Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data

Abstract This study introduces a novel method called Informed Neural Networks (INNs), developed to enhance flood forecasting accuracy, particularly under limited data conditions. Accurate flood forecasts are crucial for timely evacuations, especially as heavy rainfall increasingly threatens areas pr...

Full description

Saved in:
Bibliographic Details
Main Authors: K. Komiya, H. Kiyotake, R. Nakada, M. Fujishima, K. Mori
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2023WR036380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687885467353088
author K. Komiya
H. Kiyotake
R. Nakada
M. Fujishima
K. Mori
author_facet K. Komiya
H. Kiyotake
R. Nakada
M. Fujishima
K. Mori
author_sort K. Komiya
collection DOAJ
description Abstract This study introduces a novel method called Informed Neural Networks (INNs), developed to enhance flood forecasting accuracy, particularly under limited data conditions. Accurate flood forecasts are crucial for timely evacuations, especially as heavy rainfall increasingly threatens areas previously unaffected by flooding. Traditional methods often require extensive data and frequent updates, making them costly and challenging to maintain. INNs address these challenges by enabling accurate predictions under limited data conditions. We propose an INN architecture for rivers in regions like Japan, where floods are predominantly caused by rainfall. We applied the INN to both rainfall‐dominated and non‐rainfall‐dominated floods to evaluate its effectiveness and limitations. Our experiments show that the INN effectively integrates domain knowledge, maintains performance, and achieves lower prediction errors than ANN in data‐scarce scenarios. These findings highlight the potential of INNs as a promising approach for future flood forecasting, particularly in data‐limited environments.
format Article
id doaj-art-ad7e596392c54d6ba0a230d4e4a08121
institution DOAJ
issn 0043-1397
1944-7973
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-ad7e596392c54d6ba0a230d4e4a081212025-08-20T03:22:12ZengWileyWater Resources Research0043-13971944-79732025-03-01613n/an/a10.1029/2023WR036380Informed Neural Networks for Flood Forecasting With Limited Amount of Training DataK. Komiya0H. Kiyotake1R. Nakada2M. Fujishima3K. Mori4Digitial Twin Computing Research Center Tokyo JapanDigitial Twin Computing Research Center Tokyo JapanDigitial Twin Computing Research Center Tokyo JapanDigitial Twin Computing Research Center Tokyo JapanDigitial Twin Computing Research Center Tokyo JapanAbstract This study introduces a novel method called Informed Neural Networks (INNs), developed to enhance flood forecasting accuracy, particularly under limited data conditions. Accurate flood forecasts are crucial for timely evacuations, especially as heavy rainfall increasingly threatens areas previously unaffected by flooding. Traditional methods often require extensive data and frequent updates, making them costly and challenging to maintain. INNs address these challenges by enabling accurate predictions under limited data conditions. We propose an INN architecture for rivers in regions like Japan, where floods are predominantly caused by rainfall. We applied the INN to both rainfall‐dominated and non‐rainfall‐dominated floods to evaluate its effectiveness and limitations. Our experiments show that the INN effectively integrates domain knowledge, maintains performance, and achieves lower prediction errors than ANN in data‐scarce scenarios. These findings highlight the potential of INNs as a promising approach for future flood forecasting, particularly in data‐limited environments.https://doi.org/10.1029/2023WR036380flood forecastingmachine learningartificial neural networksdomain‐specific knowledge
spellingShingle K. Komiya
H. Kiyotake
R. Nakada
M. Fujishima
K. Mori
Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
Water Resources Research
flood forecasting
machine learning
artificial neural networks
domain‐specific knowledge
title Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
title_full Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
title_fullStr Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
title_full_unstemmed Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
title_short Informed Neural Networks for Flood Forecasting With Limited Amount of Training Data
title_sort informed neural networks for flood forecasting with limited amount of training data
topic flood forecasting
machine learning
artificial neural networks
domain‐specific knowledge
url https://doi.org/10.1029/2023WR036380
work_keys_str_mv AT kkomiya informedneuralnetworksforfloodforecastingwithlimitedamountoftrainingdata
AT hkiyotake informedneuralnetworksforfloodforecastingwithlimitedamountoftrainingdata
AT rnakada informedneuralnetworksforfloodforecastingwithlimitedamountoftrainingdata
AT mfujishima informedneuralnetworksforfloodforecastingwithlimitedamountoftrainingdata
AT kmori informedneuralnetworksforfloodforecastingwithlimitedamountoftrainingdata