2019
DOI: 10.1061/(asce)he.1943-5584.0001850
|View full text |Cite
|
Sign up to set email alerts
|

Performance Enhancement of a Conceptual Hydrological Model by Integrating Artificial Intelligence

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

2
16
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 32 publications
(18 citation statements)
references
References 44 publications
2
16
0
Order By: Relevance
“…To account for the soil water balance at the catchment scale, machine learning models are provided with more information on the antecedent conditions; therefore, the data-driven component has a better ability to simulate streamflow. The main differences between the GR-Hyb model presented here and the one presented by Kumanlioglu & Fistikoglu (2019) are with respect to the data-driven component and their parameter optimization techniques. In this study, cubist regression (Quinlan 1992(Quinlan , 1993 is used instead of a neural network to model streamflow.…”
Section: The Hybrid Hydrological Modelmentioning
confidence: 99%
See 3 more Smart Citations
“…To account for the soil water balance at the catchment scale, machine learning models are provided with more information on the antecedent conditions; therefore, the data-driven component has a better ability to simulate streamflow. The main differences between the GR-Hyb model presented here and the one presented by Kumanlioglu & Fistikoglu (2019) are with respect to the data-driven component and their parameter optimization techniques. In this study, cubist regression (Quinlan 1992(Quinlan , 1993 is used instead of a neural network to model streamflow.…”
Section: The Hybrid Hydrological Modelmentioning
confidence: 99%
“…The first type includes process-based models in which a hydrological model is established to calculate the response of rainfall based on empirical equations (conceptual) or physical processes (Ni et al 2020). These require the calibration of parameters to estimate, for example, evapotranspiration, infiltration, percolation, surface runoff, and other processes occurring in a basin (Kumanlioglu & Fistikoglu 2019). Regarding its disadvantages, these models have limitations due to the physical conditioning of parameters, high computational power requirements for spatially explicit operations, or the use of purely conceptual parameters that are not related to the hydrological properties of the watersheds.…”
mentioning
confidence: 99%
See 2 more Smart Citations
“…Impacts of climate change and human activities can encompass different aspects, including sediment (Wen et al 2019), river flow (Ashofteh et al 2016), water level (Wang et al 2009), and hydraulic project construction (Sun et al 2016). Researchers have applied various hydrologic models to determine the impacts of different factors on various water resources [e.g., CEQUEAU (Larabi et al 2018), identification of unit hydrographs and component flows from rainfall, evapotranspiration and streamflow (IHACRES) (Ashofteh et al 2015a), the artificial neural network-genetic algorithm (ANN-GA) model (Kumanlioglu and Fistikoglu 2019), Mike-Système Hydrologique Européen (SHE) (Loliyana and Patel 2018), the soil and water assessment tool (SWAT) model (Aadhar et al 2019), the Penn State Integrated Hydrologic Model (PIHM) (Seo et al 2018), and the distributed time-variant gain model (DTVGM) (Wang et al 2009)].…”
mentioning
confidence: 99%