ENHANCING ORSEC EMERGENCY RESPONSE PLANNING IN ALGERIA THROUGH AI-POWERED DECISION SUPPORT: THE EMHELP APPROACH
Chaouki Boulekdam1,2, Abdeldjalil Belkendil1, Mohamed Zouidi1, Soumia Bendekkoum3, Aissa Lamri-Zeggar5, Nadjet Chettih1,4, Kaouther Achouri1, Houcine Bougrine1, Amer Zeghmar1, Abdelkader Moudjari5
1Centre de Recherche en Aménagement du Territoire (CRAT), Campus Zouaghi Slimane, Constantine, Algeria
2University Abdelhamid Mehri-Constantine 2, LIRE Laboratory, Constantine, Algeria
3Constantine 3 University – Salah Boubnider, Algeria
4Laboratοry of Applied Mathematics and Modeling, Department οf Mathematics, Faculty οf Exact Sciences, University of Brothers Mentouri Cοnstantine1, Constantine, Algeria.
5Ecole normale supérieure de Constantine Algeria, Pôle universitaire de Constantine 3 Ali mendjeli, Algeria
Abstract: Disaster risk management is an increasingly critical national concern in Algeria, driven by the rising frequency and severity of climatic, technological, and biological threats. With the adoption of Law No. 24-04 on February 26, 2024, Algeria established a comprehensive legal framework to enhance disaster prevention, intervention, and resilience. Central to this framework is the ORSEC (Organisation de la Réponse de Sécurité Civile) plan, a vital emergency response system designed to address large-scale crises, including earthquakes, floods, wildfires, industrial accidents, and public health emergencies. The ORSEC plan aims to ensure a coordinated and efficient response by integrating multiple stakeholders, such as governmental agencies, emergency services, and private organisations. However, its implementation faces significant operational challenges, including delayed decision-making, poor inter-agency coordination, limited integration of real-time data, and reliance on traditional protocols and human expertise. These issues are compounded by the growing impacts of climate change, rapid urbanisation, and infrastructure vulnerabilities, which amplify the need for a robust and adaptive risk management strategy. To address these challenges, this research proposes EMHelp, an AI-powered decision-support system designed to enhance ORSEC planning and execution in Algeria. EMHelp leverages multi-risk databases, machine learning (ML), and deep learning (DL) techniques, alongside scenario-based simulations, to generate optimised response strategies. A human operator validates the best scenario, which is then translated into a real-time action plan. This approach aligns with Algeria’s national legal mandates while introducing modern capabilities for predictive risk assessment, operational agility, and resource optimisation. By integrating AI-driven predictive models, EMHelp improves decision-making, enhances inter-agency collaboration, and mitigates risks more effectively. This study contributes to building a more resilient, intelligent, and responsive disaster management system for Algeria, addressing contemporary risk management needs and ensuring proactive, coordinated, and adaptive responses to crises.
Keywords: ORSEC; Law 24-04; Algeria; Disaster Risk Management; Artificial Intelligence; EMHelp; Emergency Response; Decision Support System.
VOLUME 10 ISSUE 03 2026: 146 – 159