ML for Flood Forecasting at Scale
Abstract
Effective riverine flood forecasting at scale is hindered by a multitude of factors, most notably the need to rely on human calibration in current methodology, the limited amount of data for a specific location, and the computational difficulty of building continent/global level models that are sufficiently accurate. Machine learning (ML) is primed to be useful in this scenario: learned models often surpass human experts in complex high-dimensional scenarios, and the framework of transfer or multitask learning is an appealing solution for leveraging local signals to achieve improved global performance. We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.
Cite
@article{arxiv.1901.09583,
title = {ML for Flood Forecasting at Scale},
author = {Sella Nevo and Vova Anisimov and Gal Elidan and Ran El-Yaniv and Pete Giencke and Yotam Gigi and Avinatan Hassidim and Zach Moshe and Mor Schlesinger and Guy Shalev and Ajai Tirumali and Ami Wiesel and Oleg Zlydenko and Yossi Matias},
journal= {arXiv preprint arXiv:1901.09583},
year = {2019}
}
Comments
The 2-page paper sent to NeurIPS 2018 AI for social good workshop