Water Resource Planning Research Articles

A Comparative Spatiotemporal Analysis for Long-Term Trends of Hydrometeorological Variables in Maritsa River Basin

Revealing long-term trends in hydrometeorological variables plays a critical role in the sustainable management and planning of water resources. These analyses are necessary to understand climate change impacts, taking precautions for natural disasters, plan agricultural activities, and develop water management strategies. The aim of this study is to examine the changes in monthly and annual total precipitation and evapotranspiration values in the Maritsa River Basin, a transboundary water basin between Bulgaria, Greece, and Türkiye. For this, precipitation values for the 1982-2023 water years were taken from the Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) data set, and evapotranspiration values for the 1982-2023 water years were taken from the European Reanalysis 5th Generation-Land (ERA5-Land) data set. The Mann-Kendall, Sen's slope estimator, and Innovative Trend Analysis (ITA) methods were used to determine trends. According to the test results, there is a statistically significant increase in annual total precipitation values within the 95% confidence interval and in annual total evapotranspiration values within the 99% confidence interval. Specifically with all three methods positive and statistically significant trends are observed in precipitation in October, January, May and June. In the monthly evapotranspiration trend analysis, a statistically significant increase is observed except for November, December, June and July. Trend increases were visualized using the graphical method ITA. Significant increasing trends in both monthly and annual precipitation and evapotranspiration reveal changes in the hydrological cycle of the basin. The test results can be used in planning and solving problems related to the basin area.

Evaluation of the effect of the water-energy nexus on the performance of the water-energy supply system.

In this study, the water-energy nexus is investigated throughout coupling the Water Evaluation and Planning (WEAP) and Low Emission Analysis Platform (LEAP) models under the climate change effects in the Marun basin, Iran. For this purpose, first, the climate change effects on water resources and consumption nodes are calculated under representative concentration pathway (RCP) scenarios from the fifth report of the International Panel on Climate Change (IPCC). Artificial neural network (ANN) is used to model river inflow and Cropwat model is used for agricultural water demand in future time (2015-2040). In the next step, water system is modeled in WEAP and energy system is modeled in LEAP. Then, three water-energy nexus scenarios include (1) calculating the actual hydropower generation capacity in LEAP model (W-E-N1), (2) water-energy nexus evaluation indexes in the WEAP model (W-E-N2), and (3) changes in the electricity consumption intensity in the LEAP model (W-E-N3) are modeled under RCP 2.6, RCP 4.5 and RCP 8.5 climate scenarios. The results of W-E-N1 scenario show that the actual hydropower generation capacity with water-energy nexus is reduced by 78%, 89%, and 91%, respectively, compared to no water-energy nexus under RCP 2.6, RCP 4.5, and RCP 8.5 scenarios. The results of W-E-N2 show that the hydropower generation reliability index will be reduced by 19%, 31%, and 13%, respectively under RCP 2.6, RCP 4.5, and RCP 8.5 compared no water-energy nexus. The results of W-E-N3 scenario show that the electricity consumption intensity will increase considering the electricity required for water transferring to demand sites. The results of the present study show that the water-energy nexus will lead to more accurate results and, as a result, more realistic planning for water and energy resources.

Evaluation and Adjustment of Historical Hydroclimate Data: Improving the Representation of Current Hydroclimatic Conditions in Key California Watersheds

The assumption of stationarity in historical hydroclimatic data, fundamental to traditional water resource planning models, is increasingly challenged by the impacts of climate change. This discrepancy can lead to inaccurate model outputs and misinformed management decisions. This study addresses this challenge by developing a novel monthly data adjustment approach, the Runoff Curve Year–Type–Monthly (RC-YTM) method. The application of this method is exemplified at five key California watersheds. The RC-YTM method accounts for the increasing variability and shifts in seasonal runoff timing observed in the historical data (1922–2021), aligning it with the contemporary climate conditions represented by the period from 1992 to 2021 at the study watersheds. This method adjusts both annual and monthly streamflow values using a combination of precipitation–runoff relationships, quantile mapping, and water year classification. The adjusted data, reflecting current climatic conditions more accurately than the raw historical data, serve as valuable inputs for operational water resource planning models like CalSim3, commonly used in California for water management. This approach, demonstrably effective in capturing the observed climate change impacts on streamflow at monthly timesteps, enhances the reliability of model simulations representing contemporary conditions, which can lead to better-informed decision-making in water management, infrastructure investment, drought and flood risk assessment, and adaptation strategies. While focused on specific California watersheds, this study’s findings and the adaptable RC-YTM method hold significant implications for water resource management in other regions facing similar hydroclimatic challenges in a changing climate.

Trends in Flow Intermittency, Variability, and Seasonality for Taiwan Rivers

In Taiwan, rivers have steep slopes and short lengths, making it difficult to retain water in the rivers. Therefore, understanding the flow characteristics is essential. This study analyzes data from 65 flow stations with over 30 years of records to characterize the annual mean number of low-flow days, flow variability, and the seasonality of low-flow occurrences. The analysis uses indices such as the intermittency ratio, Richards–Baker flashiness index, and six-month seasonality of the dry period (SD6) and evaluates trends in these indices using the Mann–Kendall test. The results show that nearly 70% of the stations have an intermittency ratio of less than 0.1, although the number of low-flow days has significantly increased over time. Stations in the southwestern watersheds exhibit higher flow variability; however, the trends in flow variability are not statistically significant. Low-flow events predominantly occur during the dry season, with 68% of the stations experiencing them between January and March. The findings on flow characteristics and their long-term trends provide references for river management and water resource planning in the future.

Enhancing evapotranspiration estimates in composite terrain through the integration of satellite remote sensing and eddy covariance measurements.

Accurate evaluation of water resource systems is essential for informed planning and decision-making. Evapotranspiration (ET), a key component of water resource management, is often estimated using remote sensing techniques; however, such estimates can be subject to significant uncertainties under certain conditions. In this study, we present a novel approach to improving the accuracy of ET estimates in composite terrains. The methodology involves optimizing the Surface Energy Balance Algorithm for Land (SEBAL-OPT) by integrating ground-based eddy covariance (EC) flux tower data into the satellite-based ET retrieval process. The approach was evaluated at four sites in California, each representing different land uses. Parameter optimization was achieved through Bayesian inference using the Differential Evolution Adaptive Metropolis (DREAM) algorithm, which minimized discrepancies between ET estimates derived from Landsat 8 and 9 imagery and the observed ET from EC measurements. Results from the global sensitivity analysis identified solar radiation and hot/cold pixel selection as the most sensitive parameters in the SEBAL algorithm, highlighting their critical role in reducing uncertainty in ET estimates. SEBAL-OPT demonstrated significantly improved accuracy, with root mean square error (RMSE) values ranging from 0.72mm to 1.33mm, compared to the original SEBAL parameterization (SEBAL-ORG), which produced RMSE values between 1.03mm and 2.14mm. This approach highlights that, when properly calibrated, the model can be effectively applied across diverse agricultural landscapes, regardless of the specific land use at individual sites. These findings have significant implications for water resource planning, agricultural water management, and water rights adjudication and could be applied to other remote sensing of ET models.

The Changing Landscape of Water Resources Planning in England

Abstract Water resources planning in England has undergone a significant transformation from a fragmented, piecemeal approach to a more strategic, multi-scale framework. This shift is a response to the pressing need for increased resilience in the face of climate change, population growth, and environmental pressures. Recognising the limitations of existing planning frameworks established during privatisation, new national, regional, company, and sub-regional frameworks have emerged to address gaps and enhance strategic planning efforts. Understanding the critical pathway dependencies, opportunities, and constraints allows reforms to be designed and implemented with a better chance of success. Several key features characterise water resources planning in England. Firstly, the systems are inherently complex and fragmented, requiring tailored approaches rather than one-size-fits-all solutions. Secondly, planning operates within a neoliberal framework emphasising economic efficiency. Thirdly, subjective concepts like risk, uncertainty, and value are managed through technical quantitative methods which can pose challenges for transparency. Fourthly, while legislation often operates in silos, there is a growing demand for more integrated planning approaches. Funding and regulatory powers play crucial roles in water resources planning. Access to capital is influenced by the institutional environment and broader economic and political factors, with government and regulators ultimately holding power over the framework. Companies, driven by the profit motive, are responsible for detailed planning and delivery, regulated by standards and reputational incentives. Public participation is framed as consumer engagement. Aligning incentives for public good with financial rewards and ensuring effective regulation are vital for the framework’s success.

Methodology for forecasting precipitation related to El Niño when historical meteorological data are incomplete

The interactions between the ocean and the atmosphere produce various climatic phenomena, such as the El Niño-Southern Oscillation (ENSO), that influence hydrological systems. This study serves as a basis for water resource management and planning in reservoirs and hydroelectric generation, in both the short and long term. A methodology is proposed to study the potential influence of extreme phases of ENSO on the amount of monthly and seasonal precipitation in areas where the weather stations do not have a complete historical data record. A case study is presented of the seasonal precipitation forecast for the largest water reservoir in Mexico. Data from 18 weather stations in the hydrological sub-region Grijalva-La Concordia, in the state of Chiapas, were examined, the highest on the river course of the rainwater catchment dam of the Grijalva Hydroelectric Complex, the most important complex of its kind in Mexico. From the results it is expected that climate change will bring more frequent El Niño phases. The proposed methodology has been validated, making it an effective tool to evaluate the effects of ENSO on precipitation. The methodology is applicable to other regions, particularly in developing countries where historical information is often incomplete.

The artificial intelligence-based agricultural field irrigation warning system using GA-BP neural network under smart agriculture.

This work explores an intelligent field irrigation warning system based on the Enhanced Genetic Algorithm-Backpropagation Neural Network (EGA-BPNN) model in the context of smart agriculture. To achieve this, irrigation flow prediction in agricultural fields is chosen as the research topic. Firstly, the BPNN principles are studied, revealing issues such as sensitivity to initial values, susceptibility to local optima, and sample dependency. To address these problems, a genetic algorithm (GA) is adopted for optimizing the BPNN, and the EGA-BPNN model is used to predict irrigation flow in agricultural fields. Secondly, the EGA-BPNN model can overcome the local optimization and overfitting problems of traditional BPNN through the global search ability of GA. Moreover, it is suitable for the irrigation flow prediction task with complex environmental factors in smart agriculture. Finally, comparative experiments compare the prediction accuracy of BPNN and EGA-BPNN using single and dual water level flow prediction models respectively. The results reveal that as the number of nodes in the hidden layer increases, the model's Mean Squared Error (MSE) and Relative Error (RE) show a decreasing trend, indicating an improvement in model prediction accuracy. When the number of nodes in the hidden layer increases from 6 to 16, the MSE of the single and dual water level flow prediction models decreases from 4.53×10-4 to 3.68×10-4 and 2.38×10-4 to 1.66×10-4, respectively. Under a standalone BPNN, the absolute relative error in flow prediction is 1.09%. In contrast, the EGA-BPNN model achieves a significantly lower mean absolute relative error of 0.41% for single-flow prediction, demonstrating superior prediction performance. Furthermore, compared to the BPNN, the EGA-BPNN model exhibits a 2.11 reduction in MSE, further emphasizing the positive impact of introducing the GA on model performance. The research outcomes contribute to more accurate water resource planning and management, providing a more reliable basis for decision-making.

Evaluation of the primary production and maximum fish production in Salman Farsi Reservoir, Fars Province, Iran

Primary production in water bodies corresponds to their fish production capacity. Aquaculture planning for water resources is conducted based on specific geographical conditions and their internal and external factors. Understanding the fish production capacity of lakes enables predictions for exploitation (fishing) and restoration of reserves. This research aims to estimate the primary production of the Salman Farsi Reservoir, Fars Province, on the Ghare Aghaj River, to evaluate fish production capacity and plan aquaculture development. Sampling was conducted to measure dissolved oxygen, water temperature, pH, conductivity, transparency, total phosphorus, total nitrogen, and chlorophyll-a in three transversal sections along the side, surface, and deep areas of the open water, with three repetitions in four seasons during 2023 – 2024. Trophic conditions were estimated using Trophic Status Index (TSI) models. Total production of the lake was calculated using the Brämick-Lemke and Koeschel models, while fish production was calculated using the Brämick-Lemke and Downing models. The annual average of dissolved oxygen, transparency, electrical conductivity, pH, total phosphorus, total nitrogen, and chlorophyll-a concentration in the lake was 8.2 ppm, 4.1 meters, 1387 μS/cm, 8.3, 0.174 ppm, 4.50 ppm, and 1.38 ppm, respectively. The average TSI based on transparency, phosphorus, chlorophyll-a, and Carlson’s index was 40, 78, 33, and 50. The initial production size in the lake was estimated 292 gC.m-²y-1. Fish production capacity was calculated based on primary production at 39 Kg.ha-1.y-1 and based on phosphorus at 33 Kg.ha-1.y-1, with an average of 36 Kg.ha-1.y-1. Considering the 2000-hectare livable area for fish in the lake, the total fish production this year was estimated at 71.8 tons. Under current lake conditions, the allowable fishing size was estimated to be 7 to 11 tons of fish per year. Determining the production capacity and trophic level can help maximize exploitation while minimizing ecological impacts and potential risks associated with restocking and fishing, such as the introduction of excessive juvenile fish into the lake.

Estimating Daily Streamflow Values Using Artificial Neural Networks, Support Vector Regression and Multiple Linear Regression Models for Ceyhan River Basin

Streamflow data are very important for effective planning and management of water resources in basins. In this study, Artificial Neural Networks (ANN), Support Vector Regression (SVR) and Multiple Linear Regression (MLR) models were developed to estimate the daily streamflow of three different rivers in the Ceyhan River Basin. Daily precipitation and temperature data obtained from The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) re-analysis data were used as predictor variables in the models. The estimation performances of the models were evaluated with different statistical performance measures. According to the evaluation results, the SVR model demonstrated the best performance in daily streamflow estimation for the Ceyhan River, achieving R² = 0.95 and RMSE = 28.20 m³ s-1. Additionally, for Söğütlü Creek, the results were R² = 0.82 and RMSE = 6.57 m³ s-1, while for Keşiş Creek, R² = 0.93 and RMSE = 1.45 m³ s-1 were obtained. The findings indicate that the SVR model predicts daily streamflow more successfully than the other models. Furthermore, it was found that the performance of the models developed using machine learning algorithms was superior to that of the linear regression model.

Developing Storylines of Plausible Future Streamflow and Generating a New Warming‐Driven Declining Streamflow Ensemble: Colorado River Case Study

AbstractPlausible future streamflow time series are essential for evaluating policies and management strategies in river basins and testing the operation of water resource systems. Relying solely on stationary historical data is not sufficient in a changing climate. However, uncertainty in the range of streamflow projections from General Circulation Models calls into question their direct use in water resources planning. An intermediate approach is needed to identify ensembles of streamflow time series based on well‐defined assumptions that represent plausible future hydrologic conditions. This paper suggests multiple quantitative storylines of plausible future conditions, each matched with a representative streamflow ensemble to serve as inputs for planning models where, to account for uncertainty, plans or policies that are robust to a range of plausible futures are developed. Applying this approach in the Colorado River Basin we found that, while three storylines were well matched with existing ensembles, there was no suitable ensemble representing increasing variability around a declining mean. To address this gap, we developed a general method to create new streamflow ensembles that account for future changes by combining observed and paleo‐reconstructed flows and adjusting the marginal distribution of the streamflow time series to incorporate the estimated decline in, and increasing variability of, future flow. The results are a set of quantitative storylines that justify a range of plausible future conditions, and a new warming‐driven declining streamflow ensemble for use in Colorado River Basin scenario evaluation and decision‐making representing the plausible increasing variability around a declining mean storyline.

Climate Change Impact on Hydro-climatic Fluxes in Kantamal Catchmentof the Middle Mahanadi River Basin, India

Climate change is now considered as a newly added threat for natural resource management, which has significant impact on agriculture and allied sectors. Climate change studies play a pivotal role in developing sustainable natural resource management strategies. The present study assesses the effect of climate change on hydro-climatic fluxes in Kantamal catchment of the Mahanadi River basin, India. Utilizing the modified Mann-Kendall test, analysis of long-term climatic variables revealed a decreasing trend in rainfall and increasing trend in temperature. Employing a bias-corrected, multi-model ensemble of three regional climate models (RegCM4-4, RCA4, REMO2009) under the Representative Concentration Pathways (RCPs) of RCP4.5 and RCP8.5 scenarios, a rise in the average maximum temperature of 0.86°C under RCP4.5 and 1.16°C under RCP8.5, as well as an increase in the average minimum temperature of 2.35°C under RCP4.5 and 2.89°C under RCP8.5, by 2099 were projected. Rainfall is projected to decrease by 29.53% (RCP4.5) and 24.34% (RCP8.5), with surface runoff decreasing by 13.91% (RCP4.5) and 9.94% (RCP8.5), actual evapotranspiration declining by 7.81% (RCP4.5) and 7.77% (RCP8.5), soil moisture reducing by 11.17% (RCP4.5) and 9.69% (RCP8.5), and water yield is projected to decline by 39.45% (RCP4.5) and 33.05% (RCP8.5) as compared to the baseline period. Water stress situation is anticipated in the catchment emphasizing the need for planning and management of water resources, and sustainable agriculture.

Prediction of Potential Evapotranspiration via Machine Learning and Deep Learning for Sustainable Water Management in the Murat River Basin

Potential evapotranspiration (PET) is a significant factor contributing to water loss in hydrological systems, making it a critical area of research. However, accurately calculating and measuring PET remains challenging due to the limited availability of comprehensive data. This study presents a detailed sustainable model for predicting PET using the Thornthwaite equation, which requires only mean monthly temperature (Tmean) and latitude, with calculations performed using R-Studio. A geographic information system (GIS) was employed to interpolate meteorological data, ensuring coverage of all sub-basins within the Murat River basin, the study area. Additionally, Python libraries were utilized to implement artificial intelligence-driven models, incorporating both machine learning and deep learning techniques. The study harnesses the power of artificial intelligence (AI), applying deep learning through a convolutional neural network (CNN) and machine learning techniques, including support vector machine (SVM) and random forest (RF). The results demonstrate promising performance across the models. For CNN, the coefficient of determination (R2) varied from 96.2 to 98.7%, the mean squared error (MSE) ranged from 0.287 to 0.408, and the root mean squared error (RMSE) was between 0.541 and 0.649. For SVM, the R2 varied from 94.5 to 95.6%, MSE ranged between 0.981 and 1.013, and RMSE ranged from 0.990 to 1.014. RF showed the best performance, achieving an R2 of 100%, MSE values of 0.326 and 0.640, and corresponding RMSE values of 0.571 and 0.800. The climate and topography data used for all algorithms were consistent, and the results indicate that the RF model outperforms the others. Consequently, The RF model’s superior accuracy highlights its potential as a reliable tool for sustainable PET prediction, supporting informed decision-making in water resource planning. By leveraging GIS, AI, and machine learning, this study enhances PET modeling methodologies, addressing critical water management challenges and promoting sustainable hydrological practices in the face of climate change and resource limitations.

Climate shapes baseflows, influencing drought severity

Abstract Baseflow, the sustained flow from groundwater, lakes, and snowmelt, is essential for maintaining surface water flow, particularly during droughts. Amid rising global water demands and climate change impacts, understanding baseflow dynamics is crucial for water resource management. This study offers new insights by assessing baseflow controls at finer temporal scales and examining their relationship with hydrological drought flows. We investigate how climatic factors influence seasonal baseflow in 7138 global catchments across five major climate regions. Our analysis identifies precipitation as the primary driver, affecting 58.3% of catchments, though its impact varies significantly across different climates. In temperate regions, precipitation dominates (61.9% of catchments), while in tropical regions, evaporative demand is the leading factor (47.3%). Snow fraction is particularly crucial in both snow-dominated (20.8%) and polar regions (48.5%). Negative baseflow trends generally emerge where the effects of evaporative demand or snow fraction outweigh those of precipitation. Specifically, in northern regions and the Rocky Mountains, where snow fraction predominantly controls baseflow changes, a negative trend is evident. Similarly, in tropical catchments, where evaporative demand drives baseflow changes, this also leads to a negative trend. Additionally, our findings indicate that baseflow changes are closely linked to hydrologic drought severity, with concurrent trends observed in 69% of catchments. These findings highlight the relationship between baseflow changes, the severity of hydrologic drought and shifts in precipitation, evaporative demand, and snow dynamics. This study provides crucial insights for sustainable water resource planning and climate change adaptation, emphasizing the importance of managing groundwater-fed river flows to mitigate drought impacts.

Application of Active Heating Tests with the Distributed Temperature Sensing to Characterize Flow Dynamics in a Tidal-Influenced Coastal Aquifer

Aquifer storage and recovery have gained attention as a solution that utilizes submarine groundwater discharge (SGD) as a surrogate water resource to alleviate water scarcity and fill the demand gap. Characterizing SGD is crucial for using coastal groundwater and improving understanding of the interaction between continental water and seawater. This study employs fiber-optical distributed temperature sensing (FODTS) and the heat tracer to quantify the groundwater flux in a coastal aquifer in northern Taiwan. The fluxes in different sections along the borehole were estimated from the temperature response caused by the active heating tests and campier groundwater flux under different tidal conditions, providing information on potential water resources for water resource planning and management. According to the active heating tests, the material of the sections with high-temperature response mainly consists of a gravel–sand mixture. Based on the estimations of groundwater fluxes along the well, the sections with low sensitivity of temperature response have low hydraulic conductivity and low groundwater flux. The estimated thermal parameters at the site are consistent with those obtained from the borehole samples in the laboratory tests. The groundwater fluxes in different sections are calculated based on the temperature response observed from the FODTS. The groundwater fluxes along the well vary between 0.02 and 1.77 m/day. There are considerable differences between the estimated fluxes during the tidal cycle in a heterogeneous coastal aquifer, indicating the high uncertainty of estimated SGD along coastlines.

Machine Learning Methods Based on Limited Meteorological Data to Simulate Potential Evapotranspiration: A Case Study of Source Region of Yellow River Basin

ABSTRACTSimulation of potential evapotranspiration (PET) is an important part of drought warning and water resource planning. However, the commonly used empirical models need to input a large number of meteorological elements. Therefore, to improve the efficiency and accuracy of PET simulation in areas lacking meteorological data, this study evaluated the performance of Extreme learning machine (ELM), multi‐layer perceptron (MLP), and Random Forest (RF) three machine learning methods to simulate daily PET using limited meteorological data in the source region of the Yellow River (SYRB). Two bionic optimization algorithms, Grey Wolf Optimizer (GWO) and Sparrow Search Algorithm (SSA), were used to optimise the hyperparameters of the model to improve the accuracy of the model. In addition, the effect of months on daily PET simulations was evaluated. The results showed that the daily maximum temperature (Tmax) was the most important factor affecting the PET simulation, and the daily average relative humidity (RH) and wind speed (U10) were the secondary factors. It is recommended to use Tmax, RH, U10, and sunshine duration as the optimum combination of input (R2 > 0.95). In the case of limited meteorological data, the input combination of Tmax, RH, U10, or Tmax, RH (R2 > 0.75) was considered. Considering the accuracy and the time and space overhead of the model, the ELM‐GWO model is recommended. When month information was used as an input factor, model performance improved in all scenarios, and June to July was the most accurate month for the model to simulate daily PET. This research resultwill allow researchers to choose the appropriate meteorological factor when simulating the PET to provide the reference.

Application of the CMIP6 Approach for Determination of Climate Change Impact on Inflow to Malampuzha Reservoir, India

Optimal operation of a reservoir is important for the efficient planning and management of water resources. Inflow estimation into the reservoir is the basic information needed by a policy maker for the optimal planning of the reservoir operation. Climate change has become a major cause for the changes in the hydrological phenomena. An attempt was made to analyse the impact of climate change on Malampuzha reservoir inflow for the future using recent Shared Socioeconomic Pathways (SSP) scenarios. Two SSP scenarios, SSP 245 and SSP 585 were considered for the evaluation of changes in the meteorological variables for the future period. Rainfall-runoff modelling of the catchment area of the Malampuzha reservoir was done with IHACRES model for the period 2003-2022. The model performance was accepted in calibration (2003-2016) and validation (2017-2022) periods with R2 of 0.90 and 0.91 and RMSE 2.63 and 4.53 m3/s respectively. The outputs of SSP245 and SSP585 scenarios were given to the developed runoff model to estimate the future inflow volume into Malampuzha reservoir for the period of 2023 to 2042. From the results, the change in monthly temperature varies from -0.88oC to 3.3oC and change in monthly precipitation varies from -0.64% to 1.73% which indicates a decrease in the inflow of water into the reservoir for future period by 2.6% and 9.3% than the base period (2003– 2022) for SSP245 and SSP585 scenarios, respectively. The results of the study implies that better planning of the reservoir operation is needed for meeting the future demands.

DRINKING WATER SUPPLY ISSUES: MODELLING AND INTEGRATED MANAGEMENT FOR FUTURE SUSTAINABILITY. THE CASE OF THE CITY OF GUELMA, NORTH-EAST ALGERIA

The city of Guelma has experienced remarkable urban sprawl over the last few decades, with a continuous expansion of the urban area to accommodate a growing population. This phenomenon is particularly accentuated by a high demographic growth rate, which increases the pressure on infrastructure and basic services, especially drinking water supply, due to the increasing needs of households. The main objective of this study is to analyse the contribution of the WEAP model to the management of drinking water supply in the different sectors of the city of Guelma. This approach aims to ensure effective and sustainable planning of water resources to meet the growing needs of the population in each sector, while preserving this essential resource. The results show that water resources are limited, with projected consumption increasing from 6 million m³ in 2008 to around 47 million m³ in 2050, while the population is expected to reach almost 800,000 inhabitants. All scenarios show a water deficit, where demand exceeds supply. The study therefore emphasises the need for integrated water resource management to ensure sustainability. It uses hydrological and demographic data to guide supply decisions and aims to develop effective strategies to address the growing water challenges in the city of Guelma.

Integrating CNN-BiLSTM Architecture for Predicting Precipitation and Meteorological Patterns

Accurate forecasting of precipitation is essential for various sectors, including agriculture, disaster management, and water resource planning. This paper presents a deep learning architecture that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) layers to predict precipitation using a set of weather parameters, including temperature, station level pressure, dew point, and calculated relative humidity. The proposed architecture leverages CNN for feature extraction and BiLSTM for capturing temporal dependencies, offering insights into the model's efficiency and the challenges associated with predicting precipitation using calculated inputs.

Assessment of reference evapotranspiration forecasting in the Mediterranean climate of Central Chile using the ASCE standardized Penman-Monteith equation, the Hargreaves-Samani equation, and weather predictions from the Global Forecast System model

Accurate estimation of crop evapotranspiration (ETc) is essential for effective agricultural water resource planning. To determine ETc it is common multiplying the reference evapotranspiration (ETref) by an appropriate crop coefficient (Kc). Forecasting ETref could be particularly beneficial for irrigation scheduling. In this work, daily and cumulative (7 days) ETref predictions were estimated with the Penman-Monteith (PM) and the Hargreaves-Samani (HS) models using environmental variables obtained from the Global Forecast System (GFS). Results were compared with ETref calculated with the ASCE (American Society of Civil Engineers) PM equation from measured daily values of solar radiation, air temperature, relative humidity and wind speed. Four weather stations located in Central Chile during 2020 to 2022 were used. The best results were obtained using the HS equation, for all weather stations, the statistical indicators for daily ETref predictions fall within the following ranges: Accuracy (defined as the percentage of daily ETref predictions with an absolute error within 1mmd−1) varies between 72.8% and 91.8%; the root mean square error (RMSE) ranges from 0.59mmd−1 to 0.98mmd−1; the normalized root mean square error (NRMSE) is between 16.1% and 24.1%; the mean bias error (MBE) is between 0.10mmd−1 and 0.36mmd−1; and the normalized mean bias error (NMBE) varies from 2.5% to 8.3%. On the other hand, the indicators for the 7-day cumulative ETref forecasts were: RMSE from 2.86mm to 5.08mm; NRMSE from 11.0% to 16.3%; MBE from 0.66mm to 2.57mm; and NMBE from 2.4% to 8.3%. These results suggest that HS ETref values predicted from GFS temperature forecasts could be effective for foreseeing near-future water demand and enhancing the accuracy of irrigation scheduling and management in Central Chile.