Preprints
https://doi.org/10.5194/nhess-2023-152
https://doi.org/10.5194/nhess-2023-152
19 Sep 2023
 | 19 Sep 2023
Status: a revised version of this preprint is currently under review for the journal NHESS.

Transferability of machine learning-based modeling frameworks across flood events for hindcasting maximum river flood depths in coastal watersheds

Maryam Pakdehi, Ebrahim Ahmadisharaf, Behzad Nazari, and Eunsaem Cho

Abstract. Despite applications of machine learning (ML) models for predicting floods, their transferability for out-of-sample data has not been explored. This paper developed an ML-based model for hindcasting maximum flood depths during major events in coastal watersheds and evaluated its transferability across other events (out-of-sample). The model considered spatial distribution of influential factors, which explain underlying physical processes, to hindcast maximum river flood depths. Our model evaluation in a HUC6 watershed in Northeastern US showed that the model satisfactorily hindcasted maximum flood depths at 116 stream gauges during a major flood event, Hurricane Ida (R2 of 0.92). The pre-trained, validated model was successfully transferred to three other major flood events, Hurricanes Isaias, Sandy, and Irene (R2 > 0.71). Our results showed that ML-based models can be transferable for hindcasting maximum river flood depths across events when informed by the spatial distribution of pertinent features and underlying physical processes in coastal watersheds.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Maryam Pakdehi, Ebrahim Ahmadisharaf, Behzad Nazari, and Eunsaem Cho

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2023-152', Anonymous Referee #1, 05 Feb 2024
  • RC2: 'Comment on nhess-2023-152', Anonymous Referee #2, 26 Feb 2024
Maryam Pakdehi, Ebrahim Ahmadisharaf, Behzad Nazari, and Eunsaem Cho
Maryam Pakdehi, Ebrahim Ahmadisharaf, Behzad Nazari, and Eunsaem Cho

Viewed

Total article views: 468 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
365 74 29 468 19 21
  • HTML: 365
  • PDF: 74
  • XML: 29
  • Total: 468
  • BibTeX: 19
  • EndNote: 21
Views and downloads (calculated since 19 Sep 2023)
Cumulative views and downloads (calculated since 19 Sep 2023)

Viewed (geographical distribution)

Total article views: 453 (including HTML, PDF, and XML) Thereof 453 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 14 Jun 2024
Download
Short summary
Machine learning (ML) models have growingly received attention for predicting flood events. However, there has been concerns about the transferability of these models (their capability in predicting out-of-sample events). Here, we showed that ML models can be transferable for hindcasting maximum river flood depths across major events (Hurricanes Ida, Isaias, Sandy, and Irene) in coastal watersheds when informed by the spatial distribution of pertinent features and underlying physical processes.
Altmetrics