Open AccessFORECASTING THE FLOOD STAGE OF A RESERVOIR BASED ON THE CHANGES IN UPSTREAM RAINFALL PATTERN
Author(s) -
Raja Nurul Mardhiah Raja Mohamad,
Wan Hussain Wan Ishak
Publication year - 2019
Publication title -
journal of technology and operations management/journal of technology and operations management
Language(s) - English
Resource type - Journals
eISSN - 2590-4175
pISSN - 1823-514X
DOI - 10.32890/jtom2019.14.2.5
Subject(s) - flood myth , stage (stratigraphy) , hydrology (agriculture) , environmental science , water resource management , upstream (networking) , flood stage , water reservoir , recreation , water level , flood forecasting , water resources , water supply , 100 year flood , environmental engineering , petroleum engineering , geography , geology , engineering , geotechnical engineering , ecology , paleontology , telecommunications , cartography , archaeology , biology
Flood is amongthe major disasters in Malaysia. Flood occurs whenthe existing waterways areunable to support large amountsof waterduring heavy rain seasons. Reservoirshavebeen used as one of the flood mitigation approachesin the country. A reservoir can hold excessive water to ensure water flow tothedownstream area is under the safe capacity of the waterway. However, due to the needs of the society, a reservoir also serves other purposes such as water supply and recreation. Therefore, reservoir water storage should be maintained to satisfy water usage,and at the same time,the water needsto be released to reserve space forincoming water. This conflict causesproblemsto reservoir operatorswhen making the water release decision. In this paper, a forecasting model wasproposed to forecast the flood stage of a reservoir based on the upstream rainfall pattern. This model couldbe used by reservoir operatorsin the early decision-makingstageofreleasingwater before the reservoir reaches its maximum capacity. Simultaneously,the reservoir water level could be maintainedfor other uses. In this study, the experiments conducted provedthat an Artificial Neural Network is capable ofproducingan acceptable performance in terms of its accuracy.