Empirical Regression Models Research Articles

The Impact of Industrial Robots on Green Total Factor Energy Efficiency: Empirical Evidence from Chinese Cities

Improving energy utilization efficiency is a crucial means to achieve energy conservation, emission reduction, and green development. At present, to establish a high-quality development framework and satisfy the growing need for a better life among all its people, China must steadfastly pursue the path of green development. Although China’s substantial economic scale and achievements in ecological civilization construction provide favorable conditions for green transformation, there remains a significant gap compared to developed countries in the application of green and clean technologies. Confronted with technological bottlenecks, leveraging emerging technologies such as industrial robots from the new round of scientific and technological revolutions to improve the green total factor energy efficiency (GTFEE) is of critical importance to China’s green development. This study explores the potential impact of industrial robots on enhancing China’s GTFEE. It begins by reviewing the current research landscape in this field, highlighting its shortcomings, and theorizing potential impact pathways of industrial robots. Subsequently, the paper analyzes data from 2010 to 2019 on the usage of industrial robots and GTFEE across 276 cities at the prefectural level or above in China. Through empirical regression models that incorporate control variables and interaction terms, the study investigates the specific impacts of industrial robots on energy efficiency and their mechanisms of action. The results indicate that industrial robots significantly enhance the GTFEE of Chinese cities, especially in the Northeastern region. Industrial robots notably improve the GTFEE in resource-based cities, old industrial bases, and low-carbon pilot cities. Additionally, robots indirectly boost GTFEE by increasing labor productivity. Enhanced levels of green innovation and environmental regulations also positively moderate the effectiveness of industrial robots in improving energy efficiency. The findings of this research can assist local government agencies in coordinating and implementing policies that are conducive to green development, making better use of industrial robots to serve the people, and are of significant importance for promoting the transformation of China’s economy and society towards high-quality development.

Synergistic approach to wear rate forecasting in AZ31/5% Yttria stabilized zirconia reinforced composite through response surface methodology-genetic algorithm integration

In this work, the wear behavior of a novel AZ31 magnesium alloy reinforced with 5% yttria-stabilized zirconia (YSZ) composite was evaluated using a hybrid Response Surface Methodology (RSM) and Genetic Algorithm (GA) approach. The composite was fabricated using ultrasonic-assisted stir squeeze casting technique, ensuring homogeneous distribution of spherical YSZ particles, as validated by the scanning electron microscope integrated with energy dispersive spectroscope. Wear tests were carried out according to the ASTM standards using a pin-on-disc (POD) tribometer, with applied load (AL), sliding speed (SS), and sliding distance (SD) as the main parameters. An empirical wear rate regression model was developed using RSM/Box-behnken design, and Genetic Algorithm was deployed for parametric optimization, achieving a minimal wear rate of 0.0144 g/m under a load of 30 N, sliding speed of 260 rpm, and sliding distance of 400 m. Confirmation tests were performed to validate the GA predictions. The wear mechanisms were observed, showing reduced wear in GA-optimized samples due to optimized load distribution resulting minimized ploughing, grooving and delamination. This work highlights the efficacy of the hybridized RSM / GA for the wear performance in advanced magnesium alloy matrix composites.

Comparative assessment of waste-to-energy scenarios to mitigate GHG emission from MSW in a developing mega city

The search for sustainable municipal solid waste management in urban areas has become a dire need as the generated unprecedented volumes of waste eventually end up in landfills and emits greenhouse gas (GHG). To offer sustainable waste management in Dhaka, Bangladesh, the performance of incineration, anaerobic digestion, and hydrothermal carbonization (HTC) based Waste to Energy (WtE) processes were assessed and compared. The population and the GDP of Dhaka North City Corporation from 2015 to 2023 were used to estimate the MSW generation rate with an empirical multivariable linear regression model. In 2023 around 3600 tons/day of MSW was generated which was 35 % higher than in 2015. The IPCC decay models, ZODM, FODM, and modified triangular model (MTM) yielded 87.3, 41.3, and 38-k tonnes of CH4 generation, respectively. The power generation from incineration-based plants can fall from 30 MW to 3 MW if the moisture content of MSW increases from 70 % to 90 %. Anaerobic digestion produces 34 MW of power. The Optimization of the HTC operating parameters was done and it demonstrates substantial energy potential (up to 65 MW with co-feeding of 420 tons/day of hydrochar with 426 tons/day of plastic from MSW) and GHG emission reduction (221.5 %) compared to landfilling. Additionally, HTC-derived wastewater presents an opportunity for nutrient recovery with 8.16 and 2.66, 0.3 tons/day of K, Na, and P reclamation potential, respectively. A comparison of different scenarios in plastic recycling in incineration and sensitivity analysis for three WtE schemes were conducted. Thus, the study provides a rigorous assessment of different pathways to offer a comprehensive framework for sustainable MSW management that contributes to a cleaner urban environment.

Comparison of methods to calculate groundwater recharge for karst aquifers under a Mediterranean climate

Karst aquifers can be particularly vulnerable to human activities and climate change due to their relatively high degree of connection with the surface. This study utilized an ensemble of event-based recharge calculation methods to address the problem of structural uncertainty for the example of the Western Mountain Aquifer (WMA), a Mediterranean karst aquifer located in Israel and the West Bank. Spatially distributed recharge estimates derived from the Soil and Water Assessment Tool (SWAT) and the process-based infiltration model (PIM) were compared to site-specific, empirical regression models. The SWAT and PIM mean annual recharge estimates ranged from 32–34.6% of precipitation, almost equating to the results of empirical regression models (32–36%). Future recharge predictions under the influence of climate change were quantified by parameterizing the SWAT and PIM methods with a downscaled regional climate model of Israel. SWAT predicts a 23% decrease in recharge by 2051–2070 relative to 1981–2001. In contrast, PIM shows a 9% decrease, possibly due to the representation of infiltration through preferential flow pathways and exclusion of surface runoff processes. These divergent projections underline key methodological differences in the representation of hydrological processes. Nevertheless, both methods effectively provided good estimates of groundwater recharge. The recharge rates estimated from the various methods were integrated into MODFLOW to assess their relative impacts on groundwater storage dynamics. The ensemble of MODFLOW projected groundwater storage outputs can provide guidance for sustainable groundwater management in the region.

Digital Mapping and Scenario Prediction of Soil Salinity in Coastal Lands Based on Multi-Source Data Combined with Machine Learning Algorithms

Salinization is a major soil degradation process threatening ecosystems and posing a great challenge to sustainable agriculture and food security worldwide. This study aimed to evaluate the potential of state-of-the-art machine learning algorithms in soil salinity (EC1:5) mapping. Further, we predicted the distribution patterns of soil salinity under different future scenarios in the Yellow River Delta. A geodatabase comprising 201 soil samples and 19 conditioning factors (containing data based on remote sensing images such as Landsat, SPOT/VEGETATION PROBA-V, SRTMDEMUTM, Sentinel-1, and Sentinel-2) was used to compare the predictive performance of empirical bayesian kriging regression, random forest, and CatBoost models. The CatBoost model exhibited the highest performance with both training and testing datasets, with an average MAE of 1.86, an average RMSE of 3.11, and an average R2 of 0.59 in the testing datasets. Among explanatory factors, soil Na was the most important for predicting EC1:5, followed by the normalized difference vegetation index and soil organic carbon. Soil EC1:5 predictions suggested that the Yellow River Delta region faces severe salinization, particularly in coastal zones. Among three scenarios with increases in soil organic carbon content (1, 2, and 3 g/kg), the 2 g/kg scenario resulted in the best improvement effect on saline–alkali soils with EC1:5 > 2 ds/m. Our results provide valuable insights for policymakers to improve saline–alkali land quality and plan regional agricultural development.

Optimization of Reservoir Water Quality Parameters Retrieval and Treatment Using Remote Sensing and Artificial Neural Networks

Inland water bodies are critical ecosystems that serve several functions including the provision of freshwater, regulation of climate and hydrological flows, and pollution control. Therefore, effective monitoring and management of these water resources is critical for sustainable water supply systems. This study evaluated the possible use of satellite data to estimate water quality parameters (WQPs) in an inland water body. The study also used artificial neural network (ANN) models in addition to the satellite data to determine the optimum coagulant dose for water treatment. The use of earth observations and machine learning methods has not been done extensively in developing countries, specifically, in water quality monitoring and management. The study utilized empirical multivariate regression modelling (EMRM) of the spectral reflectances from satellite data for the retrieval of Chla-a, Turbidity, and total suspended solids (TSS) concentrations in an inland water body. Using MLP-ANN modelling, the extracted spectral reflectance values from the selected sampling points in the reservoir were used as model inputs for the prediction of treated WQPs. A second MLP-ANN model was developed to predict the optimum coagulant dose required for raw water treatment. The R2 values achieved with AN model 1 were 0.81, 0.76, and 0.81 respectively for TSS, turbidity, and Chl-a, and 0.99 for the optimum coagulant dose. The study concluded that spectral reflectance from medium resolution satellite data products can be used to estimate WQPs from inland water bodies. Further, the ANN models demonstrate that extracted water quality data from satellite images can be used to inform ANN models for water quality predictions, and for the optimization of water treatment plant operations.

Revealing spatial-temporal impact of industrial effluent towards DOM in Riverine employing PARAFAC and MW-2D COS

Industrial activities often disrupt the natural equilibrium of water bodies, with discharged wastewater introducing dissolved organic matter (DOM) and pollutants. This study investigated the water quality along a riverine system subjected to heavy industrial influence by collecting samples from distinct points at before, during, and after industrial discharge across four seasons. By employing EEM-PARAFAC, four fluorescent components were identified at the discharge point including C1 (microbial/ terrestrial humic-like), C2 (anthropogenic humic-like materials), C3 (microbial humic-like), and C4 (wastewater/nutrient enrichment tracer). Specifically, C2 and C4 which contained wastewater and anthropogenic-like material are not found at the pre-pollutant point. Additionally, fluorescence characteristics parameters such as FI, HIX, and BIX are analyzed. Kernel Principal Component Analysis was employed to elucidate the non-linear relationships inherent in the data that able to covered up to 97 % of the data variance, offering nuanced insights into complex behavior of water characteristics across seasonal variations. Two-dimensional correlation spectroscopy (2D-COS) was further employed to evaluate the sequence variation of DOM components and further identify the temporal effect across season with moving window 2D-COS. The sequence order of the DOM fractions was identified as C2→C4→C1→C3 by following the Noda’s rule. In order to understand the interactions between the water characteristics and the DOM components, an empirical polynomial regression model is developed with an average MAPE of 2.2 %. The interaction between DOM-related parameters was identified using structural equation modeling. These findings underscore the dynamic nature of DOM composition under industrial influences considering the spatial-temporal impact.

Estimation of shale adsorption gas content based on machine learning algorithms

Shale gas is a clean and low-carbon natural gas resource. It mainly exists in both adsorbed and free states in pores and fractures. To accurately estimate the in-situ adsorption gas content (AGC), which is helpful in resource evaluation and development planning, methane isothermal adsorption data and geological parameters have been collected, such as total organic carbon (TOC) content, thermal maturity (Ro), siliceous mineral content (VQF), total clay content (VTC), water content (VWC), and temperature (T). Using machine learning (ML) methods, the in-situ AGC estimation models were constructed and optimized. Various geological factors affecting methane adsorption were evaluated, and an application was conducted in the Wufeng-Formation shale. The results reveal that the four ML models have higher accuracy in predicting Langmuir volume (VL) and Langmuir pressure (PL) than empirical formulas and linear regression models. Among the four ML models, the Random Forest Regression (RFR) and eXtreme Gradient Boosting Regression (XGBR) models perform the best, with R2 higher than 0.85. TOC and T are the main factors affecting methane adsorption, followed by Ro and VQF, while the importance of VTC and VWC is relatively low. According to different combinations of geological parameters, there are three schemes for ML model construction. Among them, scheme 1 based on all six geological parameters has the highest accuracy and is most beneficial to predicting AGC. Gradually reducing VWC, VTC, and VQF results in a slight decrease in accuracy, with R2 decreasing by at most about 6%, scheme 2 is suitable for rougher estimation of AGC. Further removal of T and Ro results in a significant decrease in accuracy, with R2 decreasing by up to 50% and MRE exceeding 30%, rendering scheme 3 unavailable for AGC prediction. The AGC of Wufeng-Longmaxi shale is successfully predicted based on XGBR model, with AGC mainly in 1.0 m3/ton-4.0 m3/ton. Overall, the ML models based on multiple geological parameters can simulate the real reservoir environment and achieve rapid and accurate estimation of in-situ AGC.

A multivariate linear regression model for estimating chlorophyll-a concentration in Quan Son Reservoir (Hanoi, Vietnam) using Sentinel-2B Imagery

Monitoring chlorophyll-a concentration (Chla) in inland waters is vital for environmental assessment. This study develops an empirical multivariate linear regression (MLR) model to directly estimate Chla in Quan Son Reservoir using Sentinel-2B (S2B) Level 2A images. Regression analysis of a 68-point in-situ Chla dataset measured in Quan Son Reservoir between 2021 and 2023, in conjunction with the corresponding S2B reflectance data, reveals a significant correlation between Chla and a combination of the blue (B2), green (B3), and red (B4) bands (coefficient of determination, R² = 0.95). The Chla estimation model is validated using a 30-point in-situ dataset collected on various dates (R² = 0.87; the root-mean-squared error RMSE < 5%). Subsequently, the model is applied to ten S2B images acquired from 2021 to 2023, revealing Chla's spatio-temporal distribution across the reservoir. Two key trends emerge: (1) Chla is lower during winter (November and December) than in summer and early autumn (July and September), and (2) The distribution of Chla undergoes noticeable spatial changes, particularly in July, with elevated levels observed in areas characterized by tourist hotspots. This approach shows promise for monitoring Chla in similar inland waters.

Prolonged lung-to-finger circulation time indicates an increased risk of intermittent hypoxaemia in sleep apnoea patients.

Intermittent hypoxaemia is closely associated with cardiovascular dysfunction and may be a more accurate indicator of obstructive sleep apnoea (OSA) severity than conventional metrics. Another key factor is the lung-to-finger circulation time (LFCt), defined as the duration from the cessation of a respiratory event to the lowest point of oxygen desaturation. LFCt serves as a surrogate marker for circulatory delay and is linked with cardiovascular function. Yet, the specific associations between respiratory and hypoxaemia characteristics and LFCt in patients with OSA remain unclear. This study aims to investigate these associations, ultimately contributing to a more nuanced understanding of OSA severity. The study comprised 878 in-lab polysomnographies of patients with suspected OSA. The conventional OSA metrics were computed along with nine hypoxaemia metrics and then divided into quartiles (Q1-Q4) based on respiratory event duration. In addition, these were further divided into subquartiles based on LFCt. The empirical cumulative distribution functions (CDFs) and linear regression models were used to investigate the association between desaturation metrics and LFCt. The results showed that prolonged LFCt was associated with increased hypoxic severity. Based on CDFs, the hypoxic severity significantly increased with longer LFCt despite the duration of respiratory events. Furthermore, fall duration was elevated in patients with longer LFCt (Q1- desaturation fall duration (FallDur): 14.6 s; Q4-FallDur: 29.8 s; p<0.0001). The regression models also showed significant association between hypoxic severity and LFCt (Q1-desaturation fall slope (FallSlope): β=-3.224; Q4-FallSlope: β=-6.178; p<0.0001). Considering LFCt along with desaturation metrics might be useful in estimating the association between the severity of OSA, physiological consequences of respiratory events and cardiac health.

Are women satisfied with childbirth services provided in public health facilities? Evidence from two districts in Bihar, India

PurposeThis study aims to measure the level of satisfaction among women with childbirth services provided at public health facilities. Further, to analyse the impact of their socio-economic and obstetric characteristics on their level of satisfaction.Design/methodology/approachTo accomplish these objectives a cross-sectional survey was conducted in two districts of an Indian state, Bihar. Structured questionnaire was developed based on the scale proposed by Okumu and Oyugi (2018) both for vaginal and caesarean birth patients. For empirical analysis multiple linear regression model was employed.FindingsResults suggest that majority of mothers are satisfied with the care they received during childbirth, regardless of whether they chose a caesarean (55%) or vaginal delivery (53%). Women report the lowest levels of satisfaction with postpartum care and the privacy that was preserved by healthcare personnel at health facility. Further the study also confirms the association between patient’s socio-economic characteristics and their satisfaction level.Originality/valueThis is the first study of its kind to highlight the situation of public healthcare system in Bihar, which is the third most populated state in India with poor social and health indicators.

Investigation of the effect of thermal aging and wear test parameters on the wear behavior of glass fiber (GF) reinforced epoxy composites

AbstractThis study focused on the wear behavior of unidirectional, thick GF epoxy composites produced using the autoclave method. The thermal aging process was applied for 250 and 500 cycles to understand the wear behavior of the material as it ages over time. To evaluate the wear behavior of the samples, wear tests were carried out under three different loads (10, 20, and 30 N) and three different sliding distances (150, 300, and 450 m). Taguchi‐based regression analysis was used to analyze the experimental results. The results obtained were evaluated using ANOVA tables and main and contour graphs. When the test results are examined, it is surprisingly observed that the wear resistance of the composite material increases positively with the aging effect. With thermally aging while the coefficient of friction value of composite samples increases from approximately 0.12 to 0.3, the wear volume decreases from approximately 4 to 1.3 mm3. Taguchi based regression analysis showed that the relationship between wear and thermal cycle sliding distance and load can be established by reducing the number of experiments in wear studies.Highlights Thermal aging effect on wear properties of thick GFRP was determined. Minimum wear volume and COF values were determined by applying ANOVA. It was determined that a load increment has the most impact on wear volume. Worn surface images supported the reduction in the wear rates of the thick GFRP. Empirical regression models developed for the mathematical prediction.

ВПЛИВ ПІІ НА ЗАЙНЯТІСТЬ В УМОВАХ ЦИФРОВІЗАЦІЇ ЕКОНОМІКИ: ПРИКЛАД КИТАЮ

The paper investigates how the evolution of the digitalization of economies alters the influence of foreign direct investment (FDI) on employment, using China as a case study. The study focuses on China, the largest developing economy, which has a significant influence on other economies, including Ukraine. With technological shifts demanding more skilled labor, particularly within the rapid growth of the digital economy, new pathways emerge regarding how foreign investment affects the host country's job market. The development of the digital economy can reduce the costs of information retrieval, production, transactions and delivery, etc. Beyond altering organizational practices, digital technologies also impact broader social dynamics. Understanding and leveraging digital transformation require consideration of both dimensions. To examine these aspects, a set of indices was employed, estimating digital economy development through entropy estimation and the coefficient of variation. These measurements formed the basis for a digital economy development index, utilizing indicators from four digitalization sectors: digital infrastructure, industry, innovation, and tool utilization. An empirical regression model integrated multiple indicators, such as employment rate, GDP, FDI, digitization coefficient, human capital, export rates, wages, and the proxy of interaction between FDI and the economy's digitization coefficient. Different sectors and regions within China were separately studied. Analyzing panel data across 30 Chinese provinces from 2001 to 2021 revealed that increased digitalization amplifies the positive impact of FDI inflows on domestic employment. Notably, this effect is more prominent in the service sector than in manufacturing, and it's relatively stronger in the less developed western provinces compared to the eastern and central ones. As the digital economy in the western regions is less mature, investments there yield relatively higher returns. These findings support the notion that employment grows alongside rising FDI inflows. However, it's crucial to highlight that digitalization increasingly shapes the intensity of FDI's influence on employment.

Improved methods for determining the leaf surface index using unmanned aerial vehicles to determine the productivity of phytocenoses

In landscape and biogeographic studies, the assessment of the photosynthesis process, which affects the possibility of determining the productivity of phytocenoses, calculating the growth of phytomass, is of particular relevance. The use of unmanned aerial vehicles (UAVs) to evaluate the leaf surface index (LAI) is gaining more and more scope over time due to their low price, high operational efficiency and accuracy. The basis for determining LAI is a model for the slit fraction, theoretically estimated using the Bera-Booger-Lambert law. The possibility of determining the LAI of vegetation using a UAV, on board of which either a lidar or a multispectrometer can be installed, is analyzed. In the first problem, LAI is determined by calculating the logarithm of the slit function (fraction) multiplied by the cosine of the scanning angle and divided by the attenuation coefficient. The second problem uses the existing correlations between known vegetation indices and LAI. Empirical statistical regression models may be suitable for determining LAI after determining various vegetation indices. Based on the results of multispectral measurements, it was found that the LAI determination technique based on measuring the intensity of rays that passed through the crown of plants leads to highly noisy estimates. For this reason, it was decided to use the slit fraction (GF), while using the experimentally established fact that when multiplying the logarithm of the vegetation index by the height of the crown, this correlation is significantly enhanced. To increase the reliability of the obtained LAI values, it is proposed to use the average integral value of this indicator, calculated by composing and calculating an optimization variational problem containing an additional restrictive condition. At the same time, it is possible to solve both problems to the maximum, i.e. it becomes possible to increase the signal-to-noise ratio of the calculated value of the LAI index. In both optimization calculation procedures, there are generalized indicators that have different physical meanings.

Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms

Fiber-reinforced polymers (FRP) are widely utilized to improve the efficiency and durability of concrete structures, either through external bonding or internal reinforcement. However, the response of FRP-strengthened reinforced concrete (RC) members, both in field applications and experimental settings, often deviates from the estimation based on existing code provisions. This discrepancy can be attributed to the limitations of code provisions in fully capturing the nature of FRP-strengthened RC members. Accordingly, machine learning methods, including gene expression programming (GEP) and multi-expression programming (MEP), were utilized in this study to predict the flexural capacity of the FRP-strengthened RC beam. To develop data-driven estimation models, an extensive collection of experimental data on FRP-strengthened RC beams was compiled from the experimental studies. For the assessment of the accuracy of developed models, various statistical indicators were utilized. The machine learning (ML) based models were compared with empirical and conventional linear regression models to substantiate their superiority, providing evidence of enhanced performance. The GEP model demonstrated outstanding predictive performance with a correlation coefficient (R) of 0.98 for both the training and validation phases, accompanied by minimal mean absolute errors (MAE) of 4.08 and 5.39, respectively. In contrast, the MEP model achieved a slightly lower accuracy, with an R of 0.96 in both the training and validation phases. Moreover, the ML-based models exhibited notably superior performances compared to the empirical models. Hence, the ML-based models presented in this study demonstrated promising prospects for practical implementation in engineering applications. Moreover, the SHapley Additive exPlanation (SHAP) method was used to interpret the feature's importance and influence on the flexural capacity. It was observed that beam width, section effective depth, and the tensile longitudinal bars reinforcement ratio significantly contribute to the prediction of the flexural capacity of the FRP-strengthened reinforced concrete beam.

Does artificial intelligence kill employment growth: the missing link of corporate AI posture.

An intense debate has been on-going about how artificial intelligence (AI) technology investments have an impact on employment. The debate has often focused on the potential of AI for human task automation, omitting the strategic incentive for firms to cooperate with their workers as to exploit AI technologies for the most relevant benefit of new product and service innovation. We calibrate an empirical probit regression model of how changes in employment relate to AI diffusion, based on formalizing a game-theoretical model of a firm exploiting the twin role of AI innovation and AI automation for both absolute and competitive advantage. The theoretical game-theory prediction is that employment following AI technology adoption is not negative, and ultimately depends on how AI leads to new success in innovation, competition which defines the competitive reward of innovation and profit sharing between workers and firms. Our estimation, is based on a global survey of 3,000 large companies across 10 countries, demonstrates that a firm employment growth depends on two strategic postures, that is, the firm relative maturity of AI adoption as well as its relative bias toward AI-based product innovation. The contribution of this research is to highlight the twin role of firm and workers in shaping how technology will affect employment. AI in particular marries the potential of task automation with even more potential for expansion.

The Effect of Digital Currency on Monetary Policy in Tanzania: An Empirical Investigation

This study investigates the effects of digital currency on monetary policy in Tanzania., The main variables of the study included BTC and MBT as the independent variables and M3 as a dependent variable. The quantitative methodology used involved the applications of econometrics analysis as the estimation methods. The quarterly time series data (2014q1 – 2021q4) used were obtained from both the Bank of Tanzania, the Tanzania National Bureau of Statistics and the online data from www.blockchain.com. The main variables of the study included BTC and MBT as the independent variables and M3 as a dependent variable. The Vector Error Correction Model (VECM) was used to estimate the empirical regression model, while STATA software 14 was used to analyse the data. The results indicate of the VECM indicated that there was a significant negative relationship between BTC and M3 variables on the one the one hand, and a significant positive relationship between MBT and M3 variables in Tanzania. The study concluded that there was a significant effect of the digital currency on monetary policy in the country. The study recommended that the government should education the people on how the digital currency operates, it should strengthen monetary policy practices, and try to learn from others countries that use the digital currency. This would help the country to officially allow or reject the use of digital currency in the country.

Hybridization of Machine Learning Algorithms and an Empirical Regression Model for Predicting Debris-Flow-Endangered Areas

Accurate delineation of debris-flow-endangered areas (e.g., the maximum runout distance) is a necessary prerequisite for the debris-flow risk assessment and countermeasures design. Recently, machine-learning models have been proved to be an effective tool in predicting debris-flow parameters. However, existing machine-learning models are generally developed based on a very limited number of observation data, which may result in the predictive model overfitting or underfitting. How to develop a robust model for accurate forecasting of debris-flow-endangered areas still remains a difficult task. This paper proposes a hybrid method for predicting debris-flow hazard zone by integrating machine-learning algorithms and an empirical regression model. The proposed method takes the calculated maximum runout distance obtained from the empirical model as supplementary inputs to increase the amount of training data to construct hybrid machine-learning models. Three commonly used machine-learning models (i.e., multivariate adaptive regression splines (MARS), random forest (RF), and support vector machine (SVM)) are developed based on the training datasets of a specific debris basin. Then, these three machine-learning models are combined with an empirical relationship developed using the same training datasets to generate corresponding hybrid models. Finally, the performance metrics (i.e., coefficient of determination (R2), root-mean-square error (RMSE), and mean absolute error (MAE)) of the proposed hybrid models are comprehensively investigated and compared with the single predictive model (i.e., MARS, RF, SVM, and the empirical model) under fivefold cross-validation. The proposed method is illustrated using 134 channelized debris-flow events in Sichuan province, China. Results show that compared with the three individual machine-learning models, hybridization of machine-learning algorithms and the empirical model results in R2, RMSE, and MAE improved by 70.5%, 32.9%, and 41.1%, respectively. In contrast to the empirical model, the R2, RMSE, and MAE value of the proposed hybrid models are improved by 29.6%, 22.3%, and 32.5%, respectively. The proposed hybrid models generally perform better than the single machine-learning and the empirical model, providing a promising tool for accurate forecasting of a debris-flow-endangered area.

Genotype–environment interaction and yield stability analysis of Colombian yellow diploid potato cultivars using mixed linear models and environmental covariates

AbstractSeveral statistical methods have been developed to decompose the phenotypic response based mainly on the general means, the effect of the genotype, and its interaction with the environment, treating the environmental variance as a confounding factor. However, the estimation of the environmental effect from the traits evaluated would establish a dependency on the genotype, resulting in a lower fit and predictive potential of the model. The integration of environmental covariates into the models that associate edaphoclimatic characteristics with the traits of interest has been proposed, with the purpose of increasing the predictive potential and the variance contained by the models. The aim of this study was to evaluate the sensitivity of the traits of interest in yellow diploid potato (Solanum tuberosum L. Group: Phureja) crops to environmental covariates, selecting the most relevant covariates as parameters in empirical multiple regression models based on environmental variance. The results showed high yield variability due to covariates of the water component, while the quality traits were mainly affected by traits of the energetic and physicochemical components of the soil. The adjusted models explained the variance intrinsically due to the environment, reaching adjustments greater than 20%. Therefore, it is concluded that the traits have a high phenotypic sensitivity, and the incorporation of environmental covariates into the genotype‐by‐environment interaction analysis models could improve the understanding of the stability and adaptability of cultivars from the data obtained in multi‐environment trials.

ФАКТОР ЭТНОКУЛЬТУРНОГО РАЗНООБРАЗИЯ В РЕГИОНАЛЬНОМ РАЗВИТИИ США

The regional development of one of the largest federations in the world — the United States of America, which is distinguished by the extreme diversity of the population and human potential of various territories and the uneven development of the economy — is historically influenced by the factor of ethnocultural diversity. In recent decades, American federalism has been characterized by a qualitatively “new” trend associated with the regionalization of social and economic relations in the context of regional systems. Based on a theoretical and methodological review of existing studies on the relationship between economic development, ethno-demographic heterogeneity and cultural evolution in the United States, using the necessary econometric methodological support, both theoretical and a number of empirical regression models were constructed. The specifi cation and analysis of the modeling results made it possible to put forward and reasonably confirm hypotheses that refl ect the differentiation of the factor of ethnocultural diversity in the regional development of the United States depending on the mutual influence of concomitant factors, the increasing role of the cultural component and the need to determine the optimal level of ethnocultural diversity for the regions of the country that have retained or are gradually changing their socio-economic genotype. It has been established that the program regulation of regional development in order to equalize the incomes of the population of various ethnic groups, carried out within the framework of the state regional policy of the United States, is largely selective in nature and is generally successful in the retrospective period.