Sonali Swagatika, Jagadish Chandra Paul, B. B. Sahoo, Sushindra Kumar Gupta, P. K. Singh
Accurate prediction of monthly runoff is critical for effective water resource management and flood forecasting in river basins. In this study, we developed a hybrid deep learning (DL) model, Fourier transform long short-term memory (FT-LSTM), to improve the prediction accuracy of monthly discharge time series in the Brahmani river basin at Jenapur station. We compare the performance of FT-LSTM with three popular DL models: LSTM, recurrent neutral network, and gated recurrent unit, considering different lag periods (1, 3, 6, and 12). The lag period, representing the interval between the observed data points and the predicted data points, is crucial for capturing the temporal relationships and identifying patterns within the hydrological data. The results of this study show that the FT-LSTM model consistently outperforms other models across all lag periods in terms of error metrics. Furthermore, the FT-LSTM model demonstrates higher Nash–Sutcliffe efficiency and R2 values, indicating a better fit between predicted and actual runoff values. This work contributes to the growing field of hybrid DL models for hydrological forecasting. The FT-LSTM model proves effective in improving the accuracy of monthly runoff forecasts and offers a promising solution for water resource management and river basin decision-making processes.
{"title":"Improving the forecasting accuracy of monthly runoff time series of the Brahmani River in India using a hybrid deep learning model","authors":"Sonali Swagatika, Jagadish Chandra Paul, B. B. Sahoo, Sushindra Kumar Gupta, P. K. Singh","doi":"10.2166/wcc.2023.487","DOIUrl":"https://doi.org/10.2166/wcc.2023.487","url":null,"abstract":"\u0000 Accurate prediction of monthly runoff is critical for effective water resource management and flood forecasting in river basins. In this study, we developed a hybrid deep learning (DL) model, Fourier transform long short-term memory (FT-LSTM), to improve the prediction accuracy of monthly discharge time series in the Brahmani river basin at Jenapur station. We compare the performance of FT-LSTM with three popular DL models: LSTM, recurrent neutral network, and gated recurrent unit, considering different lag periods (1, 3, 6, and 12). The lag period, representing the interval between the observed data points and the predicted data points, is crucial for capturing the temporal relationships and identifying patterns within the hydrological data. The results of this study show that the FT-LSTM model consistently outperforms other models across all lag periods in terms of error metrics. Furthermore, the FT-LSTM model demonstrates higher Nash–Sutcliffe efficiency and R2 values, indicating a better fit between predicted and actual runoff values. This work contributes to the growing field of hybrid DL models for hydrological forecasting. The FT-LSTM model proves effective in improving the accuracy of monthly runoff forecasts and offers a promising solution for water resource management and river basin decision-making processes.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138998162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
J. Kopáček, Stanislav Grill, J. Hejzlar, P. Porcal, Jan Turek
The water temperature of many lakes has recently risen as a result of climate change. We evaluated trends in the cloudiness, solar radiation, wind, air and water temperatures, ice cover, thermocline depth, transparency, and composition of two Bohemian Forest lakes (Czech Republic) from 1998 to 2022. Lake water temperatures increased by 0.32–0.47 °C decade−1, and the ice cover periods decreased by 11.7–14.8 days decade−1. These changes were mostly associated with increasing air temperatures during most months and increasing solar radiation (due to decreasing cloudiness) especially in March and November (the months preceding ice-on/off). Decreasing snow cover in winter (by 3.8 cm decade−1) further accelerated the earlier ice melt. The number of days with water temperature ≥4 °C increased similarly in both lakes by 12–13 days decade−1. However, the number of days with water temperature ≥20 °C increased and the depth of the summer thermocline decreased more in the lake with tree dieback in its catchment. Tree dieback accelerated the leaching of organic carbon and phosphorus, increasing water brownification, algal production, and decreasing water transparency. Solar radiation was absorbed in shallower water layers. Changes in catchment forest thus contributed to the variability in the response of lake water temperatures to climate change.
{"title":"Tree dieback and subsequent changes in water quality accelerated the climate-related warming of a central European forest lake","authors":"J. Kopáček, Stanislav Grill, J. Hejzlar, P. Porcal, Jan Turek","doi":"10.2166/wcc.2023.581","DOIUrl":"https://doi.org/10.2166/wcc.2023.581","url":null,"abstract":"\u0000 \u0000 The water temperature of many lakes has recently risen as a result of climate change. We evaluated trends in the cloudiness, solar radiation, wind, air and water temperatures, ice cover, thermocline depth, transparency, and composition of two Bohemian Forest lakes (Czech Republic) from 1998 to 2022. Lake water temperatures increased by 0.32–0.47 °C decade−1, and the ice cover periods decreased by 11.7–14.8 days decade−1. These changes were mostly associated with increasing air temperatures during most months and increasing solar radiation (due to decreasing cloudiness) especially in March and November (the months preceding ice-on/off). Decreasing snow cover in winter (by 3.8 cm decade−1) further accelerated the earlier ice melt. The number of days with water temperature ≥4 °C increased similarly in both lakes by 12–13 days decade−1. However, the number of days with water temperature ≥20 °C increased and the depth of the summer thermocline decreased more in the lake with tree dieback in its catchment. Tree dieback accelerated the leaching of organic carbon and phosphorus, increasing water brownification, algal production, and decreasing water transparency. Solar radiation was absorbed in shallower water layers. Changes in catchment forest thus contributed to the variability in the response of lake water temperatures to climate change.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138998086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
This paper focuses on exploring the potential of climate-resilient agriculture (CRA) for river basin-scale management. Our analysis is based on long-term historical and future climate and hydrological datasets within a GIS environment, focusing on the Ajoy River basin in West Bengal, Eastern India. The standardized anomaly index (SAI) and slope of the linear regression (SLR) methods were employed to analyze the spatial pattern of the climate variables (precipitation, Tmax, and Tmin) and hydrological variables (actual evapotranspiration (AET), runoff (Q), vapor pressure deficit (VPD), potential evapotranspiration (PET), and climate water deficit (DEF)) using the TerraClimate dataset spanning from 1958 to 2020. Future climate trend analysis spanning 2021–2100 was conducted using the CMIP6-based GCMs (MIROC6 and EC-Earth3) dataset under shared socio-economic pathway SSP2-4.5, SSP5-8.5, and historical). For spatiotemporal water storage analysis, we relied on Gravity Recovery and Climate Experiment (GRACE) from CSR and JPL data, covering the period from 2002 to 2021. Validation was performed using regional groundwater level data, employing various machine learning classification models. Our findings revealed a negative precipitation trend (approximately −0.04 mm/year) in the southern part, whereas the northern part exhibited a positive trend (approximately 0.10 mm/year).
{"title":"Impacts of hydroclimate change on climate-resilient agriculture at the river basin management","authors":"C. Singha, Satiprasad Sahoo, Ajit Govind, Biswajeet Pradhan, Shatha Alrawashdeh, Taghreed Hamdi Aljohani, Hussein Almohamad, Abu Reza Md Towfiqul Islam, Hazam Ghassan Abdo","doi":"10.2166/wcc.2023.656","DOIUrl":"https://doi.org/10.2166/wcc.2023.656","url":null,"abstract":"\u0000 \u0000 This paper focuses on exploring the potential of climate-resilient agriculture (CRA) for river basin-scale management. Our analysis is based on long-term historical and future climate and hydrological datasets within a GIS environment, focusing on the Ajoy River basin in West Bengal, Eastern India. The standardized anomaly index (SAI) and slope of the linear regression (SLR) methods were employed to analyze the spatial pattern of the climate variables (precipitation, Tmax, and Tmin) and hydrological variables (actual evapotranspiration (AET), runoff (Q), vapor pressure deficit (VPD), potential evapotranspiration (PET), and climate water deficit (DEF)) using the TerraClimate dataset spanning from 1958 to 2020. Future climate trend analysis spanning 2021–2100 was conducted using the CMIP6-based GCMs (MIROC6 and EC-Earth3) dataset under shared socio-economic pathway SSP2-4.5, SSP5-8.5, and historical). For spatiotemporal water storage analysis, we relied on Gravity Recovery and Climate Experiment (GRACE) from CSR and JPL data, covering the period from 2002 to 2021. Validation was performed using regional groundwater level data, employing various machine learning classification models. Our findings revealed a negative precipitation trend (approximately −0.04 mm/year) in the southern part, whereas the northern part exhibited a positive trend (approximately 0.10 mm/year).","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138997406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
Water resources and flood hazards in global watersheds are heavily influenced by climate change. In this study, the impact of climate change on the streamflow of the Qinglong River located in northern China is predicted. The streamflow of the Qinglong River (2021–2100) under two climate change scenarios (RCP 4.5 and RCP 8.5) was mainly synthesized over multiple timescales. The meteorological data from 31 global climate models (GCMs) in the Coupled Model Intercomparison Project Phase 5 (CMIP5) were used as inputs of the Hydrological Simulation Program-Fortran (HSPF) for hydrological simulation. Results show that the peak flood flow and average daily streamflow for the RCP4.5 scenario are at least 101.15 and 110.14% of the historical phase, and at least 108.89 and 121.88% of the historical phase for the RCP8.5 scenario. Under both scenarios, the proportion of summer streamflow to annual total streamflow is projected to increase from 61.46% (historical phase) to over 85%, while the proportion of winter streamflow to annual total streamflow is projected to decrease from 8.84% (historical phase) to below 0.5%. Compared to the historical period, the maximum increase in future multi-year average annual streamflow for the RCP4.5 and RCP8.5 scenarios is 30.34 and 31.48%, respectively.
{"title":"Impacts of climate change on streamflow of Qinglong River, China","authors":"Xingpo Liu, Zixuan Tang","doi":"10.2166/wcc.2023.568","DOIUrl":"https://doi.org/10.2166/wcc.2023.568","url":null,"abstract":"\u0000 \u0000 Water resources and flood hazards in global watersheds are heavily influenced by climate change. In this study, the impact of climate change on the streamflow of the Qinglong River located in northern China is predicted. The streamflow of the Qinglong River (2021–2100) under two climate change scenarios (RCP 4.5 and RCP 8.5) was mainly synthesized over multiple timescales. The meteorological data from 31 global climate models (GCMs) in the Coupled Model Intercomparison Project Phase 5 (CMIP5) were used as inputs of the Hydrological Simulation Program-Fortran (HSPF) for hydrological simulation. Results show that the peak flood flow and average daily streamflow for the RCP4.5 scenario are at least 101.15 and 110.14% of the historical phase, and at least 108.89 and 121.88% of the historical phase for the RCP8.5 scenario. Under both scenarios, the proportion of summer streamflow to annual total streamflow is projected to increase from 61.46% (historical phase) to over 85%, while the proportion of winter streamflow to annual total streamflow is projected to decrease from 8.84% (historical phase) to below 0.5%. Compared to the historical period, the maximum increase in future multi-year average annual streamflow for the RCP4.5 and RCP8.5 scenarios is 30.34 and 31.48%, respectively.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139002295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
P. van Thienen, G. A. Chatzistefanou, Christos Makropoulos, L. Vamvakeridou-Lyroudia
The world grapples with immediate crises like COVID-19, Russia's invasion of Ukraine, floods, droughts and wildfires. However, a longer-term crisis looms due to humanity's overstepping of planetary boundaries and its disruptive consequences. Growing awareness of the potential collapse of societies due to planetary boundary violations has prompted increased attention in the scientific literature. In the water sector, where infrastructure built today might persist during a future collapse, we must therefore ask ourselves how a (basic) level of water supply can be maintained in a collapsing society. This paper explores this question and proposes research directions to address it in the short to medium term. Despite the seeming remoteness of a societal collapse scenario, it is imperative to incorporate it urgently into water infrastructure research and planning.
{"title":"What water supply system research is needed in the face of a conceivable societal collapse?","authors":"P. van Thienen, G. A. Chatzistefanou, Christos Makropoulos, L. Vamvakeridou-Lyroudia","doi":"10.2166/wcc.2023.351","DOIUrl":"https://doi.org/10.2166/wcc.2023.351","url":null,"abstract":"\u0000 \u0000 The world grapples with immediate crises like COVID-19, Russia's invasion of Ukraine, floods, droughts and wildfires. However, a longer-term crisis looms due to humanity's overstepping of planetary boundaries and its disruptive consequences. Growing awareness of the potential collapse of societies due to planetary boundary violations has prompted increased attention in the scientific literature. In the water sector, where infrastructure built today might persist during a future collapse, we must therefore ask ourselves how a (basic) level of water supply can be maintained in a collapsing society. This paper explores this question and proposes research directions to address it in the short to medium term. Despite the seeming remoteness of a societal collapse scenario, it is imperative to incorporate it urgently into water infrastructure research and planning.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138975515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
Urban heat islands are hotter than rural places. Sustainable urban growth and improving urban environments need understanding Urban Heat Island (UHI) causes and finding effective mitigation techniques. This research examines the seasonal deviations in surface temperatures for the UHI effect in Pune, India, focusing on land use patterns and water body cooling. Land use categorization included residential, commercial, industrial, vegetation, and open spaces. The research studied the cooling potential and temperature variance by distance from water bodies in the form of lakes, rivers, and ponds. These aquatic bodies have surface and ambient temperature sensors. Roads, soil, commercial areas, residential areas, industrial areas, and vegetation have all shown increases in NDBI, ranging from 15.84 to 36.45%. Urban regions with heat accumulation and dissipation have been revealed by DEM and contour maps. The research found that the water bodies have a cooling effect on LST till the distance of 350 m. The research finds hotter places and shows how natural features mitigate UHI by analyzing land use patterns and water body cooling. The findings emphasize the significance of green areas and water bodies in urban design and development to improve Pune's climate resilience and inhabitability.
{"title":"Geo-physical seasonal deviations of land use, terrain analysis, and water cooling effect on the surface temperature of Pune city","authors":"Kul Vaibhav Sharma, Vijendra Kumar, Lilesh Gautam, Sumit Choudhary, Aneesh Mathew","doi":"10.2166/wcc.2023.432","DOIUrl":"https://doi.org/10.2166/wcc.2023.432","url":null,"abstract":"\u0000 \u0000 Urban heat islands are hotter than rural places. Sustainable urban growth and improving urban environments need understanding Urban Heat Island (UHI) causes and finding effective mitigation techniques. This research examines the seasonal deviations in surface temperatures for the UHI effect in Pune, India, focusing on land use patterns and water body cooling. Land use categorization included residential, commercial, industrial, vegetation, and open spaces. The research studied the cooling potential and temperature variance by distance from water bodies in the form of lakes, rivers, and ponds. These aquatic bodies have surface and ambient temperature sensors. Roads, soil, commercial areas, residential areas, industrial areas, and vegetation have all shown increases in NDBI, ranging from 15.84 to 36.45%. Urban regions with heat accumulation and dissipation have been revealed by DEM and contour maps. The research found that the water bodies have a cooling effect on LST till the distance of 350 m. The research finds hotter places and shows how natural features mitigate UHI by analyzing land use patterns and water body cooling. The findings emphasize the significance of green areas and water bodies in urban design and development to improve Pune's climate resilience and inhabitability.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139008363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
K. Sahu, S. Chandniha, Manish Kumar Nema, G. K. Das, Haritha Lekshmi V., Pratibha Wadware
Rainfall is the key weather element which regulates the hydrological cycle, availability of water resources and crop production. In this study, spatial and temporal variability of rainfall has been investigated on seasonal and annual time scales of 149 blocks of Chhattisgarh State using 120 years (1901–2020) of rainfall data. Non-parametric, and Theil and Sen's slope estimator were used to identify possible trends and ascertain the variability in the magnitude. The results revealed that there exists a well-marked spatial variability in rainfall over Chhattisgarh in annual and seasonal time scales. Out of 149 blocks a significant negative rainfall was noticed in 105 blocks. Annual rainfall showed a significant positive trend in a few blocks like Bhopalpattnam, Bijapur, Usur, Konta. A similar pattern of trend was noticed in monsoon season. The results of the study demand the urgent need to formulate policies and strategies for water resource management and planning. The blocks which showed the positive rainfall trends can be identified to intensify the cultivation of more water requiring crops based on the suitability to that region. The findings of this study can be used as valuable information for crop planning, policy-making and preparation of contingency plans.
{"title":"Level long-term rainfall variability using trend analysis in a state of central India","authors":"K. Sahu, S. Chandniha, Manish Kumar Nema, G. K. Das, Haritha Lekshmi V., Pratibha Wadware","doi":"10.2166/wcc.2023.047","DOIUrl":"https://doi.org/10.2166/wcc.2023.047","url":null,"abstract":"\u0000 \u0000 Rainfall is the key weather element which regulates the hydrological cycle, availability of water resources and crop production. In this study, spatial and temporal variability of rainfall has been investigated on seasonal and annual time scales of 149 blocks of Chhattisgarh State using 120 years (1901–2020) of rainfall data. Non-parametric, and Theil and Sen's slope estimator were used to identify possible trends and ascertain the variability in the magnitude. The results revealed that there exists a well-marked spatial variability in rainfall over Chhattisgarh in annual and seasonal time scales. Out of 149 blocks a significant negative rainfall was noticed in 105 blocks. Annual rainfall showed a significant positive trend in a few blocks like Bhopalpattnam, Bijapur, Usur, Konta. A similar pattern of trend was noticed in monsoon season. The results of the study demand the urgent need to formulate policies and strategies for water resource management and planning. The blocks which showed the positive rainfall trends can be identified to intensify the cultivation of more water requiring crops based on the suitability to that region. The findings of this study can be used as valuable information for crop planning, policy-making and preparation of contingency plans.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139009006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
The present study on the hydrologic regionalization was taken up to evaluate the utility of hierarchical cluster analysis for the delineation of hydrologically homogeneous regions and multiple linear regression (MLR) models for information transfer to derive flow duration curve (FDC) in ungauged basins. For this purpose, 50 catchments with largely unregulated flows located in South India were identified and a dataset of historical streamflow records and 16 catchment attributes was created. Using selected catchment attributes, three hydrologically homogenous regions were delineated using a hierarchical agglomerative cluster approach, and nine flow quantiles (10–90%) for each of the catchments in the respective clusters was derived. Regionalization approach was then adopted, whereby using step-wise regression, flow quantiles were related with readily derived basin-physical characteristics through MLR models. Cluster-wise performance analysis of the developed models indicated excellent performance with an average coefficient of determination (R2) values of 0.85, 0.97, and 0.8 for Cluster-1, -2, and -3, respectively, in comparison to poor performance when all 50 stations were considered to be in a single region. However, Jackknife cross-validation showed mixed performances with regard to the reliability of developed models with performance being good for high-flow quantiles and poor for low-flow quantiles.
{"title":"Regionalization of flow duration curves for catchments in southern India using a hierarchical cluster approach","authors":"C. G. Hiremath, L. Nandagiri","doi":"10.2166/wcc.2023.467","DOIUrl":"https://doi.org/10.2166/wcc.2023.467","url":null,"abstract":"\u0000 \u0000 The present study on the hydrologic regionalization was taken up to evaluate the utility of hierarchical cluster analysis for the delineation of hydrologically homogeneous regions and multiple linear regression (MLR) models for information transfer to derive flow duration curve (FDC) in ungauged basins. For this purpose, 50 catchments with largely unregulated flows located in South India were identified and a dataset of historical streamflow records and 16 catchment attributes was created. Using selected catchment attributes, three hydrologically homogenous regions were delineated using a hierarchical agglomerative cluster approach, and nine flow quantiles (10–90%) for each of the catchments in the respective clusters was derived. Regionalization approach was then adopted, whereby using step-wise regression, flow quantiles were related with readily derived basin-physical characteristics through MLR models. Cluster-wise performance analysis of the developed models indicated excellent performance with an average coefficient of determination (R2) values of 0.85, 0.97, and 0.8 for Cluster-1, -2, and -3, respectively, in comparison to poor performance when all 50 stations were considered to be in a single region. However, Jackknife cross-validation showed mixed performances with regard to the reliability of developed models with performance being good for high-flow quantiles and poor for low-flow quantiles.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138980547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
This study compares the capability of Sentinel-1, Sentinel-2, and PlanetScope (PS) satellites in monitoring the variations of surface water of Dai Lai Lake, located in North Vietnam, for the 2018–2023 period. The analysis involves the utilization of Google Earth Engine to partially process Sentinel-1 and Sentinel-2 observations, while PS observations are processed using local computers, to generate VH-polarized backscatter coefficient, Normalized Difference Water Index (NDWI), and Modified of Normalized Difference Water Index (MNDWI) maps. The method for making binary water/non-water maps primarily employs the Otsu algorithm on each single map derived from the previous step. Findings reveal that the lake's water extent remains relatively stable over the 6-year period, and is not strongly affected by the seasonal cycle. Although the spatial distribution patterns of the lake exhibit significant similarity, average water extent of the lake derived from 3-m resolution PS imagery is about 2.17 and 5.60% more than that obtained from 10-m resolution Sentinel-2 and Sentinel-1 imagery, respectively. PS observations are effective for monitoring small lakes, but it is advised to check the quality of its NIR band. Sentinel-2 observations prove great effectiveness for lake monitoring, using both NDWI and MNDWI. For Sentinel-1 observations, potential misclassifications could arise due to similarities in VH-polarized backscatter coefficients between water surfaces and other flat surfaces.
{"title":"Comparison of multi-source satellite remote sensing observations for monitoring the variations of small lakes: a case study of Dai Lai Lake (Vietnam)","authors":"Binh Pham-Duc","doi":"10.2166/wcc.2023.505","DOIUrl":"https://doi.org/10.2166/wcc.2023.505","url":null,"abstract":"\u0000 \u0000 This study compares the capability of Sentinel-1, Sentinel-2, and PlanetScope (PS) satellites in monitoring the variations of surface water of Dai Lai Lake, located in North Vietnam, for the 2018–2023 period. The analysis involves the utilization of Google Earth Engine to partially process Sentinel-1 and Sentinel-2 observations, while PS observations are processed using local computers, to generate VH-polarized backscatter coefficient, Normalized Difference Water Index (NDWI), and Modified of Normalized Difference Water Index (MNDWI) maps. The method for making binary water/non-water maps primarily employs the Otsu algorithm on each single map derived from the previous step. Findings reveal that the lake's water extent remains relatively stable over the 6-year period, and is not strongly affected by the seasonal cycle. Although the spatial distribution patterns of the lake exhibit significant similarity, average water extent of the lake derived from 3-m resolution PS imagery is about 2.17 and 5.60% more than that obtained from 10-m resolution Sentinel-2 and Sentinel-1 imagery, respectively. PS observations are effective for monitoring small lakes, but it is advised to check the quality of its NIR band. Sentinel-2 observations prove great effectiveness for lake monitoring, using both NDWI and MNDWI. For Sentinel-1 observations, potential misclassifications could arise due to similarities in VH-polarized backscatter coefficients between water surfaces and other flat surfaces.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138983282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}
H. Nguyen, Dinh Kha Dang, Y. N. Nguyen, Chien Pham Van, Thi Thao Van Nguyen, Q. Nguyen, Xuan Linh Nguyen, Le Tuan Pham, Viet Thanh Pham, Quang-Thanh Bui
Flood prediction is an important task, which helps local decision-makers in taking effective measures to reduce damage to the people and economy. Currently, most studies use machine learning to predict flooding in a given region; however, the extrapolation problem is considered a major challenge when using these techniques and is rarely studied. Therefore, this study will focus on an approach to resolve the extrapolation problem in flood depth prediction by integrating machine learning (XGBoost, Extra-Trees (EXT), CatBoost (CB), and light gradient boost machines (LightGBM)) and hydraulic modeling under MIKE FLOOD. The results show that the hydraulic model worked well in providing the flood depth data needed to build the machine learning model. Among the four proposed machine learning models, XGBoost was found to be the best at solving the extrapolation problem in the estimation of flood depth, followed by EXT, CB, and LightGBM. Quang Binh province was hit by floods with depths ranging from 0 to 3.2 m. Areas with high flood depths are concentrated along and downstream of the two major rivers (Gianh and Nhat Le – Kien Giang).
{"title":"Integration of machine learning and hydrodynamic modeling to solve the extrapolation problem in flood depth estimation","authors":"H. Nguyen, Dinh Kha Dang, Y. N. Nguyen, Chien Pham Van, Thi Thao Van Nguyen, Q. Nguyen, Xuan Linh Nguyen, Le Tuan Pham, Viet Thanh Pham, Quang-Thanh Bui","doi":"10.2166/wcc.2023.573","DOIUrl":"https://doi.org/10.2166/wcc.2023.573","url":null,"abstract":"\u0000 Flood prediction is an important task, which helps local decision-makers in taking effective measures to reduce damage to the people and economy. Currently, most studies use machine learning to predict flooding in a given region; however, the extrapolation problem is considered a major challenge when using these techniques and is rarely studied. Therefore, this study will focus on an approach to resolve the extrapolation problem in flood depth prediction by integrating machine learning (XGBoost, Extra-Trees (EXT), CatBoost (CB), and light gradient boost machines (LightGBM)) and hydraulic modeling under MIKE FLOOD. The results show that the hydraulic model worked well in providing the flood depth data needed to build the machine learning model. Among the four proposed machine learning models, XGBoost was found to be the best at solving the extrapolation problem in the estimation of flood depth, followed by EXT, CB, and LightGBM. Quang Binh province was hit by floods with depths ranging from 0 to 3.2 m. Areas with high flood depths are concentrated along and downstream of the two major rivers (Gianh and Nhat Le – Kien Giang).","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138983270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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：