Dataset Information

Enhanced streamflow prediction with SWAT using support vector regression for spatial calibration: A case study in the Illinois River watershed, U.S.

ABSTRACT: Accurate streamflow prediction plays a pivotal role in hydraulic project design, nonpoint source pollution estimation, and water resources planning and management. However, the highly non-linear relationship between rainfall and runoff makes prediction difficult with desirable accuracy. To improve the accuracy of monthly streamflow prediction, a seasonal Support Vector Regression (SVR) model coupled to the Soil and Water Assessment Tool (SWAT) model was developed for 13 subwatersheds in the Illinois River watershed (IRW), U.S. Terrain, precipitation, soil, land use and land cover, and monthly streamflow data were used to build the SWAT model. SWAT Streamflow output and the upstream drainage area were used as two input variables into SVR to build the hybrid SWAT-SVR model. The Calibration Uncertainty Procedure (SWAT-CUP) and Sequential Uncertainty Fitting-2 (SUFI-2) algorithms were applied to compare the model performance against SWAT-SVR. The spatial calibration and leave-one-out sampling methods were used to calibrate and validate the hybrid SWAT-SVR model. The results showed that the SWAT-SVR model had less deviation and better performance than SWAT-CUP simulations. SWAT-SVR predicted streamflow more accurately during the wet season than the dry season. The model worked well when it was applied to simulate medium flows with discharge between 5 m3 s-1 and 30 m3 s-1, and its applicable spatial scale fell between 500 to 3000 km2. The overall performance of the model on yearly time series is "Satisfactory". This new SWAT-SVR model has not only the ability to capture intrinsic non-linear behaviors between rainfall and runoff while considering the mechanism of runoff generation but also can serve as a reliable regional tool for an ungauged or limited data watershed that has similar hydrologic characteristics with the IRW.

SUBMITTER: Yuan L

PROVIDER: S-EPMC8041176 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Populations of many shorebird species appear to be declining in North America, and food resources at stopover habitats may limit migratory bird populations. We investigated body condition of, and foraging habitat and diet selection by 4 species of shorebirds in the central Illinois River valley during fall migrations 2007 and 2008 (Killdeer [Charadrius vociferus], Least Sandpiper [Calidris minutilla], Pectoral Sandpiper [Calidris melanotos], and Lesser Yellowlegs [Tringa flavipes]). All species except Killdeer were in good to excellent condition, based on size-corrected body mass and fat scores. Shorebird diets were dominated by invertebrate taxa from Orders Diptera and Coleoptera. Additionally, Isopoda, Hemiptera, Hirudinea, Nematoda, and Cyprinodontiformes contribution to diets varied by shorebird species and year. We evaluated diet and foraging habitat selection by comparing aggregate percent dry mass of food items in shorebird diets and core samples from foraging substrates. Invertebrate abundances at shorebird collection sites and random sites were generally similar, indicating that birds did not select foraging patches within wetlands based on invertebrate abundance. Conversely, we found considerable evidence for selection of some diet items within particular foraging sites, and consistent avoidance of Oligochaeta. We suspect the diet selectivity we observed was a function of overall invertebrate biomass (51.2 ± 4.4 [SE] kg/ha; dry mass) at our study sites, which was greater than estimates reported in most other food selection studies. Diet selectivity in shorebirds may follow tenants of optimal foraging theory; that is, at low food abundances shorebirds forage opportunistically, with the likelihood of selectivity increasing as food availability increases. Nonetheless, relationships between the abundance, availability, and consumption of Oligochaetes for and by waterbirds should be the focus of future research, because estimates of foraging carrying capacity would need to be revised downward if Oligochaetes are truly avoided or unavailable for consumption.

Dataset Information

Enhanced streamflow prediction with SWAT using support vector regression for spatial calibration: A case study in the Illinois River watershed, U.S.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets