Search Results (831)

Conventional material balance methods, typically based on single- or dual-porosity models solvable via single-step linearization, are inadequate for hydraulically fractured shale oil reservoirs due to their pronounced heterogeneity and contrasting interzonal connectivity. Specifically, dual-zone models fail to represent the realistic characteristics of shale oil reservoirs because they treat artificially created hydraulic fractures and natural fractures as equivalent, despite their substantially different properties. To address this gap, this paper proposes a novel three-zone conceptual model, segmenting the reservoir into the matrix zone (MZ), the Weakly Stimulated Zone (WSZ, low-conductivity zone), and the Strongly Stimulated Zone (SSZ, high-conductivity zone). A corresponding three-zone gas injection replenishment material balance model is developed. This model explicitly captures interactions between injected gas and formation fluids and incorporates dynamic variations in pore volume and fluid saturation induced by imbibition. To solve the complexities introduced by the triple-porosity system, a dedicated two-step linearization solution procedure is proposed. Utilizing conventional production performance and basic PVT data, the method enables simultaneous estimation of zone-specific developed reserves and prediction of the Estimated Ultimate Recovery (EUR) through a least squares algorithm. Validation against actual well cases and multi-well statistics confirms that the method provides stable and reliable zonal reserve characterization and EUR forecasting. The results indicate that the MZ contributes the majority of the geological reserves, accounting for >70%. The WSZ contributes approximately 29.5% of the reserves and serves as the primary source for energy replenishment in the shale oil reservoir. In contrast, the SSZ contributes less than 0.5% of the reserves but acts as the dominant channel for flow convergence, controlling the main fluid production pathways. The proposed framework not only offers a practical tool for refined reserve assessment in shale oil reservoirs but also provides a computational basis and decision support for the design and injection parameter optimization of pre-pad CO₂ energy storage fracturing schemes. Full article

In this work, we use an Echo State Network (ESN) model, which is essentially a recurrent neural network (RNN) operating according to the reservoir computing (RC) paradigm, to classify individual ECG heartbeats using the MIT-BIH arrhythmia database. The aim is to evaluate the performance of ESN in a challenging task that involves classification of complex, unprocessed one-dimensional signals, distributed into five classes. Moreover, we investigate the performance of the ESN in the presence of (i) noise in the dynamics of the internal variables of the hidden (reservoir) layer and (ii) random variability in the activation functions of the hidden layer cells (neurons). The overall accuracy of the best-performing ESN, without noise and variability, exceeded 96% with per-class accuracies ranging from 90.2% to 99.1%, which is higher than previous studies using CNNs and more complex machine learning approaches. The top-performing ESN required only 40 min of training on a CPU (Intel i5-1235U@1.3 GHz) HP laptop. Notably, an alternative ESN configuration that matched the accuracy of a prior CNN-based study (93.4%) required only 6 min of training, whereas a CNN would typically require an estimated training time of 2–3 days. Surprisingly, ESN performance proved to be very robust when Gaussian noise was added to the dynamics of the reservoir hidden variables, even for high noise amplitudes. Moreover, the success rates remained essentially the same when random variability was imposed in the activation functions of the hidden layer cells. The stability of ESN performance under noisy conditions and random variability in the hidden layer (reservoir) cells demonstrates the potential of analog hardware implementations of ESNs to be robust in time-series classification tasks. Full article

Reservoir computing (RC) has emerged as an energy-efficient paradigm for temporal information processing, offering reduced training complexity by fixing recurrent dynamics and training only a simple readout layer. Among RC models, Echo State Networks (ESNs) and Liquid State Machines (LSMs) represent two distinct approaches based on continuous-valued and spiking neural dynamics, respectively. In this work, we present a comparative evaluation of ESNs and LSMs on the Mackey–Glass chaotic time-series prediction task, with emphasis on scalability, overfitting behavior, and robustness to reduced numerical error precision. Experimental results show that ESNs achieve lower prediction error with relatively small reservoirs but exhibit early performance saturation and signs of overfitting as reservoir size increases. In contrast, LSMs demonstrate more consistent generalization with increasing reservoir size and maintain stable performance under aggressive reservoir quantization. These findings highlight fundamental trade-offs between accuracy and hardware efficiency, and suggest that spiking RC models are well suited for energy-constrained and neuromorphic computing applications. Full article

The presence of shallow gas or overlying gas reservoirs often degrades the imaging accuracy of underlying structural formations. To address the “pull-down” effect of deep structural reflectors caused by low-velocity shallow gas anomalies, this study takes the X Gas Field in the Pearl River Mouth Basin as an example. By using spectral attenuation attributes, we finely characterize the planar distribution and temporal thickness of the shallow gas. On this basis, a shallow gas anomaly thickness correction method is established. This approach integrates the temporal thickness of shallow gas (derived from spectral attenuation), characteristics of the seismic velocity field, and velocity differences calibrated by well logs to compute specific depth correction values. Application results, validated through blind well tests, show that the accuracy of the structural map can be improved to within 5 m. This multi-data integration strategy, which combines lateral velocity variation with vertical correction, offers a valuable reference for the detailed characterization of hydrocarbon reservoirs under similar geological conditions. Full article

Horizontal well fracturing serves as a critical technology for enhancing production from tight sandstone gas reservoirs, where accurate prediction of formation breakdown pressure is essential for optimizing fracture design and improving stimulation effectiveness. This study proposes a novel fusion-driven workflow for predicting breakdown pressure in horizontal wells by synergistically integrating physics-based mechanistic modeling with data-driven machine learning. The approach overcomes the computational limitations of conventional analytical models and mitigates the data scarcity constraints inherent in purely empirical methods by using high-fidelity mechanistic simulations to generate physically consistent training samples. Results demonstrate that the hybrid dataset, with an optimal fusion ratio of 1:1.5 between field data and mechanistic-derived samples, yields the highest predictive accuracy. The proposed model, built on an XGBoost algorithm whose hyperparameters are efficiently optimized via a tree-structured Parzen estimator (TPE), exhibits superior generalization capability and robustness, achieving an average prediction error of 7.45% on unseen well data. This work confirms that the fusion framework provides a reliable and practical tool for breakdown pressure prediction in cased horizontal wells, which can directly support the design and implementation of efficient and sustainable fracturing operations in tight gas reservoirs. Full article

The advancement of Industry 5.0 hinges on the deep integration of artificial intelligence (AI) with domain expertise to foster sustainable industrial development. This study proposes a deep learning-based surrogate modeling framework that integrates reservoir production requirements with AI technologies, providing intelligent decision support for production optimization and enhanced efficiency. To evaluate AI’s effectiveness in complex industrial scenarios, we conduct an integrated analysis encompassing model construction, dynamic prediction, and production optimization using a real-world oilfield case. This oilfield features a dynamically increasing number of wells and requires dynamic adjustments to injection–production relationships. To address this challenge, we enhance the Embed-to-Control model by improving the nonlinear representation capability within its decoder structure. Subsequently, we construct a high-fidelity dataset containing 300 samples for model training and testing. The experimental results demonstrate that the proposed improved model achieves a high accuracy in predicting key state variables (pressure and saturation) and oil production. Regarding computational efficiency, a single model run requires only approximately 17.3 s, achieving an over 200× speedup relative to traditional numerical simulators. Finally, we coupled the trained surrogate model with the particle swarm optimization algorithm to optimize the injection well control strategy. The optimized scheme increases daily oil production by 13.84%, boosting economic benefits. This study demonstrates a practical technological pathway to accelerate the oil and gas industry’s transition toward Industry 5.0. Full article

Dry gas reservoirs play a pivotal transitional role in meeting the net-zero target worldwide. Accurate modelling and simulation of this energy source require fast and reliable prediction of the gas compressibility factor (Z-factor). The experimental measurements of Z-factor are the most reliable source; however, they are expensive and time-consuming. This makes developing accurate predictive models essential. Traditional methods, such as empirical correlations and Equations of States (EoSs), often lack accuracy and computational efficiency. This study aims to address these limitations by leveraging the predictive power of machine learning (ML) techniques. Hence in this study three ML models of Artificial Neural Network (ANN), Group Method of Data Handling (GMDH), and Genetic Programming (GP) were developed. These models were trained on a comprehensive dataset comprising 1079 samples where pseudo-reduced pressure (Ppr) and pseudo-reduced temperature (Tpr) served as input and experimentally measured Z-factors as output. The performance of the developed ML models was benchmarked against two cubic EoSs of Peng–Robinson (PR) and van der Waals (vdW), and two semi-empirical correlations of Dranchuk-Abou-Kassem (DAK) and Hall and Yarborough (HY), and recent developed ML based models, using statistical metrics of Mean Squared Error (MSE), coefficient of determination (R²), and Average Absolute Relative Deviation Percentage (AARD%). The proposed ANN model reduces average prediction error by approximately 70% relative to the PR equation of state and by over 35% compared with the DAK correlation, while maintaining robust performance across the full Ppr and Tpr of dry gas systems. Additionally paired t-tests and Wilcoxon signed-rank tests performed on the ML results confirmed that the ANN model achieved statistically significant improvements over the other models. Moreover, two physical equations using the white-box models of GMDH and GP were proposed as a function of Ppr and Tpr for prediction of the dry gas Z-factor. The sensitivity analysis of the data shows that the Ppr has the highest positive effect of 88% on Z-factor while Tpr has a moderate effect of 12%. This study presents the first unified, statistically validated comparison of ANN, GMDH, and GP models for accurate and interpretable Z-factor prediction. The developed models can be used as an alternative tool to bridge the limitation of cubic EoSs and limited accuracy and applicability of empirical models. Full article

Restoring longitudinal connectivity at small dams remains a significant challenge due to fluctuating reservoir levels that render traditional fish passes ineffective, this research focuses on the implementation of ecological flow, knowing that to this date, no passages in Romania have been designed to meet the bio-hydraulic conditions for longitudinal connectivity for a wide range of flows transiting through the passage. The proposed technical fish pass incorporates side valves that are individually operable to regulate water inflow across varying reservoir levels, thereby overcoming a significant drawback of conventional designs. A three-dimensional numerical model was developed using Computational Fluid Dynamics (CFD) to analyze the velocity fields and flow patterns within the basins under variable ecological flow regimes. To validate the numerical findings, an experimental investigation was conducted on a 1:10 scale physical model. The design’s primary objective is to ensure the passage remains functional despite fluctuating reservoir levels, offering a comprehensive and efficient solution for modern ecological flow management. Results indicate stable velocity profiles on the vertical slots, with values of approximately 1.1 m/s for the high-water regime and 0.85 m/s for the medium one, ensuring hydraulic conditions compatible with the swimming capacity of the targeted species. The results demonstrate that the proposed design effectively prevents high-pressure currents, ensuring a free surface flow suitable for ichthyofauna migration. Full article

Monolayer ${\mathrm{MoS}}_2$ memtransistors offer gate-tunable hysteresis for neuromorphic reservoir computing, yet the role of operating window and fading-memory dynamics in CVD devices remains underexplored. We grow CVD monolayer ${\mathrm{MoS}}_2$, fabricate back-gated memtransistors, and use a single device as a time-multiplexed reservoir node for one-step Lorenz-63 prediction. Mobility, ON/OFF, hysteresis, and drift are quantified to identify stable, tunable bias regimes. We used a transistor with field-effect mobility on the order of $10 {\mathrm{cm}}^2 {\mathrm{V}}^{-1} {\mathrm{s}}^{-1}$, an ON/OFF ratio above ${10}^5$, and a moderate hysteresis window quantified by $H\approx 2.1 \mathsf{\mu }$A·V at $V_{\mathrm{DS}} = 50$ mV and $H\approx 17 \mathsf{\mu }$A·V at $V_{\mathrm{DS}} = 500$ mV over $V_{\mathrm{GS}}\in [-10,30]$ V. Performance is bias/memory-limited rather than FET-metric-limited. Sweeping gate-window and reservoir hyperparameters shows an optimum at intermediate hysteresis with moderate drift. Performance improves when the input clock matches the fading-memory time, achieving normalized root mean square error (NRMSE) = 0.09 for one-step Lorenz-63 x-prediction. Device-level statistics (discussed in the main text) show that, despite substantial scattering in electrical parameters, the resulting device-to-device NRMSE variation remains very small under fixed operating conditions. Classical FET metrics are not limiting here; NRMSE improvement instead requires engineering the hysteresis spectrum and gate stack. The demonstration of Lorenz-63 prediction using CVD-grown monolayer ${\mathrm{MoS}}_2$ memtransistors highlights their potential as a wafer-scalable platform for compact chaotic time-series predictions. Full article

Digital transformation in water conservancy and urban water utilities demands perception systems that are accurate, fast, and energy-efficient and maintainable over long service lifecycles at the edge. We present HydroSNN, a neuromorphic computer-vision framework that couples an event-driven sensing pipeline with a spiking-transformer backbone to support monitoring of canals, reservoirs, treatment plants, and buried pipeline networks. By reducing always-on compute and unnecessary data movement, HydroSNN targets sustainability goals in smart water infrastructure: lower operational energy use, fewer site visits, and improved resilience under harsh illumination and weather. HydroSNN introduces three novel components: (i) spiking temporal tokenization (STT), which converts asynchronous events and optional frames into latency-aware spike tokens while preserving motion cues relevant to hydraulics; (ii) physics-guided spiking attention (PGSA), which injects lightweight mass-conservation/continuity constraints into attention weights via a differentiable regularizer to suppress physically implausible interactions; and (iii) cross-modal self-supervision (CM-SSL), which aligns RGB frames, event streams, and low-cost acoustic/vibration traces using masked prediction to reduce annotation requirements. We evaluate HydroSNN on public water-surface and event-vision benchmarks (MaSTr1325, SeaDronesSee, DSEC, MVSEC, DAVIS, and DDD20) and report accuracy, latency, and an operation-based energy proxy. HydroSNN improves mIoU/F1 over strong CNN/ViT baselines while reducing end-to-end latency and the estimated energy proxy in event-driven settings. These efficiency gains are practically relevant for off-grid or power-constrained deployments and support sustainable development by enabling continuous, low-power monitoring and timely anomaly response. These results demonstrate that event-driven spiking vision, augmented with simple physics guidance, offers a practical and efficient solution for resilient perception in smart water infrastructure. Full article

This study introduces a mathematical framework for analyzing unsteady gas filtration in porous media with pressure-dependent porosity variations. The physical process is formulated as a nonlinear parabolic boundary value problem that captures the coupled interaction between pressure evolution and porosity changes during gas production. To solve the equation, a numerical strategy is developed by integrating the Alternating Direction Implicit (ADI) scheme with quasi-linearization iterations, employing finite difference discretization on a two-dimensional spatial grid. Extensive computational experiments are performed to investigate the influence of key reservoir parameters—including porosity coefficient, permeability, gas viscosity, and well production rate—on the spatiotemporal behavior of pressure and porosity during long-term extraction. The results indicate significant porosity variations near the wellbore driven by local pressure depletion, reflecting strong sensitivity of the system to formation properties. The validated numerical model provides valuable quantitative insights for optimizing reservoir management and improving production forecasting in gas field development. Overall, the proposed methodology serves as a practical tool for oil and gas engineers to assess long-term reservoir performance under diverse operational conditions and to design efficient extraction strategies that incorporate pressure-dependent formation property changes. Full article

We develop a digitization-based analysis workflow for characterizing the entropy and correlation structure of truncated bosonic quantum fields after embedding them into small qubit registers, and illustrate it on the steady state of a coherently pumped micromaser. The cavity field is truncated to 32 Fock levels and embedded into a five-qubit register via a Gray-code mapping of photon number to computational basis states, with binary encoding used as a benchmark. On this register we compute reduced entropies, mutual informations, bipartite negativities and Coffman–Kundu–Wootters three-tangles for all qubit pairs and triplets, and use the resulting patterns to define information graphs. The micromaser Liouvillian naturally supports trapping manifolds in Fock space, whose structure depends on the choice of interaction angle and on thermal coupling to the reservoir. We show that these manifolds leave a clear imprint on the digitized information graph: multi-block trapping configurations induce sparse, banded patterns dominated by a few two-qubit links, while trapping on a single 32-dimensional manifold or coupling to a thermally populated cavity leads to more delocalized and collectively shared correlations. The entropy and mutual-information profiles of the register provide a complementary view on how energy and information are distributed across qubits in different parameter regimes. Although the full micromaser dynamics can in principle generate higher-order entanglement, we focus here on well-defined measures of two- and three-party correlations and treat the emerging information graph as a structural probe of digitized field states. We expect the workflow to transfer to other bosonic fields encoded in small qubit registers, and outline how the resulting information-graph view can serve as a practical diagnostic in studies of driven-dissipative correlation structure. Full article

Emerging from millions of years of evolutionary optimization, Natural products (NPs) remain unique, unparalleled sources of bioactive scaffolds. Unlike synthetic molecules engineered around single therapeutic targets, NPs often exhibit multi-target, system-level bioactivity, aligned with the principles of network pharmacology, which modulates pathways in a coordinated, non-disruptive manner. This approach reduces resistance, buffers compensatory feedback loops, and enhances therapeutic resilience. Fungal endophytes represent one of the most chemically diverse and biologically sophisticated NP reservoirs known, producing polyketides, alkaloids, terpenoids, and peptides with intricate three-dimensional architectures and emergent bioactivity patterns that remain exceptionally difficult to design de novo. Advances in artificial intelligence (AI), machine learning, deep learning, and multi-omics integration have redefined the discovery landscape, transforming previously intractable fungal metabolomes and cryptic biosynthetic gene clusters (BGCs) into tractable, predictable, and engineerable systems. AI accelerates genome mining, metabolomic annotation, BGC-metabolite linking, structure prediction, and activation of silent pathways. Generative AI and diffusion models now enable de novo design of NP-inspired scaffolds while preserving biosynthetic feasibility, opening new opportunities for direct evolution, pathway refactoring, and precision biomanufacturing. This review synthesizes the chemical and biosynthetic diversity of major NP classes from fungal endophytes and maps them onto the rapidly expanding ecosystem of AI-driven tools. We outline how AI transforms NP discovery from empirical screening into a predictive, hypothesis-driven discipline with direct industrial implications for drug discovery and synthetic biology. By coupling evolutionarily refined chemistry with modern computational intelligence, the field is poised for a new era in which natural-product leads are not only rediscovered but systematically expanded, engineered, and industrialized to address urgent biomedical and sustainability challenges. Full article

Natural bioactive peptides have emerged as pivotal candidates in modern science due to their multifaceted biological activities and versatile applications across biomedicine, biotechnology, and nutraceuticals. These molecules exhibit a broad pharmacological spectrum including antimicrobial, antiplatelet, antioxidant, antihypertensive, and antitumor properties, positioning them as potent therapeutic agents and essential functional food constituents. Compared to synthetic alternatives, their inherent structural diversity, biocompatibility, and biodegradability offer a superior safety profile by minimizing systemic toxicity and adverse effects. This review provides a comprehensive analysis of the primary natural reservoirs of these peptides, which encompass terrestrial flora and fauna as well as marine organisms and microorganisms, while elucidating their complex mechanisms of action and structure–function relationships. Furthermore, we evaluate contemporary methodologies for peptide identification and optimization, such as high-throughput proteomics, computational modeling, and strategic chemical modifications aimed at enhancing metabolic stability and bioavailability. Although bottlenecks in extraction, scalable production, and proteolytic susceptibility persist, recent breakthroughs in recombinant technology and rational design are facilitating their industrial translation. Finally, we discuss future perspectives focused on the synergy between artificial intelligence, nanotechnology, and sustainable circular economy strategies to maximize the therapeutic accessibility and functional efficacy of natural peptides. Full article

The construction of underground reservoirs in coal goafs is an innovative technology to alleviate the coal–water conflict in arid mining areas of northwest China. However, its widespread application is constrained by the challenge of accurately predicting water inflow, which fluctuates significantly due to the dynamic “expansion–closure” behavior of mining-induced fractures. This study focuses on the Shendong mining area, where repeated multi-seam mining occurs, and employs a coupled Finite Discrete Element Method (FDEM) and Computational Fluid Dynamics (CFD) numerical model, combined with in situ tests such as drilling fluid loss and groundwater level monitoring, to quantify the evolution of overburden fractures and their impact on reservoir water inflow during mining, 8 months post-mining, and after 7 years. The results demonstrate that the height of the water-conducting fracture zone decreased from 152 m during mining to 130 m after 7 years, while fracture openings in the key aquifer and aquitard were reduced by over 50%. This closure process caused a dramatic decline in water inflow from 78.3 m³/h to 2.6 m³/h—a reduction of 96.7%. The CFD-FDEM simulations showed a deviation of only 10.6% from field measurements, confirming fracture closure as the dominant mechanism driving inflow attenuation. This study reveals how fracture closure shifts water flow patterns from vertical to lateral recharge, providing a theoretical basis for optimizing the design and sustainable operation of underground reservoirs. Full article