APPLICATION OF PCFC CLUSTERING ALGORITHM FOR ANALYSIS OF SURFACE WATER QUALITY IN GUNTUR CITY
Surface water quality in rural areas usually has a great variation in India and is hard to characterize by classical statistic methods. In this paper, a PCFC clustering method is used to classify and assess rural surface water quality based on the monitoring data from 50 typical stations in 15 small cannals and 4 reservoirs in Guntur city. The results show that the 50 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 13 and 10 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 execeed those in the second cluster. Thus, the overall quality or rural surface water in study are remains good, but there also exist some cannal 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.