International Journal of Environment and Pollution (19 papers in press)

Regular Issues

• Open Access

  Predicting the cooling capacity of green buildings using probabilistic neural network models ( Free Full-text Access )

  by Hua Zheng, Pengming Wang 
  Abstract: This paper proposes a probabilistic neural network (PNN) model to predict the cooling capacity of green buildings, addressing nonlinear factors and uncertainties often overlooked by traditional regression models. The PNN model uses climate and building features as inputs, applies radial basis function (RBF) in the hidden layer for nonlinear mapping, and generates cooling capacity predictions with confidence intervals. Historical data is used to optimise parameters via backpropagation, and k-fold cross-validation prevents overfitting. Experimental results show that the PNN model achieves an R2 value above 0.95 and a 96.67% confidence interval coverage rate across different climate conditions. Compared to traditional models, the PNN demonstrates superior performance in handling nonlinearities and uncertainty in cooling capacity prediction.
  Keywords: green building cooling capacity prediction; PNN; probabilistic neural network; nonlinear modelling; uncertainty processing; data preprocessing.
  DOI: 10.1504/IJEP.2025.10072094
   
  

• Open Access

  Evaluation and trend prediction of the relationship between carbon emissions, energy, and sustainable growth based on neural networks ( Free Full-text Access )

  by Tingting Tan 
  Abstract: This study investigates the relationship between carbon emissions (CE), energy, and sustainable growth using neural networks. Data from five regions North America, South America, Europe, Asia Pacific, and Africa were analysed to model CE trends based on energy structure and consumption. A neural network model was trained and optimised to predict correlations among CE, energy use, and economic growth. Focusing on China, the study examines vehicle emissions, fuel-powered versus new energy vehicle sales, and their impact on CE and the economy. Results show a strong correlation between energy consumption and CE (R = 0.99), with energy efficiency and composition also influencing emissions. As new energy vehicle adoption rises, fossil fuel demand declines, helping curb total CE, support carbon neutrality, and promote sustainable development. The model demonstrates that optimising energy structure is key to balancing economic growth and environmental protection.
  Keywords: carbon emissions; neural networks; energy mix; energy consumption; data analysis; sustainable development; climate change.
  DOI: 10.1504/IJEP.2025.10072992
   
  

• Open Access

  Promoting the transformation of digital economy structure based on artificial intelligence in the low carbon economy environment ( Free Full-text Access )

  by Fan Chen, Aijun Liu 
  Abstract: This study investigates the impact of artificial intelligence (AI) on economic structure (ES) transformation within a low-carbon economy. Focusing on ES advancement and rationalisation, an empirical model is established incorporating control variables such as policy, openness, informatisation, and population density. Using dynamic panel analysis, results show that AI significantly promotes both ES advancement and rationalisation at the 1% level in the first lagged period. The findings indicate that AI enhances industrial efficiency and supports green development, playing a crucial role in driving sustainable, high-quality economic growth. This research provides valuable insights for policymakers seeking to integrate AI into low-carbon economic strategies.
  Keywords: economic restructuring; artificial intelligence; low-carbon economic environment; economic model analysis; expert system.
  DOI: 10.1504/IJEP.2025.10073301
   
  

• Open Access

  New algorithm for numerical simulation of beach evolution under extreme weather and neural network optimisation prediction model ( Free Full-text Access )

  by Songzhe Li, Hongqian Zhang 
  Abstract: This study proposes a novel beach evolution prediction algorithm integrating convolutional neural networks and numerical simulation to enhance accuracy under extreme weather. An improved deep-water flow model, based on the Navier-Stokes and sand-water mixing equations, captures hydrodynamic changes influenced by wind waves, tides, and currents. Meteorological and oceanic data are preprocessed using local weighted regression and interpolation methods to ensure quality. A neural network model dynamically predicts beach evolution, with k-fold cross-validation ensuring stability across extreme weather scenarios. Results show high accuracy, with mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) all below 0.4 and prediction errors under 12%.
  Keywords: extreme weather; beach evolution; numerical simulation; neural network; prediction analysis.
  DOI: 10.1504/IJEP.2025.10073562
   
  

• Open Access

  Empowering sustainable growth: the transformative impact of environmental protection inspections on heavy polluters ( Free Full-text Access )

  by Yingbo Gu, Chang Liu 
  Abstract: This study finds that environmental protection inspections (EPI) significantly improve the green total factor productivity (GTFP) of Chinas A-share heavy polluters, primarily through modest gains in green innovation and compliance behaviour. Using panel data spanning from 2011 to 2019, this study employs the super-slacks-based measure (SBM) model and the MalmquistLuenberger (ML) index to quantify GTFP, and applies a differencein-differences (DID) approach to examine the dynamic relationship between EPI and GTFP. The empirical results indicate that EPI exerts a statistically significant and positive effect on GTFP among heavily polluting enterprises, with green technological innovation identified as a key mediating mechanism. Furthermore, regional heterogeneity analysis reveals that the positive impacts of EPI are primarily concentrated in Chinas eastern and central regions, underscoring the influence of regional economic development levels on the effectiveness of environmental governance.
  Keywords: environmental protection inspections; green total factor productivity; heavy polluters; green technological innovation; environmental governance; sustainable economic development.
  DOI: 10.1504/IJEP.2025.10073694
   
  

• Open Access

  Combating illegal sand pumping: enforcement challenges and policy mechanisms in Taiwans EEZ ( Free Full-text Access )

  by Chiao-Ling Chen, Yi-Che Shih 
  Abstract: In Taiwan, the exclusive economic zone (EEZ), which overlaps with those of neighbouring coastal countries, has become a hotspot for illegal sand pumping by cross-border fleets. These activities have drawn significant criticism from the public and media for contributing to weaknesses in marine law enforcement, environmental degradation, and habitat destruction. In response, legislative, administrative, and civil society actors have demanded stronger enforcement and effective countermeasures including legal reforms, enhanced marine resource conservation, and increased enforcement to demonstrate the Taiwanese governments commitment. This study evaluates Taiwans inter-ministerial coordination strategies and proposes enforcement and management recommendations based on strengths, weaknesses, opportunities, threats (SWOT) and fishbone diagram analyses. The findings aim to inform future research and policy efforts, both domestically and in similarly affected coastal states.
  Keywords: Law Enforcement; SWOT; Sand Pumping; EEZ; Taiwan.
  DOI: 10.1504/IJEP.2025.10074105
   
  

• Open Access

  Green logistics distribution route algorithm based on carbon emissions optimisation ( Free Full-text Access )

  by Lin Zhu, Chulv Sun 
  Abstract: Aiming at the problems of high carbon emissions (CE) and low optimisation efficiency in green logistics distribution (LD) path optimisation, this paper takes CE as the goal and introduces an adaptive genetic algorithm (AGA) to dynamically adjust the crossover and mutation probabilities, reduce CE, and improve the global search capability and convergence speed. This paper first constructs an optimisation model based on the basic data of the LD network, and then constructs a carbon emission optimisation model based on fuel consumption and CE taking into account time windows and traffic constraints. Finally, this paper analyses the performance of genetic algorithm (GA), ant colony algorithm (ACO), particle swarm algorithm (PSO) and AGA algorithm in carbon emission reduction and path optimisation by comparing their optimisation results. The results show that the AGA algorithm performs well in all test scenarios, successfully reduces CE, and significantly shortens the delivery route.
  Keywords: green logistics; distribution route; route optimisation; carbon emissions; AGA; adaptive genetic algorithm; optimise efficiency.
  DOI: 10.1504/IJEP.2025.10074264
   
  

• Open Access

  Dynamic process mechanism of empowering carbon peak and carbon neutrality in architectural interior design based on digital technology ( Free Full-text Access )

  by Huiyue Hei 
  Abstract: Traditional building design methods suffer from issues such as insufficient application of technology, low data utilisation, disconnect between design and operation, lack of systemisation, and weak innovation capabilities, making them ineffective in supporting the goals of carbon peak and carbon neutrality. This paper explores how digital technologies such as the Internet of Things (IoT) and smart control systems can enhance building interior design, contributing to achieving carbon peak and carbon neutrality, and analyses their dynamic operational mechanisms. This research utilises building information modelling (BIM) software to create and optimise building models, employs virtual reality (VR) technology for virtual simulation and user experience evaluation, uses an IoT sensor network for real-time monitoring, and integrates a smart control system for automatic adjustment of lighting and air conditioning. The experimental results show that energy consumption in buildings was reduced by approximately 36%, and carbon emissions were reduced by 32.5%.
  Keywords: digital technology; BIM; building information modelling; IoT; Internet of Things; carbon neutrality; sustainable architecture.
  DOI: 10.1504/IJEP.2025.10074446
   
  

• Open Access

  Digital economy and global value chain restructuring from a cross-country sustainable industry analysis ( Free Full-text Access )

  by L.I. Zhou, Mohd Azlan Shah Zaidi, Zhanxue Wang 
  Abstract: The unprecedented expansion of the digital economy is fundamentally altering the architecture and operational dynamics of global value chains (GVCs). This study investigates the impact of digital economy development on the restructuring of global value chains (GVCs). This analysis develops a theoretical framework and employs empirical analysis utilizing cross-country industry data. These findings show that digital economy development catalyzes GVC restructuring; this kind of restructuring is mainly reflected in the changes in the network status of the global value network and with notable heterogeneity across industries, input origins, and country classifications. Mechanism analysis shows that the digital economy promotes restructuring global value chains by improving production efficiency and innovation capabilities.
  Keywords: GVC; global value chain restructuring; digital economy; production efficiency; innovation capability; mediation effect.
  DOI: 10.1504/IJEP.2025.10074674
   
  

• Open Access

  Roof garden plant selection and ecological application: comprehensive strategies to deal with environmental pollution ( Free Full-text Access )

  by Rui Guo, Zechen Xiao 
  Abstract: This paper adopts a collaborative optimisation scheme based on functional plant community construction and intelligent response system. This paper first selects local plant combinations to construct a multi-layered, multiobjective plant community, and then deploys temperature, humidity, PM2.5, nitrogen oxides (NOx) and light intensity sensors in the roof garden. Then, this paper uses sensor feedback and fuzzy control algorithms to trigger precise irrigation and ventilation equipment to optimise the plant microenvironment and pollutant diffusion paths, and finally develops a lightweight matrix layer containing activated carbon and vermiculite. Experimental results show that in the environmental chamber, the functional plant community removed PM2.5 and NOx at rates of 42.5 g/m2/h1 and 15.6 g/m2/h1, respectively, demonstrating high removal efficiency for complex pollutants. In terms of response delay and energy efficiency, the fuzzy control algorithm achieved the lowest median delay (0.9 s) and the lowest energy consumption (6.28 kWh/m2).
  Keywords: environmental pollution; roof garden; plant selection; ecological application; intelligent response system.
  DOI: 10.1504/IJEP.2025.10074680
   
  

• Open Access

  Using soil water content and energy balance model to promote sustainable development of green and low-carbon economy ( Free Full-text Access )

  by Junyi Cao 
  Abstract: This study aims to evaluate the effectiveness of low-carbon economy (LCE) policies and explore their practical applications in reducing greenhouse gas emissions and promoting efficient resource utilisation. This study uses an ecological footprint calculation method based on the energy balance (EB) model to conduct a comparative experimental analysis on two regions that implement general economic policies and low-carbon economic policies, respectively. The research results show that between 2020 and 2024, carbon dioxide emissions from manufacturing and agriculture in regions implementing low-carbon economic policies increased by 3.97% and 4.02% respectively, significantly lower than the 7.78% and 8.97% increases in regions implementing general economic policies. Meanwhile, the growth rate of water consumption was also slower. Furthermore, low-carbon energy policies had a relatively small impact on total output, indicating that they can effectively reduce the environmental burden while ensuring economic growth.
  Keywords: LCE; low-carbon economy; energy balance; sustainable development; green industry.
  DOI: 10.1504/IJEP.2025.10074681
   
  

• Open Access

  Research on green trade data prediction under global economic shock based on ConvLSTM model oriented towards reducing carbon emissions ( Free Full-text Access )

  by Nianjie Shang, Yue Zhang, Yan Zhang, GaiRong Dai 
  Abstract: Existing green trade data prediction models only focus on the temporal characteristics of the data, while ignoring the spatial relationships of the data, resulting in large prediction errors for trade volume (M and X). This paper takes Sino-Korean trade as the main research object, and uses the convolutional long short-term memory (ConvLSTM) model to predict trade volume (M and X) data by combining the advantages of spatiotemporal features. This paper first collects and preprocesses relevant green trade data, then constructs a ConvLSTM model, and finally uses the model to output the predicted values of trade volumes M and X for the next year and compares them with the actual data. Experimental results show that the RMSE and MAE of the ConvLSTM model are 16,300 and 20,500, respectively, which are 1900 and 2300 lower than those of the LSTM model.
  Keywords: economic shock; green trade; data prediction; ConvLSTM model; spatial features; low-carbon economy; trade volume.
  DOI: 10.1504/IJEP.2025.10074875
   
  

• Open Access

  Industrial chain technology paths and economic feasibility of agricultural waste resource utilisation ( Free Full-text Access )

  by Lei Xu, Cheng Cheng, Yanan Zhang, Yuanlin Wang, Menglin Ni 
  Abstract: In response to the high cost and insufficient coordination of the industrial chain in the utilization of agricultural waste, this paper constructs an optimization scheme for the coordinated scheduling of biocatalysis and digital twins. By screening heat-resistant ?-glucosidase mutants and establishing straw-enzyme adaptation rules, combined with microwave-ultrasonic pretreatment and NIR (near-infrared), the conversion efficiency is improved. The virtual industrial chain model integrates GCN (graph convolutional networks) to predict raw material fluctuations, and improves the NSGA-? (non-dominated sorting genetic algorithm II) algorithm to achieve Pareto optimality of transportation and equipment utilization. Experiments show that the reducing sugar yield of the mutant enzyme system reaches 90.2% in 72 hours; the path optimization rate of the scheduling system exceeds 0.8 within 12 months, and the equipment idle loss is controlled at 21,000-23,000 US dollars, which significantly improves the efficiency of resource utilization.
  Keywords: agricultural waste; resource utilisation; industrial chain technology path; economic feasibility; digital twin model; GCN; graph convolutional networks; NSGA Ⅱ; non-dominated sorting genetic algorithm II.
  DOI: 10.1504/IJEP.2025.10074876
   
  

• Open Access

  Urban environmental sustainability and welfare management optimisation based on ant colony optimisation and embedded systems ( Free Full-text Access )

  by Min Tang, Yanmin Cheng, Jie Deng 
  Abstract: Urban welfare management optimisation encompasses the full lifecycle of support for vulnerable populations, from initial intervention to long-term rehabilitation. In many economies, the number of employment and income opportunities is limited for destitute individuals, because of their low levels of skills, education, and capital. Rapid urbanisation has transformed many rural areas into metropolitan zones lacking open spaces, farmland, and water resources. This study investigates an enhanced ant colony optimisation (ACO) algorithm for path optimisation, combining global and local pheromone updates to improve computational efficiency and convergence. Spatial compression modification further accelerates optimisation by reducing developmental complexity. Embedded system applications promote the reuse of open spaces, offering income opportunities such as gardening and freshproduce supply for the urban poor. Although they lack certain metropolitan amenities, they maintain rural ties through visits, relocation, and participation in social and economic institutions. Integrating indigenous knowledge into urban development can empower communities, alleviate poverty, and support environmentally sustainable growth.
  Keywords: welfare management; urban; ant colony optimization; embedded systems.
  DOI: 10.1504/IJEP.2025.10074969
   
  
• Ecotoxicity and water quality assessment of the Reconquista River (Buenos Aires, Argentina) by standardized bioassays on early developmental stages of a native amphibian (Rhinella arenarum)  
  by Carolina M. Aronzon, Celina Barreiro, Julieta Peluso, Vanesa Salomone, Marcos Tascon, Gabriela Svartz 
  Abstract: This work evaluated the water quality of the middle and lower basin of the Reconquista River, one of the most affected water bodies in Argentina, by physicochemical and ecotoxicological parameters. Physicochemical parameters were analyzed in situ and in the laboratory in water samples from ten sites distributed in the basin. Standardized toxicity bioassays were carried out with embryos and larvae of the native amphibian, Rhinella arenarum, exposed to dilutions of the surface water samples for a chronic (504h) period. Water Quality Indexes revealed a marked deterioration of the water and evidenced a clear spatial pattern with higher contamination at the central section which also caused a higher significant mortality in both embryos and larvae. The results demonstrate the substantial degradation of this water body and highlight the detrimental impact on the biota and aquatic ecosystem. These findings emphasize the need for an integrated approach to environmental concerns, using multiple indicators and information as an integrative approach of environmental quality assessment.
  Keywords: physicochemical parameters; toxicity bioassays; amphibians; Reconquista River.
  DOI: 10.1504/IJEP.2025.10071747
   
  
• Studies for the optimisation of bioleaching of heavy metals from contaminated sediments from Reconquista River  
  by Natalia Porzionato, Ana Elisabeth Tufo, Mariano L. Medina, Celeste M. Grimolizzi, Gustavo A. Curuchet 
  Abstract: Bioleaching processes are effective for removing heavy metals from contaminated sediments, but optimising performance requires understanding interactions between microbial activity, sediment properties, and metal behavior. Most studies emphasise metal solubilisation, often overlooking effects on the solid phase, particle movement, and metal reprecipitation. This study evaluates bioleaching in fixed-bed reactors, testing sulphur addition and bioaugmentation with native microbial strains. It examines relationships among microbial activity, metal mobilisation and reprecipitation, and changes in solid-phase characteristics. Results showed metals were mobilised from upper to lower reactor sections, where they accumulated. Although acidification occurred, it did not reduce pH throughout the column but significantly altered particle size, surface properties, and pore networks. Additionally, compaction from drainage and movement further influenced metal mobility and speciation. Modifying reactor geometry favouring shallower designs with larger surface areas could improve performance by enhancing drainage, microbial distribution, and metal recovery. These findings highlight the importance of physical changes during bioleaching.
  Keywords: bioleaching processes; optimisation; contaminated sediments; Reconquista River; remediation technologies; solid phase.
  DOI: 10.1504/IJEP.2025.10072436
   
  
• Carbon emission forecasting and peak carbon pathway analysis based on combined BP neural network and Grey forecasting models a perspective of Chinas data, 19972021  
  by Ming-Xun Zhu, Qiu-feng Yin, Lei Wu, Huan-ying Li 
  Abstract: This study aims to forecast China's carbon emissions and identify the peak emission year using data from the China Statistical Yearbook from 1997 to 2021. Employing both the Grey forecasting model and the BP neural network, this study predicts that China's carbon emissions will peak in 2030 and then decline year by year, aligning with the nation's carbon peak commitment. The analysis suggests that with the implementation of energy-saving and emission reduction policies, along with technological advancements, China is on track to achieve its green and low-carbon development goals post-peak. This study provides valuable insights for policy formulation towards carbon neutrality by 2060.
  Keywords: Grey model; GM; BP neural network model; carbon emissions; carbon peak.
  DOI: 10.1504/IJEP.2025.10073635
   
  
• Synthesis of activated carbon from coffee husks and its effect on CO2 capture and CH4 and H2 storage  
  by Cristian Toncón, Kiara M. Montiel-Centeno, Cristian A. Diaz, Deicy Barrera, Jhonny Villarroel-Rocha, Liliana Trevani, Laura Conde, Karim Sapag 
  Abstract: This work presents the synthesis of activated carbons from coffee husk pre- treated with steam explosion. The influence of the impregnation ratio (H3PO4/precursor) and impregnation time was evaluated. The synthesised materials were characterised by N2 adsorptiondesorption isotherms at 77 K and CO2 adsorption at 273 K, scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FTIR), and Raman spectroscopy. These techniques confirmed the success of activated carbons from the coffee industry waste. Two selected activated carbons were further evaluated for their CO2, CH4, and H2 adsorption capacities at 308 K, 298 K, and 77 K, respectively, under pressures of up to 10 bar. CA-1 and CA-5 exhibited promising H2 adsorption capacities, comparable to values reported. These findings open up new possibilities for developing porous carbon- based activated materials for advanced gas separation applications.
  Keywords: activated carbon; carbon dioxide capture; methane and hydrogen storage; biomass valorisation.
  DOI: 10.1504/IJEP.2025.10073971
   
  
• Public perception of air quality: the role of temporal distribution characteristics of pollution indicator levels  
  by Xunzhou Ma, Dan Wu 
  Abstract: This study uniquely applies modern portfolio studies to analyze perceptions of air quality, thereby revealing how these perceptions are influenced by air pollution indicators. We found that individuals were less satisfied with local air quality when exposed to distributions with higher mean levels of air quality and were more satisfied with smaller distribution volatility. Moreover, we discovered that evaluations of air quality are influenced by the frequency of extremely polluted or pollution-free episodes rather than by current conditions. Notably, responses to air pollution indicators and recall windows did not significantly affect the respondents’ judgments. Our results suggest that understanding responses to air pollution requires comprehensive analyses beyond standard distribution means. These findings have significant implications for the design of effective policies to improve life satisfaction.
  Keywords: air quality perception; distribution moments; perceived mean; perceived volatility; perceived frequency of extremely high levels; perceived frequency of extremely low levels.
  DOI: 10.1504/IJEP.2025.10074126