CNN-Based Building Type Classification into EF Scale Categories to Support Tornado Damage Assessments
Bibliographic Data
| ID | 21738240 |
|---|---|
| Authors | Jooho Kim (0000-0002-0395-5107, NOAA Oceanic and Atmospheric Research), Ruthvik Kanumuri (Texas A&M University), Joshua J Hatzis (0000-0002-8291-6551, University of Wisconsin–Milwaukee), Sunyoung Park (0000-0002-6292-5514, Texas A&M University), Patrick A Campbell (0000-0001-8571-9222, NOAA Oceanic and Atmospheric Research), Kristin M Calhoun (0000-0003-2858-256X, NOAA Oceanic and Atmospheric Research) |
| Year | 2026 |
| Volume | 27 |
| Issue | 3 |
| Publication date | 2026-08-01 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Natural Hazards Review (JOURNAL) |
| Journal identifiers | ISSN: 1527-6988 • E-ISSN: 1527-6996 |
| Publisher | American Society of Civil Engineers (ASCE) (PUBLISHER • US) |
| DOI | 10.1061/nhrefo.nheng-2701 |
| OpenAlex | W7163888446 |
| Language | EN |
| References cited | 54 |
Accurate assessment of tornado impacts requires detailed information on building characteristics that influence vulnerability. This study investigates a convolutional neural network (CNN)-based approach to classify nonresidential buildings into enhanced Fujita (EF) damage categories using image data. Three deep learning architectures—CNN, ConvNeXt, and ResNet50—were evaluated on a data set representing 11 EF building categories. ResNet50 achieved the highest overall accuracy of 83%, with F1 scores above 0.75 in 8 of 11 categories. The results demonstrate the feasibility of image-based classification as an initial step toward enhancing structural data sets used in hazard modeling and disaster planning (e.g., FEMA Hazus-MH, engineering fragility curve, etc). This work highlights the potential of deep learning methods to supplement structural data. Future research will expand model scalability and incorporate spatial metadata to improve applicability for operational risk assessment
Convolutional neural network · Data set · Fragility · Geospatial analysis · Hazard · Hazard analysis · Metadata · Tornado · Vulnerability assessment · Seismology and Earthquake Studies · Tropical and Extratropical Cyclones Research · Wind and Air Flow Studies
Building instance classification using street view images
Analyzing the Influence of Urban Street Greening and Street Buildings on Summertime Air Pollution Based on Street View Image Data
Towards Detecting Building Facades with Graffiti Artwork Based on Street View Images
A Postearthquake Multiple Scene Recognition Model Based on Classical SSD Method and Transfer Learning
Validation of Time-Dependent Repair Recovery of the Building Stock Following the 2011 Joplin Tornado
Detecting and Geolocating City-Scale Soft-Story Buildings by Deep Machine Learning for Urban Seismic Resilience
An Agent-Based Modeling Approach to Protective Action Decision-Related Travel during Tornado Warnings
Building Classification Using Random Forest to Develop a Geodatabase for Probabilistic Hazard Information
Why data for a political-industrial ecology of cities
| Citation velocity | historical |
|---|---|
| Highly cited | No |