Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems
Tornado damage estimation is important for providing insights into tornado studies and assisting rapid disaster response. However, it is challenging to precisely estimate tornado damage because of the large volumes of perishable data. This study presents data-driven approaches to tornado damage esti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/9/1669 |
| _version_ | 1797536409360269312 |
|---|---|
| author | Zhiang Chen Melissa Wagner Jnaneshwar Das Robert K. Doe Randall S. Cerveny |
| author_facet | Zhiang Chen Melissa Wagner Jnaneshwar Das Robert K. Doe Randall S. Cerveny |
| author_sort | Zhiang Chen |
| collection | DOAJ |
| description | Tornado damage estimation is important for providing insights into tornado studies and assisting rapid disaster response. However, it is challenging to precisely estimate tornado damage because of the large volumes of perishable data. This study presents data-driven approaches to tornado damage estimation using imagery collected from Unpiloted Aerial Systems (UASs) following the 26 June 2018 Eureka Kansas tornado. High-resolution orthomosaics were generated from Structure from Motion (SfM). We applied deep neural networks (DNNs) on the orthomosaics to estimate tornado damage and assessed their performance in four scenarios: (1) object detection with binary categories, (2) object detection with multiple categories, (3) image classification with binary categories, and (4) image classification with multiple categories. Additionally, two types of tornado damage heatmaps were generated. By directly stitching the resulting image tiles from the DNN inference, we produced the first type of tornado damage heatmaps where damage estimates are accurately georeferenced. We also presented a Gaussian process (GP) regression model to build the second type of tornado damage heatmap (a spatially continuous tornado damage heatmap) by merging the first type of object detection and image classification heatmaps. The GP regression results were assessed with ground-truth annotations and National Weather Service (NWS) ground surveys. This detailed information can help NWS Weather Forecast Offices and emergency managers with their damage assessments and better inform disaster response and recovery. |
| first_indexed | 2024-03-10T11:59:19Z |
| format | Article |
| id | doaj.art-d21648b5683943b8b1a0f8d37e5e8425 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T11:59:19Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d21648b5683943b8b1a0f8d37e5e84252023-11-21T17:05:10ZengMDPI AGRemote Sensing2072-42922021-04-01139166910.3390/rs13091669Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial SystemsZhiang Chen0Melissa Wagner1Jnaneshwar Das2Robert K. Doe3Randall S. Cerveny4School of Earth and Space Exploration, Arizona State University, Tempe, AZ 85281, USACooperative Institute for Mesoscale Meteorological Studies, The University of Oklahoma, Norman, OK 73019, USASchool of Earth and Space Exploration, Arizona State University, Tempe, AZ 85281, USASchool of Environmental Sciences, University of Liverpool, Liverpool L69 3BX, UKSchool of Geographical Sciences and Urban Planning, Arizona State University, Tempe, AZ 85281, USATornado damage estimation is important for providing insights into tornado studies and assisting rapid disaster response. However, it is challenging to precisely estimate tornado damage because of the large volumes of perishable data. This study presents data-driven approaches to tornado damage estimation using imagery collected from Unpiloted Aerial Systems (UASs) following the 26 June 2018 Eureka Kansas tornado. High-resolution orthomosaics were generated from Structure from Motion (SfM). We applied deep neural networks (DNNs) on the orthomosaics to estimate tornado damage and assessed their performance in four scenarios: (1) object detection with binary categories, (2) object detection with multiple categories, (3) image classification with binary categories, and (4) image classification with multiple categories. Additionally, two types of tornado damage heatmaps were generated. By directly stitching the resulting image tiles from the DNN inference, we produced the first type of tornado damage heatmaps where damage estimates are accurately georeferenced. We also presented a Gaussian process (GP) regression model to build the second type of tornado damage heatmap (a spatially continuous tornado damage heatmap) by merging the first type of object detection and image classification heatmaps. The GP regression results were assessed with ground-truth annotations and National Weather Service (NWS) ground surveys. This detailed information can help NWS Weather Forecast Offices and emergency managers with their damage assessments and better inform disaster response and recovery.https://www.mdpi.com/2072-4292/13/9/1669deep learninggaussian processtornado damagedamage assessmentUAS |
| spellingShingle | Zhiang Chen Melissa Wagner Jnaneshwar Das Robert K. Doe Randall S. Cerveny Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems Remote Sensing deep learning gaussian process tornado damage damage assessment UAS |
| title | Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems |
| title_full | Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems |
| title_fullStr | Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems |
| title_full_unstemmed | Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems |
| title_short | Data-Driven Approaches for Tornado Damage Estimation with Unpiloted Aerial Systems |
| title_sort | data driven approaches for tornado damage estimation with unpiloted aerial systems |
| topic | deep learning gaussian process tornado damage damage assessment UAS |
| url | https://www.mdpi.com/2072-4292/13/9/1669 |
| work_keys_str_mv | AT zhiangchen datadrivenapproachesfortornadodamageestimationwithunpilotedaerialsystems AT melissawagner datadrivenapproachesfortornadodamageestimationwithunpilotedaerialsystems AT jnaneshwardas datadrivenapproachesfortornadodamageestimationwithunpilotedaerialsystems AT robertkdoe datadrivenapproachesfortornadodamageestimationwithunpilotedaerialsystems AT randallscerveny datadrivenapproachesfortornadodamageestimationwithunpilotedaerialsystems |