Intelligent water purifying agent adding method based on machine learning

The invention discloses an intelligent water purifying agent adding method based on machine learning, which comprises the following steps: S1, carrying out model training on a first tree model by utilizing first sample data, and outputting m adding amount predicted values; s2, performing model training on the second tree model by using second sample data, and outputting m dosage predicted values; s3, combining the m dosage predicted values in the step S1 with the m dosage predicted values in the step S2 to form a matrix A; s4, performing model training on the third tree model by using the matrix A to obtain a trained third tree model; s5, respectively inputting to-be-tested data into the trained first tree model and the trained second tree model, and outputting first and second dosage predicted values; and S6, inputting the output value in the step S5 into a trained third tree model, outputting a calculated value of the dosage, and enabling the actual dosage of the water purifying agent to be the calculated v