Copyright © 2021 ISEIS. All rights reserved
Spatiotemporal Classification Analysis of Long-Term Environmental Monitoring Data in the Northern Part of Lake Taihu, China by Using a Self-Organizing Map
Characterizing the spatiotemporal patterns of water bodies is an important environmental issue in the management and protection of water resources. The primary objective of this study was to assess the spatiotemporal characteristics of environmental monitoring data from Lake Taihu to improve water pollution control practices. A methodologically systematic application of a self-organizing map (SOM) was utilized for data mining in the northern part of Lake Taihu, China. The monitoring data set contained 14 variables from eight monitoring stations during the period 2000-2006. The SOM classified the data set into 10 clusters displaying a markedly different pattern. We determined the spatiotemporal distribution of water quality based on the data frequency at each station monitored monthly in the study area. Based on the SOM analysis results, we suggest that the government should increase the number of monitoring points in the region. Given the relatively poor water quality in the region, unnecessary points should be decreased and different control measures should be implemented during different seasons. The results of this study could assist lake managers in developing suitable strategies and determining priorities for water pollution control and effective water resource management.
Keywords: spatiotemporal classification, self-organizing map, water quality
- There are currently no refbacks.