Lake and reservoir algal bloom predicating method based on multielement nonstationary time series analysis and neural network and support vector machine compensation

Abstract

The invention discloses a lake and reservoir algal bloom predicating method based on multielement nonstationary time series analysis and neural network and support vector machine compensation, and belongs to the technical field of water quality monitoring. The method comprises the steps of characteristic factor nonstationary time series modeling, error influence factor kernel principal component analysis, neural network error modeling according to the situation of large sample data, support vector machine error modeling according to the situation of small sample data, final error compensation and predicating result obtaining. The problems that existing algal bloom predication precision is not high, and predication is hard to carry out according to the small sample data are solved, the description of the algal bloom forming process corresponds to reality better, and the result of algal bloom modeling predication is more accurate. The advantage compensation of a time series analysis method suitable for linear system modeling and a statistical learning method suitable for nonlinear system modeling is achieved, and the algal bloom predication accuracy is improved.

Description

technical field [0001] The invention relates to a water bloom prediction method, which belongs to the technical field of water quality monitoring. Specifically, it refers to performing time series modeling and prediction on the basis of multivariate non-stationary time series analysis of the random process of water bloom generation of various characteristic factors. Neural network or support vector machine algorithm is used to modify the prediction model to improve the prediction accuracy of algae bloom prediction method. Background technique [0002] With the development of social economy, the status and role of water in national economic and social development are becoming more and more prominent. However, in recent years, due to the excessive intake of plant nutrients such as nitrogen and phosphorus in my country's lakes and reservoirs, algae and other aquatic plants have grown abnormally, water transparency and dissolved oxygen have decreased, and fish and other organism...

AI Technical Summary

Problems solved by technology

[0010] The present invention studies the prediction method of water bloom in lakes and reservoirs, and aims to solve the problems of low precision of existing water bloom prediction and difficulty in predicting small sample data, etc., and aim at the characteristic factors of the formation process of water bloom that actually have non-stationary and nonlinear characteristics Time series, using the multivariate non-stationary time series analysis method to model, and considering different sample sizes, using the neural network and support vector machine method suitable for nonlinear system modeling to compensate the prediction error of the time series model, thereby improving the water bloom Prediction accuracy provides effective reference for environmental protection departments and plays an important role in the protection and improvement of lake water environment

Images