1. Title, Journal and Authors
- Title : An artiﬁcial neural network model for rainfall forecasting in Bangkok, Thailand
- Journal : Hydrology and Earth System Sciences
- Authors : N. Q. Hung, M. S. Babel, S. Weesakul, and N. K. Tripathi
Affiliation : School of Engineering and Technology, Asian Institute of Technology, Thailand
- This paper suggested a new approach to improve rainfall forecast performance using an artiﬁcial neural network (ANN).
- The study area of this research was Bangkok and the data sets consisted of 4 years of hourly data from 75 rain gauge
stations and meteorological information at the surrounding stations.
- Different network types were tested with different kinds of input data sets to provide forecasts in a near real time schedule.
- The results of training processes indicated that a feedforward ANN model with hyperbolic tangent function had the best
training performance for rainfall prediction.
- The results showed that ANN predicted rainfall for Bangkok from 1 to 3 hours ahead with high performance.
- And the sensitivity analysis showed that the most important input parameter besides rainfall itself was the wet bulb temperature.
3. Application to research
- The developed model and approaches can still be used for hydrological management ﬂood management and low impact
developments (LIDs) for the urban areas.
- The results of sensitivity analysis can be used to determine the dominant model inputs, as the suggested approaches are applied
to deep learning algorithms.
Heewon Jeong (Ph.D. program)
Environmental Systems Engineering Lab.
School of Environmental Science % Engineering
Gwangju Institute of Science and Technology
1 Oryong-dong Buk-gu Gwangju, 500-712, Korea
Phone : +82-10-8734-8657
Email : firstname.lastname@example.org