چکیده مقاله
Floods are among the most destructive natural hazards worldwide, causing significant economic losses, infrastructure damage, and threats to human life Both North and South Carolina in the United States and several regions in Iran have experienced recurrent flood events, yet comparative studies across these geographically and climatically distinct areas remain limited This research addresses the urgent need for accurate flood prediction models to enhance sustainable water management and disaster preparedness in diverse socio environmental contexts We employ advanced artificial intelligence AI techniques, including machine learning ML and deep learning DL algorithms, to model and predict flood occurrences in selected watersheds of the Carolinas and Iran Multi source datasets encompassing historical precipitation, river discharge, topography, and land use patterns were integrated Models were trained and validated using cross regional data to capture both local and global flood dynamics Key findings indicate that deep learning models outperform conventional ML methods in predicting both flash and riverine floods, with high spatial temporal accuracy across regions Comparative analysis reveals that while flood drivers differ—urbanization and impervious surfaces dominate in the Carolinas, and rainfall intensity combined with topographic vulnerability dominate in Iranian watersheds—the AI driven models successfully identify high risk zones in both contexts These results demonstrate the potential of AI, ML, and DL to provide robust, scalable, and transferable flood prediction tools The study highlights the critical importance of integrating cutting edge computational techniques into global water management strategies, offering actionable insights for policymakers, urban planners, and disaster response agencies By bridging geographic and methodological gaps, this research contributes to advancing resilient and sustainable flood mitigation practices worldwide
کلیدواژهها
نویسندگان
Mohammad Sohrabi
Phd In Urban Planing geography
Alireza Bahrami
Phd Candidate In urban planning Geography Urban Islamic Azad University Semnan
محمدرضا زندمقدم
Associate Professor In Urban Planning Geography Islamic Azad University Semnan
شیوه ارجاع
Sohrabi, Mohammad and Bahrami, Alireza and Zandmoghadam, Mohammad Reza,1404,AI, Machine Learning, and Deep Learning Approaches for Comparative Flood Prediction in North and South Carolina and Iran: Implications for Sustainable Water Management,Third International Conference on applied researches in civil engineering, architecture and urban planning
ارائهشده در
مجموعه مقالات سومین کنفرانس بین المللی پژوهش های کاربردی در مهندسی عمران، معماری و شهرسازی30 آبان 1404