Green banking and its sustainability are equally important in responsible banking, and are recognized as key drivers of operational success. It is considered extremely important that financial institutions develop a sustainable working space that can contribute to their operational performance (OP). In this context, we explored the complex relationship between Green Banking Policies (GBPs) and the OP of the banks in Pakistan, shedding light on the mediating roles played by Green Culture (GC) and Environmental Performance (EP). Employing Structural Equation Modeling (SEM) in AMOS SPSS 2022 and Binary Logistic Regression (BLR), we highlight the connected impact of green banking strategies, the integration of GC, and EP on operational outcomes. We conclude that the GBPs can indirectly impact the OP of the banks through only a mediating role of the GC and EP, thus providing insights into the causal relationships within this multifaceted framework. Its practical inferences resonate with financial institutions and policymakers, advocating for a comprehensive approach to green banking. In the ear of environmental consciousness being paramount, this research offers a timely and invaluable contribution to the ongoing dialogue on the role of green banking and sustainable finance. The research also extends its novelty in terms of addressing the debate on sustainable banking practices, especially in the case of developing countries, along with a quantitative methodological implication, thus enabling more capable and innovative research in the context.
Accurate forecasting of daily potential evapotranspiration (ETo) is vital for efficient irrigation scheduling, sustainable water resource management, and optimal crop yield, especially in arid regions. In this study, we present a novel, large-scale comparison of three advanced machine learning models, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Gene Expression Programming (GEP), for ETo prediction at the Ahvaz synoptic station in Iran. The work is distinctive in using one of the longest ETo datasets available (1979–2023; 16,084 records), incorporating a sensitivity analysis for input selection, and applying the Developed Discrepancy Ratio (DDR) as an advanced performance metric. The ANN model (MLP 4-9-1 architecture) demonstrated the highest prediction accuracy, achieving an R² of 0.9806, RMSE of 0.4122, and DDRmax of 3.27 in the training phase, and an R² of 0.9779, RMSE of 0.4327, and DDRmax of 3.22 during validation. In comparison, SVM and GEP models showed lower accuracy across all phases. These results highlight the superior capability of the ANN model for ETo forecasting and its potential as a reliable tool for irrigation planning and water resource management in arid regions like Ahvaz.
In this study, we developed and validated an integrated Radio Frequency Identification- Artificial Intelligence (RFID-AI) framework to optimize medical waste management in resource- constrained healthcare settings. The system combines: (1) UHF RFID-enabled smart bins with real- time mass and environmental monitoring, (2) a fine-tuned ResNet-50 computer vision model achieving 93.1% (±2.1%) waste classification accuracy, and (3) genetic algorithm-based route optimization reducing collection distances by 18%. Implemented across four Jordanian hospitals (92-203 beds) for six months, the system demonstrated significant improvements across key metrics: Operational efficiency (30.1% reduction in collection time, P<0.01; 81% fewer hazardous mixing incidents), staff safety (40.2% reduction in sharps injuries through AI monitoring), environmental impact (15.2% lower particulate emissions via optimized incineration scheduling), and cost-effectiveness (23.2% operational cost reduction with 14-month ROI). The framework's modular design successfully addressed institution-specific challenges, including 78.3% storage overcapacity at Princess Basma Hospital and 39.1% improper sharps disposal at Ibn Al-Nafis Hospital, while maintaining 90.3% compliance with WHO 2022 guidelines. Technical innovations included moisture-resistant RFID tags, maintaining 98.3% read accuracy in high-humidity environments and Arabic-language AI interfaces that reduced training time by 42%. These results provide empirical evidence for the viability of smart waste systems in LMICs, offering a replicable model that balances technological sophistication with practical implementation constraints. We established a new benchmark for intelligent medical waste management systems under resource limitations.
Produced water (PW) is water that is extracted alongside crude oil or gas during the drilling process, necessitating proper treatment prior to environmental discharge. In this paper, we examined the application of ceramic adsorbents, derived from residue catalytic cracking (RCC) spent catalysts and natural clay, for the reduction of total dissolved solids (TDS) in PW. The preparation of ceramic adsorbents entailed the combination of spent catalyst RCC with natural clay in various proportions. The influence of adsorbent composition, diameter, flow rate, and operating time on TDS removal was investigated. Response surface methodology (RSM) was employed to optimize the removal of TDS. The findings demonstrated that a ceramic adsorbent composed of 50% RCC spent catalyst, with a diameter of 20 mm, was most effective in removing 58.39% TDS at a flow rate of PW 8 L/min. The integration of ceramic adsorbent with reverse osmosis (RO) significantly decreases the TDS of PW by 90.73%. Ceramic adsorbents are a pretreatment method for RO to decrease TDS in PW. The findings present practical implications, offering oil and gas companies an alternative method for treating PW using RCC spent catalysts and RO membrane.
In this study, we focused on the rapid land use and land cover (LULC) changes in Bankura in 1990, 2000, 2010, and 2024, employing an integrated remote sensing, geospatial, and statistical approach to track land use changes. The supervised classification technique and change detection analysis were applied with the Supper Vector Machine (SVM), Maximum Likelihood (ML), and Random Forest (RF) methods to identify land use classes in various categories like Dense Forest, Open Forest, water body, agricultural land, settlement, barren land, and sand. The Kappa Coefficient was used for the accuracy assessment, which revealed that the overall accuracy of 1990 was 93.33%, 2000 was 93.23%, 2010 was 93.43%, and 2024 was 90%. The analysis revealed a significant increase in built-up land from agricultural and forested areas, with a higher percentage of agricultural land converted to built-up areas observed between 1990 and 2024. During this interval, the built-up land area increased by approximately 13.6%, primarily due to the conversion of agricultural land and forest cover. Agricultural land decreased by 11.45%, while dense forest cover declined by 7.75%, indicating a significant anthropogenic influence on landscape transformation. Our findings underscore the importance of sustainable land use planning, conservation efforts, and policy interventions in mitigating environmental degradation, leveraging the effectiveness of space-based inputs and geospatial techniques. The research emphasizes the need for continuous monitoring and further investigation into socio-economic drivers and environmental consequences to ensure resilient urban management and sustainable development. This reveals the importance of reforestation, preserving water bodies, and developing ecologically sensitive infrastructure. Moreover, the study highlights the importance of sustainable land use planning in mitigating adverse environmental impacts and preserving ecological balance.
[Purpose] Our purpose of this study is to construct a “psychological-behavioral- environmental” analytical framework to explore the influencing mechanism of farmers’ participation in waste classification. [Methods] An empirical analysis was conducted through questionnaires and structural equation modeling to reveal the significant effects of behavioral attitudes, Subjective norm, and perceived values on farmers’ willingness to participate. [Findings] The results showed that (1) attitude toward behavior, Subjective norm, perceived behavioral control, perceived value, perceived risk, and past experiences have a significant positive influence on farmers’ willingness to participate in source separation and reduction of rural household waste. The path coefficient of perceived value was 0.78, which is an important factor influencing willingness to participate. (2) Attitude toward behavior plays a significant mediating role in the relationship between perceived value, perceived risk, past experience, and willingness to participate. (3) Environmental regulation has a negative moderating effect on the relationship between behavioral attitudes and willingness to participate, indicating that there is a formalization problem in the current policy environment and that over-reliance on administrative intervention may not be conducive to the formation of endogenous motivation of farmers. (4) The willingness to participate was stronger among farmers with higher education and higher household income levels, while the older group showed lower motivation to participate due to lack of classification knowledge and stereotyped habits. [Originality/value] Effective enhancement of farmers’ participation in garbage classification requires the integration of cognitive reinforcement, behavioral motivation, conscious awareness cultivation, and institutional innovation.
In the context of China's long-standing extensive economic growth model and increasing environmental pressures, improving total factor energy efficiency (TFEE) has become crucial for environmental protection and sustainable development. Financial technology (FinTech), as an emerging technology-driven financial innovation model, offers potential solutions; however, empirical evidence on its environmental impact remains limited. Based on balanced panel data of 268 Chinese cities from 2011 to 2021, we employed a double machine learning approach and the SHAP value algorithm to assess the impact of FinTech on TFEE as well as its nonlinear effects, with Random Forest being the primary estimation model. The major findings were as follows: (1) FinTech has a significant promoting effect on improving TFEE, which has passed multiple robustness tests. (2) In terms of mediation mechanisms, FinTech exerts its positive influence on TFEE by promoting green finance development, facilitating industrial structure optimization, and driving green technological innovation. (3) Heterogeneity analysis indicates that the role of FinTech in enhancing TFEE is more pronounced in eastern China, non-old industrial bases, and large cities. (4) According to the distribution trend of SHAP value, the impact of FinTech on TFEE exhibits a nonlinear effect, and its positive driving force can be effectively exerted only after its development level exceeds a specific threshold around 4.2. This study provides empirical evidence on the role of FinTech in advancing TFEE, offering valuable insights for policymakers seeking to harness FinTech as an effective tool to advance energy efficiency and support sustainable economic transformation.
Machine learning models for water quality prediction often encounter challenges due to incomplete datasets resulting from issues such as sensor failures or data transmission errors. However, XGBoost can learn from incomplete data and make predictions even when some input values are missing, without requiring any manual intervention by the user. This offers a considerable advantage over other models that require complete datasets. To test this capability, we utilized XGBoost to forecast salinity levels in the Chao Phraya River, Thailand, based on investigating forecasts at lead times of 24 and 48 hours, using four predictors: the water levels from three stations and the salinity level. The tested model demonstrated high predictive performance across both complete and incomplete subsets of the data. Where the complete input dataset was available, our XGBoost model outperformed the single-level ANN model and was comparable to the multilevel ANN model. Additionally, we enhanced XGBoost’s ability to forecast under incomplete data conditions by utilizing both real and synthetic datasets. The synthetic dataset was generated by removing 1–3 predictor variables from the complete dataset. Based on the results, incorporating synthetic data into the training dataset substantially enhanced the model's robustness against missing data. Notably, training with synthetic data that excluded one variable at a time was sufficient for accurate predictions. These results underscore XGBoost’s practicality and reliability for real-world water quality forecasting, particularly under conditions of data scarcity.