Reservoir operation involves many critical decisions due to unpredicted circumstances, such as drought or flood. The reservoir water release decision is one of the challenging tasks for the reservoir operator since the decision to deal with many complicated decision variables and multipurpose operation. Typically, the water that flow into the reservoir comes from the upstream river network. The gauging stations are located at different locations and the distance between the gauging stations and

more »

... the reservoir are varied. This information indicates that there are spatial relationships between gauging stations and reservoir. This paper aims to investigate the spatial relationship between the upstream gauging stations and the reservoir by mapping temporal rainfall information on each gauging station with the reservoir water level. The mapping was established using Backpropagation Neural Network. The findings show that different location and distance of each gauging station with the Timah Tasoh reservoir does affect the water travel time from gauging stations to the reservoir.  Index Terms-backpropagation neural network, spatialtemporal data, reservoir water level forecasting