Search Results (826)

Cyanobacterial blooms in lakes and reservoirs pose significant environmental and public health risks. This paper presents an effective exploration strategy to detect them from Autonomous Surface Vehicles (ASVs) equipped with probes, whose sensing trajectories are optimized by an AI-based planner that considers the 3D spatial-temporal evolution of the cyanobacteria concentration obtained by a multiphysics model. The planner, simultaneously working on the AI decision-making and robotic domains, optimizes the surface displacement of the ASV and the depth of its probe by solving a constrained multi-objective optimization problem that minimizes the mission duration and trajectory length, maximizes the possibilities of the probe to overpass areas with high concentration of cyanobacteria, and satisfies operational constraints (such as ASV velocity or acceleration limits, and obstacle avoidance). The optimization is supported by two well-known versions of the Non-Sorted Generic Algorithm (NSGA-II and NSGA-III) and by encoding the trajectories with spline curves whose number of control points can be fixed, progressively increased, or freely manipulated by the algorithm. The performance of different configurations of the planner is tested against six scenarios obtained from different simulations of the multiphysics model (which couples water dynamics and temperature, light transmission, daily vertical migration of the cyanobacteria and their growth). The statistical analysis of the planner results determines that NSGA-III working with variable-length chromosomes and NSGA-II with the progressive increment of spline points as the best configurations for maximizing cyanobacteria detection, and minimizing mission duration and trajectory length. Full article

This study investigates upper-reservoir dam-axis siting in pumped-storage hydropower projects, where cut–fill balance and construction cost are critical under complex terrain conditions. Existing approaches still rely heavily on manual interpretation or static GIS-based analysis and therefore do not adequately optimize dam-axis geometry or earthwork balance. To address this limitation, we propose an Improved Adaptive Variable Neighborhood Search (IAVNS) algorithm that integrates high-resolution digital elevation model (DEM) data within a two-layer adaptive framework. The inner layer performs staged planar and elevation adjustments through adaptive neighborhood operators, whereas the outer layer conducts fitness-guided subregion migration to strengthen global exploration. Experiments on the Qiannan pumped-storage project show that IAVNS obtains layouts with improved cut–fill balance. In the 30-run benchmark comparison, IAVNS achieved a mean CFR of 1.31, which is close to, although slightly above, the upper bound of the adopted earthwork-balance reference interval. In the separate 20-run case-study analysis, the average storage-volume deviation was 0.13%, with run-level deviations ranging from $-1.39\%$ to $1.16\%$. In benchmark comparisons, IAVNS improves solution quality by 22.8% relative to the Genetic Algorithm (GA) and by 16.5% relative to classical Variable Neighborhood Search (VNS), while reducing convergence time by 49.5% and 27.4%, respectively. Sensitivity analysis further suggests that the framework remains locally robust under practically reasonable parameter perturbations, and the module-level ablation study indicates that the observed performance gains arise mainly from the problem-tailored search mechanisms for dam-axis siting rather than from a generic combination of metaheuristic components. Taken together, the case-study results, repeated-run comparison, sensitivity analysis, and ablation study support the use of IAVNS as a geometry-oriented decision-support framework for preliminary dam-axis design in terrain-sensitive hydraulic engineering applications. Full article

Assessing environmental flows downstream of reservoirs under changing climate and increasing water demand remains a critical challenge in catchment management. This study presents an integrated framework for optimizing environmental flow releases by explicitly linking reservoir operation with climate change and population growth. The key novelty lies in the development of a modified objective function that incorporates environmental flow requirements alongside evolving hydrological and demand conditions. Reservoir inflows were simulated using an artificial intelligence-based rainfall–runoff model, employing a neuro-fuzzy inference system to capture nonlinear relationships between climate variables and runoff. Future rainfall projections were derived from four general circulation models (ACCESS1.0, CanESM2, MIROC5, and NorESM-M1) across four-time horizons (2021–2040, 2041–2060, 2061–2080, and 2081–2100). The simulated inflows were coupled with a reservoir operation model to optimize environmental flow releases, with system performance evaluated using reliability and vulnerability metrics. Results show that climate change alone has a limited impact on environmental flow supply; however, when combined with population-driven increases in water demand, significant reductions in system performance occur. In the worst-case scenario, the reliability of meeting environmental flow requirements drops below 20%, accompanied by a marked increase in system vulnerability. These findings demonstrate that water demand pressures play a dominant role in shaping future environmental flow availability. The proposed framework provides a robust and adaptable approach for integrating hydrological variability and socio-economic drivers into reservoir management, supporting more informed decision-making for balancing water supply and ecosystem sustainability under future uncertainty. Full article

Hydraulic fracturing is a key technology for the commercial exploitation of deep shale gas reservoirs, and accurate prediction of rock-mechanical parameters is essential for optimizing these operations. Conventional approaches primarily rely on empirical formulas based on longitudinal and transverse wave velocities; however, obtaining transverse wave data is challenging, and these formulas often lack accuracy. Conventional machine learning algorithms also exhibit limited predictive performance and generalization due to the intrinsic heterogeneity of rock-mechanical data. Therefore, to address the extreme heterogeneity and complex nonlinear logging responses inherent in deep shale gas reservoirs in the Zigong (ZG) block, this study proposes a geology-tailored deep learning framework, CNN-BiGRU-AT. Unlike generic machine learning applications, this architecture is specifically designed to decode complex stratigraphic signals: the convolutional neural network (CNN) module extracts multi-scale spatial features to capture abrupt lithological transitions; the bidirectional gated recurrent units (BiGRUs) analyzes the continuous depth-sequential dependencies of overlying and underlying strata; and the attention mechanism (AT) dynamically regulates the weight allocation of critical input geophysical parameters, thereby delivering a geophysically informative and highly robust predictive performance. This paper employs the CNN-BiGRU-AT model to predict the Brittleness index (BI), using the ZG block as an example. The results demonstrate that the coefficient of determination (R²) for the brittleness index on the test dataset achieved 0.969, representing a 12% improvement over conventional models. The high accuracy of this model satisfies the precision requirements for predicting rock-mechanical parameters, thereby offering reliable theoretical support for optimizing hydraulic fracturing operations in deep shale gas reservoirs. Full article

Supercritical carbon dioxide (SC-CO₂) fracturing has emerged as an environmentally friendly alternative to conventional water-based hydraulic fracturing; however, its inherently low viscosity restricts proppant-carrying efficiency and reduces fracture conductivity. To address this limitation, this study systematically investigates the rheological behavior and sand-carrying mechanisms of CO₂ dry fracturing fluid under various thermodynamic and compositional conditions. Rheological measurements were conducted to evaluate the effects of thickener concentration, temperature, and pressure on viscosity, while visualized experiments were performed to examine the influence of injection rate, sand ratio, thickener concentration, and temperature on proppant migration and deposition. A numerical model developed in Fluent was further employed to simulate the temporal evolution of proppant transport within the fracture. The results show that higher thickener concentrations and injection rates significantly enhance proppant transport distance and uniformity, whereas elevated temperature and sand ratio promote localized settling. The simulation results agree well with the experimental observations, validating the model’s reliability. This study elucidates the coupled effects of rheology and operating parameters on CO₂ dry fracturing behavior and provides theoretical and experimental guidance for optimizing CO₂-based fracturing fluids in low-permeability reservoirs. Full article

Dominant flow channels formed during the late stages of waterflooding can severely reduce sweep efficiency and intensify ineffective interwell circulation. Conventional identification approaches, including tracer testing, well testing, and numerical simulation, often suffer from high operational cost, long execution time, or limited adaptability to heterogeneous interwell connectivity. Although ant colony optimization (ACO) is suitable for path-search problems in reservoir networks, its performance depends strongly on hyperparameter settings, and sample-by-sample parameter tuning introduces substantial online computational overhead. This study proposes a structure-informed GIN–ACO framework for adaptive dominant flow channel identification in connection-element reservoir graphs. A physics-constrained benchmark model is first established using Darcy’s law and the connection element method to provide reference flow paths. A geometry-based surrogate model is then developed to approximate flow splitting coefficients efficiently while preserving the main physical trends. Based on graph topology and geometric descriptors, a graph isomorphism network is trained to predict task-specific ACO parameters, replacing iterative online search with direct parameter inference. Experiments on 1000 synthetic reservoir graphs show that the proposed method achieves a 100% success rate with an average online computation time of 143.5 ms, outperforming fixed-parameter ACO, PSO-ACO, and BO-ACO. On 20 semi-realistic SPE10 reservoir models, GIN–ACO achieves a success rate of 92 ± 1% with an average runtime of 160.3 ± 5 ms. Ablation studies further confirm that graph-structure learning, combined topology–geometry features, and GIN-based parameter prediction are essential for robust performance. The proposed framework provides a promising and computationally efficient route for structure-aware dominant channel identification in connection-element reservoir models. Full article

A large number of reservoirs (or hydropower plants) have been constructed for flood control and energy production in the past several decades in the Yangtze River basin in China. The conventional scheduling rule curves (Scheme A) were designed in the reservoir construction period and did not consider river flow alternation, which needs to be modified to increase comprehensive benefits in the reservoir operation period. In this study, six large-scale cascade reservoirs or mega hydropower systems constructed and operated by the China Yangtze Three Gorges Corporation were selected for this case study. The current joint scheduling plans of cascade reservoirs (Scheme B) were introduced, and a joint scheduling and multi-objective coordinating operation model (Scheme C) was proposed for this mega hydropower system. The Gaussian radial basis functions (GRBFs) were used to fit operation policies of each reservoir, and the Borg multi-objective evolutionary algorithm was selected to optimize three-objective functions for Scheme C. The observed daily flow data series at main hydrometric stations from 2003 to 2025 were used to simulate and compare different operation scheduling schemes. The results show that the performance of joint scheduling of cascade reservoirs (both Schemes B and C) is much better than the single-reservoir scheduling (Schemes A) with overall benefit; Scheme C-best achieves a comprehensive target of decreasing average annual spillway wastewater by 12.82 billion m³ (or a decrease of 28.5%), increasing average annual power generation by 31.02 billion kWh (or an increase of 10.7%), and improving average annual impoundment efficiency rate by 5.0%. The GRBFs can fit reservoir operation policies well, while the Borg multi-objective evolutionary algorithm can quickly converge with high-precision non-dominated solution sets. The proposed joint scheduling and multi-objective coordinating operation model will provide a scientific basis for achieving maximum benefits in flood protection and hydropower generation for the mega hydropower system. Full article

To overcome the rapid expansion of the drawdown cone, severe inter-well interference, and high operating costs caused by independent geothermal well operation, this study investigated the coordinated optimal scheduling of geothermal water extraction. Fifteen geothermal production wells in the main urban area of Kaifeng City were selected as the study case. The intake intervals of these wells are located at depths of 1020 to 1330 m. Based on the exploitable yield of the geothermal reservoir, user water demand, and well layout, a management model for coordinated scheduling was developed. Design drawdown, water demand, and heating capacity were used as constraints. The objectives were to minimize operating cost, nodal drawdown, and drawdown interference between wells. The results from several optimization algorithms show that the improved Cheetah Optimization Algorithm converged faster and produced more consistent solutions. Compared with the preoptimization scheme, the optimized scheme reduced total operating cost by 31.64%, total drawdown in the study area by 69.5%, and the sum of inter-well drawdown interference by 34.7%. This study provides useful support for selecting efficient optimization algorithms and offers a basis for the scientific development, utilization, and protection of geothermal water resources. Full article

Coal-mine-gas-monitoring data exhibits missing phenomena due to the harsh underground operating environment. Accurate imputation of missing values in gas-monitoring sequences serves as a key data foundation for guaranteeing the continuity of gas data, enhancing the reliability of disaster early warning, and improving the accuracy of mine safety situation analysis and judgment. Aiming at the prevalent random and segmented missing issues in coal-mine-gas-monitoring time-series data, and the limitation that existing imputation methods struggle to accurately capture the nonlinear spatiotemporal correlations and long-range temporal dependencies of such data, this study proposes a missing data imputation method for coal mine gas time-series data based on the Spatio-Temporal Graph Attention Network—Echo State Network (ST-GAT-ESN). Firstly, this method extracts temporal features of the gas concentration sequence using a Gated Recurrent Unit (GRU). Subsequently, it models multiple monitoring points as graph nodes through a Graph Attention Network (GAT), constructs an adjacency matrix based on airflow propagation relationships, and adaptively learns the spatial dependency weights between monitoring points to realize the deep fusion of spatiotemporal features. Finally, it designs a dual-channel Echo State Network (ESN), synchronously inputs the spatiotemporal fusion features of the missing regions before and after, efficiently fits the nonlinear evolutionary trend of the data by virtue of the echo state property of the reservoir, and solves the output layer weights through ridge regression to achieve accurate imputation of missing values. Experimental results demonstrate that, compared with the single-ST-GAT-ESN, ESN, and ARIMA models, the proposed method achieves the optimal imputation performance in both random and segmented missing scenarios within the missing rate range of 5–50%. The three evaluation metrics—Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE)—are reduced by 30–80% compared with the benchmark models. Moreover, the imputation curve achieves the best fitting performance with the ground-truth curve at a 50% segmented missing rate. This study confirms that the ST-GAT-ESN model effectively enhances the adaptability and robustness to complex missing patterns via spatiotemporal collaborative modeling and a dual-channel fusion mechanism, providing a high-precision and highly stable technical solution for ensuring the integrity of coal-mine-gas-monitoring data, and also provides theoretical references and engineering insights for the missing-value processing of industrial time-series monitoring data. Full article

Accurate production forecasting of oil wells is of great significance for reservoir management, production optimization, and investment decisions. However, complex subsurface dynamics and sudden operational interventions frequently break the temporal symmetry of production sequences, generating highly asymmetric data distributions. Standard deep sequence architectures often suffer from severe phase lag and limited adaptability when modeling such asymmetric regime transitions. To resolve these bottlenecks, we introduce the Signature-Weighted Kolmogorov–Arnold Network with Gated Recurrent Units (SigKAN-GRU). The architecture replaces static node activations with adaptive edge–spline mappings, enabling robust approximation of asymmetric nonlinearities. Path signatures compress high-order asymmetric temporal trajectories into invariant geometric features, a learnable gating kernel filters critical variations, and a final GRU layer enforces explicit sequential memory. This integration bridges long-term depletion trends with abrupt asymmetrical perturbations while maintaining structurally controlled complexity and an interpretable decomposition of nonlinear response and temporal weighting. Validated on two real-world wells with contrasting data characteristics, SigKAN-GRU consistently minimizes absolute error metrics and phase distortions against prevailing baselines. In addition, event-sensitive evaluations further confirm its reliability in peak regions and abrupt shock intervals. The resulting framework translates erratic historical data into robust deterministic forecasts, offering a rigorous quantitative tool for field-level reservoir optimization. Full article

At the Second Water Intake Pump Station of the Chenhang Reservoir in Shanghai, suboptimal pump scheduling resulted in electricity consumption cost attributable to pump-motor equipment accounting for an exceptionally large proportion of the total power expenditure. In response to the economical operation issues, a mathematical model of power consumption cost for the pump station was established by introducing time-of-use electricity pricing and constraint suppression terms. Taking the minimum cost as the research objective, the differential evolution (DE) algorithm was employed to establish a fitness function for electricity cost, aiming to find the most economical and reliable scheduling strategy. However, owing to its low computational speed and high complexity, machine learning was introduced to establish neural network surrogate models of the DE algorithm. By comparing three surrogate models, the Multilayer Perceptron (MLP) neural network model was adopted as the most appropriate surrogate model. It was optimized for robustness improvement and verified on site. The results demonstrate that implementing the surrogate model achieves over 25% savings in electricity cost per thousand cubic meters of water, while slashing the solution time by 88.53% compared to the standard DE algorithm. Furthermore, the overall power consumption is reduced by 2.20% under a cost-priority strategy and by 15.89% under a power-priority strategy, thereby directly mitigating the carbon footprint of the pump station. The proposed hybrid computational framework in this study bridges the gap between the computationally expensive heuristic optimization and the strict real-time control requirements in engineering, highlighting its significant contribution to the sustainable and low-carbon operation of water infrastructure. Full article

Metaheuristic algorithms can fail to balance global exploration and local exploitation, occasionally becoming trapped in suboptimal regions on highly multimodal problems. The Groupers and Moray Eels (GME) algorithm, inspired by the associative hunting strategies of marine predators, provides a cooperative optimization framework. However, the sequential interaction phases of GME can fail to maintain diverse topological coverage across heavily constrained landscapes. To address these limitations, we propose an enhanced variant, GPS-CC-GME. The approach improves the initial agent distribution by deploying a number-theoretic Good Point Set (GPS) generation protocol to establish a uniformly dispersed starting space. In addition, algorithmic stagnation is addressed through a dual-crossover search architecture. A horizontal crossover stage enforces information sharing among randomized agents to sustain global diversity, and a vertical crossover phase isolates specific dimensional vectors within individual agents for localized fine-tuning. We evaluated the proposed model on the CEC2017 benchmark suite, where it secured the highest overall ranking compared to the baseline GME and several standard metaheuristics. GPS-CC-GME was then applied to a high-dimensional optimization scenario for petroleum reservoir production. The algorithm yielded higher Net Present Value (NPV) metrics than the canonical framework. The results indicate that embedding deterministic initialization and bidirectional mutation operators into multipredator models can improve search outcomes in non-linear engineering tasks. Full article

The capacitance resistance model (CRM) is an analytical tool widely used to forecast reservoir performance in enhanced oil recovery (EOR) methods. By representing flow dynamics and the connectivity between injection and production wells through the parameter of interwell connectivity, CRM offers fast computational processing and minimal input data requirements. These advantages make CRM a practical alternative for rapid reservoir analysis, especially when full-scale numerical simulations are infeasible due to time and budget constraints. CRM, rooted in material balance and productivity equations, uses injection/production rates and bottom-hole pressure data to construct reservoir models through optimization techniques, which can then be combined with oil fractional flow models for predictive purposes. Initially designed for waterflooding operations, CRM has seen limited but promising applications in gas injection projects, where research remains incomplete. This study presents a new formulation of CRM tailored for immiscible gas injection, incorporating the pseudo-pressure concept coupled with a saturation profile. The pseudo-pressure concept is a mathematical transformation that linearizes gas flow equations by accounting for variations in gas compressibility and viscosity with pressure. The proposed CRM was evaluated using a PUNQ-S3 benchmark reservoir model in the CMG IMEX black oil simulator, involving two injectors and four producers. History- matching results for fluid production rates showed that the newly developed CRM achieved the lowest NRMSE, outperforming other CRM models across a wide range of reservoir properties. Sensitivity analyses were conducted to examine the effects of gas and oil PVT properties on the model’s performance. The newly developed CRM, incorporating the pseudo-pressure concept and saturation profiles, demonstrates superior performance in predicting fluid production rates, achieving an average NRMSE of 15.3% in a base case scenario, compared to other tested CRM models. Additionally, the sensitivity analysis on the effect of fluid properties shows that higher gas viscosity, lower gas formation volume factor, and increasing oil API gravity improve the CRM model’s performance, and under all tested conditions the newly developed CRM provides the most accurate production history match. This study not only establishes the new CRM as a robust and accurate predictive tool for immiscible gas injection but also provides a comprehensive discussion on reservoir parameter ranges and model limitations, advancing the applicability of CRM in EOR processes. Full article

When a pumped storage power station utilizes its upper reservoir to store energy from a photovoltaic power plant, it often operates during periods of higher ambient temperatures. Under these conditions, the concrete panels in the upper reservoir are also hotter. The subsequent rise in the reservoir’s water level introduces a rapid temperature change and dry–wet cycles to the concrete panels, which can easily degrade the performance of these panels. While research has investigated the impact of conventional dry–wet cycles on concrete performance, studies on the effects of these cycles under variable temperatures have not yet been reported. Therefore, we conducted an optimized experimental study on variable-temperature dry–wet cycling processes, with dry:wet time ratios set at 3 h:3 h, 6 h:6 h, and 12 h:12 h. The results indicate that, after 200 cycles, the compressive strength loss rate of the concrete is three times that observed under conventional dry–wet cycles. Specifically, concrete subjected to the three tested dry:wet time ratios exhibits strength reductions of 11.25%, 22.52%, and 26.45%, respectively. When the ratio reaches 6 h:6 h, further increasing the drying and immersion times results in a similar gradual degradation effect on the strength of hydraulic concrete. Therefore, considering the time cost, a 6 h:6 h dry:wet cycle can be adopted. Full article

The efficient development of low-permeability reservoirs is critically constrained by severe geological heterogeneity, marginal permeability (<10 mD), and the consequent prevalence of low-productivity wells. Conventional intermittent production management, reliant on empirical fixed-cycle schedules, fails to adapt to dynamic reservoir behavior and wellbore conditions, leading to suboptimal energy efficiency and recovery. This study presents a physics-constrained, data-driven framework for adaptive intermittent production optimization, specifically designed to address the coupled geological-engineering complexities of such reservoirs. The methodology integrates three core innovations: (1) a hybrid flowing bottomhole pressure (FBHP) decline model coupling a “Three-Segment” wellbore pressure calculation with inflow performance relationship (IPR) curves, enabling dynamic characterization of pressure depletion; (2) a shut-in pressure buildup prediction framework combining a physically interpretable dual-exponential recovery mechanism—representing near-wellbore elastic expansion and far-field formation recharge—with a Random Forest Regression algorithm to capture the influence of geological and operational heterogeneity; and (3) a “Dual-Curve Intersection Method” that autonomously determines optimal pumping and shut-in durations by intersecting predicted pressure decline and recovery curves under geological constraints. Field implementation on 15 low-production wells in the Jiyuan Oilfield—a representative low-permeability asset—demonstrated robust performance: average pump efficiency improved from 14.3% to 14.49%, and average single-well electricity savings reached 15.61%. This work establishes a closed-loop intelligent control framework that bridges reservoir geology, wellbore hydraulics, and machine learning, offering a scalable solution for enhancing energy efficiency and production sustainability in low-permeability and unconventional resources. Full article