EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam

Pham Viet Hoa, Nguyen An Binh, Pham Viet Hong, Nguyen Ngoc An, Giang Thi Phuong Thao, Nguyen Cao Hanh, Phuong Thao Thi Ngo, Dieu Tien Bui

Earth Science Informatics · 2024-10 · 17 (5) · 4419-4440

DOI: 10.1007/s12145-024-01285-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Earth Science Informatics, online erschienen am 06.07.2024. Verfasst von Pham Viet Hoa und 7 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 122 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University Of South-Eastern Norway.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flash floods rank among the most catastrophic natural disasters worldwide, inflicting severe socio-economic, environmental, and human impacts. Consequently, accurately identifying areas at potential risk is of paramount importance. This study investigates the efficacy of Deep 1D-Convolutional Neural Networks (Deep 1D-CNN) in spatially predicting flash floods, with a specific focus on the frequent tropical cyclone-induced flash floods in Thanh Hoa province, North Central Vietnam. The Deep 1D-CNN was structured with four convolutional layers, two pooling layers, one flattened layer, and two fully connected layers, employing the ADAM algorithm for optimization and Mean Squared Error (MSE) for loss calculation. A geodatabase containing 2540 flash flood locations and 12 influencing factors was compiled using multi-source geospatial data. The database was used to train and check the model. The results indicate that the Deep 1D-CNN model achieved high predictive accuracy (90.2%), along with a Kappa value of 0.804 and an AUC (Area Under the Curve) of 0.969, surpassing the benchmark models such as SVM (Support Vector Machine) and LR (Logistic Regression). The study concludes that the Deep 1D-CNN model is a highly effective tool for modeling flash floods.

Förderung

  • University Of South-Eastern Norway

Zitieren

APA

Hoa, P. V., Binh, N. A., Hong, P. V., An, N. N., Thao, G. T. P., Hanh, N. C., Ngo, P. T. T., & Bui, D. T. (2024). One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam. Earth Science Informatics, 17(5), 4419-4440. https://doi.org/10.1007/s12145-024-01285-8

Vancouver

Hoa PV, Binh NA, Hong PV, An NN, Thao GTP, Hanh NC, et al. One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam. Earth Science Informatics. 2024;17(5):4419-4440. doi:10.1007/s12145-024-01285-8

BibTeX
@article{Hoa2024,
  author = {Hoa, Pham Viet and Binh, Nguyen An and Hong, Pham Viet and An, Nguyen Ngoc and Thao, Giang Thi Phuong and Hanh, Nguyen Cao and Ngo, Phuong Thao Thi and Bui, Dieu Tien},
  title = {One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam},
  journal = {Earth Science Informatics},
  year = {2024},
  volume = {17},
  number = {5},
  pages = {4419--4440},
  doi = {10.1007/s12145-024-01285-8}
}
Kostenlos starten →