R2 Index Research Articles

A Novel Combined Model for Predicting Humidity in Sheep Housing Facilities.

Accurately predicting humidity changes in sheep barns is important to ensure the healthy growth of the animals and to improve the economic returns of sheep farming. In this study, to address the limitations of conventional methods in establishing accurate mathematical models of dynamic changes in humidity in sheep barns, we propose a method to predict humidity in sheep barns based on a machine learning model combining a light gradient boosting machine with gray wolf optimization and support-vector regression (LightGBM-CGWO-SVR). Influencing factors with a high contribution to humidity were extracted using LightGBM to reduce the complexity of the model. To avoid the local extremum problem, the CGWO algorithm was used to optimize the required hyperparameters in SVR and determine the optimal hyperparameter combination. The combined algorithm was applied to predict the humidity of an intensive sheep-breeding facility in Manas, Xinjiang, China, in real time for the next 10 min. The experimental results indicated that the proposed LightGBM-CGWO-SVR model outperformed eight existing models used for comparison on all evaluation metrics. It achieved minimum values of 0.0662, 0.2284, 0.0521, and 0.0083 in terms of mean absolute error, root mean square error, mean squared error, and normalized root mean square error, respectively, and a maximum value of 0.9973 in terms of the R2 index.

Assessment of CMIP6 models’ performances and projection of precipitation based on SSP scenarios over the MENAP region

Abstract Precipitation is the main component of the hydrological cycle. It has a significant effect on the ecosystem especially, irrigation and drainage system design and management, crop production, and flood and drought management. In this study, 11 global circulation models (GCMs) from Coupled Model Intercomparison Project phase 6 (CMIP6) were investigated under three shared socioeconomic pathway (SSP) scenarios for precipitation simulation and projection in the future period (2021–2050). Then, the results were compared with the base period (1985–2014). The research was conducted in the MENAP region. The evaluation of GCMs’ performances by the Taylor diagram, R2, MSE, MAE, and RMSE indices showed that among the 11 models, the MPI-ESM1-2-HR model with an average R2 and RMSE of 0.6 and 18.9, respectively, was more accurate than other models in precipitation simulation in the entire region. The projection of precipitation indicated that the precipitation will mainly decrease except in areas such as the Black Sea, Mediterranean, and Red Sea coastal areas as well as mountainous and higher altitude regions in the eastern part of the study area. In addition, highest decrease rates will happen in the Middle East countries, Afghanistan, Morocco, Algeria, and Sudan. Based on different scenarios in the MENAP region, precipitation will vary between −77.3 and + 51.1 mm compared to the base period. Moreover, the lowest and highest precipitation changes were estimated based on SSP1-2.6 and SSP5-8.5 scenarios. According to the various scenarios, the amount of precipitation in the future period will decrease compared to the historical period in most parts of the areas under study.

An optimization method of mine ventilation system based on R2 index hybrid multi-objective equilibrium optimization algorithm

With the increase of mining years, the mine ventilation system becomes more and more complex, causing serious energy waste. The traditional single-objective optimization model cannot​ accurately describe the complex mine ventilation system. In order to solve this problem, this paper establishes a multi-objective optimization model for mine ventilation systems considering ventilation energy consumption, fan shaft power, and fan efficiency. Furthermore, we proposed an R2 index hybrid multi-objective equilibrium optimization algorithm(R2HMEOA). Firstly, We use R2 index to improve the sorting rules of the Pareto solution. Secondly, improve the reference point strategy, and propose an elite archiving strategy based on R2 index. We use classical test functions to test the proposed algorithm. The results show that the algorithm has obvious advantages. Furthermore, we apply the algorithm to the ventilation system optimization of Wangjialing mine of Zhongmei Huajin Energy Co. Ltd. The results show that the algorithm can effectively reduce the ventilation power consumption and improve the shaft power and efficiency of the fan, which proves the practicability of the proposed algorithm.

Prediction Models for Estimating Compressive Strength of Concrete Made of Manufactured Sand Using Gene Expression Programming Model.

The depletion of natural resources of river sand and its availability issues as a construction material compelled the researchers to use manufactured sand. This study investigates the compressive strength of concrete made of manufactured sand as a partial replacement of normal sand. The prediction model, i.e., gene expression programming (GEP), was used to estimate the compressive strength of manufactured sand concrete (MSC). A database comprising 275 experimental results based on 11 input variables and 1 target variable was used to train and validate the developed models. For this purpose, the compressive strength of cement, tensile strength of cement, curing age, Dmax of crushed stone, stone powder content, fineness modulus of the sand, water-to-binder ratio, water-to-cement ratio, water content, sand ratio, and slump were taken as input variables. The investigation of a varying number of genetic characteristics, such as chromosomal number, head size, and gene number, resulted in the creation of 11 alternative models (M1-M11). The M5 model outperformed other created models for the training and testing stages, with values of (4.538, 3.216, 0.919) and (4.953, 3.348, 0.906), respectively, according to the results of the accuracy evaluation parameters root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The R2 and error indices values revealed that the experimental and projected findings are in extremely close agreement. The best model has 200 chromosomes, 8 head sizes, and 3 genes. The mathematical expression achieved from the GEP model revealed that six parameters, namely the compressive and tensile strength of cement, curing period, water–binder ratio, water–cement ratio, and stone powder content contributed effectively among the 11 input variables. The sensitivity analysis showed that water–cement ratio (46.22%), curing period (25.43%), and stone powder content (13.55%) were revealed as the most influential variables, in descending order. The sensitivity of the remaining variables was recorded as w/b (11.37%) > fce (2.35%) > fct (1.35%).

Application of the Extended Theory of Planned Behavior to Predict Exclusive Breastfeeding Intention, In Pregnant Nulliparous Women. A Cross-Sectional Study

Objective. This study investigated the effect of Extended Theory of Planned Behavior (ETPB) extended theory of planned behavior in comparison with the Theory Of Planned Behavior (TPB) in explaining the intention of Exclusive Breastfeeding Intention (EBF) in Pregnant nulliparous women of Kerman (Iran).
 Methods. In this descriptive study, 249 pregnant women in Kerman participated via simple random sampling. The research instruments included Questionnaire related to the structures of the theory of planned behavior, breastfeeding self-efficacy and social support questionnaire for breastfeeding.
 Results. The results of the correlation test showed a significant relationship between all constructs of the theory of extended planned behavior and the intention of EBF. The highest correlation belonged to the construct of subjective norms (r=0.49). Path regression coefficients in the second model showed that the Self-Efficacy mediator variable is fully capable of meaningful mediation between Social Support and Intention (p<0.001; B=0.383). The conceptual diagram of Structural equation modeling showed a higher explained variance or R2 index for the intention variable for the developed model compared to that of the first model, i.e. (the first model: R2=0.37, the second model: R2=0.46). The goodness-of-fit index had a better status for the developed model.
 Conclusion. Extended TPB with social support and breastfeeding self-efficacy constructs can be appropriate model for predicting the intention and behavior of EBF

Predicting soybean grain yield using aerial drone images

ABSTRACT This study aimed to evaluate the ability of vegetation indices (VIs) obtained from unmanned aerial vehicle (UAV) images to estimate soybean grain yield under soil and climate conditions in the Teresina microregion, Piaui state (PI), Brazil. Soybean cv. BRS-8980 was evaluated in stage R5 and submitted to two water regimes (WR) (100 and 50% of crop evapotranspiration - ETc) and two N levels (with and without N supplementation). A randomized block design in a split-plot scheme was used, in which the plots were the water regimes and the subplots N levels, with five replicates. Each plot contained twenty 4.5 m-long rows, spaced 0.5 m apart, with a total area of 45 and 6 m² study area for grain yield evaluations. Twenty VIs obtained from multispectral aerial images were evaluated and correlated with grain yield measurements in the field. Pearson’s correlation, linear regression, and spatial autocorrelation (Global and Local Moran’s I) were used to analyze the performance of the VIs in predicting grain yield. The R2, RMSE and nRMSE indices were used to validate the linear regression models. The prediction model based on EVI-2 exhibited high spatial randomness for all the treatments, and smaller prediction errors of 149.68 and 173.96 kg ha-1 (without and with N supplementation, respectively).

Predicting Bond Strength between FRP Rebars and Concrete by Deploying Gene Expression Programming Model.

Rebars made of fiber-reinforced plastic (FRP) might be the future reinforcing material, replacing mild steel rebars, which are prone to corrosion. The bond characteristics of FRP rebars differ from those of mild steel rebars due to their different stress-strain behavior than mild steel. As a result, determining the bond strength (BS) qualities of FRP rebars is critical. In this work, BS data for FRP rebars was investigated, utilizing non-linear capabilities of gene expression programming (GEP) on 273 samples. The BS of FRP and concrete was considered a function of bar surface (Bs), bar diameter (db), concrete compressive strength (fc′), concrete-cover-bar-diameter ratio (c/d), and embedment-length-bar-diameter ratio (l/d). The investigation of the variable number of genetic parameters such as number of chromosomes, head size, and number of genes was undertaken such that 11 different models (M1–M11) were created. The results of accuracy evaluation parameters, namely coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) imply that the M11 model outperforms other created models for the training and testing stages, with values of (0.925, 0.751, 1.08) and (0.9285, 0.802, 1.11), respectively. The values of R2 and error indices showed that there is very close agreement between the experimental and predicted results. 30 number chromosomes, 9 head size, and 5 genes yielded the optimum model. The parametric analysis revealed that db, c/d, and l/d significantly affected the BS. The FRP rebar diameter size is greater than 10 mm, whereas a l/d ratio of more than 12 showed a considerable decrease in BS. In contrast, the rise in c/d ratio revealed second-degree increasing trend of BS.

Study of water resources parameters using artificial intelligence techniques and learning algorithms: a survey

Qualitative analysis of water resources is one of the most widely used topics in water resources research today. Researchers use various analysis methods of water parameters to achieve the desired goals in this field. This research uses artificial intelligence (AI), learning machine (LM), data mining, and mathematical techniques to simulate water behavior and estimate its parametric changes. The proposed model used in this study was a Self-adaptive Extreme learning machine (SAELM) to estimate hydrogeological parameters of the Meghan wetland located in Markazi province in Iran. In addition, SAELM simulation results were compared to Least square support vector machine (LSSVM), Multiple linear regression (MLR), and Adaptive Neuro-fuzzy inference system (ANFIS) models. The simulated parameters were Electrical Conductivity (EC), Total Dissolved Solids (TDS), Groundwater Level (GWL), and salinity. This information was related to sampling for 175 months in the study area. Finally, after simulation operation, four models were introduced as superior models. Mentioned exceptional models were SAELM in GWL modeling, SAELM in modeling the EC, MLR in salinity simulation, and LSSVM in the simulation of TDS parameters. Moreover, by five approaches, the models' performance was evaluated. Suggested strategies were performance evaluation by statistical indicators, Wilson score method uncertainty analysis (WSMUA), response & correlation plots, discrepancy ratio charts, and distribution error diagrams. Based on statistical indicators, the SAELMGWL model was the most accurate model with RMSE, MAPE, and R2 indices equal to 0.1496, 0.0043, and 0.9933, respectively. The ANFIS model had the worst results in simulation.

Hyperspectral reconstruction method for optically complex inland waters based on bio-optical model and sparse representing

For better use of well-performed water quality parameter estimation models and the comprehensive use of multi-source remote sensing data, hyperspectral reconstruction is urgently needed in the remote sensing of optically complex inland waters. In this study, we proposed a bio-optical–based hyperspectral reconstruction (BBHR) algorithm to generate hyperspectral above-surface remote-sensing reflectance (Rrs) data ranging in wavelength from 400 to 800 nm. One core advantage of the BBHR method is its in situ data independency, which theoretically renders the algorithm universal. The other advantage is its ability to reconstruct hyperspectral Rrs for the 400–800 nm spectral range, which facilitates the construction of more high accuracy chlorophyll-a concentration (Cchla) estimation models for optically complex waters. The reconstruction was tested by employing six widely used multispectral sensors: the Medium Resolution Imaging Spectrometer, (MERIS), Sentinel-3 Ocean and Land Color Instrument (S3 OLCI), Sentinel-2 Multispectral Instrument (S2 MSI), Geostationary Ocean Color Imager (GOCI), Visible Infrared Imaging Radiometer Suite (VIIRS), and Moderate Resolution Imaging Spectroradiometer (MODIS). The model performance was validated by using a ASD FieldSpec spectroradiometer-measured hyperspectral dataset containing 1396 samples and a satellite-in-situ match-up dataset with 66 samples. The results show that the proposed BBHR method exhibits satisfactory performance. The average mean absolute percentage error (MAPE), root mean square error (RMSE), R2 and bias indices of the BBHR-reconstructed Rrs over all spectral bands of the six multispectral sensors were 3.27%, 8.86 × 10−4 sr−1, 0.98, and − 6.53 × 10−5 sr−1, respectively. In the field Cchla estimation experiment that contained 391 samples (mean Cchla is 25.42 ± 16.37 μg/L), the BBHR algorithm improved the MAPE and RMSE indices of multispectral data from 0.47 and 12.80 μg/L to 0.42 and 10.16 μg/L, respectively. For the satellite image match-up dataset (66 samples), the BBHR method decreased the MAPE and RMSE indices of multispectral images from 0.51 and 12.94 μg/L to 0.32 and 8.01 μg/L, respectively. The proposed algorithm outperformed the other two high-accuracy models in terms of spectral fidelity and Cchla estimation. In addition, the BBHR method shows great potential for the multi-source monitoring of inland water bodies. This could improve the accuracy and robustness of the reconstruction when semi-synchronized multi-source data are input and increase the consistency of multi-source data when non-synchronized multi-source data are provided. Our results revealed that BBHR is a trustworthy algorithm that offers hyperspectral Rrs data and facilitates the remote monitoring of turbid inland waterbodies.

Forest Biometric Systems in Mexico: A Systematic Review of Available Models

Biometric systems are the basis of forest management and consist of a set of equations that describe the relationships between forest attributes and dendrometric variables. A systematic review of the state of the art of biometric systems in Mexico was carried out by a Mexican consortium (10 researchers), covering a period of 50 years ca (1970–2019), using the main scientific literature delivered by a systematic search (WoS, Scopus, Scielo, Redalyc) and a targeted search (theses, technical reports, etc.). A single selection criterion was established for the inclusion of information in the analysis: the document had to present at least one of the equations of interest. We found 376 documents containing 2524 equations for volume (69%), diameter (11%), height (9%) and site index (11%). These equations were developed for forest species mainly from temperate regions (88%), such as pine (66%) and oak (9%). Consequently, the Mexican states with the highest number of equations were Durango (28%), Chihuahua (17%), Hidalgo (13%) and Oaxaca (8%). Although large, the number of equations identified concentrated on a relatively small number of models: Schumacher & Hall and Fang et al. for volume; Chapman-Richards and Schumacher for site index and diameter; and Chapman-Richards and the allometric equation for height. An analysis of model fit, measured through R2, showed that, on average, the volume, diameter and site index models show high fit (R2 = 0.96), although this pattern was more consistent in the volume models. Publication bias was evaluated by means of a funnel plot analysis, with no apparent bias identified. A limitation of our study is that the information obtained is not updated to the present year; however, the 50-year trends allow us to assume that no recent significant changes in the patterns exist. Finally, we highlight the need to assess the predictive ability of the models to ensure accurate estimates to support better forest management decisions.

Pulmonary vein isolation with adjunctive left atrial ganglionic plexus ablation for treatment of atrial fibrillation: a meta-analysis of randomized controlled trials.

Adjunctive ganglionic plexus (GP) ablation may increase the efficacy of pulmonary vein isolation (PVI) for treatment of atrial fibrillation (AF). Prior meta-analyses examining PVI with adjunctive GP ablation have included non-randomized trials and have included trials evaluating thorascopic epicardial ablation. The objective of this study is to perform a meta-analysis of randomized controlled trials (RCTs) comparing endocardial catheter-based PVI to PVI with adjunctive GP ablation. Summary odds ratio (OR) and 95% confidence intervals (CIs) were calculated. Heterogeneity was assessed with I2 values. Sub-group analysis was performed comparing arrhythmia recurrence between patients with paroxysmal versus persistent AF at trial baseline. Meta-regressions were performed with mean left atrial diameter and left ventricular ejection fraction at trial baseline as the moderator variables. Five RCTs were identified including 814 patients: 406 PVI + GP ablation and 408 PVI alone. The mean age of participants was 56.5years and 74.7% were male. Four of these trials evaluated catheter-based endocardial ablation for a total of 574 patients: 289 PVI + GP ablation and 285 PVI alone. The odds of arrhythmia recurrence in patients undergoing adjunctive GP ablation with PVI compared with PVI alone were a reduced: odds ratio (OR) 0.58, 95% confidence interval (CI) 0.41-0.82, I2 = 40.2%. In the subgroup analysis, the odds of arrhythmia recurrence with adjunctive GP ablation were reduced in those with paroxysmal AF (OR 0.396, 95% CI 0.23-0.69, I2 = 0%). A non-significant trend to reduced arrhythmia recurrence was also observed in those with persistent AF (OR 0.726, 95% CI 0.475-1.112, I2 = 0%). When performing the meta-regression, increased left atrial diameter was associated with decreased treatment effect of adjunctive GP ablation (R2 index = 1.0, I2 = 0%). The addition of GP ablation to PVI was associated with reduced arrhythmia recurrence. Adjunctive GP ablation was more effective in paroxysmal AF and in patients with smaller atria. Larger RCTs are needed to confirm the efficacy of GP + PVI ablation.

Mathematical model of the bone biological age based on the bone mineral density and quality indicex and Ukrainian FRAX model

Background. It is well-known that with aging there is a loss of bone mass and its strength, which leads to the development of osteoporosis and its complications. The aim of the study was to create a modern mathematical model for determining the biological age of the bone system, taking into account indices of bone mineral density (BMD) and quality and the FRAX® questionnaire. Materials and methods. 77 women and 44 men aged 30 to 90 years without any significant somatic pathology were included in the study. Patients were divided into 4 age groups: 30–44 years old — young, 45–59 years — mature, 60–74 years — old age and 75–90 years— senile age. We measured the parameters of BMD in the different areas of the skeleton by means of the dual-photon X-ray absorptiometry (DXA, “Prodigy”). The 10-year probability of major osteoporotic and hip fractures was measured using the Ukrainian version of the FRAX®. Statistical analysis was performed in the Statistica 7.0 program (StatSoft Inc., USA). Results. The dependence of the indices of BMD and bone quality, risk of osteoporotic fractures on age and the need for their early determination in young people to predict the risk of osteoporosis and its complications have been proven. The coefficient of determination of the R2 model was 0.62, which indicates that 62% of the variance of the “Age” can be explained by the predictors included in the model (DXA and FRAX indices); adjusted R2 index was 0.59 (p<0.001), which indicates high significance of the model. Conclusions. The developed model for estimating the bone biological age has high accuracy and can be used to assess the risk of osteoporosis and its complications in young people for the purpose of predicting the disease.

Population genetic structure of the elephant tick Amblyomma tholloni from different elephant populations in Kenya

Understanding factors that shape tick population genetic structure is important as they may be exploited in crafting strategies for vector control. Amblyomma tholloni, or “elephant tick” is a three-host tick whose adults preferentially parasitize African elephants. The aim of this study was to determine the influence of fragmentation of the host populations on the genetic structure of this tick species from different ecosystems in Kenya, using the second internal transcribed spacer (ITS-2) and mitochondrial cytochrome oxidase 1 (CO1) loci. Population genetic analysis of ticks collected from four elephant populations using ITS-2 and CO1 loci revealed high gene diversity. Gene diversity at the ITS-2 locus was 0.91 and the nucleotide diversity was, 0.01. ITS-2 gene diversity was highest in Laikipia-Samburu ecosystem (0.947) and lowest in Tsavo (0.80). The CO1 locus also had high gene diversity, 0.790, and low nucleotide diversity, 0.006, and like ITS-2, gene diversity was higher in Laikipia-Samburu ecosystem (1.00) and lower in Tsavo (0.286). There was a modest statistically significant genetic differentiation among the four tick populations based on ITS-2 (FST = 0.104, P < 0.001; ΦST = 0.105, P < 0.001), and a 10% of molecular variance attributed to genetic variation between populations. There was also statistically significant differentiation among tick populations using haplotype frequencies for CO1 locus (FST = 0.167, P < 0.001) accounting for 17% of genetic variance among populations, but not modelled genetic distances (ΦST = 0.029, P = 0.095) suggesting very recent genetic differentiation. In addition, populations of A. tholloni in Kenya had a significantly negative Tajima D and Fu & Li's F* and D* at the CO1 locus suggesting recent positive selection. The extensive acaricide use in livestock, which host the larval stage, could be driving purifying selection and genetic hitchhiking of the CO1 locus. However, tests sensitive to demography such as Fu's FS, Ramos-Onsins & Rozas's R2 and raggedness index r were statistically significant at the ITS-2 locus suggesting ancient demographic expansion. Elephant population fragmentation appears to shape the genetic structure of A. tholloni, while agro-ecological factors could influence the genetic diversity of ticks.

Machine learning-based model development for battery state of charge–open circuit voltage relationship using regression techniques

The development of the Battery Management System mainly depends on an accurate equivalent circuit of the battery model which can be used for the estimation of State of Charge (SoC) and State of Health (SoH). The accuracy of the predicted battery model mainly depends on the exactness of the SoC–Open Circuit Voltage (OCV) relationship which is obtained through the Static Test. Numerous research works reported on various higher-order SoC–OCV battery mathematical models which are unsuitable for real-time applications. Also, there is no unique model for the estimation of battery parameters. This work proposes a Machine Learning (ML) based battery static SoC–OCV prediction method using the concept of supervised learning. The performance of the proposed ML based techniques is compared with the conventional curve fitting techniques. The real-time data of Lithium Ion battery at different temperature profiles are used to analyze the performance of the proposed techniques. The Root Mean Square Error (RMSE) and R-Square (R2) indices are considered in the study to validate the performance of the proposed algorithm. From the study, it is revealed that the Neural network based prediction method is found to be the best method with high R2 and low RMSE indices. The proposed method has the advantages such as simplicity and high accuracy. This predicted battery model can be used in electric vehicle applications.

The potential of a novel support vector machine trained with modified mayfly optimization algorithm for streamflow prediction

ABSTRACT This paper focuses on the development of a robust accurate streamflow prediction model by balancing the abilities of exploitation and exploration to find the best parameters of a machine learning model. To do so, the simulated annealing (SA) algorithm is integrated with the mayfly optimization algorithm (MOA) as SAMOA to determine the optimal hyper-parameters of support vector regression (SVR) to overcome the exploration weakness of the MOA method. The proposed method is compared with the classical SVR and hybrid SVR-MOA. To examine the accuracy of the selected methods, monthly hydroclimatic data from Jhelum River Basin is used to predict the monthly streamflow on the basis of RMSE, MAE, NSE, and R2 indices. Test results show that the SVR-SAMOA outperformed the SVR-MOA and SVR models. SVR-SAMOA reduced the prediction errors of the SVR-MOA and SVR models by decreasing the RMSE and the MSE from 21.4% to 14.7% and from 21.7% to 15.1%, respectively, in the test stage.

Spatiotemporal Changes in Plasmodium vivax msp142 Haplotypes in Southern Mexico: From the Control to the Pre-Elimination Phase.

For 20 years, Plasmodium vivax has been the only prevalent malaria species in Mexico, and cases have declined significantly and continuously. Spatiotemporal genetic studies can be helpful for understanding parasite dynamics and developing strategies to weaken malaria transmission, thus facilitating the elimination of the parasite. The aim of the current contribution was to analyze P. vivax-infected blood samples from patients in southern Mexico during the control (1993–2007) and pre-elimination phases (2008–2011). Nucleotide and haplotype changes in the pvmsp142 fragment were evaluated over time. The majority of multiple genotype infections occurred in the 1990s, when the 198 single nucleotide sequences exhibited 57 segregating sites, 64 mutations, and 17 haplotypes. Nucleotide and genetic diversity parameters showed subtle fluctuations from across time, in contrast to the reduced haplotype diversity and the increase in the R2 index and Tajima’s D value from 2008 to 2011. The haplotype network consisted of four haplogroups, the geographical distribution of which varied slightly over time. Haplogroup-specific B-cell epitopes were predicted. Since only high-frequency and divergent haplotypes persisted, there was a contraction of the parasite population. Given that 84% of haplotypes were exclusive to Mesoamerica, P. vivax flow is likely circumscribed to this region, representing important information for parasite surveillance.

The investigation of influencing factors on the degradation of sulfonamide antibiotics in iron-impregnated biochar-activated urea-hydrogen peroxide system: A QSAR study

Iron-impregnated biochar-activated urea-hydrogen peroxide (FB-activated UHP) is a potential in-situ technology for simultaneously reducing soil sulfonamide antibiotic contaminants and improving soil fertility. To better understand the degradation of sulfonamide antibiotics by FB-activated UHP, a two-dimensional quantitative structure-activity relationship (2D-QSAR) model based on quantum chemical parameters and a three-dimensional QSAR (3D-QSAR) model based on molecular force field were developed to investigate the factors influencing the removal efficiencies (Re%). The optimal 2D-QSAR model was Re%= 0.858–8.930 E-5 EB3LYP-0.175 f(+)x with the evaluation indices of R2= 0.732, q2= 0.571, and Qext2= 0.673. The given 2D-QSAR model indicated that the molecular size (EB3LYP) and Fukui index with respect to nucleophilic attack (f(+)) were intrinsic factors influencing Re%. Three degradation pathways were subsequently proposed based on the f(+) distribution. Compared to the 2D-QSAR model, the developed 3D-QSAR model exhibited a better predictive ability, with the evaluation indices of R2= 0.989, q2= 0.696, and SEE= 0.001. The analysis of field contribution rates suggested that electrostatic field (48.2%), hydrophobic field (25.3%), and hydrogen-bond acceptor field (12.7%) were the main factors influencing Re%. These findings generated critical information for evaluating the degradation mechanisms/rules and provided theoretical bases for initially estimating the Re% of sulfonamide antibiotics undergoing FB-activated UHP process.

Perceived Similarity as the Source of the Feeling of Intergroup Threat

In Cameroon, a country which has undergone a double French/British administration (1916-1961), the cohabitation between Francophones and Anglophones since 1961 is far from having erased the intergroup differences linked to their respective colonial pasts. On the contrary, over time, it has generated what has been called the Anglophone problem. In this context, is the strong tendency towards the schooling of students from francophone families in schools of the anglophone sub-system of education likely to attenuate intergroups cleavages? From the theoretical perspective of social identity, this research suggests that the perceived similarity between Anglophones and anglophonized francophones generates a threat to the specific Anglophones' linguistic identity. To test this hypothesis, the optimal distinctiveness and intergroup threat scales were administered to 462 Anglophones participants of both sexes. The correlation and linear regression analyzes provide empirical support for the hypothesis of the study. An adjusted R2 index validates the existence of a causal relationship between perceived similarity and intergroup threat.

A robust hybrid predictive model of mixed oil length with deep integration of mechanism and data

Accurate estimation of mixed oil length is highly required in multi-product pipelines because it can guide the operator to correctly handle the mixed oil segment and effectively reduce the loss of petroleum product quality. In previous study, a hybrid model combined with machine learning algorithm with existing mechanism has been developed and has good predictive accuracy. Unfortunately, due to incorrect measurement and improper recording, outliers are widely present in industrial datasets and may render the predictive performance of the previous model quite disappointing, while the effect of outliers on predictive models for the mixed oil length is rarely discussed. In order to deal with such issues, this paper first proposes a way to define the outlier sample and explicitly studies its impact on the performance of the predictive model for mixed oil prediction. Subsequentially, various new hybrid modeling methods are developed driven by both operation data (exploited by the Gradient Boosting Decision Tree algorithm) and the mechanism (based on the Austin-Palfrey equation) in different arrangements. Extensive experiments are conducted on real-life transportation pipelines, and the results show that with the clean training set, the R2 index of the proposed serial-parallel hybrid model (SPHM) is 0.96, which is higher than that of mechanism model and the existing hybrid model. Even with all the outliers added, advantage in prediction accuracy of the SPHM is still noticed, demonstrating feasibility and robustness of the hybrid modeling approach for prediction of mixed oil length.

Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach

Soil salinization is a severe danger to agricultural activity in arid and semi-arid areas, reducing crop production and contributing to land destruction. This investigation aimed to utilize machine learning algorithms to predict spatial soil salinity (dS m−1) by combining environmental covariates derived from remotely sensed (RS) data, a digital elevation model (DEM), and proximal sensing (PS). The study is located in an arid region, southern Iran (52°51′–53°02′E; 28°16′–28°29′N), in which we collected 300 surface soil samples and acquired the spectral data with RS (Sentinel-2) and PS (electromagnetic induction instrument (EMI) and portable X-ray fluorescence (pXRF)). Afterward, we analyzed the data using five machine learning methods as follows: random forest—RF, k-nearest neighbors—kNN, support vector machines—SVM, partial least squares regression—PLSR, artificial neural networks—ANN, and the ensemble of individual models. To estimate the electrical conductivity of the saturated paste extract (ECe), we built three scenarios, including Scenario (1): Synthetic Soil Image (SySI) bands and salinity indices derived from it; Scenario (2): RS data, PS data, topographic attributes, and geology and geomorphology maps; and Scenario (3): the combination of Scenarios (1) and (2). The best prediction accuracy was obtained for the RF model in Scenario (3) (R2 = 0.48 and RMSE = 2.49), followed by Scenario (2) (RF model, R2 = 0.47 and RMSE = 2.50) and Scenario (1) for the SVM model (R2 = 0.26 and RMSE = 2.97). According to ensemble modeling, a combined strategy with the five models exceeded the performance of all the single ones and predicted soil salinity in all scenarios. The results revealed that the ensemble modeling method had higher reliability and more accurate predictive soil salinity than the individual approach. Relative improvement (RI%) showed that the R2 index in the ensemble model improved compared to the most precise prediction for the Scenarios (1), (2), and (3) with 120.95%, 56.82%, and 66.71%, respectively. We applied the best model in each scenario for mapping the soil salinity in the selected area, which indicated that ECe tended to increase from the northwestern to south and southeastern regions. The area with high ECe was located in the regions that mainly had low elevations and playa. The areas with low ECe were located in the higher elevations with steeper slopes and alluvial fans, and thus, relief had great importance. This study provides a precise, cost-effective, and scientific base prediction for decision-making purposes to map soil salinity in arid regions.