Attention-based Domain Adaptation Forecasting of Streamflow in Data-Sparse Regions

Roland Oruche, Fearghal O'Donncha
2/10/2023
cs.LG

No official code found. Best implementation: rro2q2/adaf-streamflow-forecaster (3 stars, MIT, last commit 2023-06-01).

Abstract

Streamflow forecasts are critical to guide water resource management, mitigate drought and flood effects, and develop climate-smart infrastructure and governance. Many global regions, however, have limited streamflow observations to guide evidence-based management strategies. In this paper, we propose an attention-based domain adaptation streamflow forecaster for data-sparse regions. Our approach leverages the hydrological characteristics of a data-rich source domain to induce effective 24hr lead-time streamflow prediction in a data-constrained target domain. Specifically, we employ a deep-learning framework leveraging domain adaptation techniques to simultaneously train streamflow predictions and discern between both domains using an adversarial method. Experiments against baseline cross-domain forecasting models show improved performance for 24hr lead-time streamflow forecasting.

View on arXivView PDF

Code Implementations(1)

rro2q2/adaf-streamflow-forecasterCommunity100%
MIT

This is the official repository for the ICLR 2023 Climate Change AI paper "Attention-based Domain Adaptation Forecasting of Streamflow in Data Sparse Regions."

30Shell, PythonMay 4, 20233 years agoMIT

Similar Papers

Time Series Predictions in Unmonitored Sites: A Survey of Machine Learning Techniques in Water Resources

83% match2023

TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting

83% match2023

HydroDCM: Hydrological Domain-Conditioned Modulation for Cross-Reservoir Inflow Prediction

83% match2025

Short-term Streamflow and Flood Forecasting based on Graph Convolutional Recurrent Neural Network and Residual Error Learning

82% match2024

Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas

82% match1 repo12023

Accelerating Domain-aware Deep Learning Models with Distributed Training

81% match2023

Cite this paper

@article{oruche2023attentionbased,
  title  = {Attention-based Domain Adaptation Forecasting of Streamflow in Data-Sparse Regions},
  author = {Roland Oruche and Fearghal O'Donncha},
  year   = {2023},
  eprint = {2302.05386},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.05386v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.05386.svg)](https://codeofpaper.com/paper/2302.05386)

Discussion