STI Publications - View Publication #23050

Back to Search Results Print
Publication Information
Title Advancing Machine Learning Surrogate Models for Urban Street-Scale Flood Forecasting through Transfer Learning
Abstract One of the important challenges with Machine Learning (ML) is its transferability; that is, models trained for one region and their ability (or inability) to predict for another region without being completely trained for that region. Transfer Learning (TL) addresses this challenge by transferring the learned knowledge from one domain (Source) to another domain (Target). First, the weights of the pre-trained model act as learned knowledge and are used as the initial status of the transfer model. Then, the remaining weights in the transfer model are re-trained using the data available from the target domain. TL is commonly used when developing an ML model from scratch is complicated due to having less data in the target domain. TL has already been highly recognized in the artificial intelligence community but less explored in the hydrology domain, especially in an urban setting for street-scale flood forecasting, which has challenges due to the complexity of the built urban landscape an
Author(s) Diana McSpadden, Steven Goldenberg, Malachi Schram, Jonathan Goodall, Binata Roy, Yidi Wang, Chetan Kumar
Publication Date December 2024
Document Type Meeting
Primary Institution University of Virginia, Charlottesville, VA
Affiliation Comp Sci&Tech (CST) Div / Data Science / Data Science
Funding Source Other, ACES
Proprietary? No
This publication conveys Technical Science Results
Document Numbers
JLAB Number: OSTI Number:
LANL Number: Other Number:
Associated with an experiment No
Associated with EIC No
Supported by Jefferson Lab LDRD Funding No
Meeting / Conference
Meeting Name AGU24
Meeting Date 12/9/2024
Document Subtype Abstract
Attachments/Datasets/DOI Link
Document(s) (none)
Dataset(s) (none)
Back to Search Results Print