A New Method for Forecasting of Non-Point Source Pollutant Load

Abstract

Gaussian process (GP) is a newly developed machine learning technology based on statistical theoretical fundamentals, which has successful application in the field of solving for highly nonlinear problems. Conventional methods for forecasting of non-point source pollutant load often meet great difficulty since relationship between pollutant load and its influencing factors is highly complicated nonlinear. A new method based on GP is proposed for forecasting of non-point source pollutant load. The monitoring data of a certain river since 1976 to 1990 are preformed to obtain the training samples and test samples. Nonlinear mapping relationship between non-point source pollutant load and its influencing factors can be constructed by GP learning with the training samples. The monitoring data of a certain river since 1991 to 1993 are preformed to testify the effects of the method above. The results of case studies show that the method is feasible, effective and simple to implement for forecasting of non-point source pollutant load. It has merits of self-adaptive parameters determination and better capacity for solving nonlinear small sample problems comparing with the artificial neural networks method and Support Vector Machine method. The good performance of GP model makes it very attractive for a wide range of application in environmental engineering.