Citation: Alam, E.; Sufi, F.; Islam, A.R.M.T. A Scenario-Based Case Study: Using AI to Analyze Casualties from Landslides in Chittagong Metropolitan Area, Bangladesh. Sustainability 2023, 15, 4647. https://doi.org/10.3390/ su15054647 Academic Editors: Stefano Morelli, Veronica Pazzi and Mirko Francioni Received: 6 January 2023 Revised: 22 February 2023 Accepted: 23 February 2023 Published: 6 March 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). sustainability Article A Scenario-Based Case Study: Using AI to Analyze Casualties from Landslides in Chittagong Metropolitan Area, Bangladesh Edris Alam 1,2, * , Fahim Sufi 3, * and Abu Reza Md. Towfiqul Islam 4 1 Faculty of Resilience, Rabdan Academy, Abu Dhabi P.O. Box 114646, United Arab Emirates 2 Department of Geography and Environmental Studies, University of Chittagong, and Disaster Action and Development Organisation (DADO), Chittagong 4331, Bangladesh 3 School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3000, Australia 4 Department of Disaster Management, Begum Rokeya University, Rangpur 5400, Bangladesh * Correspondence: ealam@ra.ac.ae (E.A.); research@fahimsufi.com (F.S.) Abstract: Understanding the complex dynamics of landslides is crucial for disaster planners to make timely and effective decisions that save lives and reduce the economic impact on society. Using the landslide inventory of the Chittagong Metropolitan Area (CMA), we have created a new artificial intelligence (AI)-based insight system for the town planners and senior disaster recovery strategists of Chittagong, Bangladesh. Our system generates dynamic AI-based insights for a range of complex scenarios created from 7 different landslide feature attributes. The users of our system can select a particular kind of scenario out of the exhaustive list of 1.054 × 10 41 possible scenario sets, and our AI-based system will immediately predict how many casualties are likely to occur based on the selected kind of scenario. Moreover, an AI-based system shows how landslide attributes (e.g., rainfall, area of mass, elevation, etc.) correlate with landslide casualty by drawing detailed trend lines by performing both linear and logistic regressions. According to the literature and the best of our knowledge, our CMA scenario-based AI insight system is the first of its kind, providing the most comprehensive understanding of landslide scenarios and associated deaths and damages in the CMA. The system was deployed on a wide range of platforms including Android, iOS, and Windows systems so that it could be easily adapted for strategic disaster planners. The deployed solutions were handed down to 12 landslide strategists and disaster planners for evaluations, whereby 91.67% of users found the solution easy to use, effective, and self-explanatory while using it via mobile. Keywords: AI; landslides; causalities; hazards 1. Introduction Landslides are natural phenomena that have an adverse effect on human life, as well as the economy [1]. For the purpose of reducing the negative impact of landslides and to have an increased level of disaster preparedness [2], it is crucial to have a multi- dimensional understanding the attributes of landslides. The complex nature of landslide dynamics makes it extremely difficult to understand the impact of a particular type of landslide. Bangladesh is susceptible to a variety of natural and human-induced hazards including tropical cyclones, floods, droughts, earthquakes, tsunamis, and landslides [2]. In particular, landslides have become recurrent phenomena in the Southeast Bangladesh in recent decades. Therefore, the Government of Bangladesh (GoB) and its coastal residents have been engaged in reducing resultant deaths from tropical cyclones, but landslides have still caused over 500 deaths in Southeast Bangladesh with the majority occurring in informal settlements in Chittagong and Rangamati districts since 2000. The root causes contributing to the vulnerability of three different communities in the southeast part of Bangladesh. These communities are Bengali, Tribal, and Rohingya refugees, [3] and effective local risk governance was also promulgated [4]. Studies were also conducted to identify the root causes and impacts of landslides using qualitative methods (e.g., Sustainability 2023, 15, 4647. https://doi.org/10.3390/su15054647 https://www.mdpi.com/journal/sustainability