A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems
Disaster management systems require accurate disaster monitoring and prediction services to reduce damages caused by natural disasters. Digital twins of natural environments can provide the services for the systems with physics-based and data-driven disaster models. However, the digital twins might...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/13/4774 |
| _version_ | 1797442000958521344 |
|---|---|
| author | Seong-Jin Yun Jin-Woo Kwon Won-Tae Kim |
| author_facet | Seong-Jin Yun Jin-Woo Kwon Won-Tae Kim |
| author_sort | Seong-Jin Yun |
| collection | DOAJ |
| description | Disaster management systems require accurate disaster monitoring and prediction services to reduce damages caused by natural disasters. Digital twins of natural environments can provide the services for the systems with physics-based and data-driven disaster models. However, the digital twins might generate erroneous disaster prediction due to the impracticability of defining high-fidelity physics-based models for complex natural disaster behavior and the dependency of data-driven models on the training dataset. This causes disaster management systems to inappropriately use disaster response resources, including medical personnel, rescue equipment and relief supplies, to ensure that it may increase the damages from the natural disasters. This study proposes a digital twin architecture to provide accurate disaster prediction services with a similarity-based hybrid modeling scheme. The hybrid modeling scheme creates a hybrid disaster model that compensates for the errors of physics-based prediction results with a data-driven error correction model to enhance the prediction accuracy. The similarity-based hybrid modeling scheme reduces errors from the data dependency of the hybrid model by constructing a training dataset using similarity assessments between the target disaster and the historical disasters. Evaluations in wildfire scenarios show that the digital twin decreases prediction errors by approximately 50% compared with those of the existing schemes. |
| first_indexed | 2024-03-09T12:35:27Z |
| format | Article |
| id | doaj.art-f365e5504da14266acb3720f1995f987 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:35:27Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f365e5504da14266acb3720f1995f9872023-11-30T22:25:02ZengMDPI AGSensors1424-82202022-06-012213477410.3390/s22134774A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management SystemsSeong-Jin Yun0Jin-Woo Kwon1Won-Tae Kim2Future Convergence Engineering Major, Department of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaFuture Convergence Engineering Major, Department of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaFuture Convergence Engineering Major, Department of Computer Science and Engineering, Korea University of Technology and Education, Cheonan 31253, KoreaDisaster management systems require accurate disaster monitoring and prediction services to reduce damages caused by natural disasters. Digital twins of natural environments can provide the services for the systems with physics-based and data-driven disaster models. However, the digital twins might generate erroneous disaster prediction due to the impracticability of defining high-fidelity physics-based models for complex natural disaster behavior and the dependency of data-driven models on the training dataset. This causes disaster management systems to inappropriately use disaster response resources, including medical personnel, rescue equipment and relief supplies, to ensure that it may increase the damages from the natural disasters. This study proposes a digital twin architecture to provide accurate disaster prediction services with a similarity-based hybrid modeling scheme. The hybrid modeling scheme creates a hybrid disaster model that compensates for the errors of physics-based prediction results with a data-driven error correction model to enhance the prediction accuracy. The similarity-based hybrid modeling scheme reduces errors from the data dependency of the hybrid model by constructing a training dataset using similarity assessments between the target disaster and the historical disasters. Evaluations in wildfire scenarios show that the digital twin decreases prediction errors by approximately 50% compared with those of the existing schemes.https://www.mdpi.com/1424-8220/22/13/4774digital twinhybrid modelingdisaster spread simulationdisaster predictionwildfire spread simulation |
| spellingShingle | Seong-Jin Yun Jin-Woo Kwon Won-Tae Kim A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems Sensors digital twin hybrid modeling disaster spread simulation disaster prediction wildfire spread simulation |
| title | A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems |
| title_full | A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems |
| title_fullStr | A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems |
| title_full_unstemmed | A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems |
| title_short | A Novel Digital Twin Architecture with Similarity-Based Hybrid Modeling for Supporting Dependable Disaster Management Systems |
| title_sort | novel digital twin architecture with similarity based hybrid modeling for supporting dependable disaster management systems |
| topic | digital twin hybrid modeling disaster spread simulation disaster prediction wildfire spread simulation |
| url | https://www.mdpi.com/1424-8220/22/13/4774 |
| work_keys_str_mv | AT seongjinyun anoveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems AT jinwookwon anoveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems AT wontaekim anoveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems AT seongjinyun noveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems AT jinwookwon noveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems AT wontaekim noveldigitaltwinarchitecturewithsimilaritybasedhybridmodelingforsupportingdependabledisastermanagementsystems |