Open AccessUsing k-Means and Self Organizing Maps in Clustering Air Pollution Distribution in Makassar City, Indonesia
Author(s) -
Suwardi Annas,
Uca Uca,
Irwan Irwan,
Rahmat Hesha Safei,
Zulkifli Rais
Publication year - 2022
Publication title -
jambura journal of mathematics
Language(s) - English
Resource type - Journals
eISSN - 2656-1344
pISSN - 2654-5616
DOI - 10.34312/jjom.v4i1.11883
Subject(s) - cluster analysis , air pollution , air quality index , environmental science , pollution , work (physics) , government (linguistics) , geographic information system , meteorology , geography , environmental engineering , computer science , cartography , engineering , mechanical engineering , ecology , linguistics , chemistry , philosophy , organic chemistry , machine learning , biology
Air pollution is an important environmental problem for specific areas, including Makassar City, Indonesia. The increase should be monitored and evaluated, especially in urban areas that are dense with vehicles and factories. This is a challenge for local governments in urban planning and policy-making to fulfill the information about the impact of air pollution. The clustering of starting points for the distribution areas can ease the government to determine policies and prevent the impact. The k-Means initial clustering method was used while the Self-Organizing Maps (SOM) visualized the clustering results. Furthermore, the Geographic Information System (GIS) visualized the results of regional clustering on a map of Makassar City. The air quality parameters used are Suspended Particles (TSP), Sulfur Dioxide (SO2), Nitrogen Dioxide (NO2), Carbon Monoxide (CO), Surface Ozone (O3), and Lead (Pb) which are measured during the day and at night. The results showed that the air contains more CO, and at night, the levels are reduced in some areas. Therefore, the density of traffic, industry and construction work contributes significantly to the spread of CO. Air conditions vary, such as high CO levels during the day and TSP at night. Also, there is a phenomenon at night that a group does not have SO2 and O3 simultaneously. The results also show that the integration of k-Means and SOM for regional clustering can be appropriately mapped through GIS visualization.