Search Results (9,722)

The present study explores the application of RNNs for the prediction and propagation of flood waves along a section of the Bârsa River, Romania, as a fast alternative to classical hydraulic models, aiming to identify new ways to alert the population. Five neural architectures were analyzed as follows: S-RNN, LSTM, GRU, Bi-LSTM, and Bi-GRU. The input data for the neural networks were derived from 2D hydraulic simulations conducted using HEC-RAS software, which provided the necessary training data for the models. It should be mentioned that the input data for the hydraulic model are synthetic hydrographs, derived from the statistical processing of recorded floods. Performance evaluation was based on standard metrics such as NSE, $R^2$ MSE, and RMSE. The results indicate that all studied networks performed well, with NSE and $R^2$ values close to 1, thus validating their capacity to reproduce complex hydrological dynamics. Overall, all models yielded satisfactory results, making them useful tools particularly the GRU and Bi-GRU architectures, which showed the most balanced behavior, delivering low errors and high stability in predicting peak discharge, water level, and flood wave volume. The GRU and Bi-GRU networks yielded the best performance, with RMSE values below 1.45, MAE under 0.3, and volume errors typically under 3%. On the other hand, LSTM architecture exhibited the most significant instability and errors, especially in estimating the flood wave volume, often having errors exceeding 9% in some sections. The study concludes by identifying several limitations, including the heavy reliance on synthetic data and its local applicability, while also proposing solutions for future analyses, such as the integration of real-world data and the expansion of the methodology to diverse river basins thus providing greater significance to RNN models. The final conclusions highlight that RNNs are powerful tools in flood risk management, contributing to the development of fast and efficient early warning systems for extreme hydrological and meteorological events. Full article

In this study, the distribution patterns of the nitrifying and denitrifying microbiome in a large-scale biofilter (587.24 m³) in a cold freshwater recirculating aquaculture system (RAS) was investigated. Previous studies have revealed that the water quality, nitrification, and denitrification rates in the front (BFF), middle (BFM), and back (BFB) of this biofilter are different. The results showed the highest diversity of the denitrifying microbiome in the BFB, followed by BFF and BFM, whereas nitrifying microbiome diversity remained consistent across different positions. Two genera, Nitrosomonas and Nitrosospira, dominated the nitrifying microbiome, while Pseudomonas, Thauera, Cupriavidus, Dechloromonas, Azoarcus, and Paracoccus comprised the top six denitrifying genera. Principal coordinate analysis indicated a distinct spatial distribution pattern of the denitrifying microbiome but not the nitrifying microbiome. The genera Pseudomonas and Dechloromonas were the biomarkers of the BFF and BFB, respectively. Redundancy analysis showed that nitrite, nitrate, dissolved oxygen, and soluble reactive phosphorus influenced the functional microbiome distribution pattern. Network correlation analysis identified one nitrifying hub (Nitrosospira) in the BFF, five denitrifying hubs (Aromatoleum, Dechloromonas, Paracoccus, Ruegeria, and Thauera) in the BFM, and three denitrifying hubs (Azoarcus, Magnetospirillum, and Thauera) in the BFB. Exclusively negative correlations were found between hubs and its adjacent nodes in the BFF and BFB. This study demonstrates that habitat can shape the distribution patterns of the nitrifying and denitrifying microbiome in the biofilter of the RAS, with the BFF exhibiting greater benefits for the nitrification process. Full article

We present a dynamical systems approach to modeling nonlinear flood dynamics using 20 years of water level data from Durazno, Uruguay. Flood events are identified, and their periodicity and temporal distribution are analyzed in relation to rain gauge precipitation. Phase space reconstruction enables data-driven neural network modeling and quantification of the relationship between water level and soil moisture. Bifurcation diagrams define basin-specific flood thresholds, offering a mechanistic framework for improved flood forecasting and risk assessment. Full article

The level of participation and performance of water user associations (WUAs) in drained and irrigated areas is influenced by many factors. This paper aims to identify the main challenges to the functioning and performance of these associations in Poland and Ukraine using the methodology of international comparative analysis. We examined legal, organizational, and financial framework of WUAs performance in Poland and Ukraine based on selected case study areas. The results of the study indicate that creation of WUAs in both countries can be assessed as beneficial for sustainable water development in general. However, it is found that the actions intended to bring benefits can actually exacerbate the problem of drought and water shortages. Research shows that the lack of complete documentation on the layout of the drainage networks plays a huge constraint factor that can lead to problems with controlling the reconstruction of drainage networks and significant deterioration of water relations. Another significant problem is the restriction of the scope of WUA activities in Poland to those types of actions subsidized by the state, while lacking financial resources for other necessary activities. Full article

The number of CNN application areas is growing, which leads to the need for training data. The research conducted in this work aimed to obtain effective detection models trained only using simplified synthetic objects (SSOs). The research was conducted on inland shallow water areas, while images of bottom objects were obtained using a UAV platform. The work consisted in preparing SSOs, thanks to which composite images were created. On such training data, 120 models based on the YOLO (You Only Look Once) network were obtained. The study confirmed the effectiveness of models created using YOLOv3, YOLOv5, YOLOv8, YOLOv9, and YOLOv10. A comparison was made between versions of YOLO. The influence of the amount of training data, SSO type, and augmentation parameters used in the training process was analyzed. The main parameter of model performance was the F1-score. The calculated statistics of individual models indicate that the most effective networks use partial augmentation, trained on sets consisting of 2000 SSOs. On the other hand, the increased transparency of SSOs resulted in increasing the diversity of training data and improving the performance of models. This research is developmental, and further research should improve the processes of obtaining detection models using deep networks. Full article

This study applies a deep neural network (DNN) to optimize the 22.5 m pontoon hull form of a small waterplane area twin hull (SWATH) vessel with fin stabilizers, aiming to reduce calm water resistance at a Froude number of 0.8 under even keel conditions. The vessel’s resistance is simplified into three components: pontoon, strut, and fin stabilizer. Four design parameters define the pontoon geometry: fore-body length, aft-body length, fore-body angle, and aft-body angle. Computational fluid dynamics (CFD) simulations using STAR-CCM+ 2302 provide 1400 resistance data points, including fin stabilizer lift and drag forces at varying angles of attack. These are used to train a DNN in MATLAB 2018a with five hidden layers containing six, eight, nine, eight, and seven neurons. K-fold cross-validation ensures model stability and aids in identifying optimal design parameters. The optimized hull has a 7.8 m fore-body, 6.8 m aft-body, 10$°$ fore-body angle, and 35$°$ aft-body angle. It achieves a 2.2% resistance reduction compared to the baseline. The improvement is mainly due to a reduced Munk moment, which lowers the angle of attack needed by the fin stabilizer, thereby reducing drag. The optimized design provides cost-efficient construction and enhanced payload capacity. This study demonstrates the effectiveness of combining CFD and deep learning for hull form optimization. Full article

Salmonella serovar identification typically requires multiple enrichment steps using selective media, consuming considerable time and resources. This study presents a rapid, culture-independent method leveraging artificial intelligence (AI) to classify Salmonella serovars from rich hyperspectral microscopy data. Five serovars (Enteritidis, Infantis, Kentucky, Johannesburg, 4,[5],12:i:-) were analyzed from samples prepared using only sterilized de-ionized water. Hyperspectral data cubes were collected to generate single-cell spectra and RGB composite images representing the full microscopy field. Data analysis involved two parallel branches followed by multimodal fusion. The spectral branch compared manual feature selection with data-driven feature extraction via principal component analysis (PCA), followed by classification using conventional machine learning models (i.e., k-nearest neighbors, support vector machine, random forest, and multilayer perceptron). The image branch employed a convolutional neural network (CNN) to extract spatial features directly from images without predefined morphological descriptors. Using PCA-derived spectral features, the highest performing machine learning model achieved 81.1% accuracy, outperforming manual feature selection. CNN-based classification using image features alone yielded lower accuracy (57.3%) in this serovar-level discrimination. In contrast, a multimodal fusion model combining spectral and image features improved accuracy to 82.4% on the unseen test set while reducing overfitting on the train set. This study demonstrates that AI-enabled hyperspectral microscopy with multimodal fusion can streamline Salmonella serovar identification workflows. Full article

During the process of oil and gas drilling, due to the existence of pores or micro-cracks, drilling fluid is prone to invade the formation. Under the action of hydration expansion of clay in the formation and liquid pressure, wellbore instability occurs. In order to reduce the wellbore instability caused by drilling fluid intrusion into the formation, this study proposed a method of forming a dynamic hydrogen bond cross-linked network weak gel structure with modified nano-silica and P(AM-AAC). The plugging performance of the drilling fluid and the performance of inhibiting the hydration of shale were evaluated through various experimental methods. The results show that the gel composite system (GCS) effectively optimizes the plugging performance of drilling fluid. The 1% GCS can reduce the linear expansion rate of cuttings to 14.8% and increase the recovery rate of cuttings to 96.7%, and its hydration inhibition effect is better than that of KCl and polyamines. The dynamic cross-linked network structure can significantly increase the viscosity of drilling fluid. Meanwhile, by taking advantage of the liquid-phase viscosity effect and the physical blocking effect, the loss of drilling fluid can be significantly reduced. Mechanism studies conducted using zeta potential measurement, SEM analysis, contact angle measurement and capillary force assessment have shown that modified nano-silica stabilizes the wellbore by physically blocking the nano-pores of shale and changing the wettability of the shale surface from hydrophilic to hydrophobic when the contact angle exceeds 60°, thereby reducing capillary force and surface free energy. Meanwhile, the dynamic cross-linked network can reduce the seepage of free water into the formation, thereby significantly lowering the fluid loss of the drilling fluid. This research provides new insights into improving the stability of the wellbore in drilling fluids. Full article

Effective management of cascade reservoir systems is essential for balancing hydropower generation, flood control, and ecological sustainability, especially under increasingly uncertain runoff conditions driven by climate change. Traditional optimization methods, while widely used, often struggle with high dimensionality and fail to adequately address inflow variability. This study introduces a novel deep reinforcement learning (DRL) framework that tightly couples probabilistic runoff forecasting with adaptive reservoir scheduling. We integrate a Long Short-Term Memory (LSTM) neural network to model runoff uncertainty and generate probabilistic inflow forecasts, which are then embedded into a Proximal Policy Optimization (PPO) algorithm via Monte Carlo sampling. This unified forecast–optimize architecture allows for dynamic policy adjustment in response to stochastic hydrological conditions. A case study on China’s Xiluodu–Xiangjiaba cascade system demonstrates that the proposed LSTM-PPO framework achieves superior performance compared to traditional baselines, notably improving power output, storage utilization, and spillage reduction. The results highlight the method’s robustness and scalability, suggesting strong potential for supporting resilient water–energy nexus management under complex environmental uncertainty. Full article

While horizontal roughing filters (HRFs) remain widely acclaimed for their exceptional efficiency in water treatment, especially in developing countries, they are inherently susceptible to clogging, which necessitates timely maintenance interventions. Conventional methods for managing clogging in HRFs typically involve evaluating filter head loss coefficients against established water quality standards. This study utilizes artificial neural network (ANN) for the prediction of clogging duration and effluent turbidity in HRF equipment. The ANN was configured with two outputs, the clogging duration and effluent turbidity, which were predicted concurrently. Effluent turbidity was modeled to enhance the network’s learning process and improve the accuracy of clogging prediction. The network steps of the iterative training process of ANN used different types of input parameters, such as influent turbidity, filtration rate, pH, conductivity, and effluent turbidity. The training, in addition, optimized network parameters such as learning rate, momentum, and calibration of neurons in the hidden layer. The quantities of the dataset accounted for up to 70% for training and 30% for testing and validation. The optimized structure of ANN configured in a 4-8-2 topology and trained using the Levenberg–Marquardt (LM) algorithm achieved a mean square error (MSE) of less than 0.001 and R-coefficients exceeding 0.999 across training, validation, testing, and the entire dataset. This ANN surpassed models of scaled conjugate gradient (SCG) and obtained a percentage of average absolute deviation (%AAD) of 9.5. This optimal structure of ANN proved to be a robust tool for tracking the filter clogging duration in HRF equipment. This approach supports proactive maintenance and operational planning in HRFs, including data-driven scheduling of backwashing based on predicted clogging trends. Full article

As typical environmental hormones, endocrine-disrupting chemicals (EDCs) have become a global environmental health issue of high concern due to their property of interfering with the endocrine systems of organisms. As a commonly used substitute for bisphenol A (BPA), bisphenol E (BPE) has been frequently detected in environmental matrices such as soil and water in recent years. Existing research has unveiled the developmental and reproductive toxicity of BPE; however, only one in vitro cellular experiment has preliminarily indicated potential neurotoxic risks, with its underlying mechanisms remaining largely unelucidated in the current literature. Potential toxic mechanisms and action targets of BPE were predicted using the zebrafish model via network toxicology and molecular docking, with RT-qPCRs being simultaneously applied to uncover neurotoxic effects and associated mechanisms of BPE. A significant decrease (p < 0.05) in the frequency of embryonic spontaneous movements was observed in zebrafish at exposure concentrations ≥ 0.01 mg/L. At 72 hpf and 144 hpf, the larval body length began to shorten significantly from 0.1 mg/L to 1 mg/L, respectively (p < 0.01), accompanied by a reduced neuronal fluorescence intensity and a shortened neural axon length (p < 0.01). By 144 hpf, the motor behavior in zebrafish larvae was inhibited. Through network toxicology and molecular docking, HSP90AB1 was identified as the core target, with the cGMP/PKG signaling pathway determined to be the primary route through which BPE induces neurotoxicity in zebrafish larvae. BPE induces neuronal apoptosis and disrupts neurodevelopment by inhibiting the cGMP/PKG signaling pathway, ultimately suppressing the larval motor behavior. To further validate the experimental outcomes, we measured the expression levels of genes associated with neurodevelopment (elavl3, mbp, gap43, syn2a), serotonergic synaptic signaling (5-ht1ar, 5-ht2ar), the cGMP/PKG pathway (nos3), and apoptosis (caspase-3, caspase-9). These results offer crucial theoretical underpinnings for evaluating the ecological risks of BPE and developing environmental management plans, as well as crucial evidence for a thorough comprehension of the toxic effects and mechanisms of BPE on neurodevelopment in zebrafish larvae. Full article

Prolonged drought and soil degradation severely affect soil fertility and limit crop productivity. Superabsorbent hydrogels offer an effective solution for improving water retention in soil and supporting plant growth. In this work, we examined the performance of superabsorbent hydrogels based on sodium alginate, acrylic acid (AA), and poly (ethylene oxide) (PEO) cross-linked with 12.5 kGy using e-beam irradiation. The hydrogels were assessed in various aqueous environments by examining network characteristics, swelling capacity, and swelling kinetics to evaluate the impact of water’s electrical conductivity (which ranges from 0.05 to 321 μS/cm). Morphological and chemical structure changes were evaluated using SEM and FTIR techniques. The results demonstrated that water conductivity significantly affected the physicochemical properties of the hydrogels. Swelling behavior showed notable sensitivity to electrical conductivity variations, with swelling degrees reaching 28,400% at 5 μS/cm and 14,000% at 321 μS/cm, following first-order and second-order kinetics. FTIR analysis confirmed that structural modifications correlated with water conductivity, particularly affecting the O–H, C–H, and COOH groups sensitive to the ionic environment. SEM characterization revealed a porous morphology with an interconnected microporous network that facilitates efficient water diffusion. These hydrogels show exceptional swelling capacity and are promising candidates for sustainable agriculture applications. Full article

Concrete mix design plays a pivotal role in ensuring the mechanical performance, durability, and sustainability of construction projects. However, the nonlinear interactions among the mix components challenge traditional approaches in predicting compressive strength and optimizing proportions. This study presents a two-stage hybrid framework that integrates deep learning with reinforcement learning to overcome these limitations. First, a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model was developed to capture spatial–temporal patterns from a dataset of 1030 historical concrete samples. The extracted features were enhanced using an eXtreme Gradient Boosting (XGBoost) meta-model to improve generalizability and noise resistance. Then, a Dueling Double Deep Q-Network (Dueling DDQN) agent was used to iteratively identify optimal mix ratios that maximize the predicted compressive strength. The proposed framework outperformed ten benchmark models, achieving an MAE of 2.97, RMSE of 4.08, and R² of 0.94. Feature attribution methods—including SHapley Additive exPlanations (SHAP), Elasticity-Based Feature Importance (EFI), and Permutation Feature Importance (PFI)—highlighted the dominant influence of cement content and curing age, as well as revealing non-intuitive effects such as the compensatory role of superplasticizers in low-water mixtures. These findings demonstrate the potential of the proposed approach to support intelligent concrete mix design and real-time optimization in smart construction environments. Full article

Natural hydrogen is generated by fairly deep processes and/or in low-permeability rocks. In such contexts, fluids circulate mainly through the network of faults and fractures. However, hydrogen flows from these hydrogen-generating layers can reach sedimentary rocks with more typical permeability and porosity, allowing H₂ flows to spread out rather than be concentrated in fractures. In that case, three different H₂ transport modes exist: advection (displacement of water carrying dissolved gas), diffusion, and free gas Darcy flow. Numerical models have been run to compare the efficiency of these different modes and the pathway they imply for the H₂ in a sedimentary basin with active aquifers. The results show the key roles of these aquifers but also the competition between free gas flow and the dissolved gas displacement which can go in opposite directions. Even with a conservative hypothesis on the H₂ charge, a gaseous phase exists at few kilometers deep as well as free gas accumulation. Gaseous phase displacement could be the faster and diffusion is neglectable. The modeling also allows us to predict where H₂ is expected in the soil: in fault zones, eventually above accumulations, and, more likely, due to exsolution, above shallow aquifers. Full article

This comprehensive study investigates the spatial distribution of metals in surface water, their accumulation in fish tissues, and their impact on the gut microbiome dynamics of fish in the Qi River, Huanggang City, Hubei Province. Three distinct sampling regions were established: the mining area (A), the transition area (B), and the distant area (C). Our results revealed that metal concentrations were highest in the mining area and decreased with increasing distance from it. The bioaccumulation of metals in fish tissues followed the order of gut > brain > muscle, with some concentrations exceeding food safety standards. Analysis of the gut microbiota showed that Firmicutes and Proteobacteria dominated in the mining area, while Fusobacteriota were more prevalent in the distant area. Heavy metal pollution significantly altered the composition and network structure of the gut microbiota, reducing microbial associations and increasing negative correlations. These findings highlight the profound impact of heavy metal pollution on both fish health and the stability of their gut microbiota, underscoring the urgent need for effective pollution control measures to mitigate ecological risks and protect aquatic biodiversity. Future research should focus on long-term monitoring and exploring potential remediation strategies to restore the health of affected ecosystems. Full article