2026-10-14T08:40:24Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34027578 2026-09-29T20:13:02Z category_7 category_734 category_931 category_135 portal_63 item_type_3 month_year_09_2026

Threat Zones Identification and Consequence Modeling Approach of Ammonia Dispersion via Machine Learning Zohaib Atiq Khan (25138857) Muhammad Imran Rashid (17583317) Abdul Rehman (604331) Muhammad Athar (9914163) Muhammad Nawaz (2246698) Medicine Biological Sciences not elsewhere classified Information Systems not elsewhere classified Computational Biology world industrial site values exceeding 0 surrogate model trained scenarios provides first preliminary consequence assessment enabling quick decisions consequence modeling approach available aloha software ammonia dispersion using aloha simulation software aloha simulation outputs trained ann surrogate target output variables rapid scenario evaluation ann surrogate model save crucial time inference time demonstrates threat zones identification performance metrics represent demonstrating excellent agreement comprehensive data set 2 < sup toxic chemicals study presents significant reduction process industries new framework hand information 000 times Release of toxic chemicals from process industries is a threat to our environment, and simulating such scenarios provides first-hand information to make decisions regarding measures to tackle such situations. The available ALOHA software for such simulations is time-consuming. Therefore, this study presents a new framework for ammonia dispersion using a multioutput artificial neural network (ANN) surrogate model trained on 4989 scenarios simulated via the readily available simulation software to save crucial time, enabling quick decisions. The simulation is based on a real-world industrial site in Sheikhupura, Pakistan, and results in the generation of a comprehensive data set. The data set has taken into consideration various input variables and studied their effect on target output variables. Next, the ANN surrogate model is optimized via hyperparameter tuning, and its performance is evaluated using standard regression metrics, demonstrating excellent agreement with ALOHA simulation outputs, with R2 values exceeding 0.98 and mean absolute percentage errors below 2.6% for all output parameters. These performance metrics represent the agreement between the ANN surrogate model and ALOHA simulation outputs. Comparing the speed of the trained ANN surrogate over the ALOHA simulation software, a superiority of 27,000 times is observed, that is, predictions are made in milliseconds. This significant reduction in inference time demonstrates the capability of the proposed ANN surrogate model to provide a rapid approximation of ALOHA simulation outputs for rapid scenario evaluation and preliminary consequence assessment. 2026-09-29T00:00:00Z Dataset Dataset 10.1021/acs.chas.6c00015.s001 https://figshare.com/articles/dataset/Threat_Zones_Identification_and_Consequence_Modeling_Approach_of_Ammonia_Dispersion_via_Machine_Learning/34027578 CC BY-NC 4.0