Developing reliable methods to estimate baseflow has been a subject of research interest over the past decades due to its importance in catchment response and sustainable watershed management (e.g. ground water recharge vs. extraction). Limitations and complexities of existing methods have been addressed by a number of researchers. For instance, physically based numerical models are complex, requiring substantial computational time and data which may not be always available. Artificial Intelligence (AI) tools such as Genetic Programming (GP) have been used widely to reduce the challenges associated with complex hydrological systems without losing the physical meanings. However, up to date, in the absence of complex numerical models, baseflow is frequently estimated using statistically derived empirical equations without significant physical insights. This study investigates the capability of GP in estimating baseflow for a small intensively monitored semi-urban catchment (8.5 ha) located in Singapore. The validated GP model for Singapore is tested on a larger vegetation-dominated basin located in the USA (24 km2). For each study case, the baseflow predictions from the established GP model were compared with baseflow estimates obtained through the use of the Recursive Digital Filters (RDFs) method using the available discharge time series. The Nash–Sutcliffe efficiency of 0.94 and 0.91 are found with comparing the baseflow estimated by GP and RDFs in the first and second study sites, respectively. These results indicate that GP is an effective tool in determining baseflow. Overall, this study proposes a new approach which can predict the baseflow with only information on three parameters including minimum baseflow in dry period, area of the catchment and groundwater table.
Meshgi, Ali; Schmitter, Petra; Babovic, Vladan; and Chui, Ting Fong May, "Predicting Baseflow Using Genetic Programing" (2014). CUNY Academic Works.