Prediction of sulfur dioxide concentrations at a site near downtown Santiago,Chile |
| |
| Institution: | 1. Seismic Research Centre, The University of the West Indies, St. Augustine, Trinidad and Tobago;2. Department of Chemistry, The University of the West Indies, St. Augustine, Trinidad and Tobago;3. Soufrière Regional Development Foundation, Soufrière, Saint Lucia;1. Cellular and Molecular Research Center, School of Medicine, Zahedan University of Medical Sciences, Zahedan, Iran;2. Clinical Immunology Research Center, School of Medicine, Zahedan University of Medical Sciences, Zahedan, Iran;3. Department of Clinical Biochemistry, School of Medicine, Zahedan University of Medical Sciences, Zahedan, Iran;4. Department of Biology, Zabol University, Zabol, Iran;5. Department of Clinical Biochemistry and Molecular Biology, School of Medicine, shahidsadoughi University of Medical Sciences, Yazd, Iran;6. Department of Hematology, Faculty of Applied Medicine, Iran University of Medical Sciences, Tehran, Iran |
| |
| Abstract: | We have analyzed the possibility to predict hourly averages of sulfur dioxide concentrations in the atmosphere at a site not far from the downtown area in the city of Santiago, Chile. We have compared the forecasts produced assuming persistence, linear regressions and feed forward neural networks. The effect of meteorological conditions is included by using forecasted values of temperature, relative humidity and wind speed at the time of the intended prediction as inputs to the different models. The best predictions for hourly averages are obtained with a three-layer neural network that has hourly averages of sulfur dioxide concentrations every 6 h on the previous day plus the actual values of the meteorological variables as input. Training the network with 1995 data, error in 8 h in advance prediction for 1996 data is of the order of 30%. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
