Uncertainty propagation analysis for distributed hydrological forecasting using a neural network

The last few decades have presented a significant increase in hydrological disasters, such as floods. In some countries, most of the environmental, socioeconomic, and biodiversity losses are caused by floods. Thus, flood forecasting is crucial to support an efficient disaster warning system. This wo...

Full description

Saved in:
Bibliographic Details
Published inTransactions in GIS Vol. 28; no. 5; pp. 971 - 992
Main Authors Soares, Jaqueline A. J. P., Diniz, Michael M., Bacelar, Luiz, Lima, Glauston R. T., Soares, Allan K. S., Stephany, Stephan, Santos, Leonardo B. L.
Format Journal Article
LanguageEnglish
Published Oxford Blackwell Publishing Ltd 01.08.2024
Subjects
Biodiversity
Biodiversity loss
Data analysis
Disasters
Emergency warning programs
Flood forecasting
Flood predictions
Floods
Hydrology
Meteorological radar
Neural networks
Noise prediction
Noise propagation
Noise threshold
Outlets
Radar
Radar data
Rainfall
Rivers
Uncertainty
Uncertainty analysis
Warning systems
Weather forecasting
Online AccessGet full text

Cover

More Information
Summary:The last few decades have presented a significant increase in hydrological disasters, such as floods. In some countries, most of the environmental, socioeconomic, and biodiversity losses are caused by floods. Thus, flood forecasting is crucial to support an efficient disaster warning system. This work proposes a model for hydrological forecasting based on a neural network with a geographically aligned input named GeoNN. It employs weather radar data to obtain accumulated rainfall in each grid cell of the watershed and make 15‐ and 120‐min predictions of the outlet river level. An uncertainty propagation analysis was performed for GeoNN from a collection of test cases obtained by either using different schemes of the dataset partitioning or introducing different additive‐noise rates to the input data to provide a probability of flood occurrence and also an ensemble prediction. Both this probability and the ensemble were able to detect occurrences of river levels exceeding a given flood threshold.
ISSN:1361-1682
1467-9671
DOI:10.1111/tgis.13169