Optimal Management Of Water Resources Research Articles

Stacked machine learning algorithms and bidirectional long short-term memory networks for multi-step ahead streamflow forecasting: A comparative study

Prediction of river flow rates is an essential task for both flood protection and optimal water resource management. The high uncertainty associated with basin characteristics, hydrological processes, and climatic factors affecting river flows make streamflow prediction a very challenging problem. These reasons, together with the increasingly wide availability of data relating to flow rates and rainfall, frequently lead to a preference for data-driven models over physically based or conceptual forecasting models.This study shows the results of an in-depth comparison between two different daily streamflow prediction models: a novel simpler model based on the stacking of the Random Forest and Multilayer Perceptron algorithms, using the Elastic Net algorithm as meta-learner, and a more complex model based on bi-directional Long Short-Term Memory (LSTM) networks. Bayesian optimization was employed in selecting hyperparameters. The two prediction models were compared through the analysis of four different case studies: the Bacchiglione River, the Raccoon River, the Wilson River, and the Trent River.The two models showed comparable forecasting capabilities. In the most favourable cases, both models demonstrated very high accuracy (R2 greater than 0.93, Mean absolute percentage error approximately equal to 10%). The stacked model outperformed the bi-directional LSTM network model in several cases in predicting peak flow rates but was less accurate in forecasting low flow rates. In addition, its computation times are significantly shorter. The prediction accuracy of both models decreased as the forecast horizon increased. The length of the time series plays an essential role in developing models with satisfactory forecasting capabilities. In this study, the effectiveness of forecasting models was not influenced by the river regime. However, a high variance of the input dataset and a large number of outliers in the time series can reduce the accuracy of prediction models.

Drought Monitoring Using MOWCATL Data Mining Algorithm in Aras Basin, Turkey

Drought is a natural phenomenon that occurs frequently and has some adverse effects on the ecosystem and humanity. Determination of drought beforehand is vital for optimal management of water resources. Many different methods have been developed to detect drought. Sequential association analysis is used for the data series analysis containing time information and is one of the methods used to determine the drought. A correlation can be established between the values taken by the data at different times when determining association rules with this method. The primary purpose of this study is to determine the sequential association patterns between precipitation and climate oscillation index for Aras Basin. The Aras basin is a region where irrigation and animal husbandry are common. Today, many dams and hydroelectric power plants, together with the increasing population, meet the water and energy needs. A possible drought event in this region will adversely affect the living things in the basin. Therefore, the study focused on this basin. Finding sequential associations between precipitation and climate oscillation index can determine the temporal correlations between these parameters and specifically detect drought. The MOWCATL (Minimal Occurrences with Constraints and Time Lags) algorithm was used to detect sequential associations, and the J-measure was used to evaluate the patterns in the study. Sequential association patterns were determined by applying this method to the precipitation data obtained from 6 meteorology stations in the Aras basin. AO (Arctic Oscillation) Index, MEI (Multivariate ENSO) Index, NAO (North Atlantic Oscillation) Index, Oceanic Niño Index (ONI), PDO (Pacific Decadal Oscillation) Index, PNA (Pacific/North American), and SOI (Southern Oscillation Index), followed by the 1, 3, 6 and 12-month Agricultural Standardized Precipitation Index (a-SPI) were used in sequential association. The study results revealed that the antecedent parameters were ineffective in detecting arid conditions in Ardahan and Doğubeyazıt stations, and they were influential on drought conditions, especially in a-SPI-3 and a-SPI-12 month periods at other stations. Although the altitude and geographical features are different, similar climatic patterns have been detected in some stations. As a result, it has been determined that climatic oscillations generally bring about typical situations in terms of drought for the Aras Basin.

Performance improvement of machine learning models via wavelet theory in estimating monthly river streamflow

River streamflow is an essential hydrological parameters for optimal water resource management. This study investigates models used to estimate monthly time-series river streamflow data at two hydrological stations in the USA (Heise and Irwin on Snake River, Idaho). Five diverse types of machine learning (ML) model were tested, support vector machine-radial basis function (SVM-RBF), SVM-Polynomial (SVM-Poly), decision tree (DT), gradient boosting (GB), random forest (RF), and long short-term memory (LSTM). These were trained and tested alongside a conventional multiple linear regression (MLR). To improve the estimation and model performance, hybrid models were designed by coupling the models with wavelet theory (W). The models performance was assessed using root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), and Willmott’s index (WI). A side-by-side performance assessment of the stand-alone and hybrid models revealed that the coupled models exhibit better estimates of monthly river streamflow relative to the stand-alone ones. The statistical parameter values for the best model (W-LSTM4) during the test phase was RMSE = 36.533 m3/s, MAE = 26.912 m3/s, R2 = 0.947, NSE = 0.946, WI = 0.986 (Heise station), and RMSE = 33.378 m3/s, MAE = 24.562 m3/s, R2 = 0.952, NSE = 0.951, WI = 0.987 (Irwin station).

A short-term water demand forecasting model using multivariate long short-term memory with meteorological data

Abstract Sustainable management of water resources is a key challenge nowadays and in the future. Water distribution systems have to ensure fresh water for all users in an increasing demand scenario related to the long-term effects due to climate change. In this context, a reliable short-term water demand forecasting model is crucial for the optimal management of water resources. This study proposes a novel deep learning model based on long short-term memory (LSTM) neural networks to forecast hourly water demand. Due to the limitations of using multiple input sequences with different time lengths using LSTM, the proposed deep learning model is developed with two modules that process different temporal sequences of data: a first module aimed at dealing with short-term meteorological information and a second module aimed at representing the longer-term information of the water demand. The proposed dual-module structure allows a multivariate selection of the inputs with sequences of a different time length. The performance of the proposed deep learning model is compared to a conventional multi-layer perceptron (MLP) and a seasonal integrated moving average (SARIMA) model in a real case study. The results highlight the potential of the proposed multivariate approach in short-term water demand prediction, outperforming the more conventional approaches.

Water Resource Management in Hotels Using a Sustainable Balanced Scorecard

It is essential to find a balance between tourism development and sustainable consumption of water resources. To achieve this goal, a Sustainable Balanced Scorecard connected to the Sustainable Development Goals (SDG) is proposed for optimal water resource management in the hotel sector. The Scorecard is based on four perspectives: customer, internal processes, learning and improvement, and financial. The key variables were agreed on with stakeholders in the sector, and the Sustainable Balanced Scorecard was tested empirically on a sample of 70 hotels in island tourism destinations in the Macaronesia region. The results revealed that though more and more hotels have tried to implement strategies to save water, they were still a long way from reaching the international standard of 140 L per guest night. In addition, there were significant differences concerning water consumption according to hotel category. The Sustainable Balanced Scorecard in this paper adds to the existing works about materiality in sustainability. It can also support business decision making about the SDGs and help potential investors.

A Hybrid Model Integrating Elman Neural Network with Variational Mode Decomposition and Box–Cox Transformation for Monthly Runoff Time Series Prediction

Precise and reliable monthly runoff prediction plays a vital role in the optimal management of water resources, but the nonstationarity and skewness of monthly runoff time series can pose major challenges for developing appropriate prediction models. To address these issues, this paper proposes a novel hybrid prediction model by introducing variational mode decomposition (VMD) and Box–Cox transformation (BC) into the Elman neural network (Elman), named the VMD-BC-Elman model. First, the observed runoff is decomposed into sub-time series using VMD for better frequency resolution. Second, the input datasets are transformed into a normal distribution using Box–Cox, and as a result, skewedness in the data is removed, and the correlation between the input and output variables is enhanced. The proposed VMD-BC preprocessing technology is expected to overcome the problems arising from nonstationary and skewed runoff data. Finally, Elman is used to simulate the respective sub-time series. The proposed model is evaluated using monthly runoff time series at Zhangjiashan, Zhuangtou and Huaxian hydrological stations in the Wei River Basin in China. The model performances are compared with those of single models (SVM, Elman), decomposition-based (VMD-SVM, VMD-Elman et al.) and BC-based models (BC-SVM and BC-Elman) by employing four metrics. The results show that the hybrid models outperform single models, and the VMD-BC-Elman model performs best in all considered hybrid models with an NSE greater than 0.95, R greater than 0.98, NMSE less than 4.7%, and PBIAS less than 0.4% in both the training and testing periods. The study indicates that the VMD-BC-Elman model is a satisfactory data-driven approach to predict nonstationary and skewed monthly runoff time series, representing an effective tool for predicting monthly runoff series.

Role of energy storage in energy and water security in Central Asia

Central Asia has faced major energy and water security challenges. Technically, water from the Pamir and Tian Shan Mountain ranges could be sufficient to meet the needs of the countries in the region, if there was no temporal mismatch between the availability of water for irrigation and electricity generation. While water is required for agriculture in downstream countries during the summer, demand for hydro electricity generation is mainly in the wintertime in upstream countries. With the aid of the open-source MESSAGEix energy systems optimization modelling framework, we study a renewable energy transition in the region through to 2050, considering innovative long duration water and energy storage solutions for optimal management of water and energy resources in different seasons. The modelling approach demonstrates that the proposed "dual water and energy storage scheme", with two different hydrological cycles for up- and down-stream regions, can guarantee enough water for energy generation in upstream countries in winter while ensuring water availability for irrigation downstream in summer. This scheme is economically feasible and, with further detailed analyses and geo-political considerations, it can serve to improve energy security and water resource management, towards achieving sustainable development goals in Central Asia.

Flood frequency analysis at ungauged catchments with the GAM and MARS approaches in the Montreal region, Canada

Regional frequency analysis (RFA) aims to estimate quantiles of extreme hydrological variables (e.g. floods or low-flows) at sites where little or no hydrological data is available. This information is of interest for the optimal planning and management of water resources. A number of regional estimation models are evaluated and compared in this study and then used for regional estimation of flood quantiles at ungauged catchments located in the Montreal region in southern Quebec, Canada. In this study, two neighborhood approaches using canonical correlation analysis (CCA) and the region of influence (ROI) method are applied to delineate homogenous regions. Three regression methods namely log-linear regression model (LLRM), generalized additive models (GAM), and multivariate adaptive regression splines (MARS), recently introduced in the RFA context, are considered for regional estimation. These models are also applied considering all stations (ALL). The considered models, especially MARS, have never been used previously in a concrete application. Results indicate that MARS and GAM have comparable predictive performances, especially when applied with the whole dataset. Results also show that MARS used in combination with the CCA approach provide improved performances compared to all considered regional approaches. This may reflect the flexibility of the combination of these two approaches, their robustness, and their ability to better reproduce the hydrological phenomena, especially in real-world conditions when limited data are available.

Management of energy and water resources by minimizing the rejected renewable energy

Energy and water independence and reduction of the consumption of fossil fuels can be achieved by the exploitation of the rich wind potential of the Greek islands and the optimal management of water resources. Produced wind energy can be either sent directly to the Local Production Station or can be used for pumping and storing water in the upper reservoir, for use when low winds prevail. However, a percentage of produced wind energy cannot be utilized immediately but neither can be stored and is being rejected. The objective of this paper is to provide the methodological framework for a Hybrid Renewable Energy scheme, where the rejected energy is minimized, while the hybrid system contributes satisfactorily to electricity and water and irrigation coverage. The proposed framework can be used as a planning tool for energy managers and decision and policymakers to determine the operation plan of a hybrid system in terms of minimum rejected energy. The methodology is applied, as a case study, on a Mediterranean island, in the Aegean Sea, in Greece. Direct wind energy equal to 30% leads to the minimization of rejected energy, while coverage of drinking, irrigation and electricity demands is 60%, 21% and 31% respectively.

Ensemble streamflow forecasting based on variational mode decomposition and long short term memory

Reliable and accurate streamflow forecasting plays a vital role in the optimal management of water resources. To improve the stability and accuracy of streamflow forecasting, a hybrid decomposition-ensemble model named VMD-LSTM-GBRT, which is sensitive to sampling, noise and long historical changes of streamflow, was established. The variational mode decomposition (VMD) algorithm was first applied to extract features, which were then learned by several long short-term memory (LSTM) networks. Simultaneously, an ensemble tree, a gradient boosting tree for regression (GBRT), was trained to model the relationships between the extracted features and the original streamflow. The outputs of these LSTMs were finally reconstructed by the GBRT model to obtain the forecasting streamflow results. A historical daily streamflow series (from 1/1/1997 to 31/12/2014) for Yangxian station, Han River, China, was investigated by the proposed model. VMD-LSTM-GBRT was compared with respect to three aspects: (1) feature extraction algorithm; ensemble empirical mode decomposition (EEMD) was used. (2) Feature learning techniques; deep neural networks (DNNs) and support vector machines for regression (SVRs) were exploited. (3) Ensemble strategy; the summation strategy was used. The results indicate that the VMD-LSTM-GBRT model overwhelms all other peer models in terms of the root mean square error (RMSE = 36.3692), determination coefficient (R2 = 0.9890), mean absolute error (MAE = 9.5246) and peak percentage threshold statistics (PPTS(5) = 0.0391%). The addressed approach based on the memory of long historical changes with deep feature representations had good stability and high prediction precision.

1975-2020年疏勒河流域绿洲时空变化研究

PDF HTML阅读 XML下载 导出引用 引用提醒 1975-2020年疏勒河流域绿洲时空变化研究 DOI: 10.5846/stxb202105111232 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学青年基金项目（42007430，41801079，41701062）；第二次青藏高原综合科学考察研究项目（2019QZKK0608） Spatiotemporal change of oasis in Shule River Basin during 1975-2020 Author: Affiliation: Fund Project: National Natural Science Foundation of China;the second Tibetan Plateau Scientific Expedition and Research Program (STEP) 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:掌握内陆河流域绿洲时空动态是内陆河流域实现水资源优化配置和动态管理的基本前提。基于Landsat系列数据，结合面向对象随机森林和目视解译方法，分析了1975-2020年疏勒河流域绿洲的时空格局、结构变化及其成因，并探讨了人工/天然绿洲比例变化对生态环境的影响。结果表明：（1）2020年疏勒河流域绿洲面积为5790.24km2，占流域面积比例的4.65%，其中人工绿洲、自然绿洲和过渡带分别占绿洲总面积比例为45.29%、51.07%和3.64%；（2）疏勒河流域绿洲分布模式主要为内陆河沙漠区模式和干流模式；（3）1975-2020年疏勒河流域绿洲面积整体上呈扩张趋势，且绿洲变化以人工绿洲扩张、天然绿洲和荒漠-绿洲过渡带减少为主要特征，土地类型的主要变化为草地和荒漠被开垦，绿洲变化可分为1975-2000年缓慢扩张和2000-2020年迅速扩张2个阶段，主要原因为流域径流量增加和外来移民输入；（4）随着人工与天然绿洲面积之比由3：7（1975年）增加到5：5（2020年），流域绿洲生态环境质量呈现先上升后下降趋势，2005年达到最高。研究可为疏勒河流域绿洲生态系统稳定发展提供数据支撑和科学依据。 Abstract:Grasping spatial-temporal dynamics of oasis in the inland river basin is the basic premise for realizing optimal allocation and dynamic management of water resources for the inland river basin. Shule River Basin, located in the west of Hexi Corridor, is a typical sensitive area in the fragile zone of ecosystem. In recent years, with the warming of the climate, the diameter flow out of the mountains has increased year by year, providing a good environmental background for the expansion of artificial oases and the restoration of natural oasis. Many scholars had carried out a lot of research work on ecological quality, service function and carrying capacity in this basin. However, there were relatively few studies on the spatio-temporal changes of oasis pattern and structure in long time series at watershed scale. Therefore, based on Landsat data of years 1975, 1990, 1995, 2000,2005, 2010, 2015 and 2020 combining object-oriented random forest and visual interpretation method, this paper analyzed the spatio-temporal pattern, structure change and causes of oasis in Shule River Basin from 1975 to 2020. And it also discussed the impact of artificial oasis area to natural oasis area ratio on the quality of ecological environment. The results showed that:(1) The total area of oasis was 5790.24 km2 in the Shule River Basin in 2020, accounting for 4.65% of the total area of the basin, of which the artificial oases, natural oases and desert-oasis ecotone accounted for 45.29%, 51.07% and 3.64%, respectively; (2) The distribution patterns of oasis in Shule River Basin are mainly the inland river desert region model and the mainstream flow model. (3) The oasis area in Shule River Basin showed an overall trend of expansion from 1975 to 2020. The oasis changes were mainly characterized by the expansion of artificial oases and the decrease of natural oasis and desert-oasis transition zones. The main changes of land cover types were the reclamation of grassland and desert. And the land cover types of artificial oasis in Shule River Basin showed an increasing trend from 1975 to 2020. The oasis changes could be divided into two stages:slow expansion from 1975 to 2000 and rapid expansion from 2000 to 2020. (4) As the ratio of artificial to natural oases area increased from 3:7 (1975) to 5:5 (2020), the eco-environmental quality of oases increased firstly and then decreased, reaching the highest value in 2005. This study can provide data support and scientific basis for the steady development of oasis ecosystem in Shule River Basin. 参考文献 相似文献 引证文献

Applicability of recurrent neural networks to retrieve missing runoff records: challenges and opportunities in Turkey.

Acquiring river flow records is the primary precondition for providing optimal water resource management practices and preserving the ecohydrological balance. In Turkey, some river gauging stations go intermittently out of service due to some technical problems or unexpected difficulties. Consequently, river flow records are lost, and this is especially true in the rural and remote areas of the nation. In this regard, we investigated the ability of recurrent neural networks (RNN) as a supportive approach for retrieving daily river flow data for some stations, namely, Akçaşehir and Dağgüney located on the Susurluk basin in Bursa, Turkey. To meet the study goal, flow records from nearby stations were collected. In addition, a RNN with two hidden layers was developed. Initially, the model was trained and validated; then, we tried to predict missing records. The findings showed the potential of RNN in providing good predictions during low and mid flows with acceptable uncertainties rate (less than 30%) even with limited number of input data. Moreover, we discussed the current challenges and opportunities of this issue in remote areas of Turkey. Overall, our findings suggested that RNN may be considered as a practical method to predict the likely periods of floods and droughts in remote areas and interpolate missing records instead of using classical approaches.

Environmental and hydrological risks in the Lake Baikal basin water resources management

For optimal water resources management of the Angara reservoirs cascade (a complex “Lake Baikal – Irkutsk, Bratsk, Ust-Ilimsk and Boguchansk reservoirs”) and water users provision in the MIKE 11 software a quasi-two-dimensional simulation hydrodynamic model of the Angara hydroelectric power stations (HPS) cascade from Lake Baikal to the Boguchansk HPS downstream, which is a tool for reproducing the features of the water flow hydrodynamic structure, was developed. A hydrodynamic computer model using the built-in module “Regulating structures” module makes it possible to form reasonable operating modes of the Angarsk cascade of reservoirs that meet the most significant requirements of water users: ecology, fisheries and utilities, transport and energy. Hydrodynamic calculations and the flood zones obtained in the GIS project of the territory showed that catastrophic phenomena in the floodplain and coastal zone of Irkutsk occur even when releases into the lower pool of the Irkutsk reservoir exceed 3200 m3/s. The developed hydrodynamic model of the Angarsk cascade of reservoirs makes it possible to determine the objects and floodplain areas most susceptible to flooding in the downstream of the Irkutsk HPS for further development of scientifically based measures to protect them, prevent flooding and develop evacuation plans in an emergency.

Seasonal variation and controlling factors of evapotranspiration over dry semi-humid cropland in Guanzhong Plain, China

The Guanzhong Plain is a critical food production area in the Yellow River Basin that frequently suffers from water shortages. In this study, long-term (June 2013 to June 2018) water and energy fluxes were observed, and path analysis was conducted over an irrigated winter wheat (Triticum aestivum L.) / summer maize (Zea mays L.) rotation field to identify the controlling factors of evapotranspiration (ET). Total ET for each crop year ranged from 627 to 775 mm, with an average growing season ET of 398 mm for wheat and 310 mm for maize. There is significant seasonal variation in both ET and surface conductance (Gs). Daily ET varied from 0.0 to 6.0 mm d–1 for wheat and 0.0 to 6.7 mm d–1 for maize. The peak daily values of Gs were 29.5 mm s–1 for wheat and 19.5 mm s–1 for maize. The direct and indirect effects of environmental and biological factors—net radiation (Rn), surface conductance (Gs), saturation vapor pressure deficit (VPD), leaf area index (LAI), air temperature (Tair), and volumetric soil water content (VWC)—on ET were calculated using the path analysis method. Rn was determined to be the primary controlling factor of ET for both the summer maize and winter wheat growing seasons. Also, Gs was found to be another controlling factor that has more controlling power in the summer maize growing season than in the winter wheat season. VPD had a significant positive and direct effect on ET for both of the crop seasons, while it had a significant negative and indirect effect on ET through Gs in the summer maize season. VWC and Tair only directly affected the wheat ET. In addition, VWC had two significant paths that can indirectly affect ET through LAI and Gs. The revealed seasonal patterns and controlling factors of evapotranspiration in this agroecosystem provide a theoretical basis for optimizing water resources management of the Yellow River.

Investigating the Impact of drought on the base flow using Standardized base flow index,Case study: Kaka-Reza catchment

Understanding the interaction of drought phenomenon and hydrological response of catchments can lead to obtaining some information for optimal water resource management. The aim of this study is to investigate the temporal relationship between drought and groundwater contribution to stream flow, in Kaka –Reza sub catchment. In this study, the common period (1382-2017) was considered for the corresponding hydrometric and rain gauge stations. The standardized precipitation index (SPI) was then calculated at time scales of 3, 6, 9, 18, 12 and 24 months. Base flow and related index were calculated by B-flow-Line and Halick digital filter method in monthly, annual and total time bases. Then the standardized base flow index (SBFI), the base flow duration curve (BFDC) and the base flow duration curve shape index (SBFDC) was calculated. Changes in (BFDC) and the corresponding shape index and the relationships between (SPI) and (SBFI) were investigated and analyzed using the correlation method. The results showed that the average BFI during the research period was equal to 0.52 and its minimum and maximum were equal to 0.46 and 0.57, respectively. Also, the trend of bas flow changes is a decreasing trend with a low slope. The trend of changes SBFDC decreases over study period with a low slope. The rate of slope change is also from one to three percent, and close to the straight line, which indicates the tendency for base flow to be stable in the long time. The greatest impact of the drought phenomenon on the river base flow is in the time step of nine and twelve months. The correlation between SPI and SBFI with a coefficient of determination 0.87 confirms the increase in the groundwater contribution to base flow, with a delay of nine to twelve months.

Sensitivity and uncertainty analysis for streamflow prediction based on multiple optimization algorithms in Yalong River Basin of southwestern China

Semi-distributed model based on spatial information is effective for simulating hydrologic cycle. However, it cannot completely simulate all relevant natural processes. Uncertainty analysis is necessary for achieving high accuracy of hydrological modelling. In this study, optimization algorithms and weighted network analysis techniques were adopted to explore hydrological parameter combination characteristics as well as hydrological simulating uncertainties in Yalong River Basin (YLRB) of southwestern China based on Sequential Uncertainty Fitting version 2 (SUFI-2), Generalized Likelihood Uncertainty Estimation (GLUE) and Particle Swarm Optimization (PSO). The results indicated that: a) groundwater recession factor, effective hydraulic conductivity in channel and saturated hydraulic conductivity could significantly affect streamflow in the studying basin, b) complex parameter combination responded diversely under aforementioned three optimization algorithms. Comparatively, GLUE brought out higher autocorrelation parameter network and c) SUFI-2 and PSO performed better in terms of effective uncertainty analysis and fitting values than those of GLUE. This work could provide references and insights for sensitive parameter modification and prediction uncertainty reduction of streamflow simulation, furthermore contributing to an optimal water resource management.

Application of standardized precipitation index for monitoring meteorological drought and wet conditions in Garhwal region (Uttarakhand)

Drought is one of the most important environmental problems affecting the planet. The identification, characterization, and monitoring of droughts are of great importance for optimal planning and management of water resources. In this research, meteorological drought and wet conditions and their probabilities were analyzed at Chamoli, Dehradun, Haridwar, Pauri Garhwal, Rudraprayag, Tehri Garhwal, and Uttarkashi stations located in the Garhwal region of Uttarakhand State (India) by employing the Standardized Precipitation Index (SPI). The SPI was computed on the multi-time scale (i.e., 1, 3, 6, 9, 12, and 24) corresponding to SPI-1, SPI-3, SPI-6, SPI-9, SPI-12, and SPI-24 by using available monthly rainfall data at study stations. The evaluation of results exposed that there are 69%, 68%, 69%, 71%, 68%, 72%, and 70% chances (probability) of the normal condition (NC) at Chamoli, Dehradun, Haridwar, Pauri Garhwal, Rudraprayag, Tehri Garhwal, and Uttarkashi stations, respectively. The chances of occurrence of moderate drought (MD) and wet (MW) conditions were relatively more at all the study stations, except the Pauri Garhwal (extreme wet (EW) = 0.55) and Tehri Garhwal (extreme drought (ED) = 0.36 and 0.31). Accordingly, the results of this study are exploited in such a way to harvest the excess water during the wet periods and utilize the same in drought periods for drinking, household activities, irrigation, etc. in the study region.

Optimal reservoir operation – A climate change adaptation strategy for Narmada basin in central India

The potential impacts of climate change on the water resources of the Narmada basin in central India has been investigated using the Soil and Water Assessment Tool (SWAT). The existing dams in the river basin have been incorporated in the model setups, calibration and validation. The COordinated Regional climate Downscaling EXperiment datasets for South-Asia (CORDEX-SA) at 0.5° × 0.5° resolution for four-time horizons, viz., 1970–05 (historical), 2006–40 (near-term), 2041–70 (mid-term) and 2071–99 (end-term) under Representative Concentration Pathways (RCP) scenarios, RCP4.5 and RCP8.5 has been used to investigate the changes in the future climate and simulation of future streamflow. The proposed dams have also been incorporated for modeling the future developmental scenarios. The scenario analysis based on the projected climate variables has led to the inference that the change in the precipitation pattern coupled with the warming trends, maybe contributing towards higher variability in water availability. A future scenario of lower water availability and higher water demands thus calls for optimal utilization of available water resources in the future, so that the higher water demands can be satisfied with lower anticipated future flows. Various alternatives were explored for devising adaptation strategies using the engineering/technical solutions in which the optimal water resources management approaches were explored using the simulation-only and the genetic algorithm based simulation–optimization approaches. The simulation–optimization framework based integrated reservoir operation of four reservoirs has led to better reservoir performance and the number of irrigation failures has decreased substantially from 92 to 12 during 2006–40, 86 to 22 during 2041–70 and 89 to 10 during 2071–99. The hydropower failures have also decreased considerably from 202 to 96 during 2006–40, 192 to 28 during 2041–70 and 179 to 67 during 2071–99 under the RCP8.5 scenario. There were no failures in meeting the domestic water supply and environment flow demands. This may be an important adaptation measure to address the issues of climate change impacts on the water resources in the future in the Narmada basin.

Smart water conservation through a machine learning and blockchain-enabled decentralized edge computing network

Forecasting precise water usage corresponding to various beneficial usages is important for optimal and sustainable planning and management of water resources. Due to rapid population growth, there is an urgent need for devising water saving solutions. In this paper, we propose a blockchain based incentivized edge computing framework for water saving using soft computing methodologies. The framework facilitates decision makers in creating awareness among people about water savings in a easily understandable scientific way. Our incentivized blockchain based model uses edge computing at the house nodes of the network to predict the actual usage of a particular household in the locality based on several factors such as number of people, average income of family, profession of the members and previous water demands. By using Feed Forward Networks and Mixture Density Networks, we predict the water usage in terms of input factors and historical usage respectively, thus incorporating machine computing into the framework. With the two values from these methods, a comparison is made with the actual amount of water used by the householders. This research proposes deployment of the smart contract on the blockchain network for efficient and accurate reward distribution. Incentives and rewards are given in the blockchain network to houses with lesser consumption and penalties are imposed when usage crosses predicted and historic usage. The model ensures that accurate incentives are provided to the people in order to motivate them to avoid wastage of water. Results show that the methods used in our work perform better than other relevant networks on a self-synthesized dataset. The proposed methods converge well and show higher spatio-temporal accuracy.

Water flow Forecasting Methods for Optimal Water Resource Operation and Management: A Review

Water flow is a hydrological process that highly intermittent and dependent on nature. Water flow forecasting is an important task for operation and management of water resources for application that includes irrigation, water distribution, hydropower generation and flood prediction. There has been many methods and tools used to forecast and predicts water flow in many hydrological areas. As a result, the water flow modeling has become a key area of study due to the importance of water resource management. Hence, this paper aim to provide a comprehensive that compare methods used for water flow forecasting and summarized their key characteristics.