Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Assessment of projected change in Intensity-duration-frequency (IDF) curves for Southeastern, United States using Artificial Neural Networks.

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2022 ASABE Annual International Meeting  2200175.(doi:10.13031/aim.202200175)
Authors:   Bijoychandra S Takhellambam, Puneet Srivastava, Jasmeet Lamba, Wenpeng Zhao, Hemendra Kumar, Di Tian
Keywords:   ANN, Climate Change, GEV, stochastic, temporal disaggregation, Frequency analysis, IDF curves. 

Abstract. Anthropogenic activities have increased greenhouse gas emissions in the atmosphere. The resulting changing climate is expected to affect the rainfall characteristic mostly amount, intensity, and frequency. The rainfall Intensity Duration Frequency(IDF) curves should be updated for the projected climatic conditions. Therefore, the objective of our study is to develop future projected IDF curves using the HADGEM model under the RCP 8.5 scenario over the southeast United States. We assess a feed forward back propagation Artificial Neural Network (ANN) model for downscaling 1-hour rainfall to sub-hour monthly maximum rainfall. The Nash Sutcliff Efficiency was found in the range of 0.67 to 0.86. Moreover, the results from future projected rainfall IDF curves for a station located at Houston, Mississippi show increasing extreme rainfall event with 30-min and 45-min duration in range of 1% to 6% with a return period of 5, 10, 25, 50, and 100 years. However, 15-min duration show decreasing extreme rainfall depth in range of 2% to 4%. The spatial variation of extreme rainfall depth found both Gulf-Atlantic coast and the Appalachian Mountains are likely to receive greater rainfall than other parts of the southeast United States.

(Download PDF)    (Export to EndNotes)