Prioritized Sampling on Knowledge Distillation for Nowcasting Pluvial Flood Prediction

Kondo, Ryusuke; Du, Bojian; Narusue, Yoshiaki; Morikawa, Hiroyuki

doi:10.1109/bigdata52589.2021.9671897

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This increasingly motivates the ML model to learn more efficiently with less training data. The training data distribution is imbalanced among the spatio-temporal movement patterns of the rainfall area [30], [31], and the spread of flooding depends on the patterns of the rainfall area [32]. However, random sampling does not achieve true learning convergence until data points are sampled from minor rainfall patterns, which is time consuming.…”

Section: Prioritized Samplingmentioning

confidence: 99%

Machine Learning Framework Supervised by Hydraulic Mechanical Models for Real-time Pluvial Flood Prediction

Kondo

Narusue

et al. 2023

Journal of Information Processing

Self Cite

View full text Add to dashboard Cite

Real-time flood prediction in urban areas is an important tool for city emergency planning. Earlier studies suggest two approaches to predict flooding: a supervised machine learning approach based on observed data and a modeling approach for urban environments based on hydraulics. However, the first approach can only be applied in areas where there is sufficient data on flooding and is not accurate enough for prediction. The second approach can provide accurate predictions even for cities that have never experienced flooding, but models of complex urban environments are not suitable for real-time prediction owing to significant computational complexity. Therefore, we propose a third approach, machine learning supervised by a program. This approach consists of training a lightweight neural network using an integrated flood analysis program composed of multiple hydrologically based models. We demonstrate that this trained neural network is 19.8 times faster and and has accuracy comparable to that of the previous modeling approaches.

show abstract

Section: Prioritized Samplingmentioning

confidence: 99%