Search Results (10)

Natural gas, as a sustainable and cleaner energy source, still holds a crucial position in the energy transition stage. In shale gas exploration, total organic carbon (TOC) content plays a crucial role, with log data proving beneficial in predicting total organic carbon content in shale reservoirs. However, in complex coal-bearing layers like the marine–continental transitional Shanxi Formation, traditional prediction methods exhibit significant errors. Therefore, this study proposes an advanced, cost- and time-saving deep learning approach to predict TOC in marine–continental transitional shale. Five well log records from the study area were used to evaluate five machine learning models: K-Nearest Neighbors (KNNs), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGB), and Deep Neural Network (DNN). The predictive results were compared with conventional methods for accurate TOC predictions. Through K-fold cross-validation, the ML models showed superior accuracy over traditional models, with the DNN model displaying the lowest root mean square error (RMSE) and mean absolute error (MAE). To enhance prediction accuracy, δR was integrated as a new parameter into the ML models. Comparative analysis revealed that the improved DNN-R model reduced MAE and RMSE by 57.1% and 70.6%, respectively, on the training set, and by 59.5% and 72.5%, respectively, on the test set, compared to the original DNN model. The Williams plot and permutation importance confirmed the reliability and effectiveness of the enhanced DNN-R model. The results indicate the potential of machine learning technology as a valuable tool for predicting crucial parameters, especially in marine–continental transitional shale reservoirs lacking sufficient core samples and relying solely on basic well-logging data, signifying its importance for effective shale gas assessment and development. Full article

The growing demand for sustainable materials has significantly increased interest in biocomposites, which are made from renewable raw materials and have excellent mechanical properties. The use of machine learning (ML) can improve our understanding of their mechanical behavior while saving costs and time. In this study, the mechanical behavior of innovative biocomposite sandwich structures under quasi-static out-of-plane compression was investigated using ML algorithms to analyze the effects of geometric variations on load-bearing capacities. A comprehensive dataset of experimental mechanical tests focusing on compression loading was employed, evaluating three ML models—generalized regression neural networks (GRNN), extreme learning machine (ELM), and support vector regression (SVR). Performance indicators such as R-squared (R²), mean absolute error (MAE), and root mean square error (RMSE) were used to compare the models. It was shown that the GRNN model with an RMSE of 0.0301, an MAE of 0.0177, and R² of 0.9999 in the training dataset, and an RMSE of 0.0874, MAE of 0.0489, and R² of 0.9993 in the testing set had a higher predictive accuracy. In contrast, the ELM model showed moderate performance, while the SVR model had the lowest accuracy with RMSE, MAE, and R² values of 0.5769, 0.3782, and 0.9700 for training, and RMSE, MAE, and R² values of 0.5980, 0.3976 and 0.9695 for testing, suggesting that it has limited effectiveness in predicting the mechanical behavior of the biocomposite structures. The nonlinear load-displacement behavior, including critical peaks and fluctuations, was effectively captured by the GRNN model for both the training and test datasets. The progressive improvement in model performance from SVR to ELM to GRNN was illustrated, highlighting the increasing complexity and capability of machine learning models in capturing detailed nonlinear relationships. The superior performance and generalization ability of the GRNN model were confirmed by the Taylor diagram and Williams plot, with the majority of testing samples falling within the applicability domain, indicating strong generalization to new, unseen data. The results demonstrate the potential of using advanced ML models to accurately predict the mechanical behavior of biocomposites, enabling more efficient and cost-effective development and optimization processes in the field of sustainable materials. Full article

Dengue outbreaks persist in global tropical regions, lacking approved antivirals, necessitating critical therapeutic development against the virus. In this context, we developed the “Anti-Dengue” algorithm that predicts dengue virus inhibitors using a quantitative structure–activity relationship (QSAR) and MLTs. Using the “DrugRepV” database, we extracted chemicals (small molecules) and repurposed drugs targeting the dengue virus with their corresponding IC₅₀ values. Then, molecular descriptors and fingerprints were computed for these molecules using PaDEL software. Further, these molecules were split into training/testing and independent validation datasets. We developed regression-based predictive models employing 10-fold cross-validation using a variety of machine learning approaches, including SVM, ANN, kNN, and RF. The best predictive model yielded a PCC of 0.71 on the training/testing dataset and 0.81 on the independent validation dataset. The created model’s reliability and robustness were assessed using William’s plot, scatter plot, decoy set, and chemical clustering analyses. Predictive models were utilized to identify possible drug candidates that could be repurposed. We identified goserelin, gonadorelin, and nafarelin as potential repurposed drugs with high pIC50 values. “Anti-Dengue” may be beneficial in accelerating antiviral drug development against the dengue virus. Full article

With the increasing complexity of radar jamming threats, accurate and automatic jamming recognition is essential but remains challenging. Conventional algorithms often suffer from sharply decreased recognition accuracy under low jamming-to-noise ratios (JNR).Artificial intelligence-based jamming signal recognition is currently the main research directions for this issue. This paper proposes a new radar jamming recognition framework called Diff-SwinT. Firstly, the time-frequency representations of jamming signals are generated using Choi-Williams distribution. Then, a diffusion model with U-Net backbone is trained by adding Gaussian noise in the forward process and reconstructing in the reverse process, obtaining an inverse diffusion model with denoising capability. Next, Swin Transformer extracts hierarchical multi-scale features from the denoised time-frequency plots, and the features are fed into linear layers for classification. Experiments show that compared to using Swin Transformer, the proposed framework improves overall accuracy by 15% to 10% at JNR from −16 dB to −8 dB, demonstrating the efficacy of diffusion-based denoising in enhancing model robustness. Compared to VGG-based and feature-fusion-based recognition methods, the proposed framework has over 27% overall accuracy advantage under JNR from −16 dB to −8 dB. This integrated approach significantly enhances intelligent radar jamming recognition capability in complex environments. Full article

Temperature–frequency sweep tests were performed on silicone rubber to investigate the dynamic viscoelastic properties. The test results show that the viscoelasticity of silicone rubber presents significant temperature dependence and frequency dependence. The dynamic viscoelastic test curves at different temperatures can be shifted along the logarithmic frequency coordinate axis to construct smooth master curves at the reference temperature of 20 °C, covering a frequency range of 10 decades, which indicates thermorheological simplicity on a macro level and frequency temperature equivalence of the silicone rubber material in the experimental temperature range. The van Gurp–Palmen plot and Cole–Cole plot for the test data at various temperatures merge into a common curve, which further validates thermorheological simplicity. The temperature dependent shift factors of silicone rubber material were well characterized by the Williams–Landel–Ferry equation. Moreover, the fractional-order differential Kelvin (FDK) model, the fractional-order differential Zener (FDZ) model, and the improved fractional-order differential Zener (iFDZ) model were used to model the asymmetric loss factor master curve. The result shows that the iFDZ model is in good agreement with the test results, indicating that this model is suitable for describing the asymmetry of dynamic viscoelastic properties of silicone rubber. Full article

Human serum paraoxonase-1 (PON1) is an important hydrolase-type enzyme found in numerous tissues. Notably, it can exist in two isozyme-forms, Q and R, that exhibit different activities. This study presents an in silico (QSAR, Docking, MD and QM/MM) study of a set of compounds on the activity towards the PON1 isoenzymes (QPON1 and RPON1). Different rates of reaction for the Q and R isoenzymes were analyzed by modelling the effect of Q192R mutation on active sites. It was concluded that the Q192R mutation is not even close to the active site, while it is still changing the geometry of it. Using the combined genetic algorithm with multiple linear regression (GA-MLR) technique, several QSAR models were developed and relative activity rates of the isozymes of PON1 explained. From these, two QSAR models were selected, one each for the QPON1 and RPON1. Best selected models are four-variable MLR models for both Q and R isozymes with squared correlation coefficient R² values of 0.87 and 0.83, respectively. In addition, the applicability domain of the models was analyzed based on the Williams plot. The results were discussed in the light of the main factors that influence the hydrolysis activity of the PON1 isozymes. Full article

Gravity retaining walls are a vital structure in the area of geotechnical engineering, and academicians in earlier studies have conveyed substantial uncertainties involved in calculating the factor of safety against overturning, using a deterministic approach. Hence, to enhance the accuracy and eliminate the uncertainties involved, artificial intelligence (AI) was used in the present research. The main aim of this study is to propose a high-performance machine learning (ML) model to determine the factor of safety (FOS) of gravity retaining walls against overturning. The projected methodology included a novel hybrid machine learning model that merged with an adaptive neuro-fuzzy inference system (ANFIS) and meta-heuristic optimization techniques (particle swarm optimization (PSO), genetic algorithm (GA), firefly algorithm (FFA) and grey wolf optimization (GWO)). In this research, four hybrid models, namely ANFIS-PSO, ANFIS-FFA, ANFIS-GA and ANFIS-GWO, were created to estimate the factor of safety against overturning. The proposed hybrid models were evaluated on two distinct datasets (training 70% and testing 30%) with three input combinations, namely cohesion (c), unit weight of soil (Υ) and angle of shearing resistance (φ). To access the prediction power of different hybrid models, various statistical parameters such as R², AdjR², VAF, WI, LMI, a-20 index, PI, KGE, RMSE, SI, MAE, NMBE and MBE were computed for training (TR) and testing (TS) datasets. The overall performance of the models indicated that ANFIS-PSO provided better results among all four models. The reliability index was computed using the first-order second-moment (FOSM) method for all models, and the probability of failure was also computed. A Williams plot was drawn to check the applicability domain of the hybrid model and to check the influence of different input parameters on the prediction of the factor of safety, and the Gini index was also computed. Full article

The natural stratification and interlocking “organization” of armored sediments in heterogeneous, coarse-grained, beaches provides protection and enhances habitat for borrowing sedentary megafauna and macrofauna such as hard-shelled clams. Here, we develop a novel metric for quantifying sediment organization of large surficial beach clasts through sedimentologic and photogrammetric analyses of 37 lower intertidal heterogeneous gravel beaches in western Prince William Sound, Alaska (USA). Grain size, photogrammetric, and Wolman Pebble Count clast-size data from 64, ~1-m² study plots are combined into a clast-size-independent “Organization Metric” to quantify the degree of organization in the meshed arrangement of larger surficial sediments. This metric was validated through field manipulation experiments and comparisons of adjacent plots characterized by different clast sizes. Application of this metric to subsets of Prince William Sound beaches that underwent differential treatment following the Exxon Valdez oil spill reveals persistent physical effects of artificial beach disturbance even 21 years after the cleanup. This has important implications for beach management (e.g., cleaning or dredging) and for the diverse and productive sedentary megafaunal assemblages that live within these sediments. Overall, this study provides a new approach for quantifying organization of heterogenous coarse sediments in diverse natural settings; in particular, heterogenous gravel beaches. Full article

The planning of fuel treatments for ecological or societal purposes requires an in-depth understanding of the conditions associated with the occurrence of free-burning fire behavior for the area of concern. Detailed fire-environment analysis for Army Garrison Camp Williams (AGCW) in north-central Utah was completed as a prerequisite for fuel treatment planning, using a procedure that could be generally applied. Vegetation and fuels data, topographic and terrain features, and weather and climate data, were assessed and integrated into predictive fuel models to aid planning. A fire behavior fuel model map was developed from biophysical variables, vegetation type, and plot survey data using random forests, and resulted in an overall classification rate of 72%. The predominate vegetation type-fuel complex was grass, followed by lesser amounts of Gambel oak, Wyoming big sagebrush and Utah juniper. The majority of AGCW is mountainous in nature, characterized by slopes less than 40% in steepness with slightly more northerly and easterly aspects than south and west, and elevations that ranged from 1650 to 1950 m above mean sea level. Local fire weather data compiled from the three nearest remote automated weather stations indicated that average temperature maxima (32 °C) and relative humidity minima (12%) usually occurred between 1400 to 1500 h daily, and from July to August, seasonally. The semi-arid climate at AGCW, coupled with the corresponding preponderance of flashy fuel types and sloping terrain, constitutes a formidable fire environment in which to plan for mitigating against adverse fire behavior. Full article

In the present work, support vector machines (SVMs) and multiple linear regression (MLR) techniques were used for quantitative structure–property relationship (QSPR) studies of retention time (t_R) in standardized liquid chromatography–UV–mass spectrometry of 67 mycotoxins (aflatoxins, trichothecenes, roquefortines and ochratoxins) based on molecular descriptors calculated from the optimized 3D structures. By applying missing value, zero and multicollinearity tests with a cutoff value of 0.95, and genetic algorithm method of variable selection, the most relevant descriptors were selected to build QSPR models. MLRand SVMs methods were employed to build QSPR models. The robustness of the QSPR models was characterized by the statistical validation and applicability domain (AD). The prediction results from the MLR and SVM models are in good agreement with the experimental values. The correlation and predictability measure by r² and q² are 0.931 and 0.932, repectively, for SVM and 0.923 and 0.915, respectively, for MLR. The applicability domain of the model was investigated using William’s plot. The effects of different descriptors on the retention times are described. Full article