Hazardous atmospheric dispersion in urban areas: A Deep Learning approach for emergency pollution forecast

Mendil, Mouhcine; Leirens, S.; Armand, Patrick; Duchenne, Christophe

doi:10.1016/j.envsoft.2022.105387

Cited by 18 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, monitoring the concentration and leakage of pollutants (Fung et al, 2019) and development of safe and efficient methods (Fung et al, 2019) to reduce the exposure of humans and the detrimental risks for the environment, with fewer accidents provoked by hazardous substances (Wong et al, 2018;Wang et al, 2020), are becoming a priority in the implementation of safety plan management in many sectors of the economy (Binajjaj et al, 2018). In pollutant discharge events, immediate, precise, and intelligent intervention is needed to alarm, prevent, and control hazardous leakage (Mendil et al, 2022;Wang B. et al, 2023). Due to the fact that humans cannot identify in time possible threats, because the majority of gases are odorless, colorless, and tasteless (Visvanathan et al, 2018), implementation in environmental monitoring and detection of artificial intelligence based devices is getting more popular (Daam et al, 2019;Emaminejad and Akhavian, 2022).…”

Section: Maximizing Safety In Hazardous Environments With Ai-driven M...mentioning

confidence: 99%

“…The ventilation system has a high removal rate of the hazardous airborne particles, which is done in a short time with low power consumption. Mendil et al (2022) proposed a machine learning (ML)-based surrogate model for transport and dispersion of air pollutants that can predict, fast and accurately, the concentration and dose of pollutants in urban areas. Asha et al (2022) designed an IoT and ML based model (ETAPM-AIT) for air quality monitoring that uses a sensor array for eight pollutants, such as NH 3 , CO, NO 2 , CH 4 , CO 2 , and PM 2.5 .…”

Section: Maximizing Safety In Hazardous Environments With Ai-driven M...mentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management

Popescu,

Mansoor,

Wani

et al. 2024

Front. Environ. Sci.

View full text Add to dashboard Cite

Detecting hazardous substances in the environment is crucial for protecting human wellbeing and ecosystems. As technology continues to advance, artificial intelligence (AI) has emerged as a promising tool for creating sensors that can effectively detect and analyze these hazardous substances. The increasing advancements in information technology have led to a growing interest in utilizing this technology for environmental pollution detection. AI-driven sensor systems, AI and Internet of Things (IoT) can be efficiently used for environmental monitoring, such as those for detecting air pollutants, water contaminants, and soil toxins. With the increasing concerns about the detrimental impact of legacy and emerging hazardous substances on ecosystems and human health, it is necessary to develop advanced monitoring systems that can efficiently detect, analyze, and respond to potential risks. Therefore, this review aims to explore recent advancements in using AI, sensors and IOTs for environmental pollution monitoring, taking into account the complexities of predicting and tracking pollution changes due to the dynamic nature of the environment. Integrating machine learning (ML) methods has the potential to revolutionize environmental science, but it also poses challenges. Important considerations include balancing model performance and interpretability, understanding ML model requirements, selecting appropriate models, and addressing concerns related to data sharing. Through examining these issues, this study seeks to highlight the latest trends in leveraging AI and IOT for environmental pollution monitoring.

show abstract

Section: Maximizing Safety In Hazardous Environments With Ai-driven M...mentioning

confidence: 99%

Section: Maximizing Safety In Hazardous Environments With Ai-driven M...mentioning

confidence: 99%

Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management

Popescu,

Mansoor,

Wani

et al. 2024

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Training set can come from experimental data or, more conveniently, simulation (CFD, Monte Carlo). Researches by French teams include the prediction of the dispersion of atmospheric pollutants/radionuclides at short range (Nony, 2021), in city streets (Mendil, 2021) and in the Fukushima region (Korsakissok, 2020). Metamodel has been used likewise for the dispersion of uranium in water (Lopez, 2021).…”

Section: Modellingmentioning

confidence: 99%

Artificial intelligence and radiation protection. A game changer or an update?

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) is regarded as one of the most disruptive technology of the century and with countless applications. What does it mean for radiation protection? This article describes the fundamentals of machine learning (ML) based methods and presents the inaugural applications in different fields of radiation protection. It is foreseen that the usage of AI will increase in radiation protection. Consequently, this article explores some of the benefits and also the potential barriers and questions, including ethical ones, that can come out. The article proposes that collaboration between radiation protection professionals and data scientist experts can accelerate and guide the development of the algorithms for effective scientific and technological outcomes.

show abstract

“…If LPDMs are to be used in inverse modelling studies using very large data sets, methods must be developed to overcome their poor scaling with number of observations. Machine learning has been shown to be useful for efficiently addressing a number of problems in studies using atmospheric dispersion models, including the correction of bias (Ivatt and Evans, 2020) and urban-scale pollution modelling (Mendil et al, 2022). LPDM emulators have been developed to simulate volcanic ash plumes or releases from nuclear plants.…”

Section: Introductionmentioning

confidence: 99%

A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME

Fillola

Santos-Rodríguez

Manning

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Lagrangian particle dispersion models (LPDMs) have been used extensively to calculate source-receptor relationships (“footprints”) for use in applications such as greenhouse gas (GHG) flux inversions. Because a single model simulation is required for each data point, LPDMs do not scale well to applications with large data sets such as flux inversions using satellite observations. Here, we develop a proof-of-concept machine learning emulator for LPDM footprints over a ~350 km by 230 km region around an observation point, and test it for a range of in situ measurement sites from around the world. As opposed to previous approaches to footprint approximation, it does not require the interpolation or smoothing of footprints produced by the LPDM. Instead, the footprint is emulated entirely from meteorological inputs. This is achieved by independently emulating the footprint magnitude at each grid cell in the domain using gradient-boosted regression trees (GBRTs) with a selection of meteorological variables as inputs. The emulator is trained based on footprints from the UK Met Office Numerical Atmospheric dispersion Modelling Environment (NAME) for 2014 and 2015, and the emulated footprints are evaluated against hourly NAME output from 2016 and 2020. When compared to CH4 concentration time series generated by NAME, we show that our emulator achieves a mean R-squared score of 0.69 across all sites investigated between 2016 and 2020. The emulator can predict a footprint in around 10 ms, compared to around 10 minutes for the 3D simulator. This simple and interpretable proof-of-concept emulator demonstrates the potential of machine learning for LPDM emulation.

show abstract

Hazardous atmospheric dispersion in urban areas: A Deep Learning approach for emergency pollution forecast

Cited by 18 publications

References 26 publications

Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management

Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management

Artificial intelligence and radiation protection. A game changer or an update?

A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME

Contact Info

Product

Resources

About