Search

The reliance on thermal power plants as well as increased vehicle emissions have constituted the primary factors of serious air pollution. Inhaling too much particulate air pollution may lead to respiratory diseases and even death, especially PM2.5. By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate PM2.5 prediction becomes more important. In this thesis, we propose a PM2.5 prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Autoencoder and Linear interpolation are adopted for solving the missing value problem. Spearman's correlation coefficient is used to identify the most relevant features for PM2.5. Two prediction models (i.e., LSTM and LSTM based on K-means) are implemented which predict PM2.5 value for each Airbox device. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K-means has the best performance among all methods.

This work presents a novel scheme to retrieve soil moisture (SM) from the Cyclone Global Navigation Satellite System (CyGNSS) data, which is accomplished by using a bagged regression trees (BRT) algorithm with the inputs being the CyGNSS-derived products, the corresponding geolocation, and associated climate type. This algorithm is validated with the in situ hourly SM data acquired by China's automatic SM observation stations throughout the year 2018. High consistency between the retrieved SM results and the measured SM is achieved, with a correlation coefficient of 0.86 and a root-mean-square error of 0.05 cm³/cm³. The results obtained in this work indicate that the proposed BRT-based method can effectively estimate SM from CyGNSS data in different scenarios of various station locations and climate types in a near real-time manner.

We study estimation of the correlation ρ in the multivariate linear model with uniform correlation structure. Unbiased estimator of ρ based on moment estimator proposed by Žežula (2006) is derived. Biased and unbiased estimators are compared by bias and mean square error under normal and t-distribution.

The discrete element method has been used to simulate the particle flow in a ball mill under different operating conditions. The model was validated by comparing the simulated results of the flow pattern and input power with those measured from a same-scale laboratory mill. The impact energy of the particles under different operating conditions was analysed in detail. The results showed that the impact energy was affected by the operating conditions of the mill and can be linked to the grinding rate for a given material. The correlation between impact energy and grinding rate follows first-order grinding kinetics. Mill performance decreases with increasing mill size. Furthermore, a data-driven machine learning framework has been proposed to predict the impact energy for different operating conditions. It was found that the prediction for mills with diameters of 2000 and 3000 mm based on the training model developed by mills with diameter less than 254 mm could be achieved with an accuracy of 80% and a correlation coefficient of 0.9. Through the combination of DEM simulation and data-driven approach, the computing time required in the determination of impact energy for large scale mills can be dramatically reduced.

Fabrication of microperforated panel (MPP) using an additive manufacturing (AM) process produced imperfect perforations with an irregular shape, inconsistent size, and rough inner surface (due to burr formation). This imperfect hole condition leads to a significant deviation between measured and modeled acoustic properties. This study aims to introduce the resistance end correction factor ( α ) for quantifying this deviation. The MPP model’s current development excludes the irregular and inconsistent holes from the actual MPP. The improved resistance end correction factor ( α ) is determined based on the actual MPP samples. The MPP’s acoustic properties fabricated using AM process (3D Printing – PolyJet technology) are measured. The improved resistance end correction factor ( α ) is presented in surface plots for different geometrical parameters, perforation diameter ( d ), plate thickness ( t ), and perforation ratio ( σ ). The interpolation method is used to predict the “ α ” value based on the surface plot. The improved relative acoustic resistance value for the actual MPP sample with imperfect perforation condition (with recorded lowest hole roundness value at 0.207) is calculated using the predicted “ α ” value. Comparative results showed that the improved relative acoustic resistance determined based on the interpolated “ α ” agreed well with the experimental measurement results. The correlation coefficient for each comparison varied from 0.885 to 0.987. This finding is better than comparing calculated relative acoustic resistance values by using Maa’s theory and other MPP models with different proposed resistance end correction factors ( α ). Therefore, the proposed technique can reflect the imperfect perforation condition in actual MPP samples.

Annually, the thermal coal industries produce billion tons of fly-ash (FA) as a waste by-product. Which has been proficiently used for the manufacture of FA based geopolymer concrete (FGC). To accelerate the usage of FA in building industry, an innovative machine learning techniques namely gene expression programming (GEP) and multi expression programming (MEP) are employed for forecasting the compressive strength of FGC. The comprehensive database is constructed comprising of 311 compressive strength results. The obtained equations relate the compressive strength of FGC with eight most effective parameters i.e., curing regime (T), time for curing (t) in hours, age of samples (A) in days, percentage of total aggregate by volume (% Ag), molarity of sodium hydroxide (NaOH) solution (M), silica (SiO2) solids percentage in sodium silicate (Na2SiO3) solution (%S), superplasticizer (%P) and extra water (%EW) as percent FA. The accurateness and predictive capacity of both GEP and MEP model is assessed via statistical checks, external validation criteria suggested by different researcher and then compared with linear regression (LR) and non-linear regression (NLR) models. In comparison with MEP equation, the GEP equation has lesser statistical error and higher correlation coefficient. Also, the GEP equation is short and it would be easy to use in the field. So, the GEP model is further utilized for sensitivity and parametric study. This research will increase the re-usage of hazardous FA in the development of green concrete that would leads to environmental safety and monetarist reliefs.

ANSYS was used in this study to simulate the change in permeability of loaded coal under negative pressure. The ANSYS transient structural module was employed to simulate the coal loading conditions and to calculate the coal volumetric strain and coal porosity change. In the ANSYS Fluent module, the porosity of the porous medium was changed to replace the coal deformation, and the outlet pressure was changed to simulate the change of negative pressure. By using 1stOpt software, the relationships among the negative pressure, effective stress, and permeability of coal were fitted, and the binary nonlinear function of permeability varying with effective stress and negative pressure was obtained, and the correlation coefficient was excellent. Results showed that the coal permeability had a negative exponential relationship with effective stress. Hence, the permeability decreased with the increase of the effective stress. The change in stress loading mode caused a sudden change in porosity and permeability. The coal permeability had an approximately linear relationship with negative pressure. Hence, permeability increased with an increase in negative pressure. However, with the increase of effective stress, the influence of negative pressure on coal permeability was gradually weakened.

Porosity estimation is one of the essential issues in petroleum industries to distinguish the reservoir characteristics properly. Therefore, it is of importance to predict porosity with the optimum way to reduce the logging tests. In this study, artificial neural network and fuzzy logics are considered efficient techniques to predict the Asmari formation’s porosity. The results of porosity estimation by intelligent neuro-phase method showed the ability of this method to estimate in complex conditions in Mansouri oilfield. Preparing data before training the neural network increases the power of the network in recognizing the appropriate pattern. In estimating the porosity in the Asmari reservoir of Mansouri field, gamma, acoustic, neutron and density and diameter measurements have a more influential role. Selecting the appropriate architecture for the neuro-phase network is effective in achieving more accurate results. This architecture includes selecting the type and number of membership functions for the inputs and the training algorithm with the appropriate number of iteration steps. The best estimation results by assigning four Gaussian membership functions to gamma image data, two Gaussian membership functions to each of the audio and neutron data, and three Gaussian membership functions to density image data and creating 40 laws in the data space. Inputs were obtained using a hybrid training algorithm. The average error of estimating porosity by the neuro-phase method in well C of Mansouri field is 1.28% in the validation data set, representing a correlation coefficient of 92.5% between the porosity extracted from the fuzzy neuro-fuzzy network and the porosity of the core.

The mechanical properties of complex concentrated alloys (CCAs) depend on their formed phases and corresponding microstructures. The data-driven prediction of the phase formation and associated mechanical properties is essential to discovering novel CCAs. The present work collects 557 samples of various chemical compositions, comprising 61 amorphous, 167 single-phase crystalline, and 329 multi-phases crystalline CCAs. Three classification models are developed with high accuracies to category and understand the formed phases of CCAs. Also, two regression models are constructed to predict the hardness and ultimate tensile strength of CCAs, and the correlation coefficient of the random forest regression model is greater than 0.9 for both of two targeted properties. Furthermore, the Shapley additive explanation (SHAP) values are calculated, and accordingly four most important features are identified. A significant finding in the SHAP values is that there exists a critical value in each of the top four features, which provides an easy and fast assessment in the design of improved mechanical properties of CCAs. The present work demonstrates the great potential of machine learning in the design of advanced CCAs.

The correct identification of gene recombination cold/hot spots is of great significance for studying meiotic recombination and genetic evolution. However, most of the existing recombination spots recognition methods ignore the global sequence information hidden in the DNA sequence, resulting in their low recognition accuracy. A computational predictor called iRSpot-DCC was proposed in this paper to improve the accuracy of cold/hot spots identification. In this approach, we propose a feature extraction method based on dinucleotide correlation coefficients that focus more on extracting potential DNA global sequence information. Then, 234 representative features vectors are filtered by SVM weight calculation. Finally, a convolutional neural network with better performance than SVM is selected as a classifier. The experimental results of 5-fold cross-validation test on two standard benchmark datasets showed that the prediction accuracy of our recognition method reached 95.11%, and the Mathew correlation coefficient (MCC) reaches 90.04%, outperforming most other methods. Therefore, iRspot-DCC is a high-precision cold/hot spots identification method for gene recombination, which effectively extracts potential global sequence information from DNA sequences.

The study aims to assess the trace metals and physicochemical properties of water in the adjacent to the Sylhet gas blowout area. Trace metals were analyzed using atomic absorption spectrophotometer, whereas physicochemical parameters were evaluated in-situ state using portable instruments and also in the laboratory. Trace metals Pb, Cd, and Ni were found in the water samples higher than the acceptable limit by WHO standards, whereas the concentration of Cu and Zn were within acceptable limit, respectively. The correlation coefficient matrix and factor loading analysis spectacle that the interrelationship among the physicochemical parameters, trace elements, as well as other ions are moderate to strongly corellated which reflecting the homogeneous source of origin. According to contamination factor, Nemerow multi-factor index, pollution load index, and also, potential ecological risk index, the water of the region is quite polluted in case of Pb, Cd, and Ni but unpolluted for Cu and Zn. The water quality index indicates that treatment of water is required before using it for domestic purposes. The health quotient and hazard index results are less than standard value 1 suggesting that there is no noncarcinogenic risk in the area. The carcinogenic analysis shows that the lifetime incremental cancer risk mean value of Cd and Ni are fairly insignificant and Pb is more significant for children to cause health problem. The ILCR value of Cd and Ni are insignificant whereas Pb is significant to pose health risk for adults. Physicochemical parameters revealed that the water was slightly acidic and soft in nature implying to avoid the water from this area for drinking purposes. At the end, it can be concluded that this study will be useful for the residence as well as the policymaker to take the protective surveillance measures around the areas.

Objectives The objective of the proposed study is to exploit the technology of high-density surface electromyography (HD-sEMG), in order to evaluate the muscle activation in young and elderly subjects during a daily life gesture, namely, Sit To Stand (STS), using wireless connected ambulatory equipment (TMSi©) and Blind Source Separation (BSS) approach with Canonical Correlation Analysis (CCA). Materials and methods Sixteen subjects participated (50% females) divided into two categories (‘H1’: young (30.62 yrs ±5.92, 23.95 kg/m2 ±3.08), versus ‘H2’: old (61.87 yrs ±7.98, 23.4 kg/m2 ±3.38)), in the recording of HD-sEMG signals, using 32-electrodes square grids (4×8), during Sit To Stand (STS) motion, three times at spontaneous speed. The studied muscle is the Rectus Femoris (RF) muscle. The recorded HD-sEMG signals were analyzed with CCA approach to extract correlation coefficient sets according to two age categories (young versus old), in order to evaluate its discriminating power with ageing. Statistical tests (t-test) were used to evaluate the discrimination for these two categories. Results The calculation of CCA correlation coefficients showed a significant difference between young and old category concerning the mean CCA correlation coefficient (P Conclusion The obtained results are promising and indicate a clear difference between the obtained source variability using CCA method between the young and the old tested subjects during daily life motion. Furthermore, these estimated sources seem to be impacted by both anatomical and functional modifications with ageing.

Varying broadband irradiance and temperature are generally known as the major factors influencing the performance of PV modules, but studies have also shown the substantial impact of spectral variations. In this work, a simple and efficient method to calculate the temperature coefficient using long term data is demonstrated. Temperature coefficients of PV modules are estimated from long term performance data following IEC 60891 standard with additional spectral correction, and are compared against the datasheet values. Significant improvement of correlation coefficient from −0.89 to −0.97 is observed during the regression for maximum power temperature coefficient of two poly-crystalline modules, after spectral correction by spectral factor (SF). Also, the standard deviation of yearly estimated values of these coefficients reduced from 5–7 % to 1–2 %. In another setup involving spectral measurements and various PV technologies, the annual mean of 1.62 eV for average photon energy in 350–1700 nm range, suggests a general blue shift of the spectrum. Higher averages than reference values of useful fraction (UF) for c-Si, CIGS and HIT technologies also validate the blue shift of spectrum. Results show SF produces maximum power temperature coefficients closer to the datasheet values compared to UF, suggesting better applicability of SF as an index for spectral correction. The coefficient values were found closer to STC values and the results from Mann and Kendall test, employed to detect any underlying monotonic trend in the development of temperature coefficients over eight years, showed no increasing or decreasing trend and hence no degradation of temperature coefficients for the long-term exposed PV modules.

Monitoring sediment transport is essential for managing and maintaining rivers. Estimation of the sediment load in rivers is fundamental for the study of sediment movement, erosion, and flood control. In the current study, three machine learning models—multi-layer perceptron (MLP), multi-layer perceptron-stochastic gradient descent (MLP-SGD), and gradient boosted tree (GBT)—were utilized to estimate the suspended sediment load (SSL) at the St. Louis (SL) and Chester (CH) stations on the Mississippi River, U.S. Four evaluation criteria including the Correlation Coefficient (CC), Nash Sutcliffe Efficiency (NSE), Scatter Index (SI), and Willmott's Index (WI) were utilized to evaluate the performance of the used models. A sensitivity analysis of the models to the input variables revealed that the current day discharge variable had the most effect on the SSL at both stations, but in the absence of current-day discharge data (Qt), a combination of input parameters including S S L t − 3 , S S L t − 2 , S S L t − 1 , Q t − 3 , Q t − 2 , Q t − 1 can be used to estimate the SSL. The comparative outcomes indicated the high accuracy of MLP-SGD-5 model with a CC of 0.983, SI of 0.254, WI of 0.991, and NSE of 0.967 at station CH and the MLP-SGD-6 model with a CC of 0.933, SI of 0.576, WI of 0.961, and NSE of 0.867, respectively, at station SL. The results of MLP models were improved by SGD optimization. Therefore, the MLP-SGD method is recommended as the most accurate model for SSL estimation.

With the rapid development of wireless communication technology, the openness of wireless communication makes it more likely to be threated by radio interception or even maliciously use. As a widely used way to exfiltrate information, the wireless covert channel brings a great threat to communication security. Compared with the wireless covert channel on the upper layer, the wireless covert channel based on the physical layer (WCC-P) has better concealment and greater capacity. However, due to the high variation in the wireless communication channel, detecting WCC-P is a challenging task. Existing detection schemes are ineffective at detecting most of WCC-P schemes. In this paper, we propose a new correlation-based scheme to detect WCC-P communication signal. The proposed detection scheme is based on the correlation coefficient of the constellation error vectors (CEV) for multiple antennas. The difference in the correlation coefficient of a detection process provides a critical clue for WCC-P signal detection. Exploiting this observation, we investigate the use of the correlation coefficient in detecting WCC-P communication signal. Simulations show that the proposed scheme can effectively detect WCC-P signal. When the signal-to-noise ratio (SNR) reaches 5 dB, the detection accuracy can reach more than 90%.

IoT-enabled sensor devices and machine learning methods have played an essential role in monitoring and forecasting mine hazards. In this paper, a prediction model has been proposed for improving the safety and productivity of underground coal mines using a hybrid CNN-LSTM model and IoT-enabled sensors. The hybrid CNN-LSTM model can extract spatial and temporal features from mine data and efficiently predict different mine hazards. The proposed model also improves the flexibility, scalability, and coverage area of a mine monitoring system to an underground mine's remote locations to minimize the loss of miners' lives. The proposed model efficiently predicts miner's health quality index (MHQI) for working faces and gases in goaf areas of mines. The experimental results demonstrated that the predicted mean square error of the proposed model is less than 0.0009 and 0.0025 for MHQI; 0.0011 and 0.0033 for CH4 in comparison with CNN and LSTM models, respectively. The less means square error indicates the better prediction accuracy of the trained. Similarly, the correlation coefficient (R2) value of the proposed model is found greater than 0.005 and 0.001 for MHQI; 0.007 and 0.001 for CH4 compared to CNN and LSTM models, respectively. Thus, the proposed CNN-LSTM model performed better than the two existing models.

Laser-induced breakdown spectroscopy (LIBS) has been proved as an on-line detection technology to measure the carbon content in fly ash, which is beneficial for immediate assessment of the boiler combustion efficiency. Support vector regression (SVR) was adopted as the quantitative model for the carbon content measurement in fly ash in this study. Ash species was one of the key factors affecting quantitative accuracy. Experiments have proven that, the index of plasma temperature and the electron density among different species could be similar, while the partition function ratios and the temperature correction factor showed obvious differences among different ash species. Based on the partition function ratios, the Matrix Effect Correction Factor (MECF) was defined. SVR model was optimized by MECF and the analysis results showed that the correlation coefficient of calibration (R2) increased from 0.989 to 0.991, the root-mean-square error of calibration (RMSEC) decreased from 2.02% to 0.850%, the root-mean-square error of prediction (RMSEP) decreased from 2.13% to 1.07%, and averaged relative standard deviation (ARSD) decreased from 8.62% to 1.89%. The results showed that SVR combined with MECF was an effective method to improve the accuracy of LIBS quantitative analysis of the carbon content in fly ash.

This paper presents the development of models for the prediction of power generation at the Samanalawewa hydropower plant, which is one of the major power stations in Sri Lanka. Four regression-based machine learning and statistical techniques were applied to develop the prediction models. Rainfall data at six locations in the catchment area of the Samanalawewa reservoir from 1993 to 2019 were used as the main input variables. The minimum and maximum temperature and evaporation at the reservoir site were also incorporated. The collinearities between the variables were investigated in terms of Pearson’s and Spearman’s correlation coefficients. It was found that rainfall at one location is less impactful on power generation, while that at other locations are highly correlated with each other. Prediction models based on monthly and quarterly data were developed, and their performance was evaluated in terms of the correlation coefficient (R), mean absolute percentage error (MAPE), ratio of the root mean square error (RMSE) to the standard deviation of measured data (RSR), BIAS, and the Nash number. Of the Gaussian process regression (GPR), support vector regression (SVR), multiple linear regression (MLR), and power regression (PR), the machine learning techniques (GPR and SVR) produced the comparably accurate prediction models. Being the most accurate prediction model, the GPR produced the best correlation coefficient closer to 1 with a very less error. This model could be used in predicting the hydropower generation at the Samanalawewa power station using the rainfall forecast.

形態: カラー図版あり, Physical characteristics: Original contains color illustrations, Accepted: 2021-07-14, 資料番号: PA2210060000

The axial hydraulic force of centrifugal pump is an important parameter affecting pump performance. The force mainly includes the force inside impeller and in clearance. Due to the special structural characteristics of the clearance, the influence of grid discretization method on the calculation of axial force in the clearance is not fully understood. Therefore, based on the Reynolds-averaged method with shear stress transport turbulence model, an orthogonal experiment was designed to compare the correlation coefficient of velocity and pressure distribution between shear stress transport model and large eddy simulation models. A more suitable grid discretization strategy was found by artificial neural network for grid calibration. When the strategy is applied to the entire centrifugal pump, the prediction of axial force has high accuracy. The range analysis shows that the grid node number in the wall-wall direction has the greatest impact on velocity distribution. When the mesh parameters are in a certain range, it can compromise between the simulation accuracy and computational resource. The Reynolds-averaged model based simulation is proved accurate in capturing the complex velocity and pressure field inside clearance. The entire pump model is also used for the verification after the calibration of grid. The typical axial force law can be found under different flow rate conditions. This study provides a significant guidance in determining the grid scheme for accurate prediction of centrifugal pump’s axial force. It makes the computational fluid dynamics simulation feasible in the initial design of centrifugal pump which specifically considers the axial force problem.

The water flooding characteristic curve method is one of the essential techniques to predict recoverable reserves. However, the recoverable reserves indicated by the existing water flooding characteristic curves of low-amplitude reservoirs with strong bottom water increase gradually, and the current local recovery degree of some areas has exceeded the predicted recovery rate. The applicability of the existing water flooding characteristic curves in low-amplitude reservoirs with strong bottom water is lacking, which affects the accurate prediction of development performance. By analyzing the derivation process of the conventional water flooding characteristic curve method, this manuscript finds out the reasons for the poor applicability of the existing water flooding characteristic curve in low-amplitude reservoir with strong bottom water and corrects the existing water flooding characteristic curve according to the actual situation of the oilfield and obtains the improvement method of water flooding characteristic curve in low-amplitude reservoir with strong bottom water. After correction, the correlation coefficient between $$\frac{{k_{ro} }}{{k_{rw} }}$$ k ro k rw and $$S_{w}$$ S w is 95.92%. According to the comparison between the actual data and the calculated data, in 2021/3, the actual water cut is 97.29%, the water cut predicted by the formula is 97.27%, the actual cumulative oil production is 31.19 × 104t, and the predicted cumulative oil production is 31.31 × 104t. The predicted value is consistent with the actual value. It provides a more reliable method for predicting low-amplitude reservoirs' recoverable ability with strong bottom water and guides the oilfield's subsequent decision-making.

Owing to the indeterminacy, incompleteness, and inconsistency of decision makers’ arguments/cognitions regarding complicated decision-making problems, the truth, falsity, and indeterminacy degrees given by decision makers may imply the partial certainty and partial uncertainty information. In this case, a simplified neutrosophic set (SNS) cannot express the uncertainty degrees of the truth, falsity, indeterminacy arguments. To depict the hybrid information of SNS and neutrosophic (indeterminate) numbers (NNs) together, this study presents a simplified neutrosophic indeterminate set (SNIS) to describe the uncertainty degrees of the truth, falsity, indeterminacy, and then based on the de-neutrosophication technology using the parameterized SNSs of SNISs we introduce the q-indeterminate correlation coefficients of SNISs with a parameter q ∈ [0, 1]. Next, a simplified neutrosophic indeterminate multicriteria decision-making method using the qindeterminate correlation coefficients of SNISs is established along with decision makers’ risk attitudes, such as the small risk for q = 0, the moderate risk for q = 0.5, and the large risk for q = 1, to carry out multicriteria decision-making problems in SNIS setting. Eventually, the proposed decision-making approach is applied in an example of selecting a satisfactory slope design scheme for an open pit mine to indicate the practicality and flexibility in SNIS setting.

Correcting the forecast bias of numerical weather prediction models is important for severe weather warnings. The refined grid forecast requires direct correction on gridded forecast products, as opposed to correcting forecast data only at individual weather stations. In this study, a deep learning method called CU-net is proposed to correct the gridded forecasts of four weather variables from the European Centre for Medium-Range Weather Forecast Integrated Forecasting System global model (ECMWF-IFS): 2-m temperature, 2-m relative humidity, 10-m wind speed, and 10-m wind direction, with a forecast lead time of 24 h to 240 h in North China. First, the forecast correction problem is transformed into an image-to-image translation problem in deep learning under the CU-net architecture, which is based on convolutional neural networks. Second, the ECMWF-IFS forecasts and ECMWF reanalysis data (ERA5) from 2005 to 2018 are used as training, validation, and testing datasets. The predictors and labels (ground truth) of the model are created using the ECMWF-IFS and ERA5, respectively. Finally, the correction performance of CU-net is compared with a conventional method, anomaly numerical correction with observations (ANO). Results show that forecasts from CU-net have lower root mean square error, bias, mean absolute error, and higher correlation coefficient than those from ANO for all forecast lead times from 24 h to 240 h. CU-net improves upon the ECMWF-IFS forecast for all four weather variables in terms of the above evaluation metrics, whereas ANO improves upon ECMWF-IFS performance only for 2-m temperature and relative humidity. For the correction of the 10-m wind direction forecast, which is often difficult to achieve, CU-net also improves the correction performance.

Soil moisture (SM) plays a critical role in the water and energy cycles of the Earth system; consequently, a long-term SM product with high quality is urgently needed. In this study, five SM products, including one microwave remote sensing product – the European Space Agency's Climate Change Initiative (ESA CCI) – and four reanalysis data sets – European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis – Interim (ERA-Interim), National Centers for Environmental Prediction (NCEP), the 20th Century Reanalysis Project from National Oceanic and Atmospheric Administration (NOAA), and the ECMWF Reanalysis 5 (ERA5) – are systematically evaluated using in situ measurements during 1981–2013 in four climate regions at different timescales over the Chinese mainland. The results show that ESA CCI is closest to the observations in terms of both the spatial distributions and magnitude of the monthly SM. All reanalysis products tend to overestimate soil moisture in all regions but have higher correlations than the remote sensing product except in Northwest China. The largest inconsistency is found in southern Northeast China region, with an unbiased root mean square error (ubRMSE) value larger than 0.04. However, all products exhibit certain weaknesses in representing the interannual variation in SM. The largest relative bias of 144.4 % is found for the ERA-Interim SM product under extreme and severe wet conditions in northeastern China, and the lowest relative bias is found for the ESA CCI SM product, with the minimum of 0.48 % under extreme and severe wet conditions in northwestern China. Decomposing mean square errors suggests that the bias terms are the dominant contribution for all products, and the correlation term is large for ESA CCI. As a result, the ESA CCI SM product is a good option for long-term hydrometeorological applications on the Chinese mainland. ERA5 is also a promising product, especially in northern and northwestern China in terms of low bias and high correlation coefficient. This long-term intercomparison study provides clues for SM product enhancement and further hydrological applications.

The power output generated by wind farms (WFs) is integrated directly or indirectly into the grid through power electronic devices and the fault current is significantly different from that of conventional synchronous generators) and exhibits a limited amplitude, a controlled phase angle, rich harmonics, and strong nonlinearities. Therefore, the traditional ratio braking type differential protection may have low sensitivity or may even refuse to operate. In order to solve this problem, a pilot protection method based on Spearman's rank correlation coefficient is proposed in this article. When the system operates normally or an external fault occurs, a traversing current flows through the transmission line, so the current waveforms on both sides are the opposite. When an internal fault occurs, there are large differences in transient current waveforms on both sides. Spearman's rank correlation coefficient can be used to measure the degree of correlation between the waveforms on both sides to distinguish between faults inside and outside the zone. Compared with existing protection based on fault characteristics of WFs, the proposed method shows good performance when the power output of WFs is weak and the circuit breaker recloses with permanent failure. Both simulation results and field-testing data validate the proposed method.

The thermal compression tests of Ti–Nb alloy under T = 790–940 °C and e ˙ = 0.001–10s−1 were carried out on the thermal simulation testing machine of Gleeble-3500. The flow stress curves were obtained, and the high-temperature rheological properties of the alloy were analyzed. The 3D activation energy maps were calculated and constructed. The LSSVM model of constitutive relation was established, and the penalty coefficient γ and kernel parameter δ of the LSSVM model were optimized by the genetic algorithm (GA). The constitutive model of the alloy based on the GA-LSSVM algorithm was constructed. The predicted value of the model was also compared with the experimental data. The polar reciprocity model (PRM) and dynamic material model (DMM) were used to establish the 3D processing map of the alloy and appropriate thermal processing parameters. The results indicated that T and e ˙ have a great influence on the flow stress of Ti–Nb alloy. Ti–Nb alloy is a negative temperature-sensitive and a positive strain rate-sensitive material. The correlation coefficient (R) of the GA-LSSVM algorithm constitutive model is 0.9958. The model has high prediction accuracy and strong generalization ability, which provide a new method for establishing a high-temperature constitutive model of materials. The PRM processing map is more accurate in optimizing the processing parameters of Ti–Nb alloy than that of the DMM processing map through analyzing the 3D processing map and observing the microstructure. The instability modes in the instability region of the alloy mainly include local flow. The stability region's predominant deformation mechanism is DRX. The 870–940 °C and 0.001–0.01s−1 are the best parameters during the processing of Ti–Nb alloy.

Herein, near infrared (NIR) spectroscopy, rapid, accurate, and non-destructive method, was employed to analyze biomass composition. Calibration and prediction models for various types of biomass were developed from NIR data by applying the partial least squares method. Cellulose, hemicellulose, and lignin in a total of 75 samples were analyzed by a wet chemical method and NIR spectroscopy. The NIR model developed for hardwood accurately predicted the lignin content with a particle size of 20–80 mesh with a correlation coefficient (R2) of >0.95, low root mean square error (0.68), high ratio of error range (22.23), and high residual predictive deviation (6.07). On the other hand, the models for other compositions exhibited relatively low prediction accuracy. Different biomass particle sizes (20–80 mesh, >40 mesh, and

Brain-machine interfaces (BMIs) are useful tools for controlling assistive devices. One current approach in this field is continuous trajectory reconstruction (CTR), which decodes variables from electroencephalographic (EEG) signals. In this study, the CTR approach was applied to estimate kinetic variables from lower limb joints during pre-gait movements. The methodology consisted of a multi-layer perceptron capable of detecting patterns that represent the relation between EEG and torque signals acquired during motion tasks. The study also searched for an optimal subset of EEG channels based on the resulting patterns. A group of volunteers was recruited to execute pre-gait movements with both lower limbs to test the methodology. Results show that decodings of extracted patterns were successful in terms of the selected performance metrics; that is, the coefficient of determination, correlation coefficient, and signal-to-noise ratio. These metrics suggest that decodings for the right lower limb are better than for the left one, and that the most frequent electrodes in the optimal subsets for each task and joint show a tendency to lateralize. The results obtained suggest that this machine learning scheme could be used for future studies of the CTR of kinetic variables.

The post peak modulus of hard brittle Class II rocks are the least studied geo-mechanical properties of rocks. This is because of the difficulty associated with its determination. The Brazilian tensile strength, pre-failure mechanical properties, ultra-sonic pulse velocity and the mineralogical properties of the rocks were determined. The post peak moduli were determined under brittle uniaxial compression process. Predictive equations were developed for the estimation of the post peak modulus using backward multivariate and stochastic analysis of the rocks properties. The result of analysis show that the post peak modulus depends on the Poisson’s ratio and the quartz content of rocks. As the values of duo increases the magnitude of the post peak modulus decreases. Therefore, maximum possible magnitude of post peak modulus will be for mafic rocks with zero quartz content and low value of Poisson’s ratio. While low magnitude of post peak modulus will be for felsic rocks of high proportion of quartz content and high Poisson’s ratio. The backward multivariate analysis has a coefficient of correlation of 0.903 while the correlation coefficient was improved to 0.999 by stochastically modelling the relationship using normal distribution probability function for Poisson’s ratio and exponential distribution function for quartz content. The Mean Absolute Percentage Error (MAPE) was used as performance indicator to assess the predictive performance of the models. The stochastic model shows excellent performance with MAPE of 0.5% while the backward multivariate statistics model has MAPE of 0.9%. Both the backward multivariate and stochastic models are excellent prediction models.

The quantitative analysis of andrographolides in Andrographis paniculata plant materials is essential for pharmaceutical factories. This analysis cannot be done for all samples due to the conventional process using the extraction and HPLC methods requires a long analysis time and sample destruction. Therefore, near-infrared spectroscopy (NIRS) was employed to classify the class of A. paniculata and to determine the content of two active ingredients, andrographolide (AP1) and dehydroandrographolide (AP3) in A. paniculata, rapidly and non-destructively. One hundred twenty dried powder samples were obtained from aerial parts, branches, leaves, and branches mixed with leaves. The NIR absorption scans were collected from a broad spectral region (1000–2500 nm). Then, the scanned samples were extracted and analyzed for their AP1 and AP3 contents using an HPLC reference method. The success classification model based on AP1 level was developed using the second derivative pretreated NIR spectra of the entire wavelength region using the Partial Least Squares-Discriminant Analysis (PLS-DA) method. The NIR calibration models were developed and tested for quantitative analysis with 50 independent samples. The models were identified for the analysis of the AP1 content with excellent performance (correlation coefficient (R) = 0.98; standard error of validation (SEV) = 0.24%) and for the analysis of the AP3 content at a good level of efficiency (R = 0.93; SEV = 0.15%). This study showed that NIR spectroscopic method offers rapid analysis for the selection of A. paniculata that meets the requirement in bioactive amount. Graphic Abstract Supplementary Information The online version contains supplementary material available at 10.1007/s11696-021-01746-0.

The Yonsei Aerosol Retrieval (YAER) algorithm for the Geostationary Ocean Color Imager (GOCI) retrieves aerosol optical properties only over dark surfaces, so it is important to mask pixels with bright surfaces. The Advanced Himawari Imager (AHI) is equipped with three shortwave-infrared and nine infrared channels, which is advantageous for bright-pixel masking. In addition, multiple visible and near-infrared channels provide a great advantage in aerosol property retrieval from the AHI and GOCI. By applying the YAER algorithm to 10 min AHI or 1 h GOCI data at 6 km×6 km resolution, diurnal variations and aerosol transport can be observed, which has not previously been possible from low-Earth-orbit satellites. This study attempted to estimate the optimal aerosol optical depth (AOD) for East Asia by data fusion, taking into account satellite retrieval uncertainty. The data fusion involved two steps: (1) analysis of error characteristics of each retrieved result with respect to the ground-based Aerosol Robotic Network (AERONET), as well as bias correction based on normalized difference vegetation indexes, and (2) compilation of the fused product using ensemble-mean and maximum-likelihood estimation (MLE) methods. Fused results show a better statistics in terms of fraction within the expected error, correlation coefficient, root-mean-square error (RMSE), and median bias error than the retrieved result for each product. If the RMSE and mean AOD bias values used for MLE fusion are correct, the MLE fused products show better accuracy, but the ensemble-mean products can still be useful as MLE.

The general aim of the present study was to understand the groundwater level change of period 2001–2020 using geostatistical analysis at village level of Cuddalore district, Tamil Nadu, India. Further, three specific objectives were delineated as follows: to find the spatial pattern of groundwater level change, to estimate hot and cold spots of groundwater level change, and to model spatially varying relationship between change in groundwater level and population density. The groundwater level data have been downloaded from Central Ground Water Board (CGWB), Government of India. Gridded Population version 4 (GPWv4.11) dataset was downloaded for population density analysis. The Moran’s I method was applied to remove spatial autocorrelation as it is a correlation coefficient that measures the spatial autocorrelation present in a data. Hotspot analysis was performed to create statistically significant map of hot and cold spots with the help of Getis-Ord Gi* statistic. Geographically weighted regression (GWR) tool was implemented for modeling spatially varying relationship. The analysis results show the spatial pattern of groundwater level change is highly clustered, the z-score (57.53), which verify that the clustered sequence could be the outcome of random chance due to less than 1% likelihood. Groundwater level is found decreasing in 75% of the study area. The results of the GWR model show more groundwater level change than expected in relation to change in population density as 143 villages were classified within the band of 0.5–1.5 standard deviation, 35 villages were classified within the band of 1.5–2.5 standard deviation and 25 villages were classified in the band of > 2.5 standard deviation. Further, results indicate that groundwater level is decreasing at an alarming rate in the area. Hence, it is particularly important for policy makers to formulate policies, programs and projects specific to this region and to minimize groundwater level depletion.

Flowing bottom hole pressure (FBHP) is an indication of the fluid pressure in a porous reservoir under production. FBHP is obtained using a permanent gauge, well-testing analysis, or developing a mechanistic/correlation model. These conventional methods are costly and can be unreliable in the case of mechanistic/correlation approach. In line with this, the present study proposes the application of M5 prime for evaluating the FBHP of a well having a multiphase flow system. The proposed M5 prime FBHP model was further compared with backpropagation neural network (BPNN), generalised regression neural network (GRNN), radial basis function neural network (RBFNN), least-squares support vector machine (LSSVM), and group method of data handling (GMDH) to ascertain its performance. The M5 prime was identified as the superior technique as it attained the highest coefficient of determination (R2), correlation coefficient (R), the variance accounted for (VAF), and performance index (PI) values of 0.985, 0.99, 98.5, and 1.9, respectively, during testing. From the analysis of the contribution of each input variable, it was discovered that the tubing head pressure (THP) was the most dominant variable followed by the oil production flow rate (Qo), with the gas rate (Qg) having the least influence on the M5 prime outcome. Therefore, conclusion can be drawn that the proposed M5 prime model represents the best performing method as it can generate a more robust FBHP estimation while accounting for a superior variance of the measured data.

Pervious concrete is a kind of concrete used for storm-water management due to its high porosity and permeability. However, its’ flexural strength as the most desirable mechanical properties was predicted in this study. The paper aims to demonstrate three soft-computing models, i.e., artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS) were applied for the prediction of flexural strength ( $$\sigma f)$$ of pervious Concrete (PC) incorporated with calcium carbide waste (CCW) and rice husk ash (RHA) as supplementary cementation materials. The models were trained on the experimental data obtained by replacing cement content from 0 to 10% RHA and 0 to 20% CCW in the PC at 3-, 7-, and 28-days curing age. The results indicated that three AI-based models ANN, SVM, and ANFIS have predicted the flexural strength with high accuracy in both the testing and training stages, following the performance evaluation involving; Nash–Sutcliffe efficiency (NSE), correlation coefficient (CC), mean square error (MSE), and root mean square error (RMSE). All the input variables contribute to the accuracy of the model. The ANFIS-M5 (NSE = 0.9997 and RMSE = 0.0044 in testing phase) proved merit despite the acceptable accuracy obtained in the ANN model. The hybrid ANFIS predicts the flexural strength of hybridized pervious concrete with the highest accuracy compared to the other two soft-computing models.

Fault detection and location method are two significant techniques to recognize and clear the fault timely. This paper proposes a novel fault detection and location method for mesh-type DC microgrid. The key of this method is to implement similarity analysis on the sampled lines current and the lines current reference by employing an improved Pearson correlation coefficient. Firstly, the fault detection can be implemented by comparing the sampled lines current with steady-state lines current in a movable time window. And the fault line and fault type can be recognized based on the analysis on the correlation coefficient. Secondly, the fault location can be obtained by comparing the sampled lines current with calculation results of transient lines current, which corresponds to the estimated fault location scheme, within a fixed time window. The estimated location scheme, including the fault position and fault resistance, is updated by genetic algorithm, and will be determined when the correlation coefficient is higher than the threshold. Moreover, both numerical simulation and experiment results validate that the proposed method can recognize the fault line and fault type timely, while obtain the fault position and fault resistance accurately.

Compressional and shear wave velocities (Vp and Vs respectively) are essential reservoir parameters that can be used to delineate lithology, calculate porosity, identify reservoir fluids, evaluate fracture and for calculating mechanical properties of rocks. In this study, the potential application of intelligent systems in predicting Vp and Vs of reservoir rocks is presented. To date, considerable efforts are being carried out to obtain the best set of parameters capable of predicting Vp and Vs with a high degree of accuracy. Three intelligent models namely artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and least square support vector machine (LSSVM) were used in this study. The different models were based on the available information sourced from wireline log data. Parametric studies showed that measured depth, neutron porosity, gamma-ray, and density log data are vital in predicting both Vp and Vs. In developing the models, a comprehensive dataset available from one of the oil fields in the Norwegian North Basin was used. In evaluating the different models, two different statistical parameters namely Pearson's correlation coefficient (R2) and root mean square error (RMSE) were considered. It was found that the LSSVM model is the most accurate technique for predicting both Vp and Vs. LSSVM model predicted the Vp with R2 and RSME of 0.9706 and 0.0893 respectively. In addition, the model showed an excellent accuracy level in the prediction of Vs with R2 and RMSE of 0.9991 and 0.0457 respectively. The proposed approach if implemented is crucial for geoscientists, reservoir and drilling engineers working on reservoir characterization and drilling operations.

The type of land use and land cover plays a decisive role in land surface temperature (LST). As cities are composed of varied covers, including vegetation, built-up areas, buildings, roads and areas without vegetation, understanding LST patterns in complex urban spaces is becoming increasingly important. The present study investigated the relationship between LST and albedo, NDVI, NDWI, NDBI and NDBaI in the period between 1994 and 2017. Images from Thematic Mapper (TM) and Thermal Infrared Sensor (TIRS) onboard the Landsat 5 and 8 satellites, respectively, were used in the study. The images were processed, resampled (spatial resolution of 120 m) in the environment of the QGIS 3.0 software and, finally, centroids were extracted resulting in a total of 1252 points. A classical regression (CR) model was applied to the variables, followed by spatial autoregressive (SARM) and spatial error (SEM) models, and the results were compared using accuracy indices. The results showed that the highest correlation coefficient was found between albedo and NDBaI (r = 0.88). The relationship between albedo and LST (r = 0.7) was also positive and significant at р < 0.05. The global Moran's I index showed spatial dependence and non-stationarity of the LST (I = 0.44). The SEM presented the best accuracy metrics (AIC = 3307.15 and R2 = 0.65) for the metropolitan region of Belém, explaining considerably more variations in the relationship between explanatory factors and LST when compared to conventional CR models. Resumo O tipo e uso cobertura do solo desempenham papel decisivo para a temperatura da superfície continental (LST). Como as cidades são compostas por coberturas variadas, incluindo vegetação, áreas construídas, prédios, estradas e áreas desprovidas de vegetação, compreender os padrões da LST no complexo espaço urbano se faz cada vez mais importante. O presente estudo investigou a relação da LST com o albedo, NDVI, NDWI, NDBI e NDBaI no período de 1994 e 2017. Foram utilizadas imagens dos sensores Thematic Mapper (TM) e Thermal Infrared Sensor (TIRS) a bordo dos satélites Landsat 5 e 8, respectivamente. As imagens foram processadas, reamostradas (resolução espacial de 120 m) no ambiente do software QGIS 3.0 e, por fim, foram extraídos centroides com um total de 1252 pontos. O modelo de regressão clássica (RC) foi aplicado às variáveis seguidas por modelos espaciais autoregressivos e de erro espacial (MEAR e MEE) e os resultados foram comparados a partir de índices de acurácia. Os resultados mostram que o maior coeficiente de correlação existe foi verificado entre albedo e NDBaI (r = 0,88). A relação entre o albedo e a LST, com r = 0,7, também é positiva e significativa ao nível de (р < 0,05). A partir do índice I de Moran Global verificou-se a dependência espacial e não estacionariedade da LST (I = 0,44). O modelo MEE apresentou as melhores métricas de acurácia (AIC = 3307,15 e R2 = 0,65) explicando consideravelmente mais variações na relação dos fatores explicativos e da LST para a região metropolitana de Belém, quando comparados aos modelos convencionais de RC.

A new Quantitative Structure-Activity Relationship model is introduced for reliable prediction of the toxicity of organic aromatic compounds based on the logarithm of 50 % growth inhibitory concentration of Tetrahymena pyriformis (log(IGC50−1)), which have extensive use in ecotoxicology and environmental safety applications. The largest experimental data set of log(IGC50−1) for 892 organic aromatic compounds is used to derive and test the new model. A core correlation based on additive variables is introduced by the number of nitro groups, carbon and halogen atoms as well as some specific polar groups and molecular weight. An improved correlation based on two non-additive correcting functions is developed for the increment of the reliability of the core correlation. The reliability of the improved correlation is tested and compared with two of the best available methods, which require complex descriptors. The predicted results for 661 and 231 of training and test sets have been confirmed by internal and external validations. The values of correlation coefficient (R2), mean error (ME), root mean squared error (RMSE), and maximum of errors (Max Error) for 661/231 of training/test aromatic compounds are 0.8442/0.7771, 0.0000/0.0149, 0.3166/0.3603, and 0.9732/0.9825, respectively, which are good results as compared to extra complex models with lower reported data. Various statistical parameters confirm the goodness-of-fit, high reliability, precision, and accuracy of the novel model.

The current paper deals with the evaluation of the BANCS erosion prediction model and its two components–the Bank Erosion Hazard Index (BEHI) and Near-Bank Stress (NBS) indices. To construct the erosion prediction curves, 18 experimental sections were established on the Kubrica Stream, district of Trencin, Slovakia. Each section was assessed through the NBS index and BEHI index and real annual bank erosion was measured using erosion toe pins. Subsequently, the relations between the BEHI and real annual bank erosion was assessed through regression and correlation analyses. The relation proved to be moderately strong, with the correlation coefficient (R) reaching 0.47. Further, the relation between the NBS index and real annual bank erosion was evaluated, which was also moderately strong, with R = 0.65. Based on the measured data, two erosion prediction curves were constructed, the first for moderate BEHI, with R = 0.69 and coefficient of determination (R2) of 0.47 and the second for high BEHI with R = 0.74 and R2 = 0.55. The prediction curves were based on data from one year of measurements and can, therefore, be used only for discharges that occurred within that year and in the region where the model was developed. In the current case, according to runoff Curve Numbers (CN), the real culmination discharge was Q = 1.88 m3/s, which is roughly equivalent to 1.5-year recurrence interval flow (Q1.5).

In a turning operation, involving removal of material from the outer diameter of a rotating cylindrical workpiece using a single-point cutting tool, there exist complex relationships between various cutting parameters and responses. In this paper, a turning operation under dry environment is considered with cutting speed, feed rate, and depth of cut as the input parameters, as well as material removal rate, average surface roughness, and cutting force as the responses. Dry turning operation reduces energy consumption and machining cost, thus eventually resulting in sustainable machining. For the considered process, the corresponding response values are envisaged using four prediction models, that is, multivariate regression analysis, fuzzy logic, artificial neural network, and adaptive neurofuzzy inference system (ANFIS), and their prediction performance is contrasted using five statistical metrics, that is, root mean squared percent error, mean absolute percentage error, root mean squared log error, correlation coefficient, and root relative squared error. It is noticed that ANFIS model consisting of the advantages features of both fuzzy logic and neural network outperforms the other prediction models with respect to the computed values of the considered statistical measures. Based on their acceptable values, it can be propounded that the ANFIS model can be effectively employed for prediction of process responses while treating different machining parameters as the input variables.

Confining is a very common method of reinforcing concrete columns, and numerous experiments have been performed on different-strength RC columns confined with FRP sheets. Since models proposed to determine the compressive strength of normal-strength (less than 50 MPa) concretes are many, but those of higher strength ones (greater than 50 MPa) are few, this study has collected a large set of laboratory data from different FRP-confined circular specimens with strengths greater than 50 MPa and has used the data to present modified models to determine their compressive strength. The FRP strain efficiency is defined as the ratio of the actual FRP hoop rupture strain in confined columns to that obtained from the coupon test. These models integrate the FRP strain efficiency and strength increase factors and consider the integration as a function of: (1) strain ratio, (2) confinement stiffness ratio, and (3) the combination of the latter two. These functions’ constant coefficients were so calculated by the whale optimization algorithm as to minimize the difference between the models and experimental results. A comparison of the results showed that the proposed models in this study perform better than the models of previous studies for estimating compressive strength of FRP-confined circular specimens with compressive strengths greater than 50 MPa. Also, among the models presented in this study, the model that used the integrated factor as a combinatory function estimated the columns’ compressive strength better so that the correlation coefficient (R2) of this model was 89%.

In order to demonstrate the relationship between the fuel injection quantity and the structural parameters of the fuel system for large marine diesel engines, an AMESim model of a double-valve controlled fuel system is proposed. The accuracy of the model is validated in view of fuel injection quantity and system pressures. The correlation analysis is performed to illustrate the effects of single parameters and the interactions between different parameters on the fuel injection quantity. Considering the high calculation cost of the simulation model, the prediction model between the fuel injection quantity and the structural parameters for each working condition is obtained based on D-optimal design of experiments and the response surface methodology in this article. For the maximum deviation between the calculated and predicted fuel injection quantity is only 4.27%, the prediction models could be used for further analysis. And the results show that the diameters of high-pressure fuel tube (HPFT), small and big ends of pressure amplification piston (PAP) are the key single parameters. The absolute values of their correlation coefficients are between 0.77 and 0.87, between 0.22 and 0.43 and between 0.14 and 0.26 respectively. The correlation coefficients for the other parameters are all relatively small. For interactive parameters, the absolute values for all the correlation coefficients are less than 0.1. And the interactions between the diameters of big and small diameters of PAP, between the diameter of small end of PAP and the diameter of HPFT, between the diameter of HPFT and the pre-tightening force of needle spring influence the fuel injection quantity relatively obviously.

Preference data are a particular type of ranking data where some subjects (voters, judges,...) express their preferences over a set of alternatives (items). In most real life cases, some items receive the same preference by a judge, thus giving rise to a ranking with ties. An important issue involving rankings concerns the aggregation of the preferences into a “consensus”. The purpose of this paper is to investigate the consensus between rankings with ties, taking into account the importance of swapping elements belonging to the top (or to the bottom) of the ordering (position weights). By combining the structure of $$\tau _x$$ τ x proposed by Emond and Mason (J Multi-Criteria Decis Anal 11(1):17–28, 2002) with the class of weighted Kemeny-Snell distances, a position weighted rank correlation coefficient is proposed for comparing rankings with ties. The one-to-one correspondence between the weighted distance and the rank correlation coefficient is proved, analytically speaking, using both equal and decreasing weights.

The difficulty of the problem of the flow hydraulics in compound channels is due to the implicit interaction between the floodplains and the main channel, characterizing every particular shape of the compound channel. The problem is much more complicated when it comes to an energy dissipator like a hydraulic jump as is the case in the present study. In this paper, the general regression neural network (GRNN) was applied to predict the basic characteristics of hydraulic jumps in a straight rectangular compound channel: (i) the sequent depths ratios, (ii) the relative energy losses, and (iii) the relative lengths. Experiments were carried out with three different values of the ratio between the main channel width and the flood plain one (Wy). The Wy values were: (1/4, 1/3, and 1/2). For each Wy ratio, several values of inflow Froude number were considered according to the five inflow ratio depths’ (Wz) values (0.167, 0.200, 0.253, 0.287, and 0.333) between the first sequent depth and of the main channel one. The predicted values in the testing stages using GRNN followed the experimental ones with a correlation coefficient (R) of 0.990 for the sequent depth’s ratios, 0.982 for relative energy losses, and 0.873 for the relative lengths of hydraulic jumps. The best models have been selected among several input configurations for each of three considered characteristics of the jump.

Runoff–sediment process modeling is highly variable and nonlinear in nature. For sediment yield prediction, the difficulty of rainfall–runoff–sediment yield hydrological processes remains challenging. The present study uses a simple nonlinear dynamic (NLD) model to predict daily sediment yields, taking into account the degree of daily–sediment yield in catchment areas, and its findings were compared to three widely used models including artificial neural networks (ANN), support vector machine (SVM), and gene expression programming (GEP). The daily measured discharge–sediment data for 25 years were obtained from Shakkar Watershed; Central India as in the current study. The coefficient of correlation (CC), Nash-Sutcliff (NS), and root-mean-square error (RMSE) were employed to assess the performance of the models. The results show that the NLD model was found better than ANN, SVM, and GEP model. These models had correlation coefficient (CC = 0.975, 0.887, 0.843, and 0.901), root-mean-square error (RMSE = 0.748, 1.751, 1.961, and 1.545), and Nash–Sutcliffe efficiency (0.952, 0.784, 0.673, and 0.814) correspondingly. Hence, the NLD model can be used for predicting sediment. In order to implement appropriate measures of soil conservation in the watershed to reduce the sediment load in the river, predicting the sediment yield is very necessary to maximize the life of the structure.

The recovery of date palm leaflet waste (DPLW), generated by palms through anaerobic digestion (AD) technology, attracts more attention because of its many economic, social, and environmental benefits. In this study, a laboratory-scale experiment using a continuous stirring tank reactor digester (CSTR) operating in mesophilic semi-batch mode was conducted to evaluate experimental methane production, biodegradability, and organic loading rate (OLR). Besides, a theoretical estimate of methane was assessed using a Buswell–Neave equation. Moreover, three modified kinetic models (Logistic, Gompertz, and Richards) were applied to adjust the experimental methane production from the AD of DPLW. This study showed that the experimental methane yield and biodegradability of DPLW were 133 NmL CH4/g VS and 33%, respectively, while the OLR was 2.76 kg VS/m3.d. The kinetic results showed that all three modified models (Gompertz, Richards, and Logistic) were useful for predicting methane production as a function of the added loads. However, the modified Gompertz model was the most suitable for experimental data, even under critical conditions. Indeed, the modified Gompertz model fitted the experimental methane production with an optimal correlation coefficient R2 = 0.998.

The impact energy prediction model of low carbon steel was investigated based on industrial data. A three-layer neural network, extreme learning machine, and deep neural network were compared with different activation functions, structure parameters, and training functions. Bayesian optimization was used to determine the optimal hyper-parameters of the deep neural network. The model with the best performance was applied to investigate the importance of process parameter variables on the impact energy of low carbon steel. The results show that the deep neural network obtains better prediction results than those of a shallow neural network because of the multiple hidden layers improving the learning ability of the model. Among the models, the Bayesian optimization deep neural network achieves the highest correlation coefficient of 0.9536, the lowest mean absolute relative error of 0.0843, and the lowest root mean square error of 17.34 J for predicting the impact energy of low carbon steel. Among the variables, the main factors affecting the impact energy of low carbon steel with a final thickness of 7.5 mm are the thickness of the original slab, the thickness of intermediate slab, and the rough rolling exit temperature from the specific hot rolling production line.

In order to establish the combined prediction model of milling noise based on force-thermal-vibration multi-feature fusion, a simultaneous milling noise-vibration-thermal-force test system was established. Based on the gray correlation theory and test data, the relationship between milling sound pressure and milling parameters, milling vibration, milling force, and milling thermal was analyzed. Based on the least square method, three single prediction models of milling sound pressure level for three-directional vibration, milling thermal, and three-directional milling force were established. Then, the weight coefficients of the combined model are determined by the standard errors of the three single models, and the linear combination model of the mean square root of milling sound pressure level expressed by the three single prediction models and the corresponding weight coefficients was established. The correlation coefficient of the combined prediction model of sound pressure is 0.95, which is larger than the correlation coefficient of three single prediction models. It shows that the combined prediction model of sound pressure level with multiple features can better predict milling noise and provide theoretical guidance for milling tool condition monitoring.

Landslide failure time prediction is considered a challenging issue in landslide research. A significant goal of landslide research is to provide scientific and accurate prediction methods. In this paper, the short-term forecasting of landslides (STFL) model is proposed by analyzing landslide deformation characteristics in a known evolution process. The landslides on the southern slope of the West open pit mine (SSWOPM) in Liaoning province, northeast China, and Huangci in Gansu province, northwest China, were selected as the study cases. After pre-processing, which include eliminating abnormal data (t test), adding missing data (cubic spline interpolation), and smoothing noisy data (Savitzky–Golay filters), the displacement data are assembled to serve as the model’s input parameters. The parameters of STFL can be obtained through the Levenberg–Marquardt (LM) algorithm. Using the forecasting criterion, the time of failure of landslides can be predicted and determined. Forecasting results provide evidence that the STFL model can achieve an accurate prediction of landslide displacement (correlation coefficient R2 > 0.99). The forecasting results of the SSWOPM and Huangci landslides indicate that the forecasting failure time of the STFL model is March 10, 2014 and January 31, 1995, respectively, which are near the actual failure time compared with those obtained using the Verhulst model. This finding indicates that the new method has excellent reliability and accuracy in landslide prediction and a robust description of the landslide movement.

The aim of this paper is to propose the generalized version of the multipolar neutrosophic soft set with operations and basic properties. Here, we define the AND, OR, Truth-Favorite, and False-Favorite operators along with their properties. Also, we define the necessity and possibility of operations for them. Later on, to extend it to solve the decision-making problems, we define some information measures such as distance, similarity, and correlation coefficient for the generalized multipolar neutrosophic soft set. Several desirable properties and their relationship between them are derived. Finally, based on these information measures, a decision-making algorithm is stated under the neutrosophic environment to tackle the uncertain and vague information. The applicability of the proposed algorithm is demonstrated through a case study of the medical-diagnosis and the decision-making problems. A comparative analysis with several existing studies reveals the effectiveness of the approach.