Water Quality Assessment for Fishpond via Multisource Information Fusion

Abstract

Data fusion can effectively process multisource information so as to obtain more accurate and reliable results. The data of water quality in a fishpond comes from various sensors, therefore the data must be fused. In this study, K-nearest interpolation, Grubbs criterion, a fuzzy comprehensive evaluation method, as well as an improved fruit fly optimization algorithm (IFOA) to find optimal parameters γ and σ of least squares support vector regression (LSSVR), were combined to provide accurate data for multisource information fusion modeling. The K-nearest interpolation method and grubbs criterion were employed to process abnormal data gross errors. Besides, a batch estimation adaptive weighted fusion algorithm was employed to, respectively, integrate the data from dissolved oxygen, water temperature, PH, and ammonia nitrogen concentration. A fuzzy comprehensive evaluation method, as well as analytic hierarchy process (AHP) were employed to obtain the true value of water quality grade. In addition, an IFOA-LSSVR model was proposed to predict the future water quality, which can better fit the nonlinear relationship between complex environmental factors and water quality. Experimental results show that the presented method can improve the data accuracy and provide decision results and scientific basis for the precision control of water quality environment.