UV/vis spectrometric quantification is widely applied in water quality monitoring systems. The UV/vis spectrum contains a huge amount of information about the water composition so that it can be used to measure the density of substances. However, the traditional methods to estimate densities using spectrum based on Lambert-Beer's law become invalid in UV/vis spectrum because of the strong correlation among the absorption ratio of different wavelengths in the UV/vis spectrum. So we need to find a new estimating algorithm for water quality monitoring systems based on the UV/vis spectrum. In this paper, we analyze the traditional estimating algorithms. After that, we design an efficient estimating algorithms for water quality monitoring systems and evaluate it through orthogonal experiments.

Multi-task learning (MTL) exhibits improved performance in many problems in reality by utilizing the intrinsic features among multiple related tasks. In this paper, the problem of water quality monitoring is considered as multi-task learning, in which different tasks correspond to changes caused by new environment or different spectrometers. An improved learning model is presented describing the relationship between wavelengths and pollutant concentration as well as capturing the task relationships with a low-rank shared structure. Under the assumption that different tasks share some common wavelengths, an optimization problem is proposed with the predictors affected by these features and their corresponding coefficients that vary in different tasks. An alternating minimization algorithm is proposed to solve this problem. Experimental results demonstrate the effectiveness of the proposed algorithm in application.