The increase in population has increased the need for agricultural and food products, and thus agricultural production should be increased. This goal may cause increases in emissions and environmental impacts by increasing the consumption of agricultural inputs. The prediction of environmental impacts plays an important role in evaluating pollutant emissions in crop production. This study employed two artificial intelligence (AI) methods: the adaptive neuro-fuzzy inference system–fuzzy c-means (ANFIS–FCM) algorithm as a novel computational method, and an artificial neural network (ANN) as a conventional computational method to predict the environmental impacts of soybean production in different scenarios (i.e., soybean cultivation after rapeseed (R-S), wheat (W-S), and fallow (F-S)). The life cycle of soybean production was assessed in terms of environmental impacts through the IMPACT2002+ method in SimaPro. In the present study, the production of one ton of soybeans was considered the functional unit, and the boundary of the system was considered the gate of the field. According to the results, the production of each ton of soybean in the defined scenarios resulted in 0.0009 to 0.0016 DALY, 5476.18 to 8799.80 MJ primary, 1033.68 to 1840.70 PDF × m² × yr, and 563.55 to 880.61 kg CO₂-eq damage to human health, resources, ecosystem quality, and climate change, respectively. Moreover, the weighted analysis indicated that various soybean production scenarios led to 293.87–503.73 mPt damage to the environment, in which the R-S scenario had the best environmental performance. According to the results, the ANFIS–FCM algorithm acted as the best prediction model of environmental indicators for soybean cultivation in all cases related to the ANN. The range of calculated R² for the ANFIS-FCM and ANN models were between 0.9967 to 0.9989 and 0.9269 to 0.9870, respectively. It can be concluded that the proposed ANFIS–FCM model is an efficient technique for obtaining accurate environmental prediction parameters of soybean cultivation. Full article

This study evaluated the performance of a downflow hanging sponge (DHS) in reducing the concentrations of chemical oxygen demand (COD), ammonia (NH₃), total suspended solids (TSS), and total dissolved solids (TDS) in high-strength organic wastewater (HSOW). The DHS unit was composed of three segments connected vertically and operated under different organic loading rates (OLRs) between 3.01 and 12.33 kg COD/m³_sponge/d at a constant hydraulic retention time (HRT) of 3.6 h. The results demonstrated that the DHS system achieved COD, NH₃, TSS, and TDS removal efficiencies of 88.34 ± 6.53%, 64.38 ± 4.37%, 88.13 ± 5.42%, and 20.83 ± 1.78% at an OLR of 3.01 kg COD/m³_sponge/d, respectively. These removal efficiencies significantly (p < 0.05) dropped to 76.39 ± 6.58%, 36.59 ± 2.91%, 80.87 ± 5.71%, and 14.20 ± 1.07%, respectively, by increasing the OLR to 12.33 kg COD/m³_sponge/d. The variation in COD experimental data was well described by the first-order (R² = 0.927) and modified Stover–Kincannon models (R² = 0.999), providing an organics removal constant (K₁) = 27.39 1/d, a saturation value constant (K_B) = 83.81 g/L/d, and a maximum utilization rate constant (U_max) = 76.92 g/L/d. Adding another DHS reactor in a secondary phase improved the final effluent quality, complying with most environmental regulation criteria except those related to TDS concentrations. Treating HSOW with two sequential DHS reactors was economically feasible, with total energy consumption of 0.14 kWh/m³ and an operating cost of about 7.07 USD/m³. Accordingly, using dual DHS/DHS units to remove organics and nitrogen pollutants from HSOW would be a promising and cost-efficient strategy. However, a tertiary treatment phase could be required to reduce the TDS concentrations. Full article

This study investigates the effect of entrepreneurial orientation (EO; one of the most broadly acknowledged firm-level constructs) on the performance of small- and medium-sized enterprises (SMEs). Furthermore, we analyze the moderator effect of creating shared value (CSV) on firm performance. Our analysis was conducted using a structural equation model on a stratified sampling method of 294 manufacturing and service SMEs in Korea. The results show that an SME’s efforts in some variables in EO constructs are statistically positively related to both its financial (economic benefits) and non-financial performance (social benefits). Our study results also reveal that there is a significant positive moderator effect of CSV on the EO-performance relationship. This implies that CSV, when bundled with EO, can boost firm performance and provide SMEs with not only a competitive and sustainable advantage but also reduces their risk. This research contributes to the extant literature by investigating the interactive effect of CSV on the relationship between EO and firm performance in the context of SMEs, which has received scant attention in the extant literature. In the last section, the limitations and future research agenda of this study are presented. Full article

The coordinated development of the digital economy and green economy is a key issue that needs to be addressed. Based on the statistical data of 30 provincial-level regions in China from 2014 to 2019, this study empirically analyzed whether China’s digital economy and green economy can achieve coordinated development. In this study, a coupling coordination degree model was used to evaluate the degree of coordinated development of the digital economy and green economy in provincial regions of China. A fuzzy-set qualitative comparative analysis method was adopted to identify the realization path of the coordinated development of the digital economy and green economy. The results show the following: (1) the coordinated development degree of the digital economy and green economy in China shows an upward trend from primary coordination in 2014 to intermediate-level coordination in 2019, with great differences between different regions; (2) there are five paths to achieve coordinated development of the digital economy and green economy, which are divided into two categories (technology–environment dual-drive type, and technology–organization–environment linkage drive type); (3) technological innovation capability and government financial support can substitute for one another under certain conditions to achieve the coordinated development of the digital economy and green economy. These conclusions provide a theoretical basis for countries to formulate policies to promote the coordinated development of their digital economy and green economy. Full article

Based on China’s newly established Securities Investor Services Center (CSISC), a minority shareholder protection mechanism, we investigated how the CSISC shareholder influences the ESG performance of listed companies. Using a difference-in-differences analysis for a sample of Chinese listed companies during 2013–2017, we found that the pilot reform of CSISC shareholding has a positive influence on the ESG performance of listed companies. We also found that this effect exists in large companies and in companies in non-high-polluting industries. Besides, analysts’ attention, external auditing quality, institutional shareholding, and highly-developed market intermediary and legal systems can strengthen the effect of CSISC shareholding on corporate ESG performance. Our findings inspire regulators in emerging markets to establish suitable mechanisms to protect minority shareholder rights in the long run. Full article

Performance evaluation of green supply chains (GSC) is an important tool to improve their comprehensive management. Identifying critical indicators is crucial to evaluation. This study examines the critical indicators in performance evaluations of GPC and provides relevant suggestions for managers to improve GSCs’ performances. Firstly, we summarized 24 evaluation indicators from five dimensions—financial value, customer service-level, business processes, innovation and development, and the so-called green level. Secondly, the Delphi method was used to determine the formal research framework. The fuzzy decision-making trial and evaluation laboratory based analytic network process (fuzzy DEMATEL-based ANP) model was applied. The weighted prominence of each indicator was calculated to identify those that were critical, and a causality diagram was constructed for them. Finally, corresponding countermeasures and implications regarding those were put forward. The research results show that the critical indicators include the return rate of net assets, the growth rate of profit, the rate of service satisfaction, market share, production flexibility, and the green consensus. Among them, the green consensus, the growth rate of profit and the rate of service satisfaction form a virtuous circle, leading to the improvement of the overall performance of GSC. Full article

To meet the national green development trend and realize the sustainable development of human society, the carbon emission in cold-chain distribution is costed. We plan the vehicle distribution path reasonably and optimize the distribution path locally for immediate demand to balance the economic benefits of enterprises and customer satisfaction while reducing the environmental pollution. To minimize distribution cost and maximize customer satisfaction, we design an improved ant colony algorithm to solve the initial distribution path and use the insertion method to solve the immediate customer demand. Taking the actual data of enterprise M as an example, we obtain the optimal distribution path using MATLAB software and optimize the distribution path locally according to the immediate customer demand. The results show that the proposed model and the designed algorithm are practical in satisfying the sustainable development of cold-chain logistics in China. Full article

This study focused on pre-flood measures to estimate evacuation times impacted by flood depths and identify alternate routes to reduce loss of life and manage evacuation measures during flood disasters. Evacuation measures, including traffic characteristics, were reviewed according to different flood depths. Several scenarios were constructed for different flooding situations and traffic volumes. Evacuation times in the study area were evaluated and compared for all scenarios with reference to dry conditions. Results of network performance indicators compared to the dry situation showed that average speed dropped to 2 km/h, VHT rose above 200%, and VKT rose above 30%. Cumulative evacuee arrival percentage increased when flood levels were higher than 5 cm. Flood levels of 10–15, 15–20, 20–25, and 25–30 cm represented percentages of remaining evacuees at 9%, 19%, 49%, and 83%, respectively. Time taken to evacuate increased according to flood level. For flood depths of 5–30 cm, travel time increased by 40, 90, 260, and 670 min, respectively, suggesting the need for early evacuation before the flood situation becomes serious. Full article

Machine learning (ML) models, including artificial neural networks (ANN), generalized neural regression networks (GRNN), and adaptive neuro-fuzzy interface systems (ANFIS), have received considerable attention for their ability to provide accurate predictions in various problem domains. However, these models may produce inconsistent results when solving linear problems. To overcome this limitation, this paper proposes hybridizations of ML and autoregressive integrated moving average (ARIMA) models to provide a more accurate and general forecasting model for evapotranspiration (ET₀). The proposed models are developed and tested using daily ET₀ data collected over 11 years (2010–2020) in the Samsun province of Türkiye. The results show that the ARIMA–GRNN model reduces the root mean square error by 48.38%, the ARIMA–ANFIS model by 8.56%, and the ARIMA–ANN model by 6.74% compared to the traditional ARIMA model. Consequently, the integration of ML with ARIMA models can offer more accurate and dependable prediction of daily ET₀, which can be beneficial for many branches such as agriculture and water management that require dependable ET₀ estimations. Full article

Taking Erdaojiang and Dongchang District of Tonghua City, Jilin Province as examples, this paper studies the ecological environment restoration and governance model of their mining areas. In this paper, the vegetation cover (NDVI) data in the past ten years were selected from the study area. The Theil–Sen median and Mann–Kendall (MK) methods were used to analyze the time series of NDVI, and the vegetation cover change trend map of the study area was obtained. Then, the land use data of the study area for 4 years were selected, and the transfer matrix method was used to analyze the land use conversion between the years. Finally, according to the characteristics of the distribution of mines in the study area, for the mining area in different natural geographical locations, it was concluded that the restoration of cultivated land and the restoration of forest land and ecological reconstruction were adopted. Among them, the restoration of forest land includes natural restoration and artificial intervention. Full article

As China’s economy moves towards a stage of high-quality development and shifts its economic development goals from GDP growth to green and sustainable growth, technological support is essential for achieving green and sustainable economic growth. Therefore, the supply of talent, as the source of innovation, is crucial. Against the backdrop of relying on innovation to drive high quality economic development, achieving the effective allocation of talent within a spatial range to maximize the release of human capital dividends and promoting the benign interaction between talent regional allocation and technological innovation is an urgent issue that needs to be addressed to achieve environmentally sustainable economic development. Based on this, this paper studies the effect of regional talent allocation on high-quality economic development, reveals the impact mechanism of regional talent allocation on high-quality economic development, and uses the panel data of 258 cities in China from 2004 to 2019 to empirically test the impact of regional talent allocation on high-quality economic development, with a view to improving regional talent allocation, releasing talent potential, and promoting the improvement of regional environmental quality and the convergence of new ideas for high-quality economic development. This research indicates the following: (1) The improvement of the talent regional allocation level can effectively promote high-quality economic development, and mechanism verification shows that talent regional allocation promotes high-quality economic development by influencing regional innovation;. (2) The heterogeneity test found that the impact of regional talent allocation on high-quality economic development indicated a law of an increasing marginal effect from east to west, while innovation drive and the interaction between regional talent allocation and innovation drive showed the strongest characteristics in the central region, followed by the west, with the weakest being in the east. In addition, both the regional allocation of talent and the innovation-driven impact on the high-quality development of the economy have a higher marginal effect in non-urban agglomeration cities than in urban agglomeration cities. (3) There is a dual threshold effect of innovation-driven regional talent allocation on the development of a high-quality economy. When the innovation drive is between 0.4898 and 10.2214, the spillover effect of innovation-driven talent flow is less than the negative impact of talent flow, which is not conducive to the development of a high-quality economic development effect of regional talent allocation. Studying the impact of regional talent allocation on high-quality economic development not only helps to supplement and improve the theory of human capital mobility, providing new explanations for high-quality economic development in the new era, but also contributes to enriching the content of modern macroeconomic theory. Full article

Computers have enabled diverse and precise data processing and analysis for decades. Researchers of humanities and social sciences are increasingly adopting computational tools such as artificial intelligence (AI) and machine learning (ML) to analyse human behaviour in society by identifying patterns within data. In this regard, this paper presents the modelling of teachers and students’ perceptions regarding gender bias in text books through AI. The data was collected from 470 respondents through a questionnaire using five different themes. The data was analysed with support vector machines (SVM), decision trees (DT), random forest (RF) and artificial neural networks (ANN). The experimental results show that the prediction of perceptions regarding gender varies according to the theme and leads to the different performances of the AI techniques. However, it is observed that when data from all the themes are combined, the best results are obtained. The experimental results show that ANN, on average, demonstrates the best performance by achieving an accuracy of 87.2%, followed by RF and SVM, which demonstrate an accuracy of 84% and 80%, respectively. This paper is significant in modelling human behaviour in society through AI, which is a significant contribution to the field. Full article

The symbiotic photovoltaic (PV) electrofarming system introduced in this study is developed for the PV setup in an agriculture farming land. The study discusses the effect of different PV system design conditions influenced by annual sunhours on agricultural farm land. The aim is to increase the sunhours on the PV panel for optimized electricity generation. Therefore, this study combines the Taguchi method with Grey Relational Analysis (GRA) to optimize the two quality characteristics of the symbiotic electrofarming PV system with the best design parameter combination. The selected multiple quality characteristics are PV power generation and sunhours on farm land. The control factors include location, upright column height, module tilt angle, and PV panel width. First, the Taguchi method is used to populate a L9(3⁴) orthogonal array with the settings of the experimental plan. After the experimental results are obtained, signal-to-noise ratios are calculated, factor response tables and response graphs are drawn up, and analysis of variance is performed to obtain those significant factors which have great impact on the quality characteristics. The experiments show that the parameters which effects power generation are: location, upright column height, module tilt angle, and PV panel width. The ranking of the degree of influence of the control factors on the quality characteristics is location > PV panel width > module tilt angle > upright column height. By controlling these factors, the quality characteristics of the system can be effectively estimated. The results for PV power generation and sunhours on farm land both fall within the 95% CI (confidence interval), which shows that they are reliable and reproducible. The optimal design parameter realized in this research obtains a power generation of 26,497 kWh and a sunshine time of 1963 h. The finding showed that it can help to build a sustainable PV system combined with agriculture cultivation. Full article

Food coloring has become one of the main sources of water pollution. Brilliant blue (BB) is one of the dyes used in the food industry. Heterogeneous photocatalysis is increasingly used to decontaminate polluted water from food industries. The objective of this paper was to treat this pollution using a photoreactor at the laboratory (batch) and pilot scales. The photodegradation of the brilliant blue dye, chosen as a model of pollutant, was performed at room temperature in an aqueous solution of titanium dioxide supported on cellulosic paper in the presence of an external UV lamp. The surface morphology of this photoactive tissue was characterized by SEM and FTIR. The performances of two geometric configurations were examined (batch reactor and annular recirculation reactor) in accordance with degradation and pollutant mineralization. The performance of the photocatalytic system was optimized by a parametric study to improve the impact of the different parameters on the efficiency of the degradation process, namely the initial concentration of the pollutant, the TiO₂ cycle, the pH of the solution with the recirculating reactor, and the flow rate. The results showed 98% degradation of brilliant blue at the laboratory scale and 93.3% and 75% at the pilot flow rates of 800 and 200 L·h⁻¹, respectively. The supported semiconductor showed good photodegradation ability during BB decomposition, showing that photocatalysis is a promising technique for water purification. Full article

In this paper, the electrical parameters of a hybrid power system made of hybrid renewable energy sources (HRES) generation are primarily discussed. The main components of HRES with energy storage (ES) systems are the resources coordinated with multiple photovoltaic (PV) cell units, a biogas generator, and multiple ES systems, including superconducting magnetic energy storage (SMES) and pumped hydro energy storage (PHES). The performance characteristics of the HRES are determined by the constant power generation from various sources, as well as the shifting load perturbations. Constant power generation from a variety of sources, as well as shifting load perturbations, dictate the HRES’s performance characteristics. As a result of the fluctuating load demand, there will be steady generation but also fluctuating frequency and power. A suitable control strategy is therefore needed to overcome the frequency and power deviations under the aforementioned load demand and generation conditions. An integration in the environment of fractional order (FO) calculus for proportion-al-integral-derivative (PID) controllers and fuzzy controllers, referred to as FO-Fuzzy-PID controllers, tuned with the opposition-based whale optimization algorithm (OWOA), and compared with QOHSA, TBLOA, and PSO has been proposed to control the frequency deviation and power deviations in each power generation unites. The results of the frequency deviation obtained by using FO-fuzzy-PID controllers with OWOA tuned are 1.05%, 2.01%, and 2.73% lower than when QOHSA, TBLOA, and PSO have been used to tune, respectively. Through this analysis, the algorithm’s efficiency is determined. Sensitivity studies are also carried out to demonstrate the robustness of the technique under consideration in relation to changes in the sizes of the HRES and ES system parameters. Full article