Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network

10/15/2020
by   Martin Gauch, et al.
0

Long Short-Term Memory Networks (LSTMs) have been applied to daily discharge prediction with remarkable success. Many practical scenarios, however, require predictions at more granular timescales. For instance, accurate prediction of short but extreme flood peaks can make a life-saving difference, yet such peaks may escape the coarse temporal resolution of daily predictions. Naively training an LSTM on hourly data, however, entails very long input sequences that make learning hard and computationally expensive. In this study, we propose two Multi-Timescale LSTM (MTS-LSTM) architectures that jointly predict multiple timescales within one model, as they process long-past inputs at a single temporal resolution and branch out into each individual timescale for more recent input steps. We test these models on 516 basins across the continental United States and benchmark against the US National Water Model. Compared to naive prediction with a distinct LSTM per timescale, the multi-timescale architectures are computationally more efficient with no loss in accuracy. Beyond prediction quality, the multi-timescale LSTM can process different input variables at different timescales, which is especially relevant to operational applications where the lead time of meteorological forcings depends on their temporal resolution.

READ FULL TEXT
research
03/25/2016

Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction

The effectiveness of long short term memory networks trained by backprop...
research
02/07/2020

High Temporal Resolution Rainfall Runoff Modelling Using Long-Short-Term-Memory (LSTM) Networks

Accurate and efficient models for rainfall runoff (RR) simulations are c...
research
06/04/2018

CFCM: Segmentation via Coarse to Fine Context Memory

Recent neural-network-based architectures for image segmentation make ex...
research
07/13/2020

Using LSTM for the Prediction of Disruption in ADITYA Tokamak

Major disruptions in tokamak pose a serious threat to the vessel and its...
research
06/20/2016

LSTM-Based Predictions for Proactive Information Retrieval

We describe a method for proactive information retrieval targeted at ret...
research
06/14/2023

Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads

Deep Operator Network (DeepONet), a recently introduced deep learning op...
research
01/27/2022

Micro-level Reserving for General Insurance Claims using a Long Short-Term Memory Network

Detailed information about individual claims are completely ignored when...

Please sign up or login with your details

Forgot password? Click here to reset