Exploring the nexus of urban form, transport, environment and health in large-scale urban studies: A state-of-the-art scoping review

Environmental Research, Journal Year: 2024, Volume and Issue: 257, P. 119324 - 119324

Published: June 5, 2024

As the world becomes increasingly urbanised, there is recognition that public and planetary health relies upon a ubiquitous transition to sustainable cities. Disentanglement of complex pathways urban design, environmental exposures, health, magnitude these associations, remains challenge. A state-of-the-art account large-scale studies required shape future research priorities equity- evidence-informed policies.

Language: Английский

---

Systematic Review of Machine Learning and Deep Learning Techniques for Spatiotemporal Air Quality Prediction

Atmosphere, Journal Year: 2024, Volume and Issue: 15(11), P. 1352 - 1352

Published: Nov. 10, 2024

Background: Although computational models are advancing air quality prediction, achieving the desired performance or accuracy of prediction remains a gap, which impacts implementation machine learning (ML) models. Several have been employed and some hybridized to enhance index predictions. The objective this paper is systematically review deep techniques for spatiotemporal challenges. Methods: In review, methodological framework based on PRISMA flow was utilized in initial search terms were defined guide literature strategy online data sources (Scopus Google Scholar). inclusion criteria articles published English language, document type (articles conference papers), source (journal proceedings). exclusion book series books. authors’ complemented with ChatGPT-generated keywords reduce risk bias. Report synthesis achieved by keyword grouping using Microsoft Excel, leading sorting ascending order easy identification similar dissimilar keywords. Three independent researchers used research avoid bias collection synthesis. Articles retrieved 27 July 2024. Results: Out 374 articles, 80 selected as they line scope study. identified combination technique limitations processing nonlinear characteristics pollutants. ML models, such random forest, decision tree classifier among commonly predictions, promising results. Deep due hyper-parameter components, consist activation functions suitable data. emergence low-cost devices highlighted, addition use transfer federated Again, it highlighted that military activities fires impact O3 concentration, best-performing could be helpful developing predictive areas heavy activities. Limitation: This acknowledges challenges sources, there equally relevant materials other sources. choice creation subsequent filter limit articles.

Language: Английский

---

Revolutionizing air quality forecasting: Fusion of state-of-the-art deep learning models for precise classification

Urban Climate, Journal Year: 2025, Volume and Issue: 59, P. 102308 - 102308

Published: Jan. 28, 2025

Language: Английский

---

Accelerating urban street canyon wind flow predictions with deep learning method

Building Simulation, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 12, 2025

Language: Английский

---

Advances in environmental pollutant detection techniques: Enhancing public health monitoring and risk assessment

Environment International, Journal Year: 2025, Volume and Issue: 197, P. 109365 - 109365

Published: March 1, 2025

Accurate detection and monitoring of environmental pollutants are paramount importance for disease prevention public health. In recent years, the ever-expanding human activities industrial production have given rise to a sharp increase in complexity variety these pollutants, which pose significant threats well - being. Environmental stem from multiple sources, such as heavy metals, persistent organic inorganic non metallic emerging biological contaminants. Traditional technologies, though valuable their sensitivity accuracy, constrained by complex sample preparation, poor selectivity, absence standardized methods. On other hand, including nanotechnology, molecular methods, biosensors, Surface-Enhanced Raman Spectroscopy (SERS), multi-omics, big data analysis, offer promising solutions rapid sensitive pollutant detection. The establishment networks sharing platforms further enhances real time provides solid support health initiatives. Nonetheless, challenges persist, integration, exposure assessment, development cost-effective portable solutions. Future progress interdisciplinary approaches technology integration will be crucial advancing facilitating comprehensive prevention. This review systematically classifies showcases latest advancements offering critical insights protection.

Language: Английский

---

Mitigating Air Pollution Risks with Deep Learning: A Quantum-Optimized Approach for Nitrogen Dioxide Prediction in Los Angeles

Journal of Machine and Computing, Journal Year: 2025, Volume and Issue: unknown, P. 709 - 719

Published: April 5, 2025

Air pollution causes about seven million pre mature deaths globally every year, making it a critical issue that requires urgent attention. The key to mitigating its devastating effects lies in understanding nature, identifying sources and trends, predicting its. Accurate Real-time air forecasting is challenging task due spatiotemporal dynamics, requiring sophisticated modeling approaches. In our study, employed the Sequential Array-based Convolutional LSTM (SACLSTM) framework, which captures spatial temporal correlations by integrating deep CNNs for analysis with models prediction. To further enhance model's accuracy, optimized SACLSTM parameters using Quantum-based Draft Mongoose Optimization Algorithm (QDMOA). Using ten days of nitrogen dioxide (NO₂) data from Los Angeles County, developed sequential encoder-decoder network capable levels into future. By reformatting satellite quality images 5D tensor, achieved precise predictions concentrations across various locations time periods Angeles. Our results are thoroughly documented metrics visualizations, clearly demonstrating factors behind improved accuracy. comparison highlights effectiveness approach providing reliable forecasts.

Language: Английский

---

Review on environmental and mobility applications based real-time sensors

Deleted Journal, Journal Year: 2025, Volume and Issue: 7(4)

Published: April 3, 2025

Language: Английский

---

Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced Prediction

Water Air & Soil Pollution, Journal Year: 2025, Volume and Issue: 236(7)

Published: May 14, 2025

Language: Английский

---

Challenges of high-fidelity air quality modeling in urban environments – PALM sensitivity study during stable conditions

Geoscientific model development, Journal Year: 2024, Volume and Issue: 17(20), P. 7513 - 7537

Published: Oct. 29, 2024

Abstract. Urban air quality is an important part of human well-being, and its detailed precise modeling for efficient urban planning. In this study the potential sources errors in large eddy simulation (LES) runs PALM model stable conditions a high-traffic residential area Prague, Czech Republic, with focus on street canyon ventilation, are investigated. The evaluation simulations against observations obtained during dedicated campaign revealed unrealistically high concentrations modeled pollutants short period winter inversion episode. To identify reasons, sensitivities to changes meteorological boundary adjustments parameters were tested. adaptations included adding anthropogenic heat from cars, setting bottom limit subgrid-scale turbulent kinetic energy (TKE), adjusting profiles synthetic turbulence generator PALM, limiting time step. confirmed crucial role correct realistic conditions. Besides this, studied proved have significant impact these conditions, resulting decrease concentration overestimation range 30 %–66 % while exhibiting negligible influence results rest This suggested that inclusion or improvement processes desirable despite their most other Moreover, step limitation test numerical inaccuracies caused by discretization which occurred such extremely

Language: Английский

---

Phycoremediation: a path towards heavy metal bioremediation from wastewater

Journal of Chemical Technology & Biotechnology, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

Abstract Heavy metals (HMs) have emerged as a significant and complex water pollution problem globally. These pollutants are particularly concerning due to their teratogenic, mutagenic, poisonous carcinogenic properties, well non‐biodegradability. Traditional removal techniques often fall short in addressing these issues, leading search for more effective solutions. One promising alternative is the phycoremediation process, which employs microalgae remove HMs from wastewater. This method not only cost‐effective but also environmentally friendly, offering additional benefits of nutrient recovery polluted conversion into value‐added products. review delves capabilities remediating HM‐polluted water, examining various factors methods that affect process. Key improvements can enhance efficiency include immobilizing increase stability longevity, utilizing binary cultures harness synergistic effects implementing cellular genetic modifications boost HM uptake resilience. Moreover, integration algorithms artificial intelligence optimize processes by predicting controlling environmental conditions, enhancing precision effectiveness removal. The combination advanced strategies holds promise overcoming limitations conventional methods, positioning viable solution mitigating contamination bodies. © 2024 Author(s). Journal Chemical Technology Biotechnology published John Wiley & Sons Ltd on behalf Society Industry (SCI).

Language: Английский

---