Work

AI Driven Impact Assessment of Shaheen Tropical Cyclone Using Very High-Resolution Satellite Data

Year: 2025

Type: article

Abstract: Understanding tropical cyclones (TCs) impact is critical for implementing effective post–cyclone management methods. While previous researches have assessed the effects of TCs in Oman, this study uniquely examines and quantifies the impact of the Shaheen tropical cyclone (STC) using advanced image resolution and analysis, including artificial intelligence in the form of Multiple Deep learning models, as well as using very high-resolution (41 cm) satellite imagery. This study found significant vegetation loss, with 85.8 ha (51.3%) of dense and 153.2 ha (18.9%) of sparse vegetation destroyed in Al–Khabourah. Al–Suwaiq was the most affected wilayat, losing 3160 ha (55.5%) of shrubs and grasses, 1713.9 ha (67.2%) of dense vegetation, and 609.8 ha (16.6%) of sparse vegetation. The cyclone also caused drastic increases in water surface areas, especially in Al–Khabourah by 496.82 ha and Al–Suwaiq by 180.8 ha. Additionally, 32% (42.73 ha) of buildings in Al–Khabourah and 67.5% (6.4 ha) of fishermen’s coastal structures were damaged. The deep learning model accurately classified land cover types with high precision (1, 0.93, 0.89, and 0.9 for barren, dense, sparse vegetation, and buildings, respectively) and an overall accuracy of 94%. Digital Elevation Models and Ruggedness Index maps identified flood-prone zones, especially in coastal areas. Ground validation confirmed model performance with an overall accuracy of 94%. This study demonstrates the effective application of artificial intelligence in the form of multiple deep learning techniques for detecting and mapping various objects, including vegetation, buildings, and water bodies, in the aftermath of the impact of TC. These insights can support government agencies and landowners in developing more effective post–cyclone planning and climate resilience strategies, especially in urban and coastal regions. This study used high–resolution satellite imagery to assess the impact of the Shaheen tropical cyclone. The study fused pre–impact and post–impact imagery, which was processed and used to train AI models to detect changes in vegetation, buildings, and water surfaces. The AI models achieved high accuracy (94%), integrating terrain analysis to map flood zones. Results showed severe damage, including a 55.5% loss of shrubs in Al–Suwaiq and 32% building damage in Al–Khabourah. The AI–driven impact assessment offers valuable insights for planning climate resilience to help protect urban areas and biodiversity. Pre–impact and post–impact satellite imagery was acquired to carry out the impact assessment of Shaheen Tropical Cyclone (STC). AI in the form of Multiple Deep learning models was trained with different epochs and applied in the study area using multilayer backbone models. Impact assessment of STC was carried out on vegetation, buildings, and water bodies extracted using these models. In addition to a drastic increase in water bodies and destruction of vegetation, damage to buildings was also recorded in the study. Spatial maps from hot and cold spots analysis and flood inundation analysis were constructed to identify the areas affected in the same scenarios.

Source: Earth Systems and Environment

DOI: 10.1007/s41748-025-00938-y

Authors: Yaseen Al-Mulla, Mohammed Al-Muqaimi, Ahsan Ali, Farid Melgani, Krishna Parimi, Thuwaiba Al-Wahaibi

Institutions: Sultan Qaboos University, University of Trento

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDGs: Climate action, Life on land, Sustainable cities and communities

Open Access status: hybrid

Estimated APC paid: $4,090