analysis tool for the dehydration and solidification of river and lake sediment.