Application of Fuzzy C-means Clustering for Assessing Rural Surface Water Quality in Lianyungang City

Surface water quality in rural areas usually has a great variation in China and is hard to characterize by classical statistic methods. In this paper, a fuzzy c-means clustering method is used to classify and assess rural surface water quality based on the monitoring data from 33 typical stations in 23 rural rivers and 4 reservoirs in Lianyungang city. The results show that the 33 monitoring stations can be classified into 3 clusters in terms of water quality. The first cluster consists of 27 stations and most of their water quality indexes are nearly at or better than the national Grade II standards, while the second and third clusters respectively contain 5 and 1 stations, and their indexes of ammonia nitrogen and petroleum are at or worse than the national Grade V standards, and the index values in the third cluster generally exceed those in the second cluster. Thus, the overall quality of rural surface water in study area remains good, but there also exist some river sections contaminated with ammonia nitrogen and petroleum. Therefore, it is very necessary to establish water quality safety and risk assessment system for ensuring water supplies for production and daily life.