Abstract: Incluye ilustraciones, gráficos, tablas. ; This study presents an intelligent framework for assessing atmospheric dispersion in industrial accident scenarios involving chemical substances. The research focuses on modeling the dispersion of key chemicals, such as chlorine, methanol, and propane, under various accident conditions, including leaks, fires, and explosions. Atmospheric and contextual variables, such as wind speed, air temperature, tank specifications, and chemical release parameters, were thoroughly characterized to construct a robust database using experimental data and software simulations. Machine learning techniques were rigorously trained and tested to predict atmospheric dispersion, emphasizing hyperparameter optimization to enhance model performance. Dimensionality reduction methods, such as principal component analysis and correlation-based dimensionality reduction, were implemented to improve computational efficiency, reduce data noise, and maintain essential information. Results demonstrate the effectiveness of the proposed approach, with satisfactory predictions across all evaluated risk areas. Key contributions include the development of a replicable framework adaptable to diverse industrial scenarios, applying hyperparameter tuning to optimize model accuracy, and integrating dimensionality reduction techniques to streamline data processing. These advancements establish a foundation for future studies to incorporate additional chemicals and accident scenarios, improving the flexibility and reliability of atmospheric dispersion modeling. Future work will explore hybrid machine learning models and advanced dimensionality reduction methods to enhance the system’s applicability to complex industrial environments.
Relation: Y. Xie, J. Kuang, and Z. Wang, ‘‘Atmospheric dispersion model based on GIS and Gauss algorithm,’’ in Proc. 29th Chin. Control Conf., Jul. 2010, pp. 5022–5027.; J. B. Johnson, ‘‘An introduction to atmospheric pollutant dispersion modelling,’’ Environ. Sci. Proc., vol. 19, no. 1, p. 18, Jul. 2022. [Online]. Available: https://www.mdpi.com/2673-4931/19/1/18; EE Agency. (Oct. 14, 2023). Annex 5.3 Limitations and Uncertainties in Meteorological Estimates Using Dispersion Models. European Environment Agency. [Online]. Available: https://www.eea.europa.eu/publications/TEC11a/page015.html; Meteorological Data. ( Oct. 14, 2023 ). The South Coast Air Quality Management District. [Online]. Available: https://www.aqmd.gov/home/air-quality/meteorological-data; USEP Agency. ( Oct. 14, 2023 ). Air Quality Dispersion Modeling. Environmental Protection Agency. [Online]. Available: https://www.epa.gov/scram/air-quality-dispersion-modeling; R. Bhattacharya. ( Oct. 14, 2023 ). Atmospheric Dispersion. Asian Nuclear Safety Network. [Online]. Available: https://ansn.iaea.org/Common/Topics/OpenTopic.aspx?ID=13012; USEP Agency. ( Jul. 2023 ). Computer-Aided Management of Emergency Operations. United States Environmental Protection Agency. [Online]. Available: https://www.epa.gov/cameo; S. Brown. ( Oct. 14, 2023 ). Machine Learning, Explained. MIT Sloan. [Online]. Available: https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained; DOMO. ( Oct. 14, 2023 ). Machine Learning Basics. [Online]. Available: https://www.domo.com/glossary/what-are-machine-learning-basics; S. Abirami and P. Chitra, “Energy-efficient edge based real-time healthcare support system,” in The Digital Twin Paradigm for Smarter Systems and Environments: The Industry Use Cases (Advances in Computers), vol. 117, P. Raj and P. Evangeline, Eds., Amsterdam, The Netherlands : Elsevier, 2020, pp. 339–368. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0065245819300506; D. Basak, S. Pal, and D. C. Patranabis, “Support vector regression,” Neural Inf. Processing-Letters Rev., vol. 11, no. 10, pp. 203–224, 2007.; L. Breiman, “Random forests,” Mach. Learn., vol. 45, pp. 5–32, Oct. 2001.; K. Taunk, S. De, S. Verma, and A. Swetapadma, “A brief review of nearest neighbor algorithm for learning and classification,” in Proc. Int. Conf. Intell. Comput. Control Syst. (ICCS), May 2019, pp. 1255–1260.; D. Song, K. Lee, C. Phark, and S. Jung, “Spatiotemporal and layout-adaptive prediction of leak gas dispersion by encoding-prediction neural network,” Process Saf. Environ. Protection, vol. 151, pp. 365–372, Jul. 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0957582021002615; D. Ma and Z. Zhang, “Contaminant dispersion prediction and source estimation with integrated Gaussian-machine learning network model for point source emission in atmosphere,” J. Hazardous Mater., vol. 311, pp. 237–245, Jul. 2016. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0304389416302370; M. R. Delavar, A. Gholami, G. R. Shiran, Y. Rashidi, G. R. Nakhaeizadeh, K. Fedra, and S. Hatefi Afshar, “A novel method for improving air pollution prediction based on machine learning approaches: A case study applied to the capital city of Tehran,” ISPRS Int. J. Geo-Inf., vol. 8, no. 2, p. 99, 2019. [Online]. Available: https://www.mdpi.com/2220-9964/8/2/99; L. W. Young, C. N. Ho, S. K. Il, H. S. Ok, and K. J. Suk, “The reliability of pollution prediction with regression analysis and the possibility of dispersion and receptor models,” in Proc. 7th Int. Conf. Properties Appl. Dielectric Mater., vol. 3, 2003, pp. 1035–1038.; R. Miriyagalla, Y. Samarawickrama, D. Rathnaweera, L. Liyanage, D. Kasthurirathna, D. Nawinna, and J. L. Wijekoon, “On the effectiveness of using machine learning and Gaussian plume model for plant disease dispersion prediction and simulation,” in Proc. Int. Conf. Advancements Comput. (ICAC), Dec. 2019, pp. 317–322.; Ö. F. Ertuǧrul and M. E. Taǧluk, “A novel version of K nearest neighbor: Dependent nearest neighbor,” Appl. Soft Comput., vol. 55, pp. 480–490, Jun. 2017. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1568494617300984; I. Mokhtari, W. Bechkit, H. Rivano, and M. R. Yaici, “Uncertainty-aware deep learning architectures for highly dynamic air quality prediction,” IEEE Access, vol. 9, pp. 14765–14778, 2021.; S. K. Pal and S. Mitra, “Multilayer perceptron, fuzzy sets, and classification,” IEEE Trans. Neural Netw., vol. 3, no. 5, pp. 683–697, Sep. 1992.; T. Abbott, “Dark energy survey year 1 results: Constraints on extended cosmological models from galaxy clustering and weak lensing,” Phys. Rev. D, Part. Fields, vol. 99, no. 12, Jun. 2019, Art. no. 123505, doi:10.1103/PhysRevD.99.123505.; E. M. R. Devi, R. Shanthakumari, R. Rajadevi, V. Hari, and S. Lakshmanan, “Forecasting air quality pollutants using ensemble learning models,” in Proc. 2nd Int. Conf. Vis. Towards Emerg. Trends Commun. Netw. Technol. (ViTECoN), May 2023, pp. 1–6.; Z. Dou, Z. Liu, L. Li, H. Zhou, Q. Wang, J. Zhang, and L. Chen, “Atmospheric dispersion prediction of accidental release: A review,” Emergency Manage. Sci. Technol., vol. 2, no. 1, pp. 1–20, 2022, doi:10.48130/EMST-2022-0009.; M. F. El-Amin, “Detection of hydrogen leakage using different machine learning techniques,” in Proc. 20th Learn. Technol. Conf., Jan. 2023, pp. 74–79.; M. F. El-Amin and A. Subasi, “Forecasting a small-scale hydrogen leakage in air using machine learning techniques,” in Proc. 2nd Int. Conf. Comput. Inf. Sci. (ICCIS), Oct. 2020, pp. 1–5.; T. Pinthong, M. Ketcham, T. Ganokratanaa, P. Pramkeaw, and N. Chumuang, “Globally harmonized system label detection using color segmentation,” in Proc. IEEE Int. Conf. Cybern. Innov. (ICCI), Mar. 2023, pp. 1–6.; R. Jones, W. Lehr, D. Simecek-Beatty, and M. Reynolds, ALOHA (Areal Locations of Hazardous Atmospheres) 5.4.4: Technical Documentation. Washington, DC, USA : NOAA Office of Response and Restoration, 2013.; I. D. Rodionov, M. A. Gomorev, I. P. Rodionova, A. I. Rodionov, V. L. Shapovalov, D. V. Shestakov, and M. G. Golubkov, “Remote detection of emergency emissions and gas leaks,” Russian J. Phys. Chem. B, vol. 18, no. 5, pp. 1389–1395, Oct. 2024.; R. H. Vaivads, M. F. Bardon, and V. Battista, “A computational study of the flammability of methanol and gasoline fuel spills on hot engine manifolds,” Fire Saf. J., vol. 28, no. 4, pp. 307–322, Jun. 1997.; I. Mohammadfam, O. Kalatpour, and K. Gholamizadeh, “Quantitative assessment of safety and health risks in HAZMAT road transport using a hybrid approach: A case study in Tehran,” ACS Chem. Health Saf., vol. 27, no. 4, pp. 240–250, Jul. 2020.; M. I. V. Rada, B. G. Granados, C. G. Quintero M, C. Viloria-Nũńez, J. Cardona-Peña, and M. Á. J. Paba, “Atmospheric dispersion prediction for toxic gas clouds by using machine learning approaches,” in Proc. Int. Conf. Smart Technol., Syst. Appl. Cham, Switzerland : Springer, Jan. 2023, pp. 185–198.; Semana. ( Feb. 2023 ). Tren Cargado De Gas Propano Se Descarril En Florida: Autoridades Buscan Evitar Una Explosin. [Online]. Available: https://www.semana.com/mundo/noticias-estados-unidos/articulo/tren-cargado-de-gas-propano-se-descarrilo-en-florida-autoridades-buscan-evitar-una-explosion/202340/; ( Jun. 2022 ). Chlorine Gas Leak Kills 13 in Jordan Port. [Online]. Available: https://www.france24.com/en/live-news/20220628-chlorine-gas-leak-kills-13-in-jordan-port; A. Phillips. ( Mar. 2023 ). Ohio River Disaster As Barge With Tons of Toxic Methanol Sinks. [Online]. Available: https://www.newsweek.com/ohio-river-disaster-barge-toxic-methanol-louisville-kentucky-1791064; ( 2023 ). Video Del Momento Exacto En El Que Se Accident Un Camin Lleno De Cloro En El Tnel De Occidente2023. [Online]. Available: https://telemedellin.tv/video-accidente-camion-tunel-occidente/628708/; L. R. Online. ( Mar. 2021 ). (Videos) Se Incendia Camin Con 800 Litros De Metanol En CDMX. [Online]. Available: https://www.razon.com.mx/ciudad/videos-incendia-camion-800-litros-metanol-cdmx-426522; T. Nguyen and Perez-CarrilloMelissa. ( Mar. 2023 ). Train Carrying Propane Derailed Near Florida Airport; No Leaks Detected, Officials Say. [Online]. Available: https://www.usatoday.com/story/news/nation/2023/02/28/sarasota-florida-derailment-propane-officials/11368082002/; S. Wold, K. H. Esbensen, and P. Geladi, “Principal component analysis,” Chemometric Intell. Lab. Syst., vol. 2, nos. 1–3, pp. 37–52, Aug. 1987. [Online]. Available: https://www.sciencedirect.com/science/article/pii/0169743987800849; Optuna. ( Oct. 26, 2023 ). Optuna: A Hyperparameter Optimization Framework. [Online]. Available: https://optuna.readthedocs.io/en/stable/; https://hdl.handle.net/20.500.12585/13676
Processing Request
No Comments.