Water quality prediction method and system based on integrated learning model

Abstract

The invention provides a water quality prediction method and system based on an integrated learning model. The method comprises the following steps: acquiring historical data of water quality indexes; extracting a training data set in the historical data of the water quality indexes, respectively constructing an autoregressive integral moving average model and a time sequence prediction model for the training data set, and obtaining a comprehensive prediction result data set of the water quality indexes; extracting a result training set in the water quality index comprehensive prediction result data set, and inputting the result training set into the multilayer neural network model to obtain a third model water quality index prediction result data set; and calculating a water quality index prediction result according to the water quality index comprehensive prediction result data set and the third model water quality index prediction result data set. The water quality prediction accuracy and the water quality prediction effect are improved, and the invention is suitable for water quality prediction of all stations.

Description

technical field [0001] The present application relates to the technical field of water quality monitoring, in particular to a water quality prediction method and system based on an integrated learning model. Background technique [0002] Water quality prediction plays an important guiding role in water environment management. At present, there are many methods for predicting water quality, such as using the moving average of the past moment or the data of the same period in the past as the predicted value. In addition, water quality monitoring data, as a kind of data with time series attributes, can also be predicted by using statistical time series models and machine learning models. [0003] Considering that there are many factors affecting the water environment, a single model cannot accurately learn the laws of the water quality monitoring data itself, and it cannot make accurate predictions. The deep learning model based on neural network, because it can simulate the ...

AI Technical Summary

Problems solved by technology

[0003] Considering that there are many factors affecting the water environment, a single model cannot accurately learn the laws of the water quality monitoring data itself, and it cannot make accurate predictions

The deep learning model based on neural network, because it can simulate the nonlinear relationship between complex data, is prone to overfitting, has poor generalization ability, and cannot make accurate predictions.

Furthermore, there are many water quality sites, and a single model architecture cannot be well applied to all sites

Images