Forecasting high SC>2 concentration levels with fuzzy clustering techniques J. Ricardo Perez-Correa^ M Victoria Letelier^, Aldo
Hector Jorqucra · 1998
The city of Copiapo in Chile, close to the Hernan Videla Lira smelting copper plant, often suffers episodes of high SO] concentration levels that seriously affect the well-being of its inhabitants. A system forecasting high SO] levels was developed in order to alert the people of Copiapo and to give the plant engineers time to alter the operating conditions and thereby prevent the occurrence of these episodes or at least minimise their magnitude. The system uses a fuzzy clustering technique to process on-line data streaming from five monitoring stations every minute. The system is capable of forecasting SO] levels precisely two hours in advance during the summer season, when SO] concentrations are usually low. However, during winter, when SO] levels are high, the system underpredicts maximum values.