International Journal of Global Warming (30 papers in press)

Regular Issues

• Collaborative System of Low-Carbon Sustainable Energy and Grassroots Governance Based on Big Data Analysis  
  by Binghui Lei, Peng Xu 
  Abstract: Low-carbon energy operation at the grassroots level suffers from disconnected energy-governance data, feedback lag, and no computable coupling mechanism. This study constructs a collaborative system based on big data, forming a heterogeneous temporal graph through unified mapping and time alignment, and introducing attention-driven dynamic graph representation learning to model energy and governance behaviour evolution. Low-carbon constraints and policy gradient updates drive energy scheduling and governance incentives within a shared closed loop. Experiments show carbon emission intensity stabilises at 0.39 kgCO2kWh, supply-demand deviation at 2.39%, and governance response delay at 1.8 time windows, with a collaborative stability index converging to 0.87.
  Keywords: Big Data Analysis; Low-Carbon Sustainable Energy; Grassroots Governance; Dynamic Graph Representation Learning; Collaborative Optimization.
  DOI: 10.1504/IJGW.2026.10078595
   
  
• Energy-daylight interaction perspective: effects of natural shading, photosensor and orientation  
  by Yasin Kaya, Kadir Zengin, Sebahattin Ünalan 
  Abstract: Buildings account for a substantial share of global energy consumption and related carbon emissions, making the building sector a key component of global warming mitigation strategies. Therefore, while improving energy efficiency remains highly important, this study additionally investigates daylight comfort criteria, which also play a critical role in sustainable building design.In this study, the combined effects of natural shading, daylight-responsive photosensors, and building orientation on energy consumption and daylighting performance were comprehensively analyzed using a reference building model. These parameters were examined under different scenarios through comparative energy assessments that explicitly considered heat transfer processes.The main findings indicate that integrating photosensors with optimized building orientation significantly improves daylight comfort. Consequently, total energy consumption was reduced by up to 6.3% (4.11 MWh/year), accompanied by a 7.6% reduction in CO? emissions (2,175 kgCO?/year).
  Keywords: building; energy-daylight interaction; natural shading; photosensor; orientation.
  DOI: 10.1504/IJGW.2026.10078658
   
  
• Machine Learning Simulation Analysis of the Impact of Extreme Environmental Events Driven by Global Warming on Economic Dynamics  
  by Zhimin Wu, Ye Tian 
  Abstract: This paper proposes an XGBoost-SHAP framework to model nonlinear climate-economy linkages under extreme events. Using multi-source panel data, it constructs a hierarchical intensity index for complex extremes. Bayesian-optimised XGBoost minimises cross-validated MSE to capture climate shocks nonlinear economic impacts. TreeSHAP yields global feature rankings and local attributions, revealing key drivers: high temperature (SHAP = 0.42), precipitation frequency (0.38), and long-term drought (0.35). In agriculture-heavy economies (> 40% share), extreme heat suppresses annual growth by 0.57 on average. The model achieves RMSE 1.52.1 and MAPE 4.8%8.2%, offering high accuracy and interpretability for differentiated climate adaptation policy.
  Keywords: Climate Warming; Extreme Environmental Events; Extreme Gradient Boosting; SHapley Additive exPlanations; Nonlinear Modeling.
  DOI: 10.1504/IJGW.2026.10078664
   
  
• Analysis of Digital Marketing Strategies in Enterprise Supply Chain under the Background of Low Carbon Economy  
  by Xiaoyu Yan 
  Abstract: To study the digital marketing strategies of enterprises under the background of low-carbon economy, this paper proposes a fuzzy neural network to evaluate the digital marketing of enterprises. Evaluation is the foundation for ensuring the effective operation of enterprise work methods. Scientific, effective, and fair evaluation can stimulate the enthusiasm of enterprises. On the other hand, it can also improve the digital marketing performance of enterprises. The experimental results showed that 68 people believed shopping was very convenient under traditional marketing, while 160 people believed shopping was very convenient under digital marketing. Only 55 people believed that the service quality of traditional marketing was high, but 189 people believed that the service quality of digital marketing was high. It can be seen that under digital marketing, not only is shopping convenient, but people are also very satisfied with the service quality of digital marketing.
  Keywords: Low-carbon Economy; Fuzzy Neural Network; Enterprise Digital Marketing; Enterprise Supply Chain; Enterprise Evaluation.
  DOI: 10.1504/IJGW.2026.10078809
   
  
• Assessment of Decadal Rainfall Prediction Skill Across Southeast Asia Using CMIP6 Models  
  by Dara Kasihairani, Supari Supari, Rahmat Hidayat 
  Abstract: This study evaluates decadal climate prediction (DCP) skill over Southeast Asia using CMIP6 hindcasts initialised during 19602010. Rainfall prediction skill is assessed for winter (DJF) and summer (JJA) using the anomaly correlation coefficient (ACC), root mean square error (RMSE), and normalised standard deviation (NSD). Results show spatial clustering into three subregions (MCSEA, MLSEA, and PLSEA). Domain-averaged ACC remains weak (0.01 to 0.07) but exhibits substantial spatial variability (0.5 to 0.5). RMSE is typically 140160 mm. Skill is higher at early lead times (LY2) and in DJF, decreases at intermediate leads, and partially recovers at longer leads (LY8LY9).
  Keywords: forecast skill; decadal prediction; region; lead time; ensemble model.
  DOI: 10.1504/IJGW.2026.10078906
   
  
• A Simulation Study on the Coordination of Green Finance and Fiscal Policy to Support Regional Low-Carbon Transition  
  by Lingli Yang 
  Abstract: The current policy practice often relies on a single tool, while green finance and fiscal policy complement each other in multiple aspects, and their synergistic effects and regional differences have not been fully explored in terms of quantity. To this end, this paper constructs a stock flow consistency (SFC) model that combines heterogeneous regions and energy preference industries, introduces endogenous policy variables based on a subject based macro financial model, and incorporates multi period games and risk contagion mechanisms between regional governments, financial institutions, and high carbon enterprises. The experiment used data from eight provinces in China to simulate the dynamic feedback of fiscal and monetary incentives under different industrial endowments. The results indicate that under the sole effect of baseline fiscal policy, the green capital formation rate in underdeveloped areas only increased by 2.1%, while the coordinated strategy optimized by the coupled model increased this figure to 5.8%.
  Keywords: Green Finance; Fiscal Policy; Regional Low-Carbon Transition; Policy Coordination; Financial Risk Contagion; Regional Heterogeneity; Policy Synergy Threshold.
  DOI: 10.1504/IJGW.2026.10079409
   
  
• Copula-Based Wind-solar joint output simulation for carbon capture economic dispatch optimisation in power systems  
  by Yunyu Yang 
  Abstract: To address insufficient correlation modeling of wind-solar outputs and limited economic regulation of carbon capture in conventional power dispatch, this study constructs a carbon-integrated economic dispatch model via wind-solar joint simulation. Vine Copula is adopted to estimate the joint probability distribution and characterize the correlation of wind and solar outputs, while marginal distribution fitting and the K-Nearest Neighbor method generate high-precision joint scenarios. A stepped carbon trading mechanism is embedded to dynamically control carbon costs. Results demonstrate that the model yields a determination coefficient of 0.9557 and scenario coverage of 92.09%, superior to benchmark models. It reduces power loss to 69.35 kW, wind/solar curtailment rates to 1.40% and 1.27%, carbon emissions to 6876 t, and total operating costs. The model effectively balances economic and low-carbon performance, supporting low-cost, low-carbon operation of high-renewable power systems.
  Keywords: Copula; Wind and solar output; Carbon capture; Economic dispatch; Low carbon.
  DOI: 10.1504/IJGW.2027.10080040
   
  
• Optimisation Algorithms for Green Protection, Renovation and Reconstruction of Historical Buildings Aiming at Low Carbon Goals  
  by Sheng-Nan Li, Yan He 
  Abstract: This study proposes a constrained NSGA-II algorithm balancing cultural authenticity and low-carbon performance in historic building preservation. By encoding appearance fidelity and structural safety as hard constraints, the method minimizes lifecycle carbon emissions and economic costs via hybrid discrete-continuous encoding. A constraint-priority mechanism ensures regulatory compliance. This paper tests the approach across various scenarios; it achieves minimum lifecycle carbon emissions of 301.3 kgCO?e/m? and costs of 2164.9 CNY/m?. Operational carbon intensity falls below 43 kgCO?e/m??year, with over 50% energy savings. This framework provides a robust decision-making tool for sustainable historic urban renewal without compromising heritage integrity.
  Keywords: Historical Buildings; Green Protection; Low-Carbon Goals; Renovation and Upgrading; Multi-Objective Optimization; NSGA-II Algorithm.
  DOI: 10.1504/IJGW.2026.10080132
   
  
• Optimisation Framework for Residential Landscape Design Based on the Synergistic Benefits of Carbon Sequestration and Biodiversity  
  by Ru An 
  Abstract: In the current field of residential landscape design, there is a lack of tools for comprehensive quantitative evaluation and optimisation feedback on the synergistic benefits of carbon sequestration and biodiversity, resulting in the inability to predict and balance the comprehensive ecological performance of the landscape during the design phase. This paper developed a design optimisation framework that integrates parameter modelling and multiobjective optimisation algorithms. This framework first establishes a parameter model of landscape design elements and combines it with a fixed quantum model of core benefits such as carbon storage increment and habitat structure complexity index. The experimental results showed that compared with the traditional baseline scheme, the balanced collaborative scheme generated by the optimisation framework improved carbon efficiency and biodiversity efficiency by 20.5% and 19.0%, respectively. Pareto front analysis indicates that the balanced collaborative approach achieves the optimal balance between two objectives.
  Keywords: Carbon-Biodiversity Synergy; Residential Landscape; Multi-Objective Optimization; Parametric Design; Non-Dominated Sorting Genetic Algorithm.
  DOI: 10.1504/IJGW.2026.10080294
   
  
• Simulation of the Path for Green Finance and Industrial Policy Synergy to Support the Transformation of High-Carbon Industries  
  by Xi Zhang, Xinmiao Jiang 
  Abstract: This paper simulates a high carbon industry transition by coupling heterogeneous agent modelling with deep deterministic policy gradient. Green finance and industrial policy parameters are encoded into state vectors. A multi objective reward function drives adaptive enterprise decisions. Monte Carlo simulations reveal a phase transition in year 12 under synergistic optimisation, with carbon intensity converging to below 1.50 tons/10,000 CNY and financing cost volatility converging to below 4.0%. The optimal policy mix trajectory balances economic stability and emission reduction efficiency.
  Keywords: Green Finance; Industrial Policy; Agent Modeling; Deep Deterministic Policy Gradient; High-Carbon Transition.
  DOI: 10.1504/IJGW.2027.10080296
   
  
• Century-Scale Temperature Trends in Central and Northern Australia (1878-2024): Urban Heat Island Biases and Multi-Decadal Climate Cycles  
  by Alberto Boretti 
  Abstract: Analysis of 140 years of unaltered temperature data from Alice Springs and Darwin (1878-2024) reveals distinct regional trends obscured by homogenised datasets. Darwin shows cooling in maximum temperatures (0.0045(0.0045C/year), while Alice Springs exhibits only modest warming (+0.004C/year). These patterns reflect natural climate variability (ENSO, IOD) and non-climatic factors like urban heat islands and airport development. Homogenisation methods (NASA GISS, ACORN-SAT) lower historical temperatures and exaggerate recent warming, manufacturing an artificial acceleration inconsistent with local instrumental records.
  Keywords: Long-term temperature trends; Alice Springs; Darwin; Northern Territory; urban heat island effect; climate cycles; climate change; historical temperature data; data bias adjustments; ENSO; IOD.
  DOI: 10.1504/IJGW.2027.10080457
   
  
• A New City-Level Insights on Air Quality: The Role of Energy Consumption in Particulate Matter Emissions  
  by Hakan Uslu 
  Abstract: This study analyses the impact of energy consumption on particulate matter (PM) emissions using provincial data from T?rkiye. Utilising Autoregressive Distributed Lag models, it finds that urban electricity consumption is the primary long-term driver of particulate accumulation, while petroleum consumption has a negative effect. Natural gas lowers coarse PM10 emissions but increases fine PM2.5 levels long-term due to secondary transformations. Including overall electricity generation shows that T?rkiyes clean energy efforts help reduce baseline PM. Notably, the nonlinear analysis indicates that improvements in air quality from reduced energy use are greater than the decline caused by equivalent increases in consumption.
  Keywords: energy consumption; fossil fuel consumption; air pollution; fine particulate matter; PM10; city-level analysis; emission intensity.
  DOI: 10.1504/IJGW.2027.10080819
   
  
• Sustainable Operations for Battery Thermal Management Systems with Life Cycle Analysis Perspective  
  by Enis Altuntop 
  Abstract: This study employs LCA to evaluate the GWP of LIBs under 25 C and 80 C operating conditions, specifically analyzing a BTMS using decanoic acid and active air cooling. Results indicate that unmanaged operation at 80 C results in excessive emissions of 402.09 kg CO2-eq/kWh due to shortened lifespans. Implementing BTMS maintains 25 C conditions, reducing emissions to 48 kg CO2-eq/kWh when including second life and recycling credits. BTMS hardware adds negligible 0.07 kg CO2-eq/kWh per battery, it reduces total carbon emissions by approximately seven times. These findings highlight that using PCM can be critical material for BTMS as a critical component for sustainable electric vehicle operations.
  Keywords: Life cycle assessment (LCA); battery thermal management system (BTMS); lithium-ion battery (LIB); phase change materials; PCM; sustainability.
  DOI: 10.1504/IJGW.2027.10080883
   
  
• Knowledge, Attitude, Practice, and Concerns about Climate Change in the United Arab Emirates  
  by Ahmad Z. Al Meslamania, Anan S. Jarab, Marwa Alloush, Hebatallah Ahmed Mohamed Moustafa 
  Abstract: Background: Climate change is a public health concern. Methods: This cross-sectional study assessed climate changes knowledge, attitudes, practices (KAP) and concerns among 1,004 United Arab Emirates (UAE) adults. Results: Results revealed moderate knowledge (median 5/10) and practice scores (8/16), but lower attitude scores (5/12). Females and highly educated participants reported significantly higher knowledge and attitude scores. Increased age, being married, and positive attitudes significantly predicted better climate change practices. Conclusion: Multifaceted approaches to enhance the public's awareness of climate change and sustainable behaviors are needed.
  Keywords: Climate change; UAE; Public Health; Environmental health; KAP.
  DOI: 10.1504/IJGW.2027.10080889
   
  
• MOF-Engineered Ceria Catalysts for Efficient Dimethyl Carbonate Production from CO2 and Methanol under Thermodynamically Favourable Conditions  
  by Weihai Liang, Samiran Bhattacharjee, Wenxing Ye, Chao Chen 
  Abstract: Acid-base bifunctional Co-MOF@CeO2 catalysts were synthesized through a MOF-modification strategy for direct dimethyl carbonate (DMC) production from CO2 and methanol. Incorporating Co into the CeO2 lattice introduced Lewis acidic sites (Ce3+/Ce4+) and oxygen vacancies, enhancing CO2 affinity and enabling efficient activation of both reactants. The optimized catalyst achieved a fourfold higher DMC yield than pristine CeO2. Using a dehydrating agent, it delivered a DMC formation rate of 48.73 mmol?g-1?h-1 (yield 3.95%) under mild conditions (2 MPa, 120 oC), outperforming many systems requiring higher pressures.
  Keywords: Dimethyl carbonate; CO2 conversion; MOF-modification; surface oxygen vacancies; Lewis acidic sites.
  DOI: 10.1504/IJGW.2027.10080914
   
  
• A Novel Hybrid Approach for Greenhouse Gas Emission Prediction using MOA based Recursive BiLSTM-SARIMA  
  by Tzu-Chia Chen 
  Abstract: In this work, an advanced optimization enabled deep learning technique is used for GHG prediction. Feature selection process is done using proposed Serial Exponential Meerkat Optimization Algorithm (SE-MOA), which is integrated by Exponential Weighted Moving Average concept with Meerkat Optimization Algorithm (MOA). Finally, GHG emission prediction is performed using novel approach, called Recursive BiLSTM-SARIMA, which is created by combining Recursive Bidirectional Long Short-Term Memory (BiLSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Experimental evaluation reveals that SE-MOA based Recursive BiLSTM-SARIMA achieves 2.83% of MAE, 1.07% of MSE, 3.27% of RMSE, 0.64% of MBE and 10.47% of MAPE.
  Keywords: Greenhouse Gas; Emission Prediction; Deep Learning; Optimization Algorithm; Feature Selection.
  DOI: 10.1504/IJGW.2027.10080942
   
  
• Evaluation of Ecological Product Value Conversion Efficiency Based on Low-Carbon Development  
  by Yan Wang, Zhengyin Wang 
  Abstract: Under low-carbon constraints, this paper evaluates ecological product value conversion efficiency, incorporating carbon emissions as undesirable output. Using super-efficient SBM (Slack-Based Measure) and GML (Global Malmquist-Luenberger) index models for 41 Yangtze River Delta cities (20102020) and panel Tobit for mechanism analysis, the paper finds that average efficiency rose, with GML index growing 3.4% annually, driven by technological progress. Mediation tests show that technological innovation and industrial upgrading explain 30.6% and 17.5% of the total effect, respectively. This provides evidence for a coordinated low-carbon transition and the realization of ecological value.
  Keywords: Low-Carbon Development; Ecological Products; Conversion Efficiency; Yangtze River Delta Urban Agglomeration; Super-Efficiency SBM Model.
  DOI: 10.1504/IJGW.2027.10081015
   
  
• Machine LearningDriven Analysis of Meteorological Influences on Streamflow Dynamics  
  by Nguyen Thi Luong Hang, Nguyen Tien Thanh, Nguyen Thai Son, Nguyen Ho Phuong Thao 
  Abstract: This study applies linear regression (LR), support vector regression (SVR), and M5P combined with principal component and elasticity analyses to quantify meteorological influences on streamflow across temporal scales. The results show that LR performs best at annual and wet season scales, while M5P outperforms at dry season and monthly scales. Precipitation dominates streamflow variability annually (61.83%) and seasonally. During the dry season, humidity contributes significantly under low evaporative demand (38.56%), whereas precipitation dominates under high stress (85.91%). At the monthly scale, potential evapotranspiration dominates under low demand, while humidity, temperature, and evapotranspiration jointly influence streamflow under high evaporative stress.
  Keywords: Principal Component Analysis (PCA); Linear Regression (LR); Support Vector Regression (SVR); M5P; Weka software.
  DOI: 10.1504/IJGW.2027.10081028
   
  
• Green investment and efficiency improvement: a study on the eco-economic effects of environmental protection expenditure in fine chemical enterprises  
  by Wangsi Chen 
  Abstract: Under the dual carbon goal, this study examines whether environmental protection expenditures enhance eco-economic efficiency (EEE) in fine chemical firms. Using 20162025 data, SBM and threshold models reveal that green investment significantly improves EEE (coefficient ~0.76), with marginal effects strengthening when green technology or resource allocation efficiency exceeds critical thresholds. Results show efficiency gains depend on internal capacity, not merely expenditure scale.
  Keywords: Green investment; Eco-economic efficiency; Fine chemical enterprises; Heterogeneity analysis; Threshold effect.
  DOI: 10.1504/IJGW.2027.10081058
   
  
• Temperature Extreme Event in Lampung Province Based on NEX-GDDP-CMIP6  
  by Della Ramadhanti, Alvin Pratama, Amalia Nurlatifah 
  Abstract: Climate change is intensifying temperature extremes in tropical regions, yet projections for southern Sumatra remain limited. This study examines near-surface air temperature changes in Lampung Province during 20152060 using a four-member CMIP6 ensemble under SSP?2.6, SSP?4.5, SSP?7.0, and SSP8.5. Bias-corrected MERRA-2 data and MannKendall trend analysis show significant increases in mean, maximum, and minimum temperatures across all scenarios. Warming is strongest under SSP8.5, while minimum temperature increases most under SSP?4.5, indicating enhanced nighttime warming.
  Keywords: Climate change; extreme temperatures; CMIP6; statistical downscaling; linear scaling; Sen’s Slope; Mann-Kendall.
  DOI: 10.1504/IJGW.2027.10081200
   
  
• The Green Blueprint: Unlocking Value Through Sustainable Innovation  
  by Duygu Toplu Yaşlioğlu, Esin Bengu Ceran, Ugur Emre Temelli 
  Abstract: This study examines how integrating sustainability and value innovation creates a value creation mechanism for companies. Although sustainability and innovation are frequently discussed together in the existing literature, studies explaining the effects of the strategic integration of these two approaches on business performance and environmental outputs are limited. The research is based on a qualitative analysis of the sustainability and integrated reports of 23 companies included in the BIST25 Sustainability Index during the 2022-2023 period. A document analysis method was used within the framework of a multiple case study design, and the data were inductively coded using MAXQDA software. As a result of the analysis, a conceptualization of sustainable value innovation consisting of nine dimensions environmental impact, innovation and R&D, digital transformation, collaboration, social impact, and governance - was developed. The findings show that when sustainability moves beyond being an adaptation-based activity and is integrated into innovation processes, it strengthens cost-effectiveness and strategic resilience as well as environmental performance. The study provides a transferable conceptual framework for sustainable value innovation.
  Keywords: Sustainability; Value innovation; Green value; Sustainable value innovation.
  DOI: 10.1504/IJGW.2026.10081233
   
  
• Enhancement of Environmental Carrying Capacity of Urban Renewal Areas by Green Intelligent Construction in the Context of Low-Altitude Economy  
  by Shuai Liu 
  Abstract: Under the rapid development of the low-altitude economy, urban renewal areas face growing tension between spatial restructuring and ecological carrying pressure. This paper builds a coupled analytical framework linking the low-altitude economy, urban renewal, and green intelligent construction, integrating Building Information Modeling (BIM) and digital twin technology with an AHP-EWM(Analytic Hierarchy Process-Entropy Weight Method) evaluation model and a coupling coordination model. Using empirical data from Shenzhen, Shanghai, and Chengdu, results show resource utilization rising from 0.57 to 0.85, ecological pressure from 0.52 to 0.81, and coupling coordination reaching 0.68 in industrial zone renewal, demonstrating significant system synergy.
  Keywords: Low-Altitude Economy; Urban Renewal; Green Intelligent Construction; Environmental Carrying Capacity; Coupling and Coordination Analysis.
  DOI: 10.1504/IJGW.2027.10081246
   
  
• Green Closed-loop Supply Chain Model based on Optimized Fuzzy Algorithm and Its Environmental Friendly Recycling Application  
  by Zexu Zhao, Huangzheng Lu 
  Abstract: Traditional supply chains face problems such as low efficiency, wasted resources, and environmental issues with product recycling. Additionally, uncertainties make it difficult to discover the best recycling path. In this study, we present a model based on an optimised fuzzy algorithm for green closed-loop supply chains under uncertainty. The model integrates fuzzy logic and genetic algorithms to model uncertainties, design global optimisation algorithms, and implement a system framework for improved recovery of resources, reduced costs, and reduced environmental impacts. The algorithm is implemented at each link in the supply chain and enhances recycling efficiency by 14.5%, reduces energy consumption by 84 GJ, and decreases carbon dioxide emissions by 45 tons at each link.
  Keywords: Green Closed-loop Supply Chain; Environmental Protection and Recycling Treatment; Fuzzy Algorithm Optimization; Uncertainty Optimization; Resource Recycling Utilization.
  DOI: 10.1504/IJGW.2026.10081330
   
  
• Artificial Intelligence, Environmental Taxation, Renewable Energy and CO2 Emissions: Quantile Evidence from a Cross-Country Panel  
  by Muhammad Zahid Rafique  
  Abstract: Interrelationships among artificial intelligence (AI), environmental taxation, renewable energy, and CO2 emissions remain underexplored in cross-country energy policy research. This study examines the effects of AI adoption and environmental tax revenue on emissions in 42 economies from 2000 to 2019. Method of Moments Quantile Regression, which traces covariate effects across the conditional distribution of emissions, shows that AI adoption is associated with lower emissions, especially at higher quantiles. Environmental taxation reduces emissions mainly at lower quantiles, while the AI-tax interaction strengthens towards the upper tail, indicating fiscal-technology complementarity; the pattern is robust to fixed-effects and System GMM estimation. The findings support coordinated decarbonisation strategies.
  Keywords: Artificial intelligence; Environmental taxation; CO₂ emissions; Renewable energy; Method of Moments Quantile Regression.
  DOI: 10.1504/IJGW.2027.10081436
   
  
• Spatiotemporal evolution and source of differences in carbon emissions of resource-based cities in China-Based on the perspective of different types of cities  
  by Li Ji, Huadong Gao, Longgao Chen, Jihong Dong 
  Abstract: As an important target of China's carbon reduction policies, resource-based cities (RBCs) face significant emission pressure. This study analyzes spatiotemporal evolution and sources of differences in urban carbon emissions, and clarifies their spatial distribution, agglomeration patterns, and dynamic evolution. Results show that: (1) Carbon emissions generally increase, with large variations among city types. (2) Overall differences mainly stem from supervariable density. (3) High-high agglomeration is the dominant spatial type. (4) Spatial interaction and dynamic transfer exist, mostly between adjacent levels. These findings offer important insights for promoting green, low-carbon transformation in RBCs.
  Keywords: Resource-based cities; carbon emission; spatiotemporal evolution; city types; disparity sources.
  DOI: 10.1504/IJGW.2027.10081489
   
  
• Improving Municipal Solid Waste Prediction for Sustainable Urban Management Using Trend-Adaptive Asymmetric Fuzzification  
  by Ankit Bansal, Umang Soni, Aqueel Ahmad 
  Abstract: Automated diabetic retinopathy grading is constrained by ordinal progression and class imbalance. This study investigates whether the bottleneck is feature quality or classifier expressiveness. RetinaScan combines a frozen CLIP ViT-B/16 backbone with a projection head, text-guided prototypes, and a CORAL ordinal head. Trained on 16,231 fundus images across five datasets, a central finding is a 22.8-point accuracy gap on identical features: KNN on 512-dimensional embeddings achieves 74.75% validation accuracy while the trained linear ordinal head reaches 51.97%, suggesting classifier expressiveness as a limitation. KNN maintains strong performance on the held-out test set (73.04% accuracy), with 84.55% off-by-one accuracy suggesting screening utility. Text-guided prototypes provide per-grade interpretability.
  Keywords: Solid Waste Management; Fuzzy Membership Function; Machine Learning Framework; Sustainable Urban Development; Smart City Planning.
  DOI: 10.1504/IJGW.2027.10081495
   
  
• A Hybrid Deep Quasi Recurrent Feed Forward Network for Air Quality Index Prediction  
  by Kohila C, Meena Alias Jeyanthi, Kasthuri Rengan P 
  Abstract: This paper introduces a Deep Quasi Recurrent Feed Forward Network (DQReF-Net) to predict the Air Quality Index (AQI) using time-series data. Here, the input time series data is normalized by exploiting the Tanh estimator, and then the technical feature indicators are mined from the normalized data. After this, feature fusion is carried out by utilizing Deep Belief Networks (DBN) with Topsoe similarity. At last, the air quality prediction is carried out by exploiting the newly formulated DQReF-Net approach. Furthermore, the DQReF-Net technique is devised by incorporating two methods, such as Quasi-Recurrent Neural Network (QRNN) and Deep FeedForward Neural Network (DFNN). Furthermore, the newly presented DQReF-Net technique obtained a high R2 score of 0.937, and minimum Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Weighted Absolute Percentage Error (WAPE), Mean Absolute Error (MAE) of 0.221, 0.049, 0.098, 0.238, 0.188, respectively.
  Keywords: Air quality prediction; Environmental monitoring; Time series data; Deep learning; Feature fusion; Deep Quasi Recurrent Feed Forward Network.
  DOI: 10.1504/IJGW.2026.10081697
   
  
• Risk Assessment Model and Its Application in Low-Carbon Project Financing Based on Neural Networks  
  by Chanjuan Zhang, Yuee Guo 
  Abstract: Multi-source heterogeneous data and nonlinear risk coupling make traditional risk assessment methods ineffective for low-carbon project financing. In this paper, we propose a risk assessment model based on a deep neural network. Multi-source indicators in financial, technology, policy, and environmental dimensions are standardized and hierarchically fused into a unified feature space for nonlinear learning. The DNN employs backpropagation, adaptive optimization, and regularization to enhance the prediction performance. The experimental results show that the accuracy is 93.6%, the F?score is 0.921, the AUC is 0.957, it converges within 50 epochs, and the loss is less than 0.03, indicating an effective and reliable financing risk assessment.
  Keywords: Low Carbon Projects; Financing Risk Assessment; Deep Neural Network; Multi-Source Data Fusion; Nonlinear Feature Modeling.
  DOI: 10.1504/IJGW.2027.10081713
   
  
• Evaluating Renewable, Nuclear and Carbon Capture Strategies for Chinas Energy Transition and Their Global Climate Spillovers  
  by Temidayo Alex-Oke, Olusola Bamisile, Dongsheng Cai, Qi Huang 
  Abstract: Chinas net-zero timing strongly shapes global mitigation feasibility and adaptive capacity. Using a multi-sector integrated assessment, this study shows that advancing Chinas target from 2060 to 2040 reshapes emissions, carbon pricing and resource pressures with major implications for the rest of the world (ROW). The accelerated pathway cuts ROW CO by more than 70 percent by mid-century, with the power sector turning net-negative through expanded carbon removal. Although the 2040 pathway requires higher near-term carbon prices, it reduces cumulative costs and limits global mean temperature to 1.59 ?C by 2100, avoiding a 3.7 ?C outcome without mitigation. Renewables provide the structural backbone of the transition, nuclear offers firm capacity, and CCS and hydrogen add system flexibility. Earlier action also eases land and water pressures, supporting food security and ecological resilience.
  Keywords: GCAM; Net-zero emissions; Global spillovers; carbon pricing; Renewable Energy; Nuclear Energy
  
  
• Explainable Ensemble Machine Learning for Interpreting Direct Nitrous Oxide Emissions from Synthetic Nitrogen Fertilizers in Farming Systems  
  by Sireesha Mantena, Goriparthi Nagavallika, Abdul Gaffar Sheik 
  Abstract: Accurate prediction of synthetic fertilizer-derived nitrous oxide (NO) emissions remains important for understanding emission variability and supporting sustainable agricultural management. The present research introduces an explainable ensemble machine learning approach based on the models of RF, GB, AdaBoost, CatBoost, and XGBoost for reliable and interpretable prediction of NO emissions. All ensemble models exhibited excellent predictive ability, and the best results were obtained using GB (R? = 0.98, RMSE = 419.89, MAE = 183.56, and VAF = 0.98). SHAP was employed to enhance model transparency by quantifying feature contributions and interaction effects influencing NO emissions.
  Keywords: Agriculture; climate-smart agricultural; explainable artificial intelligence; Predication; Nitrous oxide.