Pub Date : 2023-09-05DOI: 10.1080/02626667.2023.2243463
Wasu Manawko Tefera, K. S. Kasiviswanathan
ABSTRACT This study explored the potential of three calibration approaches – single-site, multisite, and multisite–multivariable – to simulate the streamflow and sediment yield of the Upper Blue Nile (UBN) river basin using the Soil and Water Assessment Tool (SWAT). Several statistical indices were used to verify the SWAT model performance. While all three approaches reasonably estimate the streamflow and sediment yield, the multisite calibration approach was found to perform better in handling the spatial variability of parameters and their influence on streamflow and sediment yield over the entire catchment. Further, evaluations of hydropower potential at the selected location were conducted to demonstrate the importance of calibration approaches in planning and designing various water resource structures.
{"title":"Potential assessment of calibration approaches using the SWAT hydrological model for streamflow and sediment yield for a large-scale catchment","authors":"Wasu Manawko Tefera, K. S. Kasiviswanathan","doi":"10.1080/02626667.2023.2243463","DOIUrl":"https://doi.org/10.1080/02626667.2023.2243463","url":null,"abstract":"ABSTRACT This study explored the potential of three calibration approaches – single-site, multisite, and multisite–multivariable – to simulate the streamflow and sediment yield of the Upper Blue Nile (UBN) river basin using the Soil and Water Assessment Tool (SWAT). Several statistical indices were used to verify the SWAT model performance. While all three approaches reasonably estimate the streamflow and sediment yield, the multisite calibration approach was found to perform better in handling the spatial variability of parameters and their influence on streamflow and sediment yield over the entire catchment. Further, evaluations of hydropower potential at the selected location were conducted to demonstrate the importance of calibration approaches in planning and designing various water resource structures.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47803231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-31DOI: 10.1080/02626667.2023.2253227
Marjorie B. Kreis, J. Taupin, N. Patris, V. Vergnaud-Ayraud, C. Leduc, P. Lachassagne, J. Burte, E. Martins
ABSTRACT Shallow crystalline groundwater in the semi-arid hinterland of Ceará is brackish or saline with mixed chloride or sodium chloride facies. Very few hydrochemical data are available for the area and the drivers behind this salinity are not clearly identified. In this study, extensive field data collection was performed to provide new information about the hydrogeological functioning and the salinization processes, through the implementation of piezometric, hydrogeochemical, isotopic (18O, 2H) and multitracer dating (14C, 3H, CFC, SF6) monitoring. Piezometric and isotopic data evidence fast flow circulation processes and a high contribution of evaporated surface water to aquifer recharge. Multitracer dating shows the groundwater is essentially composed of seasonal vertical infiltration flows that mix with older waters stored in the aquifer. Chemical analyses suggest the groundwater, originally low mineralized, has become progressively saltier due to leaching of salts that were evapoconcentrated in either surface waters or the unsaturated zone during drier periods.
{"title":"Explaining the groundwater salinity of hard-rock aquifers in semi-arid hinterlands using a multidisciplinary approach","authors":"Marjorie B. Kreis, J. Taupin, N. Patris, V. Vergnaud-Ayraud, C. Leduc, P. Lachassagne, J. Burte, E. Martins","doi":"10.1080/02626667.2023.2253227","DOIUrl":"https://doi.org/10.1080/02626667.2023.2253227","url":null,"abstract":"ABSTRACT Shallow crystalline groundwater in the semi-arid hinterland of Ceará is brackish or saline with mixed chloride or sodium chloride facies. Very few hydrochemical data are available for the area and the drivers behind this salinity are not clearly identified. In this study, extensive field data collection was performed to provide new information about the hydrogeological functioning and the salinization processes, through the implementation of piezometric, hydrogeochemical, isotopic (18O, 2H) and multitracer dating (14C, 3H, CFC, SF6) monitoring. Piezometric and isotopic data evidence fast flow circulation processes and a high contribution of evaporated surface water to aquifer recharge. Multitracer dating shows the groundwater is essentially composed of seasonal vertical infiltration flows that mix with older waters stored in the aquifer. Chemical analyses suggest the groundwater, originally low mineralized, has become progressively saltier due to leaching of salts that were evapoconcentrated in either surface waters or the unsaturated zone during drier periods.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43819867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-30DOI: 10.1080/02626667.2023.2252406
Chris Leong, Maletina Solomone, R. Shinjo, Daiki Tomojiri, Christmas Uchiyama, J. Yasumoto, B. Razafindrabe
ABSTRACT This paper provides an assessment of hydrological research activity conducted in the Oceania Region. Literature from three databases (Web of Science (WOS), Scopus, and Google Scholar) was collected and analysed. Results show large gaps in the variety of themes and poor collaborative efforts between regional water specialists. Results also suggest that local specialists potentially lack the ability to conduct quality hydrological research or that, due to the region’s developing status, more focus has been placed on project-based objectives rather than building a body of research. A solution could be the development of a self-reliant base for conducting hydrological research by empowering and improving capabilities of local citizens. Firstly, an overhaul of organization policies regarding the introduction of research and performance monitoring is needed. Secondly, education in hydrology must be improved to suit local capabilities while addressing the complex socio-cultural environment with transdisciplinary measures. This assessment could benefit the future management of hydrological services.
{"title":"An assessment of small island hydrological research activity conducted in the Oceania region","authors":"Chris Leong, Maletina Solomone, R. Shinjo, Daiki Tomojiri, Christmas Uchiyama, J. Yasumoto, B. Razafindrabe","doi":"10.1080/02626667.2023.2252406","DOIUrl":"https://doi.org/10.1080/02626667.2023.2252406","url":null,"abstract":"ABSTRACT This paper provides an assessment of hydrological research activity conducted in the Oceania Region. Literature from three databases (Web of Science (WOS), Scopus, and Google Scholar) was collected and analysed. Results show large gaps in the variety of themes and poor collaborative efforts between regional water specialists. Results also suggest that local specialists potentially lack the ability to conduct quality hydrological research or that, due to the region’s developing status, more focus has been placed on project-based objectives rather than building a body of research. A solution could be the development of a self-reliant base for conducting hydrological research by empowering and improving capabilities of local citizens. Firstly, an overhaul of organization policies regarding the introduction of research and performance monitoring is needed. Secondly, education in hydrology must be improved to suit local capabilities while addressing the complex socio-cultural environment with transdisciplinary measures. This assessment could benefit the future management of hydrological services.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42672150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-30DOI: 10.1080/02626667.2023.2252816
Arthur Jordan de Azevedo Toné, A. Costa, Mário Ubirajara Gonçalves Barros, Hermilson Barros de Freitas, José Rodrigo Vasconcelos Cavalcante, I. L. Lima Neto
ABSTRACT This study analyses the spatiotemporal river–aquifer interactions in a large dryland river with high anthropic intervention. Measurements of water level and flow rate were performed and analysed together with secondary data on hydrogeology, water use and satellite images. Average transmission losses ranged from about 12 to 28% of the river inflow, while transmission gains ranged from 10 to 34%. Transmission losses occurred at the beginning of the rainy season (rainfall ≤ 10 mm/d), while the transmission gains were preponderant after intense rainfall events (> 20 mm/d). A direct relationship between the transmission losses/gains and river inflow was also observed. Linear equations were adjusted to estimate the order of magnitude of transmission losses (R2 > 0.85) and gains (R2 > 0.60). The transmission loss equation was validated for rivers in similar regions (R2 ≈ 0.85). A conceptual model is proposed to describe river–aquifer interactions in large dryland rivers.
{"title":"Spatiotemporal river–aquifer interactions of a large tropical dryland river with high anthropic intervention","authors":"Arthur Jordan de Azevedo Toné, A. Costa, Mário Ubirajara Gonçalves Barros, Hermilson Barros de Freitas, José Rodrigo Vasconcelos Cavalcante, I. L. Lima Neto","doi":"10.1080/02626667.2023.2252816","DOIUrl":"https://doi.org/10.1080/02626667.2023.2252816","url":null,"abstract":"ABSTRACT This study analyses the spatiotemporal river–aquifer interactions in a large dryland river with high anthropic intervention. Measurements of water level and flow rate were performed and analysed together with secondary data on hydrogeology, water use and satellite images. Average transmission losses ranged from about 12 to 28% of the river inflow, while transmission gains ranged from 10 to 34%. Transmission losses occurred at the beginning of the rainy season (rainfall ≤ 10 mm/d), while the transmission gains were preponderant after intense rainfall events (> 20 mm/d). A direct relationship between the transmission losses/gains and river inflow was also observed. Linear equations were adjusted to estimate the order of magnitude of transmission losses (R2 > 0.85) and gains (R2 > 0.60). The transmission loss equation was validated for rivers in similar regions (R2 ≈ 0.85). A conceptual model is proposed to describe river–aquifer interactions in large dryland rivers.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44585543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-29DOI: 10.1080/02626667.2023.2251968
Melike Kiraz, G. Coxon, Thorsten Wagener
ABSTRACT Multi-model studies are widespread in large-sample hydrology. However, significant challenges remain in identifying interpretable connections between high-performing model structures and catchment characteristics, and thus in developing a coherent strategy for developing tailored multi-model ensembles. Here, we assess the importance of selecting model structures that are consistent with the expected hydrological variability across the study domain. We compare results of two modular modelling frameworks across 998 catchments in Great Britain. The RRMT framework includes model structures historically evolved in the UK, while the FUSE framework employs model structures from diverse global origins. While both groups of model structures contain high-performing members, the historically evolved group members separate between catchments in line with our expectation of hydrologic differences. We find that four hydrologic signatures organize these distinctions. Our results emphasize (1) the importance of model structure selection based on explicit perceptual models, and (2) the need to look beyond statistical performance alone.
{"title":"A priori selection of hydrological model structures in modular modelling frameworks: application to Great Britain","authors":"Melike Kiraz, G. Coxon, Thorsten Wagener","doi":"10.1080/02626667.2023.2251968","DOIUrl":"https://doi.org/10.1080/02626667.2023.2251968","url":null,"abstract":"ABSTRACT Multi-model studies are widespread in large-sample hydrology. However, significant challenges remain in identifying interpretable connections between high-performing model structures and catchment characteristics, and thus in developing a coherent strategy for developing tailored multi-model ensembles. Here, we assess the importance of selecting model structures that are consistent with the expected hydrological variability across the study domain. We compare results of two modular modelling frameworks across 998 catchments in Great Britain. The RRMT framework includes model structures historically evolved in the UK, while the FUSE framework employs model structures from diverse global origins. While both groups of model structures contain high-performing members, the historically evolved group members separate between catchments in line with our expectation of hydrologic differences. We find that four hydrologic signatures organize these distinctions. Our results emphasize (1) the importance of model structure selection based on explicit perceptual models, and (2) the need to look beyond statistical performance alone.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44437916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-29DOI: 10.1080/02626667.2023.2251957
Yuzhuang Chen, Yuntong She
ABSTRACT Modelling snow- and ice-affected streamflow in cold regions is challenging. Neglecting the streamflow from ungauged regions/sub-basins of a river basin in the inflow boundaries of a river ice model adds further uncertainties. This study combined a river ice model (River1D) with a hydrological model (Soil and Water Assessment Tool, SWAT) to investigate the impacts of ungauged sub-basin streamflow on peak flow simulation under both open water and river ice breakup conditions in the Peace River Basin (PRB). Results showed that ungauged sub-basins of the PRB can greatly affect peak flow simulation of the River1D for both open water and river ice breakup events, especially for flood events. Although they represent only about 26.54% of the whole modelled area in the PRB, the SWAT model simulated results show that the ungauged sub-basins can contribute nearly 50% of peak flow for the open water and river ice breakup flood events.
{"title":"A hydrologic and river ice modeling framework for assessing ungauged subbasin streamflow impact in a large cold-region river basin","authors":"Yuzhuang Chen, Yuntong She","doi":"10.1080/02626667.2023.2251957","DOIUrl":"https://doi.org/10.1080/02626667.2023.2251957","url":null,"abstract":"ABSTRACT Modelling snow- and ice-affected streamflow in cold regions is challenging. Neglecting the streamflow from ungauged regions/sub-basins of a river basin in the inflow boundaries of a river ice model adds further uncertainties. This study combined a river ice model (River1D) with a hydrological model (Soil and Water Assessment Tool, SWAT) to investigate the impacts of ungauged sub-basin streamflow on peak flow simulation under both open water and river ice breakup conditions in the Peace River Basin (PRB). Results showed that ungauged sub-basins of the PRB can greatly affect peak flow simulation of the River1D for both open water and river ice breakup events, especially for flood events. Although they represent only about 26.54% of the whole modelled area in the PRB, the SWAT model simulated results show that the ungauged sub-basins can contribute nearly 50% of peak flow for the open water and river ice breakup flood events.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48291055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-23DOI: 10.1080/02626667.2023.2251468
H. Dadashi, M. Rahimzadegan
ABSTRACT The total precipitable water vapour (TPW) extraction algorithm using the Sentinel-3A Ocean and Land Colour Instrument (OLCI) has the potential to be improved on a regional scale. The aim of this study was to improve the TPW extraction algorithm of OLCI for the first time using environmental variables, including the Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), and elevation from mean sea level, on a regional scale over Iran. A previously developed TPW recovery algorithm was applied to the OLCI data during cloud-free days throughout a one-year period (1 January–29 December 2020). The artificial neural network (ANN) methodology was utilized in eight models. The evaluation results revealed the effectiveness of the models varied based on the topography and climate of each station. The assessment findings demonstrated that model 2, which integrated LST, elevation, and NDVI data in the ANN framework, outperformed other models across the study area.
{"title":"A new approach to improve precipitable water vapour estimations of Sentinel-3A satellite data using LST, elevation and NDVI over Iran","authors":"H. Dadashi, M. Rahimzadegan","doi":"10.1080/02626667.2023.2251468","DOIUrl":"https://doi.org/10.1080/02626667.2023.2251468","url":null,"abstract":"ABSTRACT The total precipitable water vapour (TPW) extraction algorithm using the Sentinel-3A Ocean and Land Colour Instrument (OLCI) has the potential to be improved on a regional scale. The aim of this study was to improve the TPW extraction algorithm of OLCI for the first time using environmental variables, including the Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), and elevation from mean sea level, on a regional scale over Iran. A previously developed TPW recovery algorithm was applied to the OLCI data during cloud-free days throughout a one-year period (1 January–29 December 2020). The artificial neural network (ANN) methodology was utilized in eight models. The evaluation results revealed the effectiveness of the models varied based on the topography and climate of each station. The assessment findings demonstrated that model 2, which integrated LST, elevation, and NDVI data in the ANN framework, outperformed other models across the study area.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49388808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-22DOI: 10.1080/02626667.2023.2249456
E. E. Başakın, Ö. Ekmekcioğlu, M. Özger
ABSTRACT This study aimed to review the existing research focalizing on the missing data imputation techniques for the systems enabling actual evapotranspiration calculation (such as eddy covariance, Bowen ratio, and lysimeters) and divergent evapotranspiration related variables, i.e. temperature, wind speed, humidity, and solar radiation. Thus, the Scopus engine was utilized to scan the entire literature and 62 articles were diligently investigated. Results show classical approaches have been widely used by researchers due to their ease of implementation. However, the applicability and validity of these methods heavily rely on assumptions made about the distribution and characteristics of missing data. Hence, advanced imputation techniques produce more accurate outcomes as they handle complex and non-linear problems. Also, current trends embraced by the research community revealed that employing deep learning techniques and incorporating explainable artificial intelligence into imputations have significant potential to make insightful contributions to the body of knowledge.
{"title":"Providing a comprehensive understanding of missing data imputation processes in evapotranspiration-related research: A systematic literature review","authors":"E. E. Başakın, Ö. Ekmekcioğlu, M. Özger","doi":"10.1080/02626667.2023.2249456","DOIUrl":"https://doi.org/10.1080/02626667.2023.2249456","url":null,"abstract":"ABSTRACT This study aimed to review the existing research focalizing on the missing data imputation techniques for the systems enabling actual evapotranspiration calculation (such as eddy covariance, Bowen ratio, and lysimeters) and divergent evapotranspiration related variables, i.e. temperature, wind speed, humidity, and solar radiation. Thus, the Scopus engine was utilized to scan the entire literature and 62 articles were diligently investigated. Results show classical approaches have been widely used by researchers due to their ease of implementation. However, the applicability and validity of these methods heavily rely on assumptions made about the distribution and characteristics of missing data. Hence, advanced imputation techniques produce more accurate outcomes as they handle complex and non-linear problems. Also, current trends embraced by the research community revealed that employing deep learning techniques and incorporating explainable artificial intelligence into imputations have significant potential to make insightful contributions to the body of knowledge.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45833382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-21DOI: 10.1080/02626667.2023.2249874
P. Nakhaei, O. Kisi
ABSTRACT The rapid decline of Lake Urmia in northwest Iran, caused by both human and natural factors, motivated our utilization of the Soil and Water Assessment Tool (SWAT) model. The objective was to identify the most effective reservoir outflow simulation scheme and assess the influence of land use changes in the Zarrineh River basin on Lake Urmia. The target release approach for controlled reservoirs and the measured outflow schemes were evaluated. Despite improved calibration results in the latter method, the former demonstrated superior performance during the validation phase. Three land use scenarios – a model with the 2001 land use map, a model with the 2008 land use map, and a model with a gradually updating land use map – were considered. The gradually updating land use scenario exhibited a significant enhancement in validation results; it showed a 250% increase in water yield, while evapotranspiration declined by 3%.
{"title":"Evaluating the effects of reservoir outflow and land-use change on the Zarrineh River basin","authors":"P. Nakhaei, O. Kisi","doi":"10.1080/02626667.2023.2249874","DOIUrl":"https://doi.org/10.1080/02626667.2023.2249874","url":null,"abstract":"ABSTRACT The rapid decline of Lake Urmia in northwest Iran, caused by both human and natural factors, motivated our utilization of the Soil and Water Assessment Tool (SWAT) model. The objective was to identify the most effective reservoir outflow simulation scheme and assess the influence of land use changes in the Zarrineh River basin on Lake Urmia. The target release approach for controlled reservoirs and the measured outflow schemes were evaluated. Despite improved calibration results in the latter method, the former demonstrated superior performance during the validation phase. Three land use scenarios – a model with the 2001 land use map, a model with the 2008 land use map, and a model with a gradually updating land use map – were considered. The gradually updating land use scenario exhibited a significant enhancement in validation results; it showed a 250% increase in water yield, while evapotranspiration declined by 3%.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44745735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-21DOI: 10.1080/02626667.2023.2248112
Shabnam Majnooni, M. Nikoo, Banafsheh Nematollahi, Mahmood Fooladi, N. Alamdari, G. Al-Rawas, A. Gandomi
ABSTRACT This study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based precipitation time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected using historical precipitation data. Four methods were tested, and quantile mapping (QM) was the best. After pre-processing data, 19 machine-learning models were developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, and K-nearest-neighbours were chosen as the best models based on Complex Proportional Assessment (COPRAS) measurement. After hyperparameter adjustment, the Bayesian back-propagation regularization algorithm fused the results. The superior models’ predictions were considered inputs, and the target’s initial step was labeled. The next 11 steps at each station followed this approach, and the fusion models accurately predicted all steps. The 12th step’s average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation coefficient (R) were 0.937, 52.136, 0.880, and 0.869, respectively, demonstrating the framework’s effectiveness at high forecasting horizons to help policymakers manage water resources.
{"title":"Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning","authors":"Shabnam Majnooni, M. Nikoo, Banafsheh Nematollahi, Mahmood Fooladi, N. Alamdari, G. Al-Rawas, A. Gandomi","doi":"10.1080/02626667.2023.2248112","DOIUrl":"https://doi.org/10.1080/02626667.2023.2248112","url":null,"abstract":"ABSTRACT This study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based precipitation time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected using historical precipitation data. Four methods were tested, and quantile mapping (QM) was the best. After pre-processing data, 19 machine-learning models were developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, and K-nearest-neighbours were chosen as the best models based on Complex Proportional Assessment (COPRAS) measurement. After hyperparameter adjustment, the Bayesian back-propagation regularization algorithm fused the results. The superior models’ predictions were considered inputs, and the target’s initial step was labeled. The next 11 steps at each station followed this approach, and the fusion models accurately predicted all steps. The 12th step’s average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation coefficient (R) were 0.937, 52.136, 0.880, and 0.869, respectively, demonstrating the framework’s effectiveness at high forecasting horizons to help policymakers manage water resources.","PeriodicalId":55042,"journal":{"name":"Hydrological Sciences Journal-Journal Des Sciences Hydrologiques","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43428891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：