Quantitative Prediction Method Research Articles

A Quantitative Seismic Topographic Effect Prediction Method Based upon BP Neural Network Algorithm and FEM Simulation

A Quantitative Seismic Topographic Effect Prediction Method Based upon BP Neural Network Algorithm and FEM Simulation

Quantitative prediction of soil chromium content using laboratory-based visible and near-infrared spectroscopy with different ensemble learning models

Soil heavy metal chromium pollution poses significant threats to human health and ecosystems, necessitating accurate quantitative prediction methods for effective monitoring and management. This study aims to develop robust predictive models for soil chromium content in farmland soils of Mojiang Hani Autonomous County, Pu’er City, Yunnan Province, China. These models utilize ensemble learning techniques based on visible and near-infrared spectroscopy. Operations before model building involved partitioning datasets with the Kennard-Stone algorithm to ensure representative training and testing sets. Visible and near-infrared spectroscopy-data preprocessing was performed using Savitzky-Golay smoothing and first-order derivative transformations to enhance signal quality. Bands selection was achieved through the Successive Projections Algorithm (SPA), effectively reducing data dimensionality and collinearity. Six ensemble learning models were constructed and assessed for their predictive performance: Bagging-DTR, Random Forest (RF), Adaboost-DTR, XGBoost-DTR, Stacking-1, and Stacking-2. These models utilized Decision Trees (DTR) and Linear Regression (LR) as base learners. Results demonstrated that ensemble models significantly outperformed individual base learners. Notably, the Stacking-2 model achieved the highest accuracy with an R^2 of 0.954, RMSE of 125.967 mg/kg, and RPD of 4.667. To validate the model’s practical applicability, spatial interpolation of soil Cr content was conducted using the Kriging method based on Stacking-2 model predictions. The spatial distribution maps of measured and predicted values exhibited high congruence, underscoring the model’s effectiveness in accurately mapping Cr distribution across the study area. This study underscores the efficacy of integrating ensemble learning with visible and near-infrared spectroscopy-data preprocessing and SPA for precise soil heavy metal prediction. The findings offer valuable insights and a scientific basis for enhanced soil quality monitoring, environmental risk assessment, and informed agricultural land management and pollution control.

Quantitative Analysis and Prediction Methods for Sports Competition Results

In the era of big data, sports performance prediction becomes critical by analyzing accumulated competition data, especially the influence of momentum factors on competition results, although its definition and quantification are controversial in academia. This study explores the application of momentum in predicting the results of sports competitions and proposes a comprehensive research framework combining sports science and sports psychology. By collecting and analyzing the competition data, the feasibility of momentum as an important index in predicting the results of the competition is confirmed. The results show that momentum not only reflects the immediate performance of athletes in the game but also predicts their future results. This finding is of great significance for coaches and athletes to formulate strategies and adjust tactics in the game. Through continuous accumulation and analysis of data, we can more accurately predict the results of the game, and improve the level and fairness of sports competition.

Quantitative prediction methods and applications of digital ore deposit models

With the depletion of surface mineral deposits, attention has shifted to deep mineral exploration prospecting. The emergence of three-dimensional digital ore deposit models, facilitated by the advancement of computer technology, has transformed traditional two-dimensional geological models into computer-recognizable numerical-symbolic digital models. This transformation allows qualitative geological concepts, originally expressed in natural language, to be quantitatively expressed, thereby enhancing the accuracy of deep mineral exploration. This paper first outlines the development from traditional ore deposit models to digital ore deposit models, asserting that digital ore deposit models can encompass a more comprehensive array of multidisciplinary geological information, including mineralogy, ore deposit types, structural geology, geochemistry, and geophysics. Building upon digital ore deposit models, a three-dimensional geological model is constructed, combining regional metallogenic regularities, identifying ore-forming favorable information, and conducting quantitative extraction. Subsequently, a comprehensive prospecting model is established, followed by the integration of deep learning methods for deep-seated mineral exploration, forming a unified system of quantitative prospecting methodology for hidden mineral deposits under the framework of geological prospecting models, three-dimensional geological modeling, and three-dimensional quantitative prospecting. Finally, using the Zaozigou gold deposit in Gansu Province as a case study, this approach is applied to mineral exploration prospecting, delineating prospective target areas and providing valuable reference for future exploration efforts.

Quantitative prediction of the fracture scale based on frequency-dependent S-wave splitting

The development of natural fractures has a significant impact on underground reservoirs and leads to seismic anisotropy. Furthermore, the scale of natural fractures directly affects oil and gas preservation, hydraulic fracture construction, and the production development of shale reservoirs. The S-wave anisotropy is a frequency-dependent parameter and the change in S-wave anisotropy with frequency is a function of the fracture scale. We develop an innovative method for predicting the fracture scale quantitatively using frequency-dependent S-wave anisotropy. The quantitative relationship between different fracture scales and the frequency-dependent response of the S-wave splitting (SWS) anisotropy can be obtained using a dynamic rock-physics model. The frequency-dependent S-wave anisotropy is calculated via SWS analysis in the frequency domain, after which this quantitative relationship and the calculated frequency-dependent response are used to establish an objective function for the inversion of the fracture scale at different depths using the least-squares algorithm. We synthesize data under ideal conditions, test our method, apply our method to field data, and find that the quantitative prediction method of the fracture scale yielded reasonable prediction results. The S-wave anisotropy is calculated based on the SWS analysis from the horizontal components of the upgoing wavefields of the field vertical seismic profile. We compare the fracture scale calculated from logging data using our method, and the results obtained indicate that this method can successfully predict the fracture scale quantitatively.

Convolutional neural network for predicting the TOC content of source rocks in the Shahejie Formation, Liaohe Western Depression

The total organic carbon (TOC) content is an important index to evaluate the quality of hydrocarbon source rocks. It is proposed that accurate and effective prediction methods of TOC content are beneficial to the progress of conventional and unconventional oil and gas exploration research. The Liaohe western depression is rich in oil and gas resources. Among them, the Shahejie Formation Section 4 is the main oil-generating layer, and a comprehensive and accurate evaluation of its organic matter content can provide ideas for shale oil exploration in this area. Based on this, this article proposes three methods for quantitative prediction of TOC content in the Shahejie Formation Section 4 in the Liaohe western depression: simple linear regression, ΔLogR, and convolutional neural network (CNN) simulation, which has different correlation coefficients of 0.3, 0.55, and 0.88. Compared with the laboratory sample analysis and testing results, the prediction results of the three methods show that the CNN simulation method is more reliable and accurate for predicting TOC content. Therefore, this method is more suitable for evaluating hydrocarbon source rocks in the Liaohe western depression and has great potential for application in the evaluation of hydrocarbon resources in the future.

Three-dimensional quantitative mineral prediction from convolutional neural network model in developing intelligent cleaning technology

The aim of this study is to explore a three-dimensional (3D) quantitative mineral prediction method to address the issues of low accuracy and efficiency in mineral resource exploration. The experiment constructs a 3D mineral image prediction model based on intelligent clean technology, incorporating an attention convolutional neural network (CNN). This model first introduces the ShuffleNet V2 network, a lightweight and efficient CNN renowned for handling complex geological resource image data. Additionally, the model incorporates graph attention modules and channel attention modules to enhance the network's focus on crucial channel information, enabling better extraction of spatiotemporal features from 3D mineral resource samples. The results show that, compared to CNN algorithms, the accuracy of the proposed model in 3D mineral identification reaches 95.25%, a minimum accuracy improvement of 1.41%. Moreover, under induced fault geological types, this model achieves a Mean Intersection over Union (mIoU) value of 94.55%. The constructed model demonstrates high accuracy and precision in prediction performance and sustainability, providing strong support for the sustainable development and strategic direction of mineral resource exploration.

Quantitative prediction of transporter-mediated drug-drug interactions using the mechanistic static pharmacokinetic (MSPK) model

Guidance/guidelines on drug-drug interactions (DDIs) have been issued in Japan, the United States, and Europe. These guidance/guidelines provide decision trees for conducting metabolizing enzyme-mediated clinical DDI studies; however, the decision trees for transporter-mediated DDIs lack quantitative prediction methods. In this study, the accuracy of a net-effect mechanistic static pharmacokinetics (MSPK) model containing the fraction transported (ft) of transporters was examined to predict transporter-mediated DDIs. This study collected information on 25 oral drugs with new active reagents that were used in clinical DDI studies as perpetrators (42 cases) from drugs approved in Japan between April 2016 and June 2020. The AUCRs (AUC ratios with and without perpetrators) of victim drugs were predicted using the net-effect MSPK model. As a result, 83 and 95% of the predicted AUCRs were within 1.5- and 2-fold error in the observed AUCRs, respectively. In cases where the victims were statins in which pharmacokinetics several transporters are involved, 70 and 91% of the predicted AUCRs were within 1.5- and 2-fold errors, respectively. Therefore, the net-effect MSPK model was applicable for predicting the AUCRs of victims, which are substrates for multiple transporters.

Borehole stability in naturally fractured rocks with drilling mud intrusion and associated fracture strength weakening: A coupled DFN-DEM approach

Borehole instability in naturally fractured rocks poses significant challenges to drilling. Drilling mud invades the surrounding formations through natural fractures under the difference between the wellbore pressure (Pw) and pore pressure (Pp) during drilling, which may cause wellbore instability. However, the weakening of fracture strength due to mud intrusion is not considered in most existing borehole stability analyses, which may yield significant errors and misleading predictions. In addition, only limited factors were analyzed, and the fracture distribution was oversimplified. In this paper, the impacts of mud intrusion and associated fracture strength weakening on borehole stability in fractured rocks under both isotropic and anisotropic stress states are investigated using a coupled DEM (distinct element method) and DFN (discrete fracture network) method. It provides estimates of the effect of fracture strength weakening, wellbore pressure, in situ stresses, and sealing efficiency on borehole stability. The results show that mud intrusion and weakening of fracture strength can damage the borehole. This is demonstrated by the large displacement around the borehole, shear displacement on natural fractures, and the generation of fracture at shear limit. Mud intrusion reduces the shear strength of the fracture surface and leads to shear failure, which explains that the increase in mud weight may worsen borehole stability during overbalanced drilling in fractured formations. A higher in situ stress anisotropy exerts a significant influence on the mechanism of shear failure distribution around the wellbore. Moreover, the effect of sealing natural fractures on maintaining borehole stability is verified in this study, and the increase in sealing efficiency reduces the radial invasion distance of drilling mud. This study provides a directly quantitative prediction method of borehole instability in naturally fractured formations, which can consider the discrete fracture network, mud intrusion, and associated weakening of fracture strength. The information provided by the numerical approach (e.g. displacement around the borehole, shear displacement on fracture, and fracture at shear limit) is helpful for managing wellbore stability and designing wellbore-strengthening operations.

Benchmarking Travel Time and Demand Prediction Methods Using Large-scale Metro Smart Card Data

Urban mass transit systems generate large volumes of data via automated systems established for ticketing, signalling, and other operational processes. This study is motivated by the observation that despite the availability of sophisticated quantitative methods, most public transport operators are constrained in exploiting the information their datasets contain. This paper intends to address this gap in the context of real-time demand and travel time prediction with smart card data. We comparatively benchmark the predictive performance of four quantitative prediction methods: multivariate linear regression (MVLR) and semiparametric regression (SPR) widely used in the econometric literature, and random forest regression (RFR) and support vector machine regression (SVMR) from machine learning. We find that the SVMR and RFR methods are the most accurate in travel flow and travel time prediction, respectively. However, we also find that the SPR technique offers lower computation time at the expense of minor inefficiency in predictive power in comparison with the two machine learning methods.

Peroxymonosulfate activation with Co3O4 by microstructure engineering for efficient degradation of tetracycline: Efficiency, mechanism and stability

In recent years, advanced oxidation technologies employ peroxynitrite activation have exhibited exceptional effectiveness in eliminating various emerging contaminants. In this study, different calcination temperatures were used to derive Co3O4 nanospheres with varying surface morphologies. This method effectively addresses the issue of high cost associated with high-performance catalyst synthesis or poor catalytic performance of low-cost catalysts. The active species like O2•−, •OH, SO4•−, 1O2 played significant role in TC degradation and 1O2 was the dominant reactive oxygen species (ROS). The study also proposed possible degradation pathways based on the 15 intermediates identified through HPLC-MS. Furthermore, the developmental toxicity of the identified intermediates was evaluated using a quantitative conformational relationship prediction method. This paper delves into the reaction mechanism of Co3O4 nanospheres in the activation of PMS and examines the impact of surface morphology on their catalytic performance, providing a new approach to developing a persulfate catalyst that is cost-effective and has high catalytic performance, with a simple synthesis step.

A Quantitative Prediction Method for the Human Pharmacokinetics of Fc-Fusion Proteins.

Fc fusion is an effective strategy for extending the half-lives of therapeutic proteins. This study aimed to evaluate the applicability of a human pharmacokinetics prediction method for Fc-fusion proteins by extending on reported methods for monoclonal antibodies (mAbs). To predict human pharmacokinetic profiles following intravenous (IV) dosing, the pharmacokinetic data for 11 Fc-fusion proteins in monkeys were analysed by two approaches: a species-invariant time method with a range of allometric exponents in clearance (CL, 0.7-1.0) and a two-compartment model reported for mAbs. The pharmacokinetic profiles following subcutaneous (SC) dosing were predicted by simple dose normalisation from monkeys or using the geometric means of the absorption rate constant (Ka) and bioavailability (BA) for mAbs or Fc-fusion proteins in humans and compared. In the case of IV administration, the area under the curve could be predicted for more than 85% of Fc-fusion proteins within a twofold difference from the observed value using the species-invariant time method (scaling exponent for CL, 0.95). For SC dosing, incorporating the geometric means of absorption parameters for both mAbs (BA 68.2%, Ka 0.287 day-1) and Fc-fusion proteins (BA 63.0%, Ka 0.209 day-1) in humans provided better accuracy than simple normalisation from monkeys. We have successfully predicted the human pharmacokinetic profiles of Fc-fusion proteins for both IV and SC administration within twofold of the observed value from monkey pharmacokinetic data by extending on reported methods for mAbs. This method will facilitate drug discovery and development of Fc-fusion proteins.

Prediction of Antigenic Distance in Influenza A Using Attribute Network Embedding.

Owing to the rapid changes in the antigenicity of influenza viruses, it is difficult for humans to obtain lasting immunity through antiviral therapy. Hence, tracking the dynamic changes in the antigenicity of influenza viruses can provide a basis for vaccines and drug treatments to cope with the spread of influenza viruses. In this paper, we developed a novel quantitative prediction method to predict the antigenic distance between virus strains using attribute network embedding techniques. An antigenic network is built to model and combine the genetic and antigenic characteristics of the influenza A virus H3N2, using the continuous distributed representation of the virus strain protein sequence (ProtVec) as a node attribute and the antigenic distance between virus strains as an edge weight. The results show a strong positive correlation between supplementing genetic features and antigenic distance prediction accuracy. Further analysis indicates that our prediction model can comprehensively and accurately track the differences in antigenic distances between vaccines and influenza virus strains, and it outperforms existing methods in predicting antigenic distances between strains.

Interpretable machine-learning for predicting power conversion efficiency of non-halogenated green solvent-processed organic solar cells based on Hansen solubility parameters and molecular weights of polymers

The green-solvent-processable strategies (e.g., open-air-printable ink for environmentally-friendly fabrication) are crucial to enable sustainable manufacturing of large-scale devices with safety considerations (e.g., uncomplicated handling, low hazard potential, and high availability) to the commercialization of Bulk heterojunction (BHJ) based organic solar cells (OSCs). Unfortunately, identifying the relationship between the performances of non-halogenated green solvent-processed BHJ-based OSCs and arbitrary polymer-solvent pairs has been a challenging problem for the profound sustainable development of the OSCs field because of the lack of reliable quantitative and accurate prediction methods. To address this problem, we show that the Gradient Boosting (GB) machine-learning model, trained on several types of potentially relevant descriptors (e.g., polymer molecular weight (MW) and Hansen solubility parameters (δd, δp, δh)), can be used to predict power conversion efficiency (PCE) of non-halogenated green solvent-processed OSCs, thereby providing a novel data-driven paradigm to select appropriate polymer-solvent pairs. The feature importance analysis, generated by the SHAP method, reveals that polymer MW has a profound impact on the prediction of PCE of non-halogenated green solvent-processed BHJ-based OSCs. The GB machine-learning model constructed here is capable of extracting the highly non-linear polymer/non-halogenated green solvent pairs-performance mapping of BHJ-based OSCs, and the SHAP feature importance analysis can be easily applied to strengthening the relationship between the complex machine-learning models and the scientists in the experimental device optimization of non-halogenated green solvent-processed BHJ-based OSCs.

An improved 3D model of composite bolted joints with detailed thread structure and progressive damage analysis of realistic tightening process

Bolted joint is a common connection method in composite structure assembling. The initial assembly state has a significant influence on the subsequent performance. To realize the simulation of the assembly process of composite bolted joints, an improved 3D model is proposed. This model considers the detailed thread structure and can be used to simulate the realistic tightening process. The relationship between the tightening torque and bolt tension is analyzed and the effect of the friction coefficient on the value of the tightening coefficient is analyzed using this model. A new fitting model for the nonlinear pressure distribution state on the outer surface of the composite laminates during the assembly process is proposed. And a quantitative analysis and prediction method of the nonlinear pressure distribution state is established. Finally, the effects of bolt tension and washer type on initial assembly damage are analyzed and experimentally verified.

Improved-GEP-based models for predicting distortion control indices of curved composite box girders

Curved steel-concrete composite box girders are subjected to complex torsional actions under vertical loads, which may generate excessive distortional warping stresses. However, the complexity of the distortional warping stresses makes it challenging to obtain a quantitative prediction method, which may result in the adoption of potentially unsafe or uneconomical diaphragm designs. In this paper, improved-GEP (gene expression programming)-based models for predicting two distortion control indices of curved composite girder bridges are proposed. The key parameters in distortion equation for the curved composite box girder bridges are derived first, and then a comprehensive parametric analysis is conducted. Subsequently, an improved GEP algorithm is proposed to establish the formulas for calculating two distortion control indices. Compared to the traditional GEP, the proposed algorithm can markedly improve the mining ability of the constant terms and coefficients and enhance the global search ability by introducing a least squares algorithm and a new-generation and quasi-offspring mixed competitive strategy. In addition, with the operative and terminal symbols determined based on distortion theory, the efficiency and physical significance of the GEP models are effectively enhanced. The statistical indices and sensitivity analysis demonstrate that the proposed models for predicting the two distortion control indices agree with the finite element analysis results and distortion theory.

Research and Application of a Quantitative Prediction Method for Sandstone Thickness in a Zone with Dense Well Pattern Development Based on an Objective Function

The seismic amplitude along a layer in a section can reveal lateral reservoir changes and is one of the important means of reservoir prediction, but it is often difficult to establish the quantitative relationship between the seismic amplitude and sandstone thickness in wells in blocks with denser development. The use of a lower-amplitude slice for precisely quantitatively predicting the sandstone thickness, based on the goal of obtaining data on layers in the development zone with a dense well pattern, is accurate and has a valuable advantage. The method of formation slice optimization based on an objective function is studied to improve the ability of reservoir characterization by seismic attributes. This method has been applied to the reservoir prediction of the G I2 sedimentary unit in the ZQX block of the SRT oilfield and has achieved good results.

Coalbed Methane Reservoir Parameter Prediction and Sweet-Spot Comprehensive Evaluation Based on 3D Seismic Exploration: A Case Study in Western Guizhou Province, China

As a kind of clean energy, the exploration and development of coalbed methane (CBM) are of great importance and significance. In this paper, the CBM reservoir parameters of a working area in Western Guizhou Province, China, were predicted by using 3D seismic exploration technology, and the sweet-spot area was evaluated based on the prediction results. In terms of data interpretation, while the traditional technology is extended to the study of CBM, new technologies and methods suitable for CBM were also actively explored, especially in the quantitative prediction methods of parameters such as coal seam thickness, CBM content, coal body structure, in situ stress, etc., and a three-highs quantitative prediction technology of CBM sweet spots characterized by high precision, high resolution, and high coincidence was explored, which is based on logging evaluation and petrophysics. In addition, in the comprehensive evaluation of multiparameter sweet spots, the multiparameter weighted step-by-step evaluation method based on inversion was innovatively proposed, which made the prediction of CBM sweet spots more focused, effective, and practical, and the distribution law of sweet spots was more consistent with the geological law, providing enough basis for subsequent well location deployment. Based on this method, the C409 coal seam was selected as the sweet spot.

Quantitative Prediction Method of Liquid Retention Based on Nuclear Magnetic Resonance

For tight gas reservoirs such as water-sensitive and low permeability, the incoming fluids are the most important external factors that damage oil and gas reservoirs. The liquid phase retention has become an important influence factor of production capacity. At present, the water blockage damage degree is often used to evaluate the liquid phase retention degree. Therefore, based on the study of fractal dimension by a NMR (nuclear magnetic resonance) experiment, using the existing formula of the fractal calculation of the relative permeability curve, this paper improves the relevant formula for calculating water blockage damage for NMR and studies the relative permeability curve and water blockage damage rate of tight gas reservoirs. According to the calculation results, the fractal dimension of the samples is 2.3551–2.7417, and the average value is 2.492. This shows that the micro-pore structure of core samples is relatively complex with medium heterogeneity. Through the analysis of the relative permeability curve, it can be deduced that the rocks in this block have strong hydrophilicity, and the gas–water two-phase seepages in this block strongly interfere with each other. Besides, the comparative analysis shows that the method of calculating water blockage damage rate is accurate and the average error is only 4.59%. The average damage degree of water blockage in this block is moderate water blockage damage. The results of the parametric analysis also demonstrate that irreducible water saturation and pore-throat structure relationship are the key factors governing the water blockage degree, which determines the damage degree of foreign liquid retention to reservoirs.

Tensile behaviour of isotactic polypropylene with different crystallinities and service temperatures

Isotactic polypropylene (iPP) has been increasingly used owing to its advantages. However, the variation in crystallinity and service temperature of this material will affect its mechanical behaviour significantly, resulting in a lightweight material and an unreliable fatigue resistance prediction. In this study, a prediction model was established for the tensile behaviour, crystallinity, and service temperature of iPP. The model was composed of three parameter functions established separately based on three stress-strain stages. The undetermined material constants of the model were obtained by fitting the tensile experimental data under different crystallinities and service temperatures. Additionally, a control group of the tensile experiment was conducted under different conditions, and the predicted values were compared with the stress results of the control experiment to verify the accuracy of the prediction model. The results showed that the fitted R-square values were all greater than 0.91 for the undetermined material constants, and the maximum error between the experimental and predicted data was 9.58%. The model provides a quantitative prediction method for the tensile behaviour of iPP considering both crystallinity and service temperature, achieving both a lightweight material and fatigue resistance prediction of iPP.