Bhavin Devabhai Ram, M. Gaur, G. R. Patel, M. K. Tiwari
The hyetograph represents the temporal spread of rainfall intensity occurring at a point or over a watershed during a storm. The importance of regionally derived/developed hyetographs and the pooled sets of categorical seasonal curves on intensity-duration, intensity-depth, and depth-duration are of multifarious conveniences and importance. Twenty-one years of daily and sub-daily rainfall records (2000–2020) regained via satellite-observed precipitation products were examined and used to retrieve a valid understanding towards annual, monthly, daily, and hourly based variability of rainfall across six different stations. An attempt was made to compare the shapes of synthesized seasonal rain mass curves with that of the historic Soil Conservation Service (SCS) mass curve. The results indicate that the location-specific patterns and trends of curves do not align closely with any historical SCS curves or theoretical curves prevalent in the literature and commonly adopted. It has been observed that region-specific rainfall and its temporal distributions exhibit unique trends, not necessarily conforming to the standard SCS-based curves categorized as Types I, Ia, II, and III. This emphasizes the need to rely more on region-specific curves rather than instinctively adopting a standard set of curves.
水文图表示暴雨期间某点或流域降雨强度的时间分布。按区域推导/开发的降雨滞留图以及强度-持续时间、强度-深度和深度-持续时间的分类季节曲线集合具有多种便利性和重要性。通过卫星观测降水产品重新获得的 21 年(2000-2020 年)日降雨量和亚日降雨量记录被用于检索对六个不同站点降雨量的年、月、日和小时变化的有效理解。尝试将合成的季节性降雨量曲线形状与历史上的土壤保护局(SCS)降雨量曲线形状进行比较。结果表明,特定地点的曲线形态和趋势与历史上的 SCS 曲线或文献中普遍采用的理论曲线并不十分吻合。据观察,特定地区的降雨量及其时间分布呈现出独特的趋势,不一定符合基于 SCS 的标准曲线(分为 I 型、Ia 型、II 型和 III 型)。这就强调需要更多地依靠特定地区的曲线,而不是本能地采用一套标准曲线。
{"title":"Deriving location-specific synthetic seasonal hyetographs using GPM records and comparing with SCS curves","authors":"Bhavin Devabhai Ram, M. Gaur, G. R. Patel, M. K. Tiwari","doi":"10.2166/wcc.2024.553","DOIUrl":"https://doi.org/10.2166/wcc.2024.553","url":null,"abstract":"\u0000 The hyetograph represents the temporal spread of rainfall intensity occurring at a point or over a watershed during a storm. The importance of regionally derived/developed hyetographs and the pooled sets of categorical seasonal curves on intensity-duration, intensity-depth, and depth-duration are of multifarious conveniences and importance. Twenty-one years of daily and sub-daily rainfall records (2000–2020) regained via satellite-observed precipitation products were examined and used to retrieve a valid understanding towards annual, monthly, daily, and hourly based variability of rainfall across six different stations. An attempt was made to compare the shapes of synthesized seasonal rain mass curves with that of the historic Soil Conservation Service (SCS) mass curve. The results indicate that the location-specific patterns and trends of curves do not align closely with any historical SCS curves or theoretical curves prevalent in the literature and commonly adopted. It has been observed that region-specific rainfall and its temporal distributions exhibit unique trends, not necessarily conforming to the standard SCS-based curves categorized as Types I, Ia, II, and III. This emphasizes the need to rely more on region-specific curves rather than instinctively adopting a standard set of curves.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139684399","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}
Ressy Fitria, Michael Timothy, Roald Marck J. Revellame
The reliability of evapotranspiration (ET) models is crucial to comprehending land–atmosphere interactions and water balance dynamics in various available resources of the model. This study compared two different models based on energy and water balance models, a surface energy balance system (SEBS) and SPHY, and evaluated against ground observation data from flux towers for different land cover characteristics (forest and savanna) in Southeast Africa. We found that both models have a good correlation with flux tower data for both sites (ZM-Mon and ZM-Kru). The SEBS model showed a lower root-mean-square error (RMSE; 2.17 mm day−1) at the savanna site (ZM-Kru) than the SPHY model (2.27 mm day−1). However, at the forest site (ZM-Mon), the SEBS model showed a higher RMSE value (1.90 mm day−1) than the SPHY model (0.88 mm day−1). Then, we analyzed the ET model's sensitivity to the precipitation variable. We found that SPHY overestimated ET during the winter season and underestimated it during the summer season, which might be influenced by the dependency of the SPHY model to water excess and water shortage stress parameters in ET calculations. Overall, SPHY, with fewer input data, showed a reasonably good result compared to the SEBS. The results revealed that each model possesses its unique strengths and limitations in relation to specific land covers and vegetation composition, offering opportunities for improvement and optimization.
{"title":"Evaluation of evapotranspiration using energy-based and water balance hydrological models","authors":"Ressy Fitria, Michael Timothy, Roald Marck J. Revellame","doi":"10.2166/wcc.2024.499","DOIUrl":"https://doi.org/10.2166/wcc.2024.499","url":null,"abstract":"\u0000 \u0000 The reliability of evapotranspiration (ET) models is crucial to comprehending land–atmosphere interactions and water balance dynamics in various available resources of the model. This study compared two different models based on energy and water balance models, a surface energy balance system (SEBS) and SPHY, and evaluated against ground observation data from flux towers for different land cover characteristics (forest and savanna) in Southeast Africa. We found that both models have a good correlation with flux tower data for both sites (ZM-Mon and ZM-Kru). The SEBS model showed a lower root-mean-square error (RMSE; 2.17 mm day−1) at the savanna site (ZM-Kru) than the SPHY model (2.27 mm day−1). However, at the forest site (ZM-Mon), the SEBS model showed a higher RMSE value (1.90 mm day−1) than the SPHY model (0.88 mm day−1). Then, we analyzed the ET model's sensitivity to the precipitation variable. We found that SPHY overestimated ET during the winter season and underestimated it during the summer season, which might be influenced by the dependency of the SPHY model to water excess and water shortage stress parameters in ET calculations. Overall, SPHY, with fewer input data, showed a reasonably good result compared to the SEBS. The results revealed that each model possesses its unique strengths and limitations in relation to specific land covers and vegetation composition, offering opportunities for improvement and optimization.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140481868","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 study is carried out to investigate the surface runoff depth with changing precipitation due to climate change in the study area where sandy loam and loamy soil are dominant. In this study, future rainfall is projected by a statistical downscaling model (SDSM) using a set of predictors derived from a Coupled Model Intercomparison Project Phase 6 (CMIP6) global climate model (GCM) [the Norwegian Earth System Model (NorESM)] with updated scenarios SSP 4.5 and SSP 8.5. Daily rainfall values for the observed period (1981 to 2014) are validated using statistical learning and evaluated with matrices, namely, root mean square error (RMSE), coefficient of correlation, and Nash–Sutcliffe efficiency (NSE), which are found to be valid for further predictions. Rainfall projections show a decrease in rainfall trend by 50% from 2030 to 2040 for scenario SSP 4.5 and an increase of 7% from 2040 to 2050. Predicted rainfall for scenario SSP 8.5 shows a similar trend of decreasing rainfall by 24% for the period 2030–2040 and an increase by 19% in the period 2040–2050. Furthermore, these rainfall values are spatially modelled in a geographic information system (GIS) and rainfall maps are obtained. The obtained rainfall map, land-use map, and soil map are overlaid to compute curve numbers and runoff depths. A similar trend of decrease in runoff is observed for the period 2030–2050. The overall trend of climate change shows a water-stressed scenario.
{"title":"Hydroclimatic projection: statistical learning and downscaling model for rainfall and runoff forecasting","authors":"Shweta Kodihal, M. Akhtar, Satya Prakash Maurya","doi":"10.2166/wcc.2024.562","DOIUrl":"https://doi.org/10.2166/wcc.2024.562","url":null,"abstract":"\u0000 \u0000 The study is carried out to investigate the surface runoff depth with changing precipitation due to climate change in the study area where sandy loam and loamy soil are dominant. In this study, future rainfall is projected by a statistical downscaling model (SDSM) using a set of predictors derived from a Coupled Model Intercomparison Project Phase 6 (CMIP6) global climate model (GCM) [the Norwegian Earth System Model (NorESM)] with updated scenarios SSP 4.5 and SSP 8.5. Daily rainfall values for the observed period (1981 to 2014) are validated using statistical learning and evaluated with matrices, namely, root mean square error (RMSE), coefficient of correlation, and Nash–Sutcliffe efficiency (NSE), which are found to be valid for further predictions. Rainfall projections show a decrease in rainfall trend by 50% from 2030 to 2040 for scenario SSP 4.5 and an increase of 7% from 2040 to 2050. Predicted rainfall for scenario SSP 8.5 shows a similar trend of decreasing rainfall by 24% for the period 2030–2040 and an increase by 19% in the period 2040–2050. Furthermore, these rainfall values are spatially modelled in a geographic information system (GIS) and rainfall maps are obtained. The obtained rainfall map, land-use map, and soil map are overlaid to compute curve numbers and runoff depths. A similar trend of decrease in runoff is observed for the period 2030–2050. The overall trend of climate change shows a water-stressed scenario.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2024-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139525202","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}
Elias Gebeyehu Ayele, Esayas Tesfaye Ergete, Getachew Bereta Geremew
Flooding due to overtopping during peak flow in embankment dams primarily causes dam failure. The Kessem River watershed of the Awash basin in the Rift Valley of the Afar region in Ethiopia has been studied intricately to predict the causes of the Kessem Dam safety using machine learning predictive models and Risk Management Centre-Reservoir Frequency Analysis (RMC-RFA). Recently developed recurrent neural network (RNN) predictive models with hybrid with Soil Conservation Service Curve Number (SCS-CN) were used for simulation of the river flow. Peak daily inflow to the reservoir is predicted to be 467.72, 435.88, and 513.55 m3/s in 2035, 2061, and 2090, respectively. The hydrologic hazard analysis results show 2,823.57 m3/s and 935.21 m; 2,126.3 m3/s and 934.18 m; and 11,491.1 m3/s and 942.11 m peak discharge and maximum reservoir water level during the periods of 2022–2050, 2051–2075, and 2076–2100, respectively, for 0.0001 annual exceedance probability (AEP). The Kessem Dam may potentially be overtopped by a flood with a return period of about 10,000 years during the period of 2076–2100. Quantitative hydrologic risk assessment of the dam is used for dam safety evaluation to decide whether the existing structure provides an adequate level of safety, and if not, what modifications are necessary to improve the dam's safety.
{"title":"Predicting the peak flow and assessing the hydrologic hazard of the Kessem Dam, Ethiopia using machine learning and risk management centre-reservoir frequency analysis software","authors":"Elias Gebeyehu Ayele, Esayas Tesfaye Ergete, Getachew Bereta Geremew","doi":"10.2166/wcc.2024.320","DOIUrl":"https://doi.org/10.2166/wcc.2024.320","url":null,"abstract":"\u0000 \u0000 Flooding due to overtopping during peak flow in embankment dams primarily causes dam failure. The Kessem River watershed of the Awash basin in the Rift Valley of the Afar region in Ethiopia has been studied intricately to predict the causes of the Kessem Dam safety using machine learning predictive models and Risk Management Centre-Reservoir Frequency Analysis (RMC-RFA). Recently developed recurrent neural network (RNN) predictive models with hybrid with Soil Conservation Service Curve Number (SCS-CN) were used for simulation of the river flow. Peak daily inflow to the reservoir is predicted to be 467.72, 435.88, and 513.55 m3/s in 2035, 2061, and 2090, respectively. The hydrologic hazard analysis results show 2,823.57 m3/s and 935.21 m; 2,126.3 m3/s and 934.18 m; and 11,491.1 m3/s and 942.11 m peak discharge and maximum reservoir water level during the periods of 2022–2050, 2051–2075, and 2076–2100, respectively, for 0.0001 annual exceedance probability (AEP). The Kessem Dam may potentially be overtopped by a flood with a return period of about 10,000 years during the period of 2076–2100. Quantitative hydrologic risk assessment of the dam is used for dam safety evaluation to decide whether the existing structure provides an adequate level of safety, and if not, what modifications are necessary to improve the dam's safety.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139526134","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}
Juliana-Andrea Alzate-Gómez, Hélène Roux, L. Cassan, Thomas Bonometti, Jorge Alberto Escobar Vargas, Luis-Javier Montoya Jaramillo
This paper presents an analysis of air–water exchange in a Colombian tropical reservoir. A coupled thermal-3D hydrodynamic model using TELEMAC-3D and WAQTEL is implemented to evaluate the dynamics of thermal processes in the reservoir. A sensitivity analysis is carried out on various modeling parameters, such as turbulence models, temperature diffusion coefficients, and heat exchange at the free surface based on observations. In particular, three different approaches have been tested to study the impact of air–water exchanges at the free surface: a constant water temperature, constant meteorological forcing, and time-varying meteorological forcing. All the simulations correctly represent the constant heating at the free surface for the first meters. However, no simulation has been able to correctly reproduce the amplitude of temperature oscillations in the surface layers: only the simulations with time-varying meteorological forcing show temperature oscillations, but their amplitude is greatly overestimated. Eventually, the analysis shows that the most crucial parameters for a correct representation of the observed temperature behavior are the heat exchange coefficient and the wind. The different approaches tested all have limitations, but they can reproduce reservoir temperature trends at different depths with a maximum standard deviation ranging from 3 to 8 °C.
{"title":"Analysis of different hypotheses for modeling air–water exchange and temperature evolution in a tropical reservoir","authors":"Juliana-Andrea Alzate-Gómez, Hélène Roux, L. Cassan, Thomas Bonometti, Jorge Alberto Escobar Vargas, Luis-Javier Montoya Jaramillo","doi":"10.2166/wcc.2023.567","DOIUrl":"https://doi.org/10.2166/wcc.2023.567","url":null,"abstract":"\u0000 This paper presents an analysis of air–water exchange in a Colombian tropical reservoir. A coupled thermal-3D hydrodynamic model using TELEMAC-3D and WAQTEL is implemented to evaluate the dynamics of thermal processes in the reservoir. A sensitivity analysis is carried out on various modeling parameters, such as turbulence models, temperature diffusion coefficients, and heat exchange at the free surface based on observations. In particular, three different approaches have been tested to study the impact of air–water exchanges at the free surface: a constant water temperature, constant meteorological forcing, and time-varying meteorological forcing. All the simulations correctly represent the constant heating at the free surface for the first meters. However, no simulation has been able to correctly reproduce the amplitude of temperature oscillations in the surface layers: only the simulations with time-varying meteorological forcing show temperature oscillations, but their amplitude is greatly overestimated. Eventually, the analysis shows that the most crucial parameters for a correct representation of the observed temperature behavior are the heat exchange coefficient and the wind. The different approaches tested all have limitations, but they can reproduce reservoir temperature trends at different depths with a maximum standard deviation ranging from 3 to 8 °C.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453326","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}
A traditional hydrologic water infrastructure design assumes that the climate is stationary, and that historic data reflect future conditions. The traditional approach may no longer be applicable since the earth's climate is not stationary. Thus, there is a need for a new way of designing water infrastructure that accounts for the effects of climate change by shifting the current static design paradigm to a more dynamic paradigm. Researchers have proposed several approaches accounting for climate change. In this paper, we group the approaches into five groups (adaptive management, inverse climate change impact, machine learning, flood frequency analysis, and soft computing approaches), outline each approach's strengths and weaknesses, and assess their applicability to the water infrastructure design. We find that the flood frequency analysis approach is most applicable to the water infrastructure design as it is the least disruptive in terms of standard hydrological analysis methods, is cost-effective, and adaptable to most basins. However, adaptive management approaches are best suited for uncertainty reductions since they provide opportunities to constantly adjust decisions based on improved climate change data. Combining these two approaches could provide an optimal way of accounting for non-stationarity.
{"title":"Accounting for climate change in the water infrastructure design: evaluating approaches and recommending a hybrid framework","authors":"Kenneth Hunu, S. A. Conrad, M. DePue","doi":"10.2166/wcc.2023.611","DOIUrl":"https://doi.org/10.2166/wcc.2023.611","url":null,"abstract":"\u0000 \u0000 A traditional hydrologic water infrastructure design assumes that the climate is stationary, and that historic data reflect future conditions. The traditional approach may no longer be applicable since the earth's climate is not stationary. Thus, there is a need for a new way of designing water infrastructure that accounts for the effects of climate change by shifting the current static design paradigm to a more dynamic paradigm. Researchers have proposed several approaches accounting for climate change. In this paper, we group the approaches into five groups (adaptive management, inverse climate change impact, machine learning, flood frequency analysis, and soft computing approaches), outline each approach's strengths and weaknesses, and assess their applicability to the water infrastructure design. We find that the flood frequency analysis approach is most applicable to the water infrastructure design as it is the least disruptive in terms of standard hydrological analysis methods, is cost-effective, and adaptable to most basins. However, adaptive management approaches are best suited for uncertainty reductions since they provide opportunities to constantly adjust decisions based on improved climate change data. Combining these two approaches could provide an optimal way of accounting for non-stationarity.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138946442","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 article presents the results of the dike breach for the La Giang dike, in the Ha Tinh province, Vietnam. The study combined a field survey and mathematical simulation to assess the consequences of the dike breach. Through the field survey, potential dike breach locations were specifically identified. This minimizes the number of calculation scenarios. The mathematical model was calibrated and validated with large floods in the area. The results show that the model is consistent with the observation data, with the Nash index at good to very good levels. A series of simulations were performed to assess the dike breach consequence. In each case, the study provided details on the inundation area and the number of affected residents for each inundation level by an administrative unit. Based on the calculated results, the degree and scope of consequence varied depending on the locations of the dike breach. This is very useful information for the decision-makers to establish different response plans for different emergency cases.
文章介绍了越南河静省 La Giang 堤坝决口的结果。该研究结合了实地调查和数学模拟来评估决堤的后果。通过实地调查,具体确定了潜在的决堤位置。这最大限度地减少了计算方案的数量。数学模型通过该地区的大洪水进行了校准和验证。结果表明,模型与观测数据一致,纳什指数处于良好到非常好的水平。为评估决堤后果,进行了一系列模拟。在每种情况下,研究提供了按行政单位划分的每个淹没等级的淹没面积和受影响居民人数的详细信息。根据计算结果,堤坝决口的位置不同,后果的程度和范围也不同。这对于决策者针对不同的紧急情况制定不同的应对方案是非常有用的信息。
{"title":"Consequence assessment of the La Giang dike breach in the Ca river system, Vietnam","authors":"Chau Kim Tran, Thai Canh Nguyen","doi":"10.2166/wcc.2023.380","DOIUrl":"https://doi.org/10.2166/wcc.2023.380","url":null,"abstract":"\u0000 \u0000 The article presents the results of the dike breach for the La Giang dike, in the Ha Tinh province, Vietnam. The study combined a field survey and mathematical simulation to assess the consequences of the dike breach. Through the field survey, potential dike breach locations were specifically identified. This minimizes the number of calculation scenarios. The mathematical model was calibrated and validated with large floods in the area. The results show that the model is consistent with the observation data, with the Nash index at good to very good levels. A series of simulations were performed to assess the dike breach consequence. In each case, the study provided details on the inundation area and the number of affected residents for each inundation level by an administrative unit. Based on the calculated results, the degree and scope of consequence varied depending on the locations of the dike breach. This is very useful information for the decision-makers to establish different response plans for different emergency cases.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138994560","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 quality assessment plays a crucial role in various aspects, including human health, environmental impact, agricultural productivity, and industrial processes. Machine learning (ML) algorithms offer the ability to automate water quality evaluation and allow for effective and rapid assessment of parameters associated with water quality. This article proposes an ML-based classification model for water quality prediction. The model was tested with 14 ML algorithms and considers 20 features that represent various substances present in water samples and their concentrations. The dataset used in the study comprises 7,996 samples, and the model development involves several stages, including data preprocessing, Yeo–Johnson transformation for data normalization, principal component analysis (PCA) for feature selection, and the application of the synthetic minority over-sampling technique (SMOTE) to address class imbalance. Performance metrics, such as accuracy, precision, recall, and F1 score, are provided for each algorithm with and without SMOTE. LightGBM, XGBoost, CatBoost, and Random Forest were identified as the best-performing algorithms. LightGBM achieved the highest accuracy of 96.25% without SMOTE, while XGBoost attained the highest precision of 0.933. The application of SMOTE enhanced the performance of CatBoost. These findings provide valuable insights for ML-based water quality assessment, aiding researchers and professionals in decision-making and management.
水质评估在人类健康、环境影响、农业生产力和工业流程等各个方面都发挥着至关重要的作用。机器学习(ML)算法能够自动进行水质评价,并能有效、快速地评估与水质相关的参数。本文提出了一种基于 ML 的水质预测分类模型。该模型使用 14 种 ML 算法进行了测试,并考虑了代表水样中各种物质及其浓度的 20 个特征。研究中使用的数据集包括 7,996 个样本,模型开发涉及多个阶段,包括数据预处理、用于数据归一化的 Yeo-Johnson 转换、用于特征选择的主成分分析 (PCA),以及用于解决类不平衡问题的合成少数过度采样技术 (SMOTE)。每种算法在有 SMOTE 和没有 SMOTE 的情况下,都有准确度、精确度、召回率和 F1 分数等性能指标。LightGBM、XGBoost、CatBoost 和随机森林被认为是性能最好的算法。在没有 SMOTE 的情况下,LightGBM 的准确率最高,达到 96.25%,而 XGBoost 的精度最高,达到 0.933。SMOTE 的应用提高了 CatBoost 的性能。这些发现为基于 ML 的水质评估提供了宝贵的见解,有助于研究人员和专业人员进行决策和管理。
{"title":"Water quality prediction: A data-driven approach exploiting advanced machine learning algorithms with data augmentation","authors":"Karthick K, S. Krishnan, R. Manikandan","doi":"10.2166/wcc.2023.403","DOIUrl":"https://doi.org/10.2166/wcc.2023.403","url":null,"abstract":"\u0000 \u0000 Water quality assessment plays a crucial role in various aspects, including human health, environmental impact, agricultural productivity, and industrial processes. Machine learning (ML) algorithms offer the ability to automate water quality evaluation and allow for effective and rapid assessment of parameters associated with water quality. This article proposes an ML-based classification model for water quality prediction. The model was tested with 14 ML algorithms and considers 20 features that represent various substances present in water samples and their concentrations. The dataset used in the study comprises 7,996 samples, and the model development involves several stages, including data preprocessing, Yeo–Johnson transformation for data normalization, principal component analysis (PCA) for feature selection, and the application of the synthetic minority over-sampling technique (SMOTE) to address class imbalance. Performance metrics, such as accuracy, precision, recall, and F1 score, are provided for each algorithm with and without SMOTE. LightGBM, XGBoost, CatBoost, and Random Forest were identified as the best-performing algorithms. LightGBM achieved the highest accuracy of 96.25% without SMOTE, while XGBoost attained the highest precision of 0.933. The application of SMOTE enhanced the performance of CatBoost. These findings provide valuable insights for ML-based water quality assessment, aiding researchers and professionals in decision-making and management.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138958792","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}
Based on the daily precipitation data and ERA5 reanalysis data of 40 years from 1981 to 2018 in the middle Yangtze River Valley (MYRV), the climatic characteristics of extreme precipitation are analyzed using statistical methods. The multivariate empirical orthogonal functions and spectral clustering methods are used to classify and synthesize the extreme precipitation weather. The results show that: (1) The spatial distribution of the extreme precipitation threshold is uneven due to the regional topography. The spatial distribution of the average precipitation and frequency of extreme precipitation days is characterized by the north-south antiphase distribution. (2) According to the main influencing systems, the 215 regional extreme precipitation days in the MYRV in the past 40 years can be classified into three types: southwest vortex type, typhoon type, and cold trough shear line type. (3) The southwest vortex type of extreme precipitation occurs in the deep warm and humid airflow in front of the southwest vortex trough, but the typhoon type has better thermal dynamic conditions, and the cold and warm airflow convergence of the cold trough shear line type is more obvious. The rainfall area of three types of extreme precipitation is the result of the synergistic effect of the system.
{"title":"Climatic characteristics and main weather patterns of extreme precipitation in the middle Yangtze River valley","authors":"Hongzhuan Chen, Xinhuai Yin, Xiaoyu Huang, Enrong Zhao, Xiaofeng Ou, Chengzhi Ye","doi":"10.2166/wcc.2023.545","DOIUrl":"https://doi.org/10.2166/wcc.2023.545","url":null,"abstract":"\u0000 \u0000 Based on the daily precipitation data and ERA5 reanalysis data of 40 years from 1981 to 2018 in the middle Yangtze River Valley (MYRV), the climatic characteristics of extreme precipitation are analyzed using statistical methods. The multivariate empirical orthogonal functions and spectral clustering methods are used to classify and synthesize the extreme precipitation weather. The results show that: (1) The spatial distribution of the extreme precipitation threshold is uneven due to the regional topography. The spatial distribution of the average precipitation and frequency of extreme precipitation days is characterized by the north-south antiphase distribution. (2) According to the main influencing systems, the 215 regional extreme precipitation days in the MYRV in the past 40 years can be classified into three types: southwest vortex type, typhoon type, and cold trough shear line type. (3) The southwest vortex type of extreme precipitation occurs in the deep warm and humid airflow in front of the southwest vortex trough, but the typhoon type has better thermal dynamic conditions, and the cold and warm airflow convergence of the cold trough shear line type is more obvious. The rainfall area of three types of extreme precipitation is the result of the synergistic effect of the system.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138954590","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}
N’da Jocelyne Maryse Christine Amichiatchi, Jean Hounkpè, G. Soro, Ojelabi Oluwatoyin Khadijat, I. Larbi, A. Limantol, A. M. Alhassan, T. A. G. Bi, A. E. Lawin
The purpose of this study is to analyse trends in annual rainfall extremes over five watersheds within Côte d'Ivoire using observed data (1976–2017) and projected (2020–2050) rainfall data from the fourth version of the Rossby Centre regional atmospheric model, RCA4, for the representative concentration pathways RCP 4.5 and RCP 8.5. Four rainfall extreme indices, namely, the consecutive dry days (CDD), maximum annual rainfall (Pmaxan), very wet day (R95p), and maximum 5-day rainfall (Rx5days), were considered for trend analysis by using the non-parametric modified Mann–Kendall test and the distribution mapping bias-correction technique to adjust the simulated regional climate model climate of the simulated daily precipitation. As a result, it is found that during the period 1976–2017, there was a significant downward trend in the drought-related index (CDD) at the Bagoue, Baya, Agneby, and Lobo watersheds. The Baya and N'zo watersheds also experienced a significant downward trend under the RCP 4.5 and RCP 8.5 scenarios. The flood-related indices (Pmaxan, R95p, and Rx5days) show a clear downward trend in the recorded data for almost all the considered watersheds and generally a significant upward trend for both cases. These findings indicate that the watersheds are vulnerable to climate-induced disasters.
{"title":"Analyse of past and projected changes in extreme precipitation indices in some watersheds in côte d'Ivoire","authors":"N’da Jocelyne Maryse Christine Amichiatchi, Jean Hounkpè, G. Soro, Ojelabi Oluwatoyin Khadijat, I. Larbi, A. Limantol, A. M. Alhassan, T. A. G. Bi, A. E. Lawin","doi":"10.2166/wcc.2023.365","DOIUrl":"https://doi.org/10.2166/wcc.2023.365","url":null,"abstract":"\u0000 The purpose of this study is to analyse trends in annual rainfall extremes over five watersheds within Côte d'Ivoire using observed data (1976–2017) and projected (2020–2050) rainfall data from the fourth version of the Rossby Centre regional atmospheric model, RCA4, for the representative concentration pathways RCP 4.5 and RCP 8.5. Four rainfall extreme indices, namely, the consecutive dry days (CDD), maximum annual rainfall (Pmaxan), very wet day (R95p), and maximum 5-day rainfall (Rx5days), were considered for trend analysis by using the non-parametric modified Mann–Kendall test and the distribution mapping bias-correction technique to adjust the simulated regional climate model climate of the simulated daily precipitation. As a result, it is found that during the period 1976–2017, there was a significant downward trend in the drought-related index (CDD) at the Bagoue, Baya, Agneby, and Lobo watersheds. The Baya and N'zo watersheds also experienced a significant downward trend under the RCP 4.5 and RCP 8.5 scenarios. The flood-related indices (Pmaxan, R95p, and Rx5days) show a clear downward trend in the recorded data for almost all the considered watersheds and generally a significant upward trend for both cases. These findings indicate that the watersheds are vulnerable to climate-induced disasters.","PeriodicalId":49150,"journal":{"name":"Journal of Water and Climate Change","volume":null,"pages":null},"PeriodicalIF":2.8,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138962047","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}