Rapid monitoring of heavy metal pollution in lake water using nitrogen and phosphorus nutrients and physicochemical indicators by support vector machine. (October 2021)

• Record Type: Journal Article
• Authors: Li, Xiaolong; Yang, Jinxiang; Fan, Yifan; Xie, Mengxing; Qian, Xin; Li, Huiming
• Is Part Of: Chemosphere. Volume 280(2021)
• Publication Date: 2021-10
• Subjects: Heavy metals -- Support vector machine (SVM) -- Nitrogen and phosphorus nutrients -- Physicochemical indicators -- Prediction; Pollution -- Periodicals; Pollution -- Physiological effect -- Periodicals; Environmental sciences -- Periodicals; Atmospheric chemistry -- Periodicals; 551.511
• DOI: 10.1016/j.chemosphere.2021.130599
• Languages: English
• ISSNs: 0045-6535

Abstract

Abstract: A novel method of predicting heavy metal concentration in lake water by support vector machine (SVM) model was developed, combined with low-cost, easy to obtain nutrients and physicochemical indicators as input variables. 115 surface water samples were collected from 23 sites in Chaohu Lake, China, during different hydrological periods. The particulate concentrations of heavy metals in water were much higher than the dissolved concentrations. According to Nemerow pollution index (Pi), pollution degrees by Fe, V, Mn and As ranged from heavy (2 ≤ Pi < 4) to serious (Pi ≥ 4). The concentrations of most heavy metals were the highest during the medium-water period and the lowest during the dry season. Non-metric Multidimensional Scaling Analysis confirmed heavy metal concentrations had slight spatial difference but relatively large seasonal variation. Redundancy Analysis indicated the close associations of heavy metals with nutrient and physicochemical indicators. When both nutrient and physicochemical indicators were used as input variables, the simulation effects for most elements in total and particulate were relatively better than those obtained using only nutrient or only physicochemical indicators. The simulation effects for As, Ba, Fe, Ti, V and Zn were generally good, based on their training R values of 0.847, 0.828, 0.856, 0.867, 0.817 and 0.893, respectively, as well as their test R values of 0.811, 0.836, 0.843, 0.873, 0.829 and 0.826, respectively; and meanwhile, in both the training and test stages, these metals also had relatively lower errors. The spatial distribution of heavy metals in Chaohu Lake was then predicted using the fully trained SVM models. Graphical abstract: Image 1 Highlights: Spatiotemporal distribution of total, particulate and dissolved metals of lake were analyzed. Metals were simulated with nutrients and physicochemical indicators as inputs using SVM models. Simulation effects of As, Ba, Fe, Ti, V and Zn were promising with higher R values. Spatial distribution of metals in different phases can be predicted by lake indicators easy to get.