Search

Accurate streamflow prediction is essential for optimal water management and disaster preparedness. While data-driven methods' performance often surpasses process-based models, concerns regarding their 'black-box' nature persist. Hybrid models, integrating domain knowledge and process modeling into a data-driven framework, offer enhanced streamflow prediction capabilities. This study investigated watershed memory and process modeling-based hybridizing approaches across diverse hydrological regimes - Korean and Ethiopian watersheds. Following watershed memory analysis, the Soil and Water Assessment Tool (SWAT) was calibrated using the recession constant and other relevant parameters. Three hybrid models, incorporating watershed memory and residual error, were developed and evaluated against standalone long short-term memory (LSTM) models. Hybrids outperformed the standalone LSTM across all watersheds. The memory-based approach exhibited superior and consistent performance across training, evaluation periods, and regions, achieving 17-66% Nash-Sutcliffe efficiency coefficient improvement. The residual error-based technique showed varying performance across regions. While hybrids improved extreme event predictions, particularly peak flows, all models struggled at low flow. Korean watersheds' significant prediction improvements highlight the hybrid models' effectiveness in regions with pronounced temporal hydrological variability. This study underscores the importance of selecting a specific hybrid approach based on the desired objectives rather than solely relying on statistical metrics that often reflect average performance. [ABSTRACT FROM AUTHOR]

Jeju is a volcanic island dependent mainly on the groundwater supply. Overexploitation of groundwater is becoming a concern in the area resulting in saltwater intrusion. Eastern area of the island was selected as a field-scale study site to simulate the saltwater intrusion phenomenon. Prior to the saltwater intrusion modeling work, a regional groundwater flow models were employed to evaluate the water balance and hydrogeological characteristics by taking the advantage of a long time, 18 years, recorded groundwater level data. Hydraulic conductivity was one of the major parameters to be calibrated with inverse modeling using pilot point technique. The groundwater recharge was estimated using SWAT(Arnold et al., 1998). Using the field measurements and outputs of the regional scale model the saltwater intrusion at the local scale was simulated using SEAWAT(Langevin et al., 2007) which combines MODFLOW and MT3DMS in a single code. Several scenarios were created to test the effect of groundwater pumping by varying the current pumping rates, distribution of pumping wells, and the location of well screens. The results show that the amount of current groundwater pumping at the coastal region induced saltwater intrusion and the increase in pumping rate would have an impact on further saltwater intrusion. The location of the well screen affects the profile of the saltwater wedge. In addition, the distribution of the wells in the model creates significant change both in the prevention and in the enhancement of the intrusion. From this study, it is evident that cautiously designed well location and pumping schedules are possible management alternatives.* Corresponding author : Il-Moon ChungACKNOWLEDGMENTS: This work was supported by a grant (19RDRP-B076272-05) from Infrastructure and Transportation Technology Promotion Research Program funded by the Ministry of Land, Infrastructure, and Transport of Korean government.References:Arnold JG, Srinivasan R, Muttiah RS, Williams JR. 1998. Large Area Hydrologic Modeling and Assessment Part I: Model Development. Journal of the American Water Resources Association 34 (1): 73–89 DOI: 10.1111/j.1752-1688.1998.tb05961.xLangevin CD, Thorne Jr. DT, Dausman AM, Sukop MC, Guo W. 2007. SEAWAT Version 4: A Computer Program for Simulation of Multi-Species Solute and Heat Transport. U.S. Geological Survey Techniques and Methods Book 6: 39 Available at: https://pubs.usgs.gov/tm/tm6a22/pdf/tm6A22.pdf [Accessed 19 June 2018] [ABSTRACT FROM AUTHOR]