Water is the active basis for the movement and transformation of various biological, physical and chemical substances and the flow of energy. On the one hand, the quality of water environment is very sensitive to changes in the external world; on the other hand, water quality affects the health of organisms and ecosystems through ecological support and other functions. The space-time distribution of water quality was analyzed according to the composition of basic substances and established water quality standards, which provided scientific basis for the rational development and utilization of water resources planning and management. In this paper, the stochastic forest algorithm was used to evaluate the water pollution degree of Qingshui River basin. This paper first analyzed the causes of Qingshui River pollution, and introduced the establishment method of random forest (RF) classification model. After that, this paper established the evaluation criteria of water pollution degree, and constructed the evaluation model of water pollution degree of Qingshui River basin according to the RF algorithm. In the experiment part, the quantity of decision trees (DT) of the RF model was set to 400 through sample training, and the classification accuracy of the RF classification model and the artificial neural network (ANN) model was compared. The experimental results showed that the RF classification model has a high classification accuracy rate of 97.33%, which can be used to assess the degree of water pollution. At the end of this paper, the RF classification model was used to evaluate the water pollution degree of the Qingshui River basin. The results showed that for the three stations in the Qingshui River basin, the water quality classification results are Class I, Class III, and Class IV. The water pollution degree of the Qingshui River basin is relatively serious.

Xianmin Ma. Assessment of Water Pollution Degree in Qingshui River Basin Based on Stochastic Forest Algorithm. Water Pollution Prevention and Control Project (2021), Vol. 2, Issue 1: 1-10. https://doi.org/10.38007/WPPCP.2021.020101.

[1] Evans, Alexandra EV. "Agricultural water pollution: key knowledge gaps and research needs." Current opinion in environmental sustainability 36.2 (2019): 20-27.

[2] Feng, Xiaofang. "Review MXenes as a new type of nanomaterial for environmental applications in the photocatalytic degradation of water pollutants." Ceramics International 47.6 (2020): 7321-7343.

[3] Ji, Mengzhi. "Bacteriophages in water pollution control: Advantages and limitations." Frontiers of Environmental Science & Engineering 15.84 (2020): 1-15.

[4] Sharma, Rohit. "Water pollution examination through quality analysis of different rivers: a case study in India." Environment, Development and Sustainability 24.6 (2020): 7471-7492.

[5] Morin-Crini, Nadia. "Worldwide cases of water pollution by emerging contaminants: a review." Environmental Chemistry Letters 20.4 (2020): 2311-2338.

[6] Wikurendra, Edza Aria. "Water quality analysis of pucang river, sidoarjo regency to control water pollution." Environmental Quality Management 32.1 (2020): 133-144.

[7] Iqbal, Mudassir, Daxu Zhang, and Fazal E. Jalal. "Durability evaluation of GFRP rebars in harsh alkaline environment using optimized tree-based random forest model." Journal of Ocean Engineering and Science 7.6 (2020): 596-606.

[8] Lu, Shengfu. "Semi-supervised random forest regression model based on co-training and grouping with information entropy for evaluation of depression symptoms severity." Math. Biosci. Eng 18.4 (2020): 4586-4602.

[9] Sadler, J. M. "Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and Random Forest." Journal of hydrology 559.4 (2018): 43-55..

[10] Wang, Jing. "Risk assessment of coronary heart disease based on cloud-random forest." Artificial Intelligence Review 56.1 (2020): 203-232.

[11] Dharumarajan, Subramanian, and Rajendra Hegde. "Digital mapping of soil texture classes using Random Forest classification algorithm." Soil Use and Management 38.1 (2020): 135-149.

[12] Mobley, William. "Quantification of continuous flood hazard using random forest classification and flood insurance claims at large spatial scales: a pilot study in southeast Texas." Natural Hazards and Earth System Sciences 21.2 (2020): 807-822.

[13] Alnahit, Ali O., Ashok K. Mishra, and Abdul A. Khan. "Stream water quality prediction using boosted regression tree and random forest models." Stochastic Environmental Research and Risk Assessment 36.9 (2020): 2661-2680.

[14] Liu, Yang. "Risk prediction and diagnosis of water seepage in operational shield tunnels based on random forest." Journal of Civil Engineering and Management 27.7 (2020): 539-552.

[15] Li, Xing, Zhiping Wen, and Huaizhi Su. "An approach using random forest intelligent algorithm to construct a monitoring model for dam safety." Engineering with Computers 37.6 (2020): 39-56.