A deterministic linearized recurrent neural network for recognizing the transition of rainfall–runoff processes

Characterizing the dynamic relationship between rainfall and runoff is a highly interesting modeling problem in hydrology. This study develops a deterministic linearized recurrent neural network (denoted as DLRNN) that deals with the system’s nonlinearity by recalibration at each time interval, and relates the weights of DLRNN to unit hydrographs in order to describe the transition of the rainfall–runoff processes. Case studies of 38 events, from 1966 to 1997, are implemented in the Wu-Tu watershed of Taiwan, where the runoff path-lines are short and steep. A comparison between the DLRNN and a feed-forward neural network demonstrates the advantage of DLRNN as a dynamic system model. It is concluded that DLRNN shows superiority in the performance of rainfall–runoff simulations and the ability to recognize transitions in hydrological processes.