Search Results (61)

This study develops an intelligent multi-indicator collaborative approach to improve coal seam roof water inrush warnings. A multidimensional dataset is constructed using microseismic data, borehole water levels, electrical measurements, and daily water inflow. A VMD-LSTM algorithm is proposed to predict roof rupture height, while regression analysis handles remaining indicators. Results show that during water-conducting channel development, microseismic activity, electrical data, and water inflow increase synchronously, whereas borehole water levels decline significantly—trends that reverse post-development. Compared to traditional LSTM, the VMD-LSTM model reduces MAE by 15.38%, RMSE by 20.00%, MAPE by 17.39%, HH by 9.52%, GPI by 10.76%, and improves NSE by 6.90%, demonstrating high accuracy. The central tendency prediction errors for the remaining indicators range from 0.63% to 5.73%. This integration of intelligent algorithms and multi-indicator analysis enables precise prediction of water inrush precursors, offering a new technical framework for roof water hazard prevention. Full article

Deep reinforcement learning (DRL) has been increasingly used in reservoir operation, but several key challenges and limitations need further study. This paper developed a novel and optimal reservoir operation model incorporating inflow forecasts based on DRL and the deterministic policy gradient algorithm. A multi-dimensional reward function was derived from the objective functions and constraints, and an optimal scheduling scheme was established with dynamically weighted reward functions. The observed daily flow data and 5-day inflow forecasts of the Three Gorges Reservoir (TGR) during flood seasons (from 10 June to 31 October) from 2010 to 2025 were used to evaluate the model performance and compared with the actual operation results. The results show that, compared with the actual operation, Scheme-1 with dynamic weights increases annual average flood prevention storage capacity by approximately 36.8%, enhances power generation by about 2.86 billion kW·h (≈5.49%), and reduces spillway waste water volume by around 3.33 billion m³. This study demonstrates that the optimal scheduling model can substantially improve the overall efficiency of reservoir operation, and the improvement is even more pronounced when the reward function weights are set dynamically. Full article

Reservoir release induced flooding is a major downstream hazard worldwide, yet most warning systems rely on hydraulic modeling and underuse real time reservoir operation data. This study presents a data driven framework to detect flood discharge events, assess downstream operational severity, and forecast daily discharges using deep learning. The approach was validated at the Ba Ha hydropower reservoir (Vietnam) with inflow, discharge, water level, and CHIRPS rainfall data to represent basin-scale precipitation forcing. More than 160 discharge events were identified using a composite Operational Severity Index (OSI) based on peak discharge, duration, and rise rate; although only ~2% were extreme, they posed the greatest risks. Among three Transformer-based models, Informer achieved the best short-term forecasting performance (RMSE ≈ 78 m³/s, R² ≈ 0.80), while Autoformer showed greater stability at longer horizons (3–7 days). In contrast, all models exhibited reduced skill under abrupt and extreme discharge conditions. These results demonstrate that combining trend and anomaly-aware modeling enables reliable discharge prediction and severity assessment without complex hydraulic simulations. The proposed framework provides a practical foundation for reservoir early warning systems by transforming routine operational data into actionable flood-risk information. Full article

Accurate runoff forecasting is essential for effective water resource management, hydropower operation, and flood risk mitigation. In this study, daily inflow runoff in the Xin’an River Basin, eastern China, was simulated using four ensemble learning models: Gradient Boosting Decision Tree (GBDT), XGBoost, CatBoost, and Stacking. Among them, the CatBoost model achieved the best performance, with a correlation coefficient (CC) exceeding 0.97, Nash–Sutcliffe efficiency (NSE) above 0.95, and reduced RMSE and MAE compared with the currently operational hydrological model. To extend the forecast lead times, two hydro–meteorological coupled models were developed by integrating the CatBoost model with a single numerical weather prediction model (EC) and a dynamically weighted multi-model ensemble precipitation forecast system (OCF). The coupled models were evaluated for lead times up to 240 h. The forecast skill value was highest within 96 h, with CC values above 0.80 and NSE around 0.50. The OCF-coupled model demonstrated improved reliability for lead times of 48–96 h, whereas the EC-driven forecasts performed better within the first 48 h. Case studies during the 2021–2022 flood seasons confirmed that the coupled framework accurately reproduced flood evolution and peak discharge dynamics, demonstrating its practical value for medium-range runoff forecasting in humid river basins. Full article

Tidal inundation plays a critical role in maintaining the ecosystem services of the Sundarbans mangrove forest. In this study, we configured and calibrated a coupled one-dimensional (1D) river network and two-dimensional (2D) floodplain hydrodynamic model for the Sundarbans in Bangladesh. Model calibration was performed using gauged water levels, inundation maps, and Google Earth (Version 7.3.6) imagery. Using the calibrated model, we assessed potential changes in inundation extent, depth, and duration across the Sundarbans for varying freshwater inflow and tidal height scenarios. Results show variation in inundation extent, depth, and duration spatially and temporarily across the Sundarbans. Inundation is relatively less during February-March (end of the dry season) and high in July-August (mid-wet season). Approximately 3158 km² (85.1%) of the Sundarbans experiences at least one inundation in March, increasing to about 3658 km² (98.6%) in July. Although a large proportion of the Sundarbans inundate during daily tidal cycles, the mean inundation depth remains shallow (0.24 to 0.33 m) due to flat topography. The influence of freshwater inflow on inundations is small (<2%). In contrast, the impacts of tidal magnitude are substantial on both inundation extent and depth. These findings provide valuable insights on inundation dynamics for understanding the hydrological and ecological functioning of the Sundarbans. Full article

Climate change can alter both the amount and timing of inflows to water supply reservoirs while also increasing heat-driven demand and the likelihood of stressful warm-season conditions. Climate-driven changes in inflow to Eagle Mountain Lake Reservoir (Texas, USA) were quantified by integrating (i) a calibrated SWAT model evaluated at four USGS stream gauges, (ii) statistically downscaled CMIP6 daily precipitation and minimum/maximum temperature at seven stations/grid points for a historical baseline (2003–2022) and two future windows (2031–2050 and 2081–2100) under SSP1-2.6, SSP2-4.5, and SSP5-8.5, and (iii) observed reservoir operations (lake level, water supply releases, and flood discharge; 1990–2022). A standard watershed climate workflow is reframed through an operations-focused lens, wherein projected inflow changes are translated into decision-relevant indicators via the utilization of observed thresholds and operating mode signals. Included within this framework are spring refill-season inflow shifts, a hot–dry month metric, and storage threshold performance measures, which are coupled with screening-level probabilities linked to multi-year inflow deficits. Across models and stations, mean annual temperature increases by 0.7–1.9 °C in the 2030s and by 0.7–6.1 °C in the 2080s, while annual precipitation changes remain uncertain (−24% to +55%). Daily projections show a strong increase in extreme heat days (daily Tmax above the historical 95th percentile), from about 18 days yr⁻¹ historically to about 30–33 days yr⁻¹ in the 2030s and about 34–82 days yr⁻¹ by the 2080s. Hot–dry months (monthly mean Tmax above the historical 90th percentile and monthly precipitation below the historical median) increase modestly by mid-century and rise to about 1.5 months yr⁻¹ on average by the 2080s under SSP5-8.5. SWAT simulations indicate that the mean annual inflow declines by 17–20% across scenarios, with the largest reductions during the spring refill period (March–June). Historical operations show that hot–dry months are associated with approximately double the mean water supply release (7.2 vs. 3.5 m³/s) and a lower monthly minimum lake level (about 0.30 m; about 1.0 ft lower on average). Flood discharges occur almost exclusively when lake elevation is at or above about 197.8 m and follow multi-day rainfall clusters (cross-validated AUC = 0.99). Together, these results indicate that earlier-season inflow reductions and more frequent hot–dry stress will tighten the operational margin between refill, summer demand, and flood management, underscoring the need for adaptive drought response triggers and integrated drought–flood planning for the Dallas–Fort Worth region. Full article

Effective reservoir operation demands a careful balance between flood risk mitigation, water supply reliability, and operational stability, particularly under evolving hydrological conditions. This study applies deep reinforcement learning (DRL) models—Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and Deep Deterministic Policy Gradient (DDPG)—to optimize reservoir operations at the Soyang River Dam, South Korea, using 30 years of daily hydrometeorological data (1993–2022). The DRL framework integrates observed and remotely sensed variables such as precipitation, temperature, and soil moisture to guide adaptive storage decisions. Discharge is computed via mass balance, preserving inflow while optimizing system responses. Performance is evaluated using cumulative reward, action stability, and counts of total capacity and flood control violations. PPO achieved the highest cumulative reward and the most stable actions but incurred six flood control violations; DQN recorded one flood control violation, reflecting larger buffers and strong flood control compliance; DDPG provided smooth, intermediate responses with one violation. No model exceeded the total storage capacity. Analyses show a consistent pattern: retain on the rise, moderate the crest, and release on the recession to keep Flood Risk (FR) < 0. During high-inflow days, DRL optimization outperformed observed operation by increasing storage buffers and typically reducing peak discharge, thereby mitigating flood risk. Full article

This study analyzed how external forcings, such as meteorological conditions and inflows, influence the average water surface temperature (WST) of the urban Lake Paranoá, Brasília-Brazil, using both in situ measurements and remote sensing estimates over a 40-year period. The temperature model calibrated for Lake Paranoá with no time lag (0-day delay) presented the following metrics: R² = 0.92, RMSE = 0.59 °C, demonstrating the feasibility of obtaining reliable thermal estimates from remote sensing even in urban water bodies. Simple and multiple regression analyses were applied to identify the main external drivers of WST across different temporal scales. A warming trend of 0.036 °C/yr in lake surface temperature was observed, higher than the concurrent increase in air temperature (0.026 °C/yr), suggesting enhanced thermal stratification that may impact water quality. The most influential variables on WST were air temperature, relative humidity, and wind speed, with varying degrees of influence depending on the time scale considered (daily, monthly, annual or seasonal). Remote sensing proved to be essential for overcoming the limitations of traditional monitoring, such as temporal gaps and limited spatial coverage, and allowed detailed mapping of thermal patterns throughout the lake. Integrating these data into hydrodynamic models enhances their diagnostic, predictive, and decision-support capabilities in the context of climate change. Full article

The impact of climate change on watershed hydrological processes has become increasingly significant, with the frequent occurrence of extreme flood events posing a severe challenge to the water resource security of the upper Yangtze River and the Three Gorges Reservoir. To enhance the understanding of runoff evolution under future climate scenarios, this study focuses on the upper Yangtze River Basin, integrating CMIP6 climate model data with the WRF-Hydro model to systematically assess the effects of climate change on runoff projections. Firstly, using CMFD data as a benchmark, the systematic biases in CMIP6 simulation results were evaluated and corrected. Precipitation and temperature data accuracy were improved through Local Intensity Correction (LOCI) and Daily Bias Correction (DBC). Secondly, a large-scale WRF-Hydro model suitable for the upper Yangtze River was developed and calibrated. Finally, based on the corrected CMIP6 data, the climate and runoff changes under the SSP2-4.5 and SSP5-8.5 scenarios for the period 2021–2050 were projected. The results show that: (1) the corrected CMIP6 data significantly improved issues of overestimated precipitation and underestimated temperature, providing a more realistic reflection of regional climate characteristics; (2) the sub-basin calibration strategy outperformed the overall calibration strategy at key control sites, with high runoff simulation accuracy during the validation period; (3) future temperatures exhibit a continuous rising trend, while precipitation changes are not significant—however, the magnitude and uncertainty of extreme events increase—and (4) under the SSP5-8.5 scenario, the inflow to the Three Gorges Reservoir during the wet season significantly increases, raising flood risk. The findings provide a scientific basis for understanding the hydrological response mechanisms in the upper Yangtze River Basin under climate change and offer decision-making support for flood control scheduling and water resource management at the Three Gorges Reservoir. Full article

In the hydropower sector, accurate estimation of short-term reservoir inflows is an essential element to ensure efficient and safe management of water resources. Short-term forecasting supports the optimization of energy production, prevention of uncontrolled water discharges, planning of equipment maintenance, and adaption of operational strategies. In the absence of data on topography, vegetation, and basin characteristics (required in distributed or semi-distributed models), data-driven approaches can serve as effective alternatives for inflow prediction. This study proposes a novel hybrid approach that reverses the conventional LSTM (Long Short-Term Memory)—ARIMA (Autoregressive Integrated Moving Average) sequence: LSTM is first used to capture nonlinear hydrological patterns, followed by ARIMA to model residual linear trends.The model was calibrated using daily inflow data in the Izvorul Muntelui–Bicaz reservoir in Romania from 2012 to 2020, tested for prediction on the day ahead in a repetitive loop of 365 days corresponding to 2021 and further evaluated through multiple seven-day forecasts randomly selected to cover all 12 months of 2021. For the tested period, the proposed model significantly outperforms the standalone LSTM, increasing the R² from 0.93 to 0.96 and reducing RMSE from 9.74 m³/s to 6.94 m³/s for one-day-ahead forecasting. For multistep forecasting (84 values, randomly selected, 7 per month), the model improves R² from 0.75 to 0.89 and lowers RMSE from 18.56 m³/s to 12.74 m³/s. Thus, the hybrid model offers notable improvements in multi-step forecasting by capturing both seasonal patterns and nonlinear variations in hydrological data. The approach offers a replicable data-driven solution for inflow prediction in reservoirs with limited physical data. Full article

Under the influence of global climate change, water conservancy projects located in the high-latitude cold regions of the world are facing severe challenges. This study addresses the contradiction between water supply stability and ecological flow during the dry season in cold regions. Taking Linhai Reservoir as the core, it integrates the HEC-RAS hydrodynamic model with multi-source data such as basin topography, hydro-meteorological data, and water conservancy project parameters to construct a multi-scenario water supply scheduling model during the dry season. The aim is to provide scientific recommendations for different reservoir operation strategies in response to varying frequencies of upstream inflow, based on simulations conducted after the reservoir’s completion. Taking into account winter runoff reduction characteristics and engineering parameters, we simulated the relationships between water level and flow, ecological flow requirements, and urban water shortages. The results indicate that in both flood and normal years, dynamic coordination of storage and discharge can achieve a daily water supply of 120,000 cubic meters, with 100% compliance for the ecological flow rate. For mild and moderate drought years, additional water diversion becomes necessary to achieve 93.5% and 89% supply reliability, respectively. During severe and extreme droughts, significantly reduced reservoir inflows lower ecological compliance rates, necessitating emergency measures, such as utilizing dead storage capacity and exploring alternative water sources. The study proposes operational strategies tailored to different drought intensities: initiating storage adjustments in September for mild droughts and implementing peak-shifting measures by mid-October for extreme droughts. These approaches enhance storage efficiency and mitigate ice blockage risks. This research supports the water supply security and river ecological health of urban and rural areas in Mudanjiang City and Hailin City and provides a certain scientific reference basis for the multi-objective coordinated operation of reservoirs in the same type of high-latitude cold regions. Full article

Predicting water losses and final storage in reservoirs has become increasingly relevant in the efficient control and optimization of water provided to agriculture, livestock, industry, and domestic consumption, aiming to mitigate the risks associated with flash floods and water crises. This research aims to develop a new Machine Learning (ML) algorithm based on a water balance model to simulate the outflow in the Cuchoquesera reservoir in the Ayacucho region. The method uses TensorFlow (TF), a powerful interface for graphing and time series forecasting, for data analysis of hydrometeorological parameters (HMP), inflow (QE_obs), and outflow (QS_obs) of the reservoir. The ML water balance model is fed, trained, and calibrated with daily HMP, QE_obs, and QS_obs data from the Sunilla station. The results provide monthly forecasts of the simulated outflow (QS_sim), which are validated with QS_obs values, with significant validation indicators: NSE (0.87), NSE-Ln (0.83), Pearson (0.94), R² (0.87), RMSE (0.24), Bias (0.99), RVB (0.01), NPE (0.01), and PBIAS (0.14), with QS_obs being slightly higher than QS_sim. Therefore, it is important to highlight that water losses due to evaporation and infiltration increased significantly between 2019 and 2023. Full article

Reservoir operations play a pivotal role in shaping the flow regime of the Chao Phraya River Basin (CPRB), where two major reservoirs exert substantial hydrological influence. Despite ongoing efforts to manage water resources effectively, current operational strategies often lack the adaptability required to address the compounded uncertainties of climate change and increasing water demands. This research addresses this critical gap by developing an optimization model for reservoir operation that explicitly incorporates climate variability. An Adaptive Neuro-Fuzzy Inference System (ANFIS) was employed using four fundamental inputs: reservoir inflow, storage, rainfall, and water demands. Daily resolution data from 2000 to 2012 were used, with 2005–2012 selected for training due to the inclusion of multiple extreme hydrological events, including the 2011 flood, which enriched the model’s learning capability. The period 2000–2004 was reserved for testing to independently assess model generalizability. Eight types of membership functions (MFs) were tested to determine the most suitable configuration, with the trapezoidal MF selected for its favorable performance. The optimized models achieved Nash-Sutcliffe efficiency (NSE) values of 0.43 and 0.47, R² values of 0.59 and 0.50, and RMSE values of 77.64 and 89.32 for Bhumibol and Sirikit Dams, respectively. The model enables the evaluation of both dam operations and climate change impacts on downstream discharges. Key findings highlight the importance of adaptive reservoir management by identifying optimal water release timings and corresponding daily release-storage ratios. The proposed approach contributes a novel, data-driven framework that enhances decision-making for integrated water resources management under changing climatic conditions. Full article

Accurate reservoir inflow predictions are critical for effective flood control and optimizing hydropower generation, thereby enhancing water resource management. This study introduces an advanced hydrological modeling approach that leverages a basic recurrent neural network (bRNN), convolutional neural network (CNN) with gated recurrent units (GRU) (bRNN-CNN-GRU), GRU with long short-term memory (LSTM) (GRU-LSTM) hybrid models, and deep neural network (DNN) to predict daily reservoir inflow at the Sefid Roud Dam. By utilizing historical data from 2018 to 2024, this study examined the following two multivariate scenarios: one incorporating water parameters such as water level, evaporation, and temperature extremes, and another focused solely on inflow delays. Training and testing sets were created from the dataset, with 80% for training and 20% for testing. For benchmarking purposes, the performance of the bRNN-CNN-GRU was evaluated against a deep neural network (DNN) and a GRU-LSTM hybrid. The evaluation metrics used were root mean square error (RMSE), correlation coefficient (r), and Nash Sutcliffe coefficient (NSE). Results demonstrated that, while all models performed better under the scenario incorporating inflow delays, the bRNN-CNN-GRU model achieved the best performance, with an RMSE of 0.71, r of 0.97, and NSE of 0.95, outperforming both the DNN and GRU-LSTM models. These findings highlight the significant advancements in hydrological modeling and affirm the applicability of the bRNN-CNN-GRU model for improved reservoir management in diverse settings. Full article

The Baltic Sea is an intra-continental marginal sea that is vertically stratified with a strong halocline isolating the saline bottom layer from the brackish surface layer. The surface layer is eutrophic, and abiotic zones lacking oxygen are common in the deeper regions. While freshwater is constantly flowing into the North Sea, oxygen-rich bottom waters can only occasionally enter the Baltic Sea following a special sequence of transient weather conditions. These so-called Major Baltic Inflow events can be monitored via the sea level gradients between the Kattegat and the Western Baltic Sea. Innovative interferometric altimetry from the Surface Water and Ocean Topography (SWOT) mission gave us the first opportunity to directly observe the sea level signal associated with the inflow event in December 2023. Recent high-rate multi-mission nadir altimetry observations support the SWOT findings for scales larger than 50 km. The SWOT observations are compared to the simulations with the regional 3D HBMnoku ocean circulation model operated by the German Federal Maritime and Hydrographic Agency (BSH). The model explains more than 80% of the variance observed by SWOT and up to 90% of the variance observed by the nadir altimeters. However, the north–south gradients of the two datasets differ by about 10% of the overall gradient. Comparisons with tide gauges suggest possible model deficiencies on daily to sub-daily time scales. In addition, the SWOT data have many fine scale structures, such as eddies and fronts, which cannot be adequately modeled. Full article