Modeling Hydrological Responses of Watershed Under Climate Change Scenarios Using Machine Learning Techniques

Climate change is the most important problem of the earth in the current century. In this study, the effects of climate change on precipitation, temperature, wind speed, relative humidity and surface runoff in Saghez watershed in Iran investigated. The main methods were using the Coupled Model Inter...

Full description

Saved in:
Bibliographic Details
Published in:Water resources management Vol. 37; no. 13; pp. 5235 - 5254
Main Authors: Karimizadeh, Keivan, Yi, Jaeeung
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 01.10.2023
Springer Nature B.V
Subjects:
Artificial neural networks
Atmospheric Sciences
Civil Engineering
Climate change
Climate effects
Earth and Environmental Science
Earth Sciences
Environment
Environmental impact
Geotechnical Engineering & Applied Earth Sciences
Humidity
Hydrogeology
Hydrologic models
Hydrology/Water Resources
Intercomparison
Iran
Machine learning
Neural networks
Precipitation
prediction
Predictions
Relative humidity
Runoff
Scaling
Socioeconomic aspects
socioeconomics
Soil and Water Assessment Tool model
Soil water
Surface runoff
temperature
Water resources
Watersheds
Weather forecasting
Wind speed
Iran
Climate change
CMIP6
SSPs
SWAT and machine learning
Saghez watershed
ISSN:0920-4741, 1573-1650
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Climate change is the most important problem of the earth in the current century. In this study, the effects of climate change on precipitation, temperature, wind speed, relative humidity and surface runoff in Saghez watershed in Iran investigated. The main methods were using the Coupled Model Intercomparison Project phase 6 (CMIP6), the Soil and Water Assessment Tool (SWAT) and the Artificial Neural Network (ANN) model under the Shared Socio-economic Pathway scenarios (SSPs) using the Linear Scaling Bias Correction (LSBC) for the future period (2021–2050) compared to the base period (1985–2014). Additionally, MAE, MSE, RMSE and R 2 indices used for model calibration and validation. The average projected precipitation was forecasted to decrease by 6.1%. In terms of the temperature, 1.4 Cº, and 1.6 Cº increases were predicted for minimum and maximum temperatures, respectively. Prediction of surface runoff using the SWAT model also illustrated that based on SSP1-2.6, SSP3-7.0 and SSP5-8.5 scenarios, runoff will decrease in the future period, which based on three mentioned scenarios is equals to 17.5%, 23.7% and 26.3% decrease, respectively. Furthermore, the assessment using the artificial neural network (ANN) also showed that the parameters of precipitation in the previous two days, wind speed and maximum relative humidity have the greatest effect on the watershed runoff. These findings may be helpful to reduce the impacts of climate change, and make the suitable long-term plans for management of the watersheds and water resources in the region.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0920-4741
1573-1650
DOI:10.1007/s11269-023-03603-z