Leveraging Machine Learning to Model Hydrocarbon-CO2 Solubility Behavior

With the in-depth implementation of China’s “National Strategy for Building a Strong Transportation Network,” the scale of expressway construction has continued to expand. As a result, the number of high-fill and deep-cut subgrade projects under complex geological conditions has increased significantly, leading to a surge in landslide-related issues. Consequently, accurate prediction of slope displacement is of critical importance for early warning and prevention of landslide disasters. This study proposes a hybrid prediction model, VMD-MPA-LSSVM-LSTM (VMLL), which integrates Variational Mode Decomposition (VMD), Marine Predators Algorithm (MPA), Least Squares Support Vector Machine (LSSVM), and Long Short-Term Memory (LSTM) networks. Using monitoring data from the high-fill embankment slope at Hongtuyao as the research subject, the VMLL model is employed to predict slope displacement based on small-sample data. The objective is to provide a more accurate method for early warning of slope displacement. Firstly, the original monitoring data are decomposed into trend displacement components and fluctuation displacement components using Variational Mode Decomposition (VMD). Subsequently, the trend component and the fluctuation component are predicted using Least Squares Support Vector Machine (LSSVM) and Long Short-Term Memory (LSTM) networks, respectively. Finally, the Marine Predators Algorithm (MPA) is employed to optimize the hyperparameters of the predictive models. Based on this framework, a VMLL-based slope displacement prediction model is constructed. To verify the superiority of the VMLL model, a comparative analysis was conducted against LSSVM, LSTM, and the VMD-LSSVM-LSTM models. The results demonstrate that the VMLL model achieves the highest prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.4022%, a Mean Absolute Error (MAE) of 0.016 mm, a Root Mean Square Error (RMSE) of 0.0206 mm, a coefficient of determination (R²) of 94.08%, and a Variance Accounted For (VAF) of 96.5%. Compared with the other three models, the VMLL model reduces the MAPE, MAE, and RMSE by 30.41–67.62%, 30.38–67.40%, and 27.32–71.00%, respectively. Meanwhile, it improves the R² and VAF by 5.95–217.51% and 0.38–11.48%, respectively. These improvements clearly demonstrate that the VMLL model outperforms the other models, indicating its significant advantage over single prediction models. Furthermore, three additional datasets were used to evaluate the model’s performance. The average values of the performance evaluation metrics for these datasets were 0.6207% (MAPE), 0.0238 mm(MAE), 0.0273 mm(RMSE), 90.33%(R²), and 96.81%(VAF), respectively. These results demonstrate the high accuracy and strong robustness of the proposed model in predicting both horizontal displacement and vertical settlement of slopes, providing a reliable methodological framework for slope stability assessment and landslide disaster early warning.

This paper is aimed to introduce and validate a gene expression programming (GEP) model to estimate the rate of air flow in triaxial conditions at various confining pressures incorporating cell pressure, air inlet pressure and air outlet pressure. To achieve the aim of this study, a series of laboratory experiments were designed and carried out and then a database comprising 47 datasets was prepared to develop new predictive models. A gene expression programming (GEP) model for prediction of air flow was proposed using the prepared datasets. In this regard, a series of sensitivity analyses were performed to choose the best GEP model. For comparison purposes, multiple regression (MR) analysis was also employed for air flow estimation. Several performance indices, i.e., coefficient of determination (CoD), mean absolute error (MAE), root mean square error (RMSE) and variance account for (VAF) were considered and calculated to evaluate the performance prediction of the developed models. Considering both training and testing datasets, the developed GEP model can provide higher performance prediction of rate of air flow in comparison to the MR model.

To overcome the low positioning accuracy of piezoelectric actuators (PEAs) caused by the hysteresis non-linearity, a hysteresis compensation control method based on truncated least squares support vector machine(T-LSSVM) is proposed. Firstly, for the low-robustness of least squares support vector machine(LS-SVM), a novel truncation strategy is proposed and a robust truncated least squares support vector machine(T-LSSVM) for hysteresis modeling is established. Then, based on T-LSSVM, the hysteresis inverse model is established to achieve real-time compensation for the hysteresis nonlinearity in PEAs. Finally, based on the hysteresis inverse compensation method, the feedforward-feedback hysteresis compensation control for PEAs is established. To test the proposed control method, the PID feedback control is introduced as comparisons. Experimental results show that the proposed control method is of higher accuracy and better generalization, realizing real-time high-precision tracking control of PEAs.

Prediction of velocity is an important parameter in curved channels. Recently, artificial intelligent methods are developing than the common costly and time-consuming experimental and numerical methods in estimation of flow variables. In the present study, Gene expression programming (GEP) model as developed genetic programming model is used to predict the flow velocity in the channel with a sharp 90° bend. Different input parameter combinations are examined in order to finding the optimum model then the model efficiency are evaluated in estimation of the flow velocity in training and testing phases. By comparing the results of the GEP model with experimental data, there is an acceptable accordance between results with the root mean square error (RMSE) values of 0.828 and 0.8197 in the training and testing phase. The results show that the input parameters of (r,q) (polar points coordinate and the flow discharge) are the most effective parameters in bend flow pattern surveying. With increasing the flow discharge, the model error at the end section of the bend in the outer channel wall is decreased. Also a practical and reliable relationship is proposed by the GEP model and the sensitivity of suggested equation to each of input parameter is evaluated. Furthermore, the uncertainty of the proposed GEP model in the velocity prediction is assessed and different confidence bounds are introduced.

Temperature and solar radiation-based modeling procedures are reported in this study for estimating daily reference evapotranspiration (ET0) by using gene expression programming (GEP) and adaptive neuro-fuzzy inference system (ANFIS). A comparison is also made among these techniques and the corresponding traditional temperature/radiation-based ET0 estimation equations. Two data management scenarios were evaluated for estimating ET0: (1) the models were trained and tested using the local data of each studied weather station; and (2) the models were trained using the pooled data from all the stations and tested in each individual station. The GEP and ANFIS models were found to be better than the Hargreaves–Samani, Makkink and Turc ET0 equations in the first scenario. Comparison of GEP and ANFIS models trained with pooled data and tested for each station showed that the ANFIS models generally performed better than the GEP models. However, the comparison of GEP and ANFIS models trained and tested with pooled data revealed that the GEP models performed better than the ANFIS models in the second scenario.

Camera calibration is one of fundamental issues in computer vision and required for achieving accurate visual measurements. Least Squares Support Vector Machines (LS-SVM) are used to achieve the camera calibration. It doesn't need to confirm the intrinsic and extrinsic parameter of the camera. For a little more accurate calibration, acquired image is divided into two regions according to radial distortion of lens and Least Squares Support Vector Machines is applied to each region. A simple and flexible camera calibration using divided Least Squares Support Vector Machines (DLS-SVM) is proposed in this paper. Experiment results and comparison with BP neural network and Least Squares Support Vector Machines prove the validity of the proposed camera calibration.

This study introduced a new predictive approach for estimating the bearing capacity of driven piles. To this end, the required data based on literature such as hammer strikes, soil properties, geometry of the pile, and friction angle between pile and soil were gathered as a suitable database. Then, three predictive models i.e., gene expression programming (GEP), radial basis function type neural networks (RBFNN) and multivariate nonlinear regression (MVNR) were applied and developed for pile bearing capacity prediction. After proposing new models, their performance indices i.e., root mean square error (RMSE) and coefficient of determination (R2) were calculated and compared to each other in order to select the best one among them. The obtained results indicated that the RBFNN model is able to provide higher performance prediction level in comparison with other predictive techniques. In terms of R2, results of 0.9976, 0.9466 and 0.831 were obtained for RBFNN, GEP and MVNR models respectively, which confirmed that, the developed RBFNN model could be selected as a new model in piling technology. Definitely, other researchers and engineers can utilize the procedure and results of this study in order to get better design of driven piles.

Rigorous modeling of CO2 equilibrium absorption in ionic liquids

Support Vector Machines (SVM) is a new type of machine learning algorithm. Compared with conventional learning algorithms, SVM enhances the generalization ability of the models by employing structural risk minimization criterion to minimize the sample errors and simultaneously decrease the upper bound of the predict error of the models. The global optimal solution can be uniquely obtained owing to that SVM converts machine learning into quadratic programming. Based on the local data from hydrogenation equipment, a predictive model using Least Squares Support Vector Machines (LS-SVM) is established for three important quality targets of diesel oil in this paper, and compared with neural network and stands SVM on precision. Finally, it is proved that the proposed predictive models based on LS-SVM can predict the quality target more efficiently and rapidly than stands SVM and neural network. It provided a method for online diagnosing fault of quality targets.

Cementitious composites' performance degrades in extreme conditions, making it more important to enhance its resilience. To further the adaptability of eco-friendly construction, waste materials are increasingly being repurposed. Cementitious composites deteriorate in both direct and indirect ways due to the facilitation of hostile ion transport by water. The effects of using eggshell and glass powder as partial substitutes for cement and sand in mortar on the water-absorption capacity were investigated using machine learning (ML) modeling techniques such as Gene Expression Programming (GEP) and Multi Expression Programming (MEP). To further assess the importance of inputs, sensitivity analysis and interaction research were carried out. The water absorption property of cementitious composites was precisely estimated by the generated ML models. It was noted that the MEP model, with an R2 of 0.90, and the GEP model, with an R2 of 0.88, accurately predicted results. The sensitivity analysis revealed that the absorption capacity of the mortar was most affected by the presence of eggshell powder, sand, and glass powder. GEP and MEP model's significance lies in the fact that they offer one-of-a-kind mathematical formulas that can be applied to the prediction of features in another database. The mathematical models resulting from this study can help scientists and engineers rapidly assess, enhance, and rationalize mixture proportioning. The built models can theoretically compute the water absorption of cement mortar made from eggshell powder and glass powder based on varied input parameters, resulting in cost and time savings.

Predictive modeling of swell-strength of expansive soils using artificial intelligence approaches: ANN, ANFIS and GEP

In this study, the simulation of groundwater fluctuations in the Kermanshah Plain is carried out via three advanced machine learning algorithms, i.e., GMDH, weighted extreme learning machine (W‐ELM) and gene expression programming (GEP). The objective of this research is to evaluate and compare the accuracy of different machine learning models in simulating and predicting such fluctuations under different conditions. The data used in this study include the monthly groundwater level, precipitation, evaporation and temperature data from 2002 to 2020. To increase the accuracy of the models, the data are processed via the min–max normalisation approach. The results obtained from the evaluation of the models using different efficiency indices, such as the root mean square error (RMSE), R 2 and NSE, indicate that the W‐ELM model, which has the best performance in both the training and testing phases, is more exact than the GMDH and GEP models. In particular, the W‐ELM achieves R 2 = 0.999, NSE = 0.979, PBIAS = 0.012 and RMSE = 0.093 in the testing phase, which indicates its high accuracy and efficiency. The results of the sensitivity analysis indicate that all the models are highly sensitive to the groundwater level lag variable GWL₋₁.This research shows that machine learning models, especially the W‐ELM model, can be utilised as effective tools for predicting groundwater level variation and the optimal management of water resources in different regions.

The hydraulic jump can be used for some purpose such as dissipating the flow energy in order to prevent bed erosion; aerating water and facilitating the mixing procedure of chemical that used for water purification. In this paper, various artificial intelligence (AI) models including gene expression programming (GEP), adaptive-neuro-fuzzy inference system with grid partition (ANFIS-GP), and neural networks (ANNs) were used to estimate developed and non-developed hydraulic jump length. Four various GEP, ANFIS-GP and ANN models including different combinations of Froude number, bed roughness height, upstream and downstream flow depth based on measured experimental data-set were developed to estimate hydraulic jump length variations. The root mean squared error (RMSE) and determination coefficient (R2) indices were applied for testing models’ accuracy. Regarding the comparison results, it was seen that the ANFIS-GP, ANN, and GEP models could be employed successfully in estimating hydraulic jump length. The comparison between three AI approaches emphasized the superiority of ANNs and ANFIS-GP over the other intelligent models for modeling developed and non-developed hydraulic jump length, respectively. For non-developed hydraulic jump, the R2 and RMSE values obtained as 0.87 and 2.84 for ANFIS-GP model.

It is well known that the performance of Least Squares Support Vector Machine (LSSVM) is guaranteed by k-fold cross-validation (k-CS) or other optimized approaches to choose an appropriate setting of a number of parameters including such as the regularization parameter (7) and the kernel parameter (σ) and so on. However, it is mentioned in a large number of research on k-CS that it need more computational time and large computational burden in the process of optimizing parameters for LSSVM. Moreover, the obtained parameters by CS method are fixed and it lead easily to a poor generalization capabilities in various application. In order to avoid k-CS and to implement parameters update online, this paper proposes a novel method which applied Unscented Kalman Filter (UKF) to dynamically implement parameter updating problem for LSSVM. To estimate LSSVM's parameters online, the state and measurement equations of UKF are first constructed by considering LSSVM's parameter choice as state variable and treating LSSVM model as the measurement equation, respectively. Then, the UKF approach is used to update the LSSVM parameters timely according to the last obtained instance. Applying the proposed method, LSSVM parameters are not any more fixed as tuned parameters on the training dataset, but are adjusted dynamically as new measurements arrived. Finally, the viability and superiority of the proposed method are verified by simulation.

For an underwater Strapdown Inertial Navigation System/Doppler velocity log (SINS/DVL) integrated navigation system, the short-term failure of DVL may lead to the loss of reliable external velocity information from DVL, which will cause the SINS errors to accumulate. To circumvent this problem, this paper proposes a velocity predictor based on fuzzy multi-output least squares support vector machine (FMLS-SVM) to predict DVL measurements when DVL malfunctions occur. Firstly, the single-output least squares support vector machine (LS-SVM) model is extended to the multi-output LS-SVM model (MLS-SVM), and the self-adaptive fuzzy membership is introduced to fuzzify the input samples to overcome the over-fitting problem caused by the excessive sensitivity to the outlier points. Secondly, the fuzzy membership function is designed from the idea of the K nearest neighbor (KNN) algorithm. Finally, considering the influence of vehicle maneuver on the prediction model of DVL, the dynamic attitude angles are extended to the input samples of the prediction model to improve the adaptability of the DVL prediction model under large maneuver conditions. The performance of the method is verified by lake experiments. The comparison results show that the velocity predictor based on FMLS-SVM can correctly provide the estimated DVL measurements, effectively prolong the fault tolerance time of DVL faults, and improve the accuracy and reliability of the SINS/DVL integrated navigation system.