Absolute Relative Error Research Articles

Analysis of Hot Tensile Fracture and Flow Behaviors of Inconel 625 Superalloy.

In this work, Inconel 625 alloy is explored regarding high-temperature tensile deformation and fracture behaviors at a strain rate of 0.005-0.01 s-1 under a deformation temperature ranging from 700-800 °C. The subsequent analysis focuses on the impact of deformation parameters on flow and fracture characteristics. The fractured surface reveals that ductile fracture is dominated by the nucleation, growth, and coalescence of microvoids as the primary failure mechanisms. The elevated deformation temperature and reduced strain rate stimulate the level of dynamically recrystallized (DRX) structures, resulting in intergranular fractures. The Arrhenius model and the particle swarm optimization-artificial neural network (PSO-ANN) model are developed to predict the hot tensile behavior of the superalloy. It indicates that the PSO-ANN model exhibits a correlation coefficient (R) as high as 0.9967, surpassing the corresponding coefficient of 0.9344 for the Arrhenius model. Furthermore, the relative absolute error of 9.13% (Arrhenius) and 1.85% (PSO-ANN model) are recorded. The developed PSO-ANN model accurately characterizes the flow features of the Inconel 625 superalloy with high precision and reliability.

Prediction of Particle Settling Velocity in Newtonian and Power-Law Fluids Using Artificial Neural Network Model

In petroleum engineering, accurately predicting particle settling velocity during various stages of a well’s life cycle is vital. This study focuses on settling velocities of both spherical and non-spherical particles in Newtonian and non-Newtonian fluids. Utilizing a dataset of 931 experimental observations, an artificial neural network (ANN) model with a 7-42-1 architecture is developed (one input layer, one hidden layer with 42 neurons, and one output layer). This model effectively incorporates particle settling orientation and the inclusion of the settling area ratio, enhancing its predictive accuracy. Achieving an average absolute relative error (AARE) of 8.51%, the ANN model surpasses traditional empirical correlations for settling velocities in both Newtonian and power-law fluids. Key influencing factors, such as the consistency index and particle equivalent diameter, were identified. This approach in ANN model construction and data analysis represents a significant advancement in understanding particle dynamics.

Statistical Modeling for Analysis of Growth and Trend Pattern of Wheat Production in Selected States of India

In the present paper, the time series analysis of wheat production in some selected states of India has been carried out by fitting well-known statistical models, viz. linear, exponential and cubic models. The selection of wheat growing states has been made on the basis of criteria of higher production and consistent growth pattern. The secondary time series data on wheat production have been utilized for the analysis. The trend values have been computed on fitting the concerned models, and the validity of the models has been tested on using the chi-square test statistic. Moreover, the coefficient of determination ( ), root mean square error (RMSE), and relative mean absolute percentage error (RMAPE) have been computed to reveal the suitability of the concerned models for exploring the trend patterns of wheat production in the concerned states of India. The findings of the investigation reveal that the above mentioned models are appropriate for forecasting of future trend of wheat production in the concerned states.

Thermal deformation behavior investigation of Ti–10V–5Al-2.5fe-0.1B titanium alloy based on phenomenological constitutive models and a machine learning method

The two-phase titanium alloy Ti–10 V–5Al-2.5Fe-0.1 B was taken as the experimental material, and thermal compression experiments were carried out at a deformation temperature of 770–920 °C and a strain rate of 0.0005–0.5 s−1. An Arrhenius model, a modified Johnson-Cook model, and an improved BP neural network model based on the sparrow search algorithm (SSA-BP) model were established to predict the high temperature rheological stress of the alloy. A comparison of the prediction accuracy of the three models was made. When the partial random data in the rheological curves was used for model building and relatively independent data were used for predicting the rheological stress, the SSA-BP model had higher prediction accuracy, which exhibits the highest mean square correlation coefficient (R2) value of 0.9992 and the lowest root mean square error (RMSE) and average absolute relative error (AARE) values of 1.3031, and 2.0947 %, respectively. The ability of three models to predict the rheological stress for the new process parameters was verified. Results show that the SSA-BP model still has better prediction ability, which exhibits the highest mean square correlation coefficient (R2) value of 0.9720 and the lowest root mean square error (RMSE) and average absolute relative error (AARE) values of 5.0099, and 6.0382 %, respectively. The predicted values of SSA-BP for the rheological stress were used to construct the hot processing map. Results show that the trend of the power dissipation factor (η) value from the hot processing map predicted by SSA-BP can well agree with the microstructure evolution of the alloy.

Novel Pressure-Based Optimization Method Using Deep Learning Techniques

Traditional optimization methods usually perform aerodynamic design by manipulating geometry shapes, which would ignore useful information in flowfields. In order to improve the defect, a novel pressure-based optimization (PBO) method is developed in this study to conduct the design of airfoils using deep learning techniques. In this method, a one-dimensional convolutional auto-encoder (1D-CAE) is employed to extract representative features from the pressure distributions. With these latent features as inputs, two multilayer perceptrons are constructed to predict airfoil profiles and forces, respectively. Furthermore, these deep learning models are combined with the genetic algorithm to minimize the drag of the RAE2822 airfoil. Finally, two data mining techniques are implemented to investigate the optimization mechanisms. Results show that, after the latent dimension reaches 12, the reconstructed pressure distributions by 1D-CAE agree well with the original ones. The predicted forces are close to the observations, with the mean absolute relative error below 0.21% for CL and 0.69% for CD on the testing set. Meanwhile, the predicted airfoils show a good match with the true profiles, and the root mean square error is less than 0.08% for all the testing samples. Optimized results show that, compared with several state-of-the-art optimization approaches, the proposed PBO method achieves a lower drag coefficient and has the potential to provide better airfoil designs. In addition, the discovered mechanisms indicate that the pressure distributions could be manipulated by varying pressure features to achieve drag reduction of airfoils.

Proposing hybrid prediction approaches with the integration of machine learning models and metaheuristic algorithms to forecast the cooling and heating load of buildings

Accurate prediction of heating and cooling loads in residential buildings is crucial for both researchers and practitioners. This study employs advanced forecasting techniques, utilizing support vector regression and extreme gradient boosting methods, enhanced by state-of-the-art metaheuristic algorithms. The metaheuristic optimizers applied include the Satin Bowerbird Optimizer, Ant Lion Optimizer, Artificial Ecosystem-Based Optimizer, Slime Mold Optimizer, Moth-Flame Optimizer, and Particle Swarm Optimizer. These optimizers are strategically used to refine the forecasting models, optimizing their parameters for increased precision. To evaluate the models, a suite of statistical indices is used, including mean square error, root mean square error, Mean Absolute Percentage Error, Mean Absolute Error, Relative Absolute Error, coefficient of correlation, Coefficient of Determination, and Normalized Mean Square Error. This comprehensive analysis assesses the effectiveness of the forecasting methods. The study's findings highlight that the combination of the Satin Bowerbird Optimizer and extreme gradient boosting is particularly effective, achieving high coefficients of determination for cooling and heating load predictions (0.95826 and 0.938048, respectively). This hybrid algorithm shows remarkable performance, with minimal error values and consistent convergence across various datasets. In summary, this research underscores the efficiency of integrating sophisticated machine learning models with metaheuristic optimization techniques, particularly identifying a potent hybrid algorithm for the accurate prediction of heating and cooling loads in residential buildings.

Flexural and split tensile strength of concrete with basalt fiber: An experimental and computational analysis

The objective of this study is to create comprehensive multiscale models for predicting the split tensile strength (STS) and flexural strength (FS) of basalt fiber-reinforced concrete, with the intention of its use in the construction industry. To meet this objective, STS and FS data were collected from various academic research investigations. The collected data was further expanded by experimentally analyzing the FS and STS of basalt fiber (0.1 %, 0.2 %, 0.3 %, and 0.4 % by volume)-loaded concrete. The experimental investigation shows FS and STS increased with basalt fiber loading. The highest FS was 5.11 MPa (0.4 % basalt fiber), and the highest STS was 2.24 MPa (0.3 % basalt fiber). The collected STS (114 data) and FS (103 data) datasets were statistically examined and modelled using soft computing techniques. Seven soft computing techniques, namely Random Forest (RF), Stochastic Random Forest (Stochastic-RF), Random Tree (RT), Stochastic Random Tree (Stochastic-RT), Bagging Random Forest (Bagging-RF), Bagging Random Tree (Bagging-RT) and Artificial Neural Network (ANN) were used to predict the FS and STS of basalt fiber-reinforced concrete using nine inputs and two outputs. The accuracy of the models was evaluated using comprehensive measure (COM), correlation coefficient (CC), mean absolute error (MAE), root relative squared error (RRSE), relative absolute error (RAE), Nash-Sutcliffe efficiency (NSE), and root mean square error (RMSE). The Stochastic-RT model had better predictive ability for FS, as seen by its lowest COM value of 0.121, and optimal values for CC, MAE, RRSE, NSE, RAE, and RMSE. Conversely, with a minimal COM value of 0.0279, the Bagging-RT model showed better accuracy in predicting the STS of concrete. Furthermore, sensitivity analysis revealed that basalt fiber length has the most significant effect on FS prediction, whereas curing time is the most crucial element influencing the STS of the concrete.

Introducing the f0% method: a reliable and accurate approach for qPCR analysis

BackgroundqPCR is a widely used technique in scientific research as a basic tool in gene expression analysis. Classically, the quantitative endpoint of qPCR is the threshold cycle (CT) that ignores differences in amplification efficiency among many other drawbacks. While other methods have been developed to analyze qPCR results, none has statistically proven to perform better than the CT method. Therefore, we aimed to develop a new qPCR analysis method that overcomes the limitations of the CT method. Our f0% [eff naught percent] method depends on a modified flexible sigmoid function to fit the amplification curve with a linear part to subtract the background noise. Then, the initial fluorescence is estimated and reported as a percentage of the predicted maximum fluorescence (f0%).ResultsThe performance of the new f0% method was compared against the CT method along with another two outstanding methods—LinRegPCR and Cy0. The comparison regarded absolute and relative quantifications and used 20 dilution curves obtained from 7 different datasets that utilize different DNA-binding dyes. In the case of absolute quantification, f0% reduced CV%, variance, and absolute relative error by 1.66, 2.78, and 1.8 folds relative to CT; and by 1.65, 2.61, and 1.71 folds relative to LinRegPCR, respectively. While, regarding relative quantification, f0% reduced CV% by 1.76, 1.55, and 1.25 folds and variance by 3.13, 2.31, and 1.57 folds regarding CT, LinRegPCR, and Cy0, respectively. Finally, f0% reduced the absolute relative error caused by LinRegPCR by 1.83 folds.ConclusionsWe recommend using the f0% method to analyze and report qPCR results based on its reported advantages. Finally, to simplify the usage of the f0% method, it was implemented in a macro-enabled Excel file with a user manual located on https://github.com/Mahmoud0Gamal/F0-perc/releases.

Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning

The safe and reliable operation of lithium-ion batteries necessitates the accurate prediction of remaining useful life (RUL). However, this task is challenging due to the diverse ageing mechanisms, various operating conditions, and limited measured signals. Although data-driven methods are perceived as a promising solution, they ignore intrinsic battery physics, leading to compromised accuracy, low efficiency, and low interpretability. In response, this study integrates domain knowledge into deep learning to enhance the RUL prediction performance. We demonstrate accurate RUL prediction using only a single charging curve. First, a generalisable physics-based model is developed to extract ageing-correlated parameters that can describe and explain battery degradation from battery charging data. The parameters inform a deep neural network (DNN) to predict RUL with high accuracy and efficiency. The trained model is validated under 3 types of batteries working under 7 conditions, considering fully charged and partially charged cases. Using data from one cycle only, the proposed method achieves a root mean squared error (RMSE) of 11.42 cycles and a mean absolute relative error (MARE) of 3.19% on average, which are over 45% and 44% lower compared to the two state-of-the-art data-driven methods, respectively. Besides its accuracy, the proposed method also outperforms existing methods in terms of efficiency, input burden, and robustness. The inherent relationship between the model parameters and the battery degradation mechanism is further revealed, substantiating the intrinsic superiority of the proposed method.

Modeling a new taper curve and form factor of tree branches using terrestrial laser scanning

Abstract Modeling branch taper curve and form factor contributes to increasing the efficiency of tree crown reconstructions: the branch taper, defined as the sequential measure of diameters along the course of the branch, is pivotal to accurately estimate key branch variables such as biomass and volume. Branch diameters or volumes have commonly been estimated from terrestrial laser scanning (TLS) based on automatized voxelization or cylinder-fitting approaches, given the whole branch length is sufficiently covered by laser reflections. The results are, however, often affected by ample variations in point cloud characteristics caused by varying point density, occlusions, and noise. As these characteristics of TLS can hardly be sufficiently controlled or eliminated in automatized techniques, we proposed a new branch taper curve model and form factor, which can be employed directly from the laser reflections and under variable point cloud characteristics. In this paper, the approach is demonstrated on primary branches using a set of TLS-derived datasets from a sample of 20 trees (six species). The results showed an R2 of 0.86 and a mean relative absolute error of 1.03 cm (29%) when validated with field-measured diameters. The approach improved the accuracy of diameter estimates for the fine branch scales (<10 cm) as compared to the quantitative structural model (QSM). Our approach also allowed branch diameter estimation for a relatively larger number of manually recognized primary branches (>85%) from point clouds when validated with panoramic images acquired simultaneously with laser scanning. Frequently used automatized crown reconstructions from QSM, on the other hand, were affected by gaps in the point clouds due to obstruction, with the crown-tops and finer branches being the most critical. Our approach reports mean form factors across the examined species of 0.35 and 0.49, with the diameters determined at 5% and 10% of the total branch length, respectively. Our approach may have the potential to produce branch volume information with reasonable accuracy from only knowing the length and respective diameter of each branch. Our model delivers a first approximation for the taper curve and form factor for primary branches but was developed on a relatively small set of samples. We believe that our approach holds the potential to improve the accuracy of the assessment of branch diameter and volume from TLS data. The approach may also be extended to other branch orders. This could expand the horizon for volumetric calculations and biomass estimates from non-destructive TLS proxies in tree crowns.

Astroconformer: The prospects of analysing stellar light curves with transformer-based deep learning models

ABSTRACT Stellar light curves contain valuable information about oscillations and granulation, offering insights into stars’ internal structures and evolutionary states. Traditional asteroseismic techniques, primarily focused on power spectral analysis, often overlook the crucial phase information in these light curves. Addressing this gap, recent machine learning applications, particularly those using Convolutional Neural Networks (CNNs), have made strides in inferring stellar properties from light curves. However, CNNs are limited by their localized feature extraction capabilities. In response, we introduce Astroconformer, a Transformer-based deep learning framework, specifically designed to capture long-range dependencies in stellar light curves. Our empirical analysis centres on estimating surface gravity (log g), using a data set derived from single-quarter Kepler light curves with log g values ranging from 0.2 to 4.4. Astroconformer demonstrates superior performance, achieving a root-mean-square-error (RMSE) of 0.017 dex at log g ≈ 3 in data-rich regimes and up to 0.1 dex in sparser areas. This performance surpasses both K-nearest neighbour models and advanced CNNs. Ablation studies highlight the influence of receptive field size on model effectiveness, with larger fields correlating to improved results. Astroconformer also excels in extracting νmax with high precision. It achieves less than 2 per cent relative median absolute error for 90-d red giant light curves. Notably, the error remains under 3 per cent for 30-d light curves, whose oscillations are undetectable by a conventional pipeline in 30 per cent cases. Furthermore, the attention mechanisms in Astroconformer align closely with the characteristics of stellar oscillations and granulation observed in light curves.

On the Evaluation of Coal Strength Alteration Induced by CO2 Injection Using Advanced Black-Box and White-Box Machine Learning Algorithms

Summary The injection of carbon dioxide (CO2) into coal seams is a prominent technique that can provide carbon sequestration in addition to enhancing coalbed methane extraction. However, CO2 injection into the coal seams can alter the coal strength properties and their long-term integrity. In this work, the strength alteration of coals induced by CO2 exposure was modeled using 147 laboratory-measured unconfined compressive strength (UCS) data points and considering CO2 saturation pressure, CO2 interaction temperature, CO2 interaction time, and coal rank as input variables. Advanced white-box and black-box machine learning algorithms including Gaussian process regression (GPR) with rational quadratic kernel, extreme gradient boosting (XGBoost), categorical boosting (CatBoost), adaptive boosting decision tree (AdaBoost-DT), multivariate adaptive regression splines (MARS), K-nearest neighbor (KNN), gene expression programming (GEP), and group method of data handling (GMDH) were used in the modeling process. The results demonstrated that GPR-Rational Quadratic provided the most accurate estimates of UCS of coals having 3.53%, 3.62%, and 3.55% for the average absolute percent relative error (AAPRE) values of the train, test, and total data sets, respectively. Also, the overall determination coefficient (R2) value of 0.9979 was additional proof of the excellent accuracy of this model compared with other models. Moreover, the first mathematical correlations to estimate the change in coal strength induced by CO2 exposure were established in this work by the GMDH and GEP algorithms with acceptable accuracy. Sensitivity analysis revealed that the Spearman correlation coefficient shows the relative importance of the input parameters on the coal strength better than the Pearson correlation coefficient. Among the inputs, coal rank had the greatest influence on the coal strength (strong nonlinear relationship) based on the Spearman correlation coefficient. After that, CO2 interaction time and CO2 saturation pressure have shown relatively strong nonlinear relationships with model output, respectively. The CO2 interaction temperature had the smallest impact on coal strength alteration induced by CO2 exposure based on both Pearson and Spearman correlation coefficients. Finally, the leverage technique revealed that the laboratory database used for modeling CO2-induced strength alteration of coals was highly reliable, and the suggested GPR-Rational Quadratic model and GMDH correlation could be applied for predicting the UCS of coals exposed to CO2 with high statistical accuracy and reliability.

A phenomenological constitutive model of Novel Rheo Gravity Die Cast Al-15Mg2Si-4.5Si-0.01Sr-0.015B composite

The present study discusses the high temperature deformation behaviour as well as phenomenological constitutive model development of the novel Rheo gravity die cast (RGDC) Al-15Mg2Si-4.5Si-0.01 Sr-0.015B composite. Within the scope of the study, uniaxial isothermal compression tests are performed on the RGDC Al-15Mg2Si-4.5Si-0.01 Sr-0.015B composite, covering a range of strain rates from 10−3 to 10 s−1 and deformation temperatures spanning from 250 °C to 450 °C. Analysis using X-ray Diffraction (XRD), Energy dispersive spectroscopy (EDS) and Electron Probe Micro Analyzer (EPMA) revealed the presence of distinct phases within the material, including primary Al, Mg2Si, and elemental Si. The study employed three different constitutive models i.e., the Johnson-Cook (JC), modified Johnson-Cook (mJC), and sine hyperbolic Arrhenius (shA) types, to predict the flow stress of the material as a function of strain, strain rate, and deformation temperature. The results indicated that the sine hyperbolic Arrhenius type model and the modified Johnson Cook model effectively accounted the coupling effect of strain, strain rate, and deformation temperature, which affect the flow stress. Statistical analysis, specifically Pearson coefficient correlation (R), average absolute relative error (AARE) and standard deviations, established a reasonable agreement between the predicted flow stress values and the experimental flow stress data. Furthermore, it is observed that the sine hyperbolic Arrhenius type model exhibited superior accuracy compared to the modified Johnson Cook model, particularly at higher strain levels.

A novel evaluation method of natural gas hydrate saturation in reservoirs based on the equivalent medium theory

Natural gas hydrate saturation (NGHS) in reservoirs is one of the critical parameters for evaluating natural gas hydrate resource reserves. Current widely-accepted evaluation methods developed for evaluating conventional natural gas saturation in reservoirs, to some extents, are not sufficient enough to obtain accurate predicted results. In light of the equivalent medium theory, the natural gas hydrate is regarded as the fluid (Mode A) when NGHS is relatively low, while it is regarded as the rock matrix (Mode B) when NGHS is high. Two mathematical model are then developed for evaluating NGHS at Mode A and B. Experimental verification shows that R2 of the predicted results based upon the proposed model is 0.968, and the average absolute relative error percentage is 8.90%. The error of the predicted results gradually decreases with increasing NGHS, whereas increases with increasing confining pressure. In addition, the proposed model has been applied to the 142.9–147.7 m well section of Well DK-1 in the permafrost region, Qilian Mountains. The results show that the error of the predicted results is less than 13.92%, with its average error being 10.51%. The predicted value gradually increases with its error decreasing as the depth continues to increase, which is consistent with the change behavior of measured data. NGHS evaluation method proposed in this paper fully considers the occurrence form of natural gas hydrate in reservoirs. The model parameters are easy to determine and the predicted results are reliable.

The development of inflow discharge for the karian multipurpose reservoir in the pursuit of reservoir management optimization

Climate change and land cover modifications result in alterations in hydrological regimes. The demand for water and electrical energy continually rises along with population growth. Consequently, optimizing the Karian Multipurpose Reservoir (Hydroelectric Exploitation) operation requires considering hydrological regime changes. The Karian multipurpose reservoir is designed to meet water needs in Banten Province. The strategic policy for the Reservoir is to provide raw water at a rate of 14.6 m3/s. Of this, 9.1 m3/s is diverted to Tangerang Regency, and 5.5 m3/s is directed to Serang City through Ciujung River. Before being released into the Ciujung River, a flow of 5.5 m3/s is channeled through turbines to generate 1.8 MW of electricity. This study compares two models for estimating discharge to support Karian Reservoir management: (1) The Rainfall Conversion Ratio (CR) and Catchment Area, and (2) The Continuous model. The Rainfall CR and Catchment Area has a correlation value of 0.523 with CR KOICA, Absolute Relative Error (ARE) of 0.54, and Root Mean Square Error (RMSE) of 10.61. Meanwhile, the continuous model has a correlation value of 0.877 with CR KOICA, ARE of 0.18, and RMSE of 3.64. The results indicate the continuous model is the most effective in estimating input discharge.

A One-Dimensional Convolutional Neural Network for Fast Predictions of the Oil-CO2 Minimum Miscibility Pressure in Unconventional Reservoirs

Summary Miscible carbon dioxide (CO2) injection has proven to be an effective method of recovering oil from unconventional reservoirs. An accurate and efficient procedure to calculate the oil-CO2 minimum miscibility pressure (MMP) is a crucial subroutine in the successful design of a miscible CO2 injection. However, current numerical methods for the unconventional MMP prediction are very demanding in terms of time and computational costs which result in long runtime with a reservoir simulator. This work proposes to employ a one-dimensional convolutional neural network (1D CNN) to accelerate the unconventional MMP determination process. Over 1,200 unconventional MMP data points are generated using the multiple-mixing-cell (MMC) method coupled with capillarity and confinement effects for training purposes. The data set is first standardized and then processed with principal component analysis (PCA) to avoid overfitting. The performance of the proposed model is evaluated with testing data. By applying the trained model, the unconventional MMP results are almost instantly produced and a coefficient of determination of 0.9862 is achieved with the testing data. Notably, 98.58% of predicting data points lie within 5% absolute relative error. This work demonstrates that the prediction of unconventional MMP can be significantly accelerated, compared with the numerical simulations, by the proposed well-trained deep learning model with a slight impact on the accuracy.

A Measure of Semantic Class Difference of Point Reprojection Pairs in Camera Pose Estimation

In this paper, we propose a new measure that evaluates the semantic errors of camera poses in visual odometry (VO) and visual simultaneous localization and mapping (VSLAM). Traditionally, VO/VSLAM methods have used photometric images to estimate camera poses, but they suffer from varying illumination and viewpoint changes. Thus, methods using semantic images have been an alternative to increase consistency, as semantic information has shown its robustness even in hostile environments. Our measure compares semantic classes of map point reprojection pairs between images to improve the camera pose estimation accuracy in VO/VSLAM. To evaluate the difference between semantic classes, we adopt the normalized information distance (NID) from information theory. Furthermore, we suggest a weight parameter to balance the existing error of VO/VSLAM with the semantic error introduced by our approach. Our experimental results, obtained from the VKITTI and KITTI benchmark datasets, show that the proposed semantic error measure reduces both the relative pose error (RPE) and absolute trajectory error (ATE) of camera pose estimation compared to the existing photometric image-based errors of indirect and direct VO/VSLAM.

Comparative Analysis of Nonlinear Methods for Multivariable Water Level Prediction: The Case Study of the Atrato River

This paper presents an innovative multivariate forecasting application for hydrological variables, using an online model based on backpropagation (BP) neural networks. The effectiveness of this approach is verified by using the Nonlinear Autoregressive with Exogenous Inputs (NARX) and the linear Autoregressive with Exogenous Inputs (ARX) methods. The proposed methodology is implemented in two hydrological stations in the department of Chocó, Colombia, located along the Atrato River. The BP neural network structure is applied to establish correlations between water level, flow, and precipitation. This structure is designed to handle the dynamic complexity of the hydrological variables and their interconnections. In addition, a short‐term water level prediction is developed for incorporation into a flood early warning system. Validation of the approach is performed by comparing various estimation errors using regression metrics such as root mean square error (RMSE), relative mean square error (MSRE), mean absolute error (MAE), relative mean absolute error (MARE), and Nash–Sutcliffe efficiency coefficient (NSE). The computation time and the accuracy of the estimated weights versus real data are also considered. The results show that the proposed structure is the most suitable for accurately predicting water levels. It is shown that the backpropagation neural network structure of the proposed model is more effective for water level prediction. This is observed when evaluating the real data compared to the estimated data, obtaining values corresponding to the regression metrics. In particular, for output 2, the RMSE is 0.0742. Compared to the NARX model (RMSE of 0.0985) and the ARX model (RMSE of 0.1265), it is observed that the backpropagation neural network model improves the estimation by 32.6 over the NARX model and by 70.4% over the ARX model. As for the NSE coefficient for output 2 of the model, the backpropagation neural network is the closest to 1 compared to the other two models. For output 2, the backpropagation model obtains a value of 0.9966, the NARX model 0.9958, and the ARX model 0.9914. Another evaluation metric applied to this model is the Kling–Gupta efficiency coefficient (KGE), which is used to evaluate the performance of hydrological models. For the output of the two hydrological stations located in the Atrato River, we observed that for the backpropagation model a value of 0.9992 was obtained, for the NARX model a value of 0.9988 was obtained, and for the linear ARX model with nonlinear structure a value of 0.9984 was obtained. This indicates that the backpropagation neural network model provides a better estimate, as its value is closer to 1. Furthermore, the computational time executed in the algorithm of the three proposed nonlinear models is calculated, where the backpropagation obtains a calculated value of 350.9 microseconds, for the NARX model the computational time is 5908.7 microseconds and for the ARX nonlinear model, the computational time is 5172.6 microseconds. The model put forward demonstrates its effectiveness in accurately predicting water levels at two key hydrological stations along Colombia’s Atrato River. By incorporating intricate interactions among hydraulic structures and dynamic hydrological conditions, it enhances prediction accuracy. This not only aids in disaster risk management but also streamlines planning processes, particularly within flood early warning systems.

Big Data User Behaviour Prediction Model Incorporating Deep Learning

Abstract With the improvement of the quality of human life, various industries utilize deep learning technology to meet the needs of users. In this paper, after exploring the deep temporal model and deep forest algorithm (DF) model in extracting the characteristics of user behavior features, we propose a user behavior prediction model based on CNN-LSTM and add a front embedding layer as well as a feature fusion layer to improve it and increase the prediction accuracy. The weighted average method is used to integrate CNN-LSTM with DF for algorithmic model fusion, aiming to improve the robustness and stability of the model and achieve accurate predictions of user behavior. In the empirical analysis, the correct rate of the fusion model proposed in this paper exceeds the proper rate of several other models by 11.75-15.73%, and it can reach 11.2% recall at k=20. Meanwhile, the lower the user behavior level is, the higher the prediction accuracy of the CNNLSTM+DF algorithm is, which can reach up to 95.20%. The lower the average relative error and average absolute error are, which can reach 13.45% and 3.92min respectively, which verifies the validity of the fusion model proposed in this paper, and provides a reference for the research in the related fields.

Aging trajectory and end-of-life prediction for lithium-ion battery via similar fragment extraction of capacity degradation curves

Considering the limitations on future general deterioration trend description and local capacity regeneration capture of existing methods, this paper designs a novel aging trajectory and end-of-life (EOL) prediction method for lithium-ion battery via similar fragment extraction of capacity degradation curves. The proposed method attempts to make the following three contributions: 1) By fusion of particle filter (PF)-based general deterioration trend description and similar fragment extraction-based local capacity regeneration capture, the developed method can achieve accurate aging trajectory and EOL prediction. 2) Considering the similarity in degradation paths, a novel dynamic time warping-based similar fragment extraction method is proposed to learn the deterioration path from the same type batteries' limited capacity degradation curves. 3) On the basis of the predicted future capacity, the PF-based capacity empiric degradation model can be iteratively updated to accurately reflect battery future general deterioration trend. The validation results based on Beijing Institute of Technology dataset demonstrate that the maximum mean absolute error and root mean squared error of predicted aging trajectory, and the maximum value of absolute relative error between reference and predicted EOL achieved by the developed method with the help of the same type of battery's limited capacity degradation curves are only 1.09%, 1.28% and 3.23%, respectively.