DeepAI
Log In Sign Up

Prediction in ungauged regions with sparse flow duration curves and input-selection ensemble modeling

11/26/2020
by   Dapeng Feng, et al.
6

While long short-term memory (LSTM) models have demonstrated stellar performance with streamflow predictions, there are major risks in applying these models in contiguous regions with no gauges, or predictions in ungauged regions (PUR) problems. However, softer data such as the flow duration curve (FDC) may be already available from nearby stations, or may become available. Here we demonstrate that sparse FDC data can be migrated and assimilated by an LSTM-based network, via an encoder. A stringent region-based holdout test showed a median Kling-Gupta efficiency (KGE) of 0.62 for a US dataset, substantially higher than previous state-of-the-art global-scale ungauged basin tests. The baseline model without FDC was already competitive (median KGE 0.56), but integrating FDCs had substantial value. Because of the inaccurate representation of inputs, the baseline models might sometimes produce catastrophic results. However, model generalizability was further meaningfully improved by compiling an ensemble based on models with different input selections.

READ FULL TEXT

page 14

page 15

11/07/2021

Use of 1D-CNN for input data size reduction of LSTM in Hourly Rainfall-Runoff modeling

An architecture consisting of a serial coupling of the one-dimensional c...
10/13/2022

Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stations

Accurate short-term passenger flow prediction in urban rail transit stat...
06/15/2021

Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM

This study investigates the relationships which deep learning methods ca...
06/20/2016

LSTM-Based Predictions for Proactive Information Retrieval

We describe a method for proactive information retrieval targeted at ret...