Multiple Linear Regression Predictive Model Research Articles

Transport characteristics of heavy metals in the soil-atmosphere-wheat system in farming areas and development of multiple linear regression predictive model

Heavy metal accumulation in agricultural products has become a major concern. Previous studies have focused on the transport of heavy metals from the soil and their accumulation in crops. However, recent studies revealed that wheat leaves, ears, and awns can also transport and accumulate heavy metals. Wheat grains can be influenced by two sources of heavy metals: soil contamination and atmospheric deposition. To comprehend the transport characteristics of heavy metals in soil, atmospheric deposition, and wheat, 37 samples each for wheat rhizosphere soil, wheat roots, stems, leaves, and grains were collected. Fifteen samples of atmospheric dry deposition and atmospheric wet deposition were collected from Linshu County (northern area), China. Based on the test data, the characteristics of heavy metals and their distribution in the study area were analyzed. Migration patterns of heavy metals in crops from different sources were investigated using Pearson correlation and redundancy analysis. Finally, a predictive model for heavy metals in wheat grains was developed using multiple linear regression analysis. Significant disparities in the distribution of heavy metals existed among wheat roots, stems, leaves, and grains. The coefficient of variation of heavy metals in atmospheric deposition was relatively high, indicating discernible spatial patterns influenced by human activities. Notably, a positive correlation was observed between the concentration of heavy metals in wheat grains and atmospheric deposition of Hg, Cd, and Pb. Conversely, Zn and Ni levels in wheat grains were significantly negatively associated with soil Zn, Ni, pH, and OM content. The contribution of heavy metal elements from different sources varied in their impact on the grain's heavy metal content. Specifically, atmospheric deposition was the primary source of Hg and Pb in wheat grains, while Cd, Ni, Cu, and Zn were predominantly derived from soil. Using a multiple linear regression model, we could accurately predict Hg, Pb, Cd, Ni, Zn, and As concentrations in crop grains. This model can facilitate quantitative evaluation of ecological risk of heavy metals accumulation in crops in the study area.

Research on Outgoing Moisture Content Prediction Models of Corn Drying Process Based on Sensitive Variables

Accurate prediction of outgoing moisture content is the key to achieving energy-saving and efficient technological transformation of drying. This study relies on a grain drying simulation experiment system which combined counter and current drying sections to design corn kernel drying experiments. This study obtains 18 kinds of temperature and humidity variables during the drying process and uses Uninformative Variable Elimination (UVE) method to screen sensitive variables affecting the outgoing moisture content. Subsequently, six prediction models for the outgoing corn moisture content were developed, innovatively incorporating Multiple Linear Regression (MLR), Extreme Learning Machine (ELM), and Long Short-Term Memory (LSTM). The results show that eight sensitive variables have been screened to predict the moisture content of outgoing corn. The sensitive variables effectively reduced the redundancy and multicollinearity of data in the MLR model and improved the coefficient of determination (R2) of ELM and LSTM models by 0.02 and 0.05. The MLR prediction model established based on the full set of temperature and humidity data has an R2 of 0.910 and a root-mean-square error (RMSE) of 0.881%, while the UVE-ELM and UVE-LSTM prediction models achieve a better fitting effect and prediction accuracy. The UVE-LSTM model is set with a batch size of 30, a learning rate of 0.01, and 100 iterations. For the training set of UVE-LSTM, the R2 value is 0.931 and the RMSE value is 0.711%. The UVE-ELM model, with sigmoid as the activation function and 14 neurons configured, runs fast and has the best prediction accuracy. The R2 values of UVE-ELM training set and validation set are 0.943 and 0.946, respectively, and the RMSEs are 0.544% and 0.581%. The models proposed in this study provide data reference and technical support for process optimization and automation control of the corn drying process.

Regional Carbon Emission Forecasting Model Considering Temporal Characteristics and Analysis of Peak Carbon Assessment in Typical Scenarios

Leading high-quality economic development with green development is an important development concept for Chinese-style modernization, and achieving the dual-carbon goals of carbon peaking and carbon neutrality is a key initiative to promote high-quality economic and social development. In order to explore the correlation between carbon emissions and population, economy and energy consumption, and to propose a reasonable carbon emissions prediction model, this paper proposes an evaluation index system integrating fossil energy consumption and new energy consumption by analyzing the sample data obtained from the research in a hierarchical, industry- and sector-specific manner. And then, we compare the reliability of the results obtained from the multiple linear regression prediction model based on the above index system and the Kaya carbon emissions prediction model, respectively. By comparing the reliability of the results obtained from the carbon emission multiple linear regression prediction model based on the above index system and the Kaya carbon emission prediction model, it is initially determined that the Kaya model will be used for regional carbon emission prediction. In order to optimize the sensitivity of the model to the temporal Characterization of the indicators, a carbon emission prediction model that incorporates the temporal characteristics of the data is set up. Lastly, the carbon emission is predicted according to the three typical scenarios analyzed according to the intensity of the macro-policy, and the year of carbon peak and the year of carbon peak are analyzed for the scenarios. Three typical scenarios are analyzed according to the intensity of macro policies, and carbon emissions are predicted under different scenarios, and the year in which each scenario reaches the carbon peak is analyzed, as well as the correlation with the implementation of related policies and energy use, with a view to providing support for the planning of the dual-carbon target value and the path of achieving it, as well as the formulation of related policies.

Artificial neural network and multiple linear regression modeling for predicting thermal transmittance of plain-woven cotton fabric

The present research compares a machine learning model with a statistical model, with specific emphasis on artificial neural networks and multiple linear regression models. The aim of this study is to forecast the thermal transmittance of a plain-woven cotton fabric using input data such as thread density measured in ends per inch, picks per inch, and fabric thickness. The artificial neural network is built using a network with feed-forward backpropagation, and the MATLAB software’s training function trainlm is used to modify its weight and basic values based on Levenberg–Marquardt optimization techniques. The sigmoid transfer function is used to set the layer output and measure network performance in terms of the root mean squared error, mean absolute error percentage, and coefficient of determination which were determined. For the artificial neural network prediction model, the root mean squared error and mean absolute error percentage were 1.05 and 3.132%, respectively, while the coefficient of determination was 0.9307. In contrast, the multiple linear regression prediction model had root mean squared error and mean absolute error percentage values of 2.98 and 8.97%, respectively, along with a coefficient of determination of 0.4727. The results reveal that the artificial neural network model outperforms the multiple linear regression model, showing superior accuracy and robustness in capturing the intricate interactions between important fabric parameters (ends per inch, picks per inch, and thickness) and thermal transmittance values. This research emphasizes the efficiency of artificial neural network modeling as a superior tool for forecasting thermal transmittance in textile applications rather than employing the time-consuming trial-and-error process for delivering significant insights for material engineering and energy-efficient design.

Research on energy-saving strategies in the architectural design of the Eastern Railway in the era of artificial intelligence

Abstract This paper takes the air conditioning energy consumption in railroad building design as the main object of analysis and uses an orthogonal experimental design method to study the influencing factors and effects of energy consumption in the Middle East railroad construction design. Stochastic working condition simulation is carried out for the typical models of passenger stations in five climate zones to obtain the data set of the passenger station energy consumption model, and the multiple linear regression prediction models of air conditioning energy consumption in different regions are established. Combined with the hour-by-hour average outdoor temperature, hour-by-hour passenger flow and lighting and related equipment data in the waiting hall of a city in July, the air-conditioning cold load of railroad passenger stations is simulated and analyzed. Explore the implementation effect of energy-saving strategies for railroad passenger station air-conditioning system, and for the traditional PID control strategy, put forward the control strategy based on model prediction, analyze the change of centralized air-conditioning system cold load and the change of the actual performance coefficient of the chiller unit under different control strategies. The data show that compared with the traditional PID control, the model prediction control reduces the total energy consumption by 0.2063, which realizes the energy-saving optimization of the air conditioning system for railroad building design.

Diagenesis and Diagenetic Mineral Control on Reservoir Quality of Tight Sandstones in the Permian He8 Member, Southern Ningwu Basin

The sandstone reservoirs of the He8 member within the Lower Permian Shihezi Formation are important targets for oil and gas exploration in the southern Ningwu Basin. This study utilized thin-section identification, scanning electron microscopy, and X-ray diffraction analysis to examine the petrological features and reservoir characteristics, and evaluate the impact of the mineral composition and diagenesis type on the porosity of the sandstone reservoir. Additionally, a multiple linear regression prediction model was developed to predict the distribution of promising sandstone reservoirs in the study area. The results of the analysis revealed that the sandstone of the He8 member is mainly composed of feldspathic lithic sandstone, followed by lithic sandstone. The main reservoir type is characterized by secondarily dissolved pores and micropores within kaolinite aggregates. The low porosity (ranging from 0.2% to 10.7%) and permeability indicate that the He8 member is a tight sandstone reservoir. This reservoir has undergone compaction, cementation, and dissolution diagenesis, and is presently in the stage of mesodiagenesis B. The rigid framework of quartz, the dissolution of feldspar grains, and the intergranular pores of kaolinite are significant contributors to reservoir quality and the main drivers of porosity. In this study, a multivariate linear regression model was developed based on the mineral content of quartz, feldspar, carbonate minerals, kaolinite, smectite, and rock fragments, which accurately predicts the porosity of the studied reservoirs. Based on this model, it was predicted that the north of the Jingle South sub-depression contains a favorable reservoir space in the tight sandstone reservoir of the He8 member. The findings of this study hold significant reference value in the quantitative characterization of tight sandstone reservoirs with similar depositional and diagenetic characteristics, and improving the prediction effect of favorable reservoirs.

Study on the Drying Process and the Influencing Factors of Desiccation Cracking of Cohesive Soda Saline-Alkali Soil in the Songnen Plain, China

The surface of cohesive soda saline-alkali soil in the Songnen Plain of China exhibits obvious desiccation cracking phenomenon during water evaporation. Quantitative research on the process and influencing factors of desiccation cracking are significant for determining the mechanical properties of salt-affected soil, improving the salinization status and the local ecological environment. This study aims to conduct laboratory-controlled cracking experiments on soda saline-alkali soils, and to regularly measure the soil moisture and the cracking status of 40 soil samples. After processing the crack images uniformly, crack characteristics including crack length, crack area, contrast texture feature, and box-counting fractal dimension are extracted. The results indicate that the decrease in soil moisture can be divided into three stages such as fast evaporation stage, slow evaporation stage and stable evaporation stage, and that the evaporation rate shows a linear negative correlation with soil salinity. The measurements also indicate that crack length rapidly increases and reaches stability with a decrease in water content compared with the crack area. The high correlation between different crack characteristics and the soil total salinity (correlation coefficient from 0.44 to 0.95) shows that salt content is the dominant factor affecting the desiccation cracking of soda saline-alkali soil. A multiple linear regression prediction model was finally established based on crack characteristics for different salinity parameters with high prediction accuracy for Na+, EC and total salinity (R2 > 0.91 and RPD > 2.5) and also certain prediction accuracy for Cl− and CO32− (R2 > 0.66 and RPD > 1.5).

Geochemical Characteristics of Cd in Different Parent Soils in Karst Area and Prediction of Cd Content in Maize

The naturally high background value region of Cd derived from the weathering of carbonate has received wide attention. Due to the significant difference in soil physicochemical properties, soil Cd content, and bioavailability of different parent materials in the karst area, there are certain limitations in using the total soil Cd content to classify the environmental quality of cultivated land. In this study, surface soil and maize samples of eluvium and alluvial parent material in typical karst areas were collected systematically; the contents of maize Cd, soil Cd, pH, and oxides were analyzed, the Cd geochemical characteristics of different parent soils and the influencing factors of their bioavailability were revealed, and scientific and effective arable land use zoning suggestions based on the prediction model were suggested. The results showed that the physicochemical properties of different parent material soils in the karst area were obviously different. The alluvial parent material soil had low Cd content but high bioavailability, and the maize Cd exceeding rate was high. The maize Cd bioaccumulation factor was significantly negatively correlated with soil CaO, pH, Mn, and TC, and the correlation coefficients were -0.385, -0.620, -0.484, and -0.384, respectively. Compared with the multiple linear regression prediction model, using the random forest model to predict the maize Cd enrichment coefficient had higher accuracy and precision. Furthermore, a new scheme for the safe utilization of cultivated land at the plot scale based on soil Cd and predicted crop Cd content was proposed in this study, making full use of arable land resources to ensure crop safety.

COVID-19 Prediction Using Black-Box Based Pearson Correlation Approach.

The novel coronavirus (COVID-19), also known as SARS-CoV-2, is a highly contagious respiratory disease that first emerged in Wuhan, China in 2019 and has since become a global pandemic. The virus is spread through respiratory droplets produced when an infected person coughs or sneezes, and it can lead to a range of symptoms, from mild to severe. Some people may not have any symptoms at all and can still spread the virus to others. The best way to prevent the spread of COVID-19 is to practice good hygiene. It is also important to follow the guidelines set by local health authorities, such as physical distancing and quarantine measures. The World Health Organization (WHO), on the other hand, has classified this virus as a pandemic, and as a result, all nations are attempting to exert control and secure all public spaces. The current study aimed to (I) compare the weekly COVID-19 cases between Israel and Greece, (II) compare the monthly COVID-19 mortality cases between Israel and Greece, (III) evaluate and report the influence of the vaccination rate on COVID-19 mortality cases in Israel, and (IV) predict the number of COVID-19 cases in Israel. The advantage of completing these tasks is the minimization of the spread of the virus by deploying different mitigations. To attain our objective, a correlation analysis was carried out, and two distinct artificial intelligence (AI)-based models-specifically, an artificial neural network (ANN) and a classical multiple linear regression (MLR)-were developed for the prediction of COVID-19 cases in Greece and Israel by utilizing related variables as the input variables for the models. For the evaluation of the models, four evaluation metrics (determination coefficient (R2), mean square error (MSE), root mean square error (RMSE), and correlation coefficient (R)) were considered in order to determine the performance of the deployed models. From a variety of perspectives, the corresponding determination coefficient (R2) demonstrated the statistical advantages of MLR over the ANN model by following a linear pattern. The MLR predictive model was both efficient and accurate, with 98% accuracy, while ANN showed 94% accuracy in the effective prediction of COVID-19 cases.

Non-Destructive Detection of Meat Quality Based on Multiple Spectral Dimension Reduction Methods by Near-Infrared Spectroscopy.

The potential of four dimension reduction methods for near-infrared spectroscopy was investigated, in terms of predicting the protein, fat, and moisture contents in lamb meat. With visible/near-infrared spectroscopy at 400-1050 nm and 900-1700 nm, respectively, calibration models using partial least squares regression (PLSR) or multiple linear regression (MLR) between spectra and quality parameters were established and compared. The MLR prediction models for all three quality parameters based on the wavelengths selected by stepwise regression achieved the best results in the spectral region of 400-1050 nm. As for the spectral region of 900-1700 nm, the PLSR prediction model based on the raw spectra or high-correlation spectra achieved better results. The results of this study indicate that sampling interval shortening and of peak-to-trough jump features are worthy of further study, due to their great potential in explaining the quality parameters.

Predictive model for the spreadability of cosmetic formulations based on large amplitude oscillatory shear (LAOS) and machine learning

Inspired by the analogy between the application process of cosmetics and large amplitude oscillatory shear (LAOS), we suggest a novel predictive model for the spreadability of cosmetic formulations via LAOS analysis and machine learning techniques. Rheological measurements of cosmetic formulations, including the transient elastic and viscous moduli from the sequence of physical process (SPP) analysis, were selected as features for the predictive models, and the spreadability of each formulation that is quantitatively rated by trained panels was set up as the target variable. First, multiple linear regression prediction models are derived, and it was shown that the LAOS-SPP parameters were more effective features than other rheological parameters that were conventionally related to spreadability of cosmetics. Additionally, a non-linear prediction model was developed based on the random forest regressor algorithm, considering the possibility of the nonlinear correlation between rheological measurements and spreadability. The random forest regressor model showed better performance than the linear regression model, and the LAOS-SPP parameters were found to be more effective features for the random forest regressor model as in the multiple linear regression model. The correlation between the LAOS-SPP parameters and the spreadability is interpreted in terms of the rheological transition during rubbing process of cosmetics. Our findings indicate the importance of the nonlinear rheological behavior in the texture perception mechanism of cosmetics, and how rheological measurements can be combined with machine learning techniques to solve complicated problems.

Rapid Detection of Available Nitrogen in Soil by Surface-Enhanced Raman Spectroscopy.

Soil-available nitrogen is the main nitrogen source that plants can directly absorb for assimilation. It is of great significance to detect the concentration of soil-available nitrogen in a simple, rapid and reliable method, which is beneficial to guiding agricultural production activities. This study confirmed that Raman spectroscopy is one such approach, especially after surface enhancement; its spectral response is more sensitive. Here, we collected three types of soils (chernozem, loess and laterite) and purchased two kinds of nitrogen fertilizers (ammonium sulfate and sodium nitrate) to determine ammonium nitrogen (NH4-N) and nitrate nitrogen (NO3-N) in the soil. The spectral data were acquired using a portable Raman spectrometer. Unique Raman characteristic peaks of NH4-N and NO3-N in different soils were found at 978 cm−1 and 1044 cm−1, respectively. Meanwhile, it was found that the enhancement of the Raman spectra by silver nanoparticles (AgNPs) was greater than that of gold nanoparticles (AuNPs). Combined with soil characteristics and nitrogen concentrations, Raman peak data were analyzed by multiple linear regression. The coefficient of determination for the validation () of multiple linear regression prediction models for NH4-N and NO3-N were 0.976 and 0.937, respectively, which deeply interpreted the quantitative relationship among related physical quantities. Furthermore, all spectral data in the range of 400–2000 cm−1 were used to establish the partial least squares (PLS), back-propagation neural network (BPNN) and least squares support vector machine (LSSVM) models for quantification. After cross-validation and comparative analysis, the results showed that LSSVM optimized by particle swarm methodology had the highest accuracy and stability from an overall perspective. For all datasets of particle swarm optimization LSSVM (PSO-LSSVM), the was above 0.99, the root mean square errors of prediction (RMSEP) were below 0.15, and the relative prediction deviation (RPD) was above 10. The ultra-portable Raman spectrometer, in combination with scatter-enhanced materials and machine learning algorithms, could be a promising solution for high-efficiency and real-time field detection of soil-available nitrogen.

Prediction of Linalool Content in Osmanthus fragrans Using E-Nose Technology

Linalool is a well-known volatile compound. It is usually extracted from plants or synthesized by chemical methods. However, there is still no rapid screening method for plants with high linalool content. Therefore, we aimed to establish a method determining linalool content in Osmanthus fragrans by electronic nose (E-nose). The volatile gases of three cultivars of O. fragrans were characterized by gas chromatography-mass spectrometry (GC-MS) and E-nose. Different concentrations of linalool were measured by E-nose. Then, the E-nose data were subjected to principal component analysis (PCA) and linear discriminant analysis (LDA) to establish a discriminant model for determining linalool concentrations. Prediction models based on principal component regression (PCR) and multiple linear regression (MLR) were developed from all sensors and feature sensors to determine linalool concentrations in the three cultivars of O. fragrans flowers. Finally, the linalool concentrations determined by gas chromatography were used to verify the accuracy of the prediction model. The results show that linalool had the highest abundance among the volatile compounds of O. fragrans, and the MLR prediction model had an R 2 of 0.992 in calibration sets and an R 2 of 0.895 in prediction sets using 10 sensors. This study describes a rapid and accurate method for the detection and quantification of linalool concentrations.

Prediction of Subgrade Strength from Index Properties of Expansive Soil Stabilized with Bagasse Ash and Calcined Termite Clay Powder Using Artificial Neural Network and Regression

When moisture levels fluctuate, expansive soils lose a large amount of volume. During the rainy and dry seasons, this type of soil expands and contracts, respectively. As a result, such problematic soils should be avoided or appropriately managed when encountered as subgrade materials. The strength of the subgrade is measured in terms of its California Bearing Ratio (CBR) value which is tiresome, uneconomical, and time‐consuming to determine in the laboratory. In the present study, the effect of bagasse ash (BA) and calcined termite clay powder (CTCP) on the strength, index, and microstructural properties of expansive soil was investigated. Laboratory tests such as Atterberg’s limits, particle size analysis, moisture‐density relationship, and CBR tests were performed on the highly expansive soil and blended with 3%, 5%, 7%, 9%, and 11% bagasse ash (BA), and 5%, 10%, 15%, 20%, and 25% CTCP separately and in combination. In addition, the microstructural properties of the raw highly expansive soil and the soil stabilized with the optimum BA‐CTCP combination were analyzed using the Scanning Electron Microscopy (SEM) machine. Soaked CBR prediction models were also developed using multiple linear regression (MLR) and artificial neural networks (ANNs) from the BA fraction (BAF), CTCP fraction (CTCPF), liquid limit (LL), plasticity index (PI), optimum moisture content (OMC), and maximum dry density (MDD). The soil understudy was very weak having a CBR value of 2.2% and a group index (GI) of 64.37 (reported as 20) and highly expansive with a PI of 51.61% and LL of 104.32%. The addition of both BA and CTCP separately and in combination had resulted in the reduction of PI and increased the strength of the soil under study. As compared with the individual effect, the combined effect of BA and CTCP was quite significant. The optimum BA and CTCP combination was determined from the free‐swell index test result; a 72.5% reduction was observed when it was blended with a combination of 9% BA and 20% CTCP. Thus, 9% BA and 20% CTCP compositions could be the optimum percentage combination to stabilize the highly expansive soil under study. The PI was decreased by 85.75%, and the CBR became 5.5 times greater when it was stabilized with 11% BA + 25% CTCP. The SEM micrographs showed that the morphology and fabric of the control specimen (raw soil) were significantly changed when the soil was stabilized with the optimum BA‐CTCP combination (9% BA + 20% CTCP). The MLR prediction model was shown to be less efficient and accurate than the ANN model.

Visualized calculation of regional power grid power data based on multiple linear regression equation

Abstract The power generation of distributed power generation systems in regional power grids is mainly affected by external environmental factors, and there are volatility and intermittent power generation issues. This paper establishes a relatively simple multiple linear regression prediction model to predict grid-connected photovoltaic power generation systems. The article uses a hybrid modelling method to filter more important weather forecast input variables through a step-by-step linear regression method to realize the visual calculation of power data. The research results show that the multiple linear regression equation methods proposed in the article have pervasive application value in the actual application of solar photovoltaic power consumption data.

Three-Hour-Ahead of Multiple Linear Regression (MLR) Models for Particulate Matter (PM10) Forecasting

The increase of air pollutants emission through anthropogenic activities and natural phenomena in the atmosphere can give an adverse impact on human health especially to some groups of people such as children, the elderly, and people that have cardiovascular problems. Multiple Linear Regression (MLR) model establishments for the particulate matter (PM10) forecasting can be useful, as it provides early warning information to the local authorities and the communities. We aim to develop MLR models for PM10 forecasting in Peninsular Malaysia, specifically in the southern part. In this study, the hourly data of PM10, meteorological factors, and gaseous pollutants from the year 2009-2011 had been used. As a result, the next first hour of the MLR prediction model, PM10,t+1 has been selected as the best-fitted model as compared to the second and third prediction hour models, PM10,t+2, and PM10,t+3, respectively. The PM10,t+1 model was explained 61.4% (R2=0.614) variance in the data which is higher compared to model PM10,t+2 and PM10,t+3 with 42.3% (R2=0.423) and 34.7% (R2=0.347), respectively. Thus, the validation of PM10, t+1 model also has a high accuracy value of R2 (55.1%) as compared to the other two models. We conclude that the development of MLR models is adequate for PM10 forecasting in the industrial area.

Statistical Prediction and Analysis on Parameters of Vibrating Sinking Pipe Gravel Pile Machines

With the rapid development of highway engineering construction in our country, Vibrating Sinking Pipe gravel pile machines have been widely used in soft foundation treatment. The main parameters of the Vibrating Sinking Pipe gravel pile machine are composed of current value, drilling depth and drilling verticality. In this paper, through the analysis of the actual parameter data collected from the intelligent monitoring system of Vibrating Sinking Pipe gravel pile machines in Sichuan Yangtze River Industrial Park, the multiple linear regression prediction model is established by using the regression prediction method; and according to the comparison between the real data and the prediction data, the determination coefficient ranges from 0.83 to 0.95.

Investigating the Working Efficiency of Typical Work in High‐Altitude Alpine Metal Mining Areas Based on a SeqGAN‐GABP Mixed Algorithm

Man‐machine efficacy evaluations of typical work in the safe mining of high‐altitude alpine metal mines are associated with fuzziness, multiple indexes, and large subjective components. This results in difficulties in the prediction of the typical work efficiency in high‐altitude alpine metal mining areas. In this study, ergonomic theory was applied to establish the evaluation index system of typical work efficiency in high‐altitude alpine metal mining areas by studying the cooperative relationship between operators, working machines, working environment, and design variables. First, we investigated the collaborative relationship between workers, operating machinery, operating environment, and design variables in order to establish the evaluation index system of typical work efficiency in high‐altitude alpine metal mining areas. Second, principal component analysis (PCA) was integrated with the fusion entropy weight method to (i) analyze the coupling correlation and overlapping effects between the factors influencing efficiency at different altitudes and (ii) to determine the key influencing factors. Third, a model based on the sequence generative adversarial network genetic algorithm backpropagation (SeqGAN‐GABP) hybrid algorithm was established to predict the trends in the operating efficiency of typical work types in high‐altitude alpine metal mining areas. Finally, three high‐altitude alpine metal mines in Xinjiang were selected as representative examples to verify the proposed framework by comparing it with other state‐of the art models (multiple linear regression prediction model, backpropagation (BP) neural network model, and genetic algorithm back propagation (GA‐BP) neural network model). Results determine the average relative error of each model as 2.74%, 1.97%, 1.29%, and 1.02%, respectively, indicating the greater accuracy of our proposed method in predicting the efficiency of typical work types in high‐altitude alpine mining areas. This study can provide a scientific basis for the establishment of mining safety judgment standards in high‐altitude alpine areas.

Benchmarking empirical models for THMs formation in drinking water systems: An application for decision support in Barcelona, Spain

Drinking water treatment plants (DWTPs) face changes in raw water quality, which affect the formation of disinfection by-products. Several empirical modelling approaches have been reported in the literature, but most of them have been developed with lab-scale data, which may not be representative of real water systems. Therefore, the application of these models for real-time operation of DWTPs might be limited. At the present study, multiple linear regression (MLR) and multi-layer perceptrons (MLP) were benchmarked using field-scale data for predicting the THMs formation in a case-study DWTP in Barcelona, Spain. After fitting the studied models, MLR exhibited good fit with the validation data set (R2 = 0.88 and MAE = 4.0 μg·L−1) and described the most plausible input-output relationships with field-scale data. The MLR predictive model was incorporated into an environmental decision support system (EDSS) for assessing the THMs formation at two critical points of the distribution network. A Monte Carlo scheme was applied for quantifying uncertainty of model predictions at these points, considering low and high water quality scenarios and different degrees of treatment by an electrodialysis reversal process. The results show that the use of the proposed EDSS can help in real operation of complex drinking water systems, which face important changes in water quality throughout the year.

Error Correction Method of Crude Oil Moisture Content Detection Based on BP Neural Network

Microwave phase-shifting sensor is one of the effective means to realize online detection of water content in high water-cut crude oil, but its detection accuracy is easily affected by salinity. Aiming at the mineralization components (NaCl and CaCl2) existing in water-bearing crude oil, the influence of different proportion and content of dual-component mineralization on the accuracy of microwave phase-shifting crude oil water content detection sensor was studied experimentally, and the influence rule of dual-component mineralization (NaCl and CaCl2) on the accuracy of crude oil water content detection was obtained. It is difficult to establish an accurate error compensation model because the relationship between the composition and content of salinity and the measured water content is affected by many factors. Therefore, a BP neural network model for error correction is established, which reduces the detection error of microwave phase-shifting crude oil moisture sensor from 13.912% to 1.821%, and improves the detection accuracy. BP neural network prediction model is superior to multiple linear regression prediction model.