Quantile-Regression-Ensemble: A Deep Learning Algorithm for Downscaling Extreme Precipitation

4Citations
Citations of this article
19Readers
Mendeley users who have this article in their library.

Abstract

Global Climate Models (GCMs) simulate low resolution climate projections on a global scale. The native resolution of GCMs is generally too low for societal-level decisionmaking. To enhance the spatial resolution, downscaling is often applied to GCM output. Statistical downscaling techniques, in particular, are well-established as a cost-effective approach. They require significantly less computational time than physics-based dynamical downscaling. In recent years, deep learning has gained prominence in statistical downscaling, demonstrating significantly lower error rates compared to traditional statistical methods. However, a drawback of regression-based deep learning techniques is their tendency to overfit to the mean sample intensity. Extreme values as a result are often underestimated. Problematically, extreme events have the largest societal impact. We propose Quantile- Regression-Ensemble (QRE), an innovative deep learning algorithm inspired by boosting methods. Its primary objective is to avoid trade-offs between fitting to sample means and extreme values by training independent models on a partitioned dataset. Our QRE is robust to redundant models and not susceptible to explosive ensemble weights, ensuring a reliable training process. QRE achieves lower Mean Squared Error (MSE) compared to various baseline models. In particular, our algorithm has a lower error for high-intensity precipitation events over New Zealand, highlighting the ability to represent extreme events accurately.

References Powered by Scopus

CBAM: Convolutional block attention module

18434Citations
N/AReaders
Get full text

The ERA5 global reanalysis

15463Citations
N/AReaders
Get full text

Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization

6898Citations
N/AReaders
Get full text

Cited by Powered by Scopus

A Reliable Generative Adversarial Network Approach for Climate Downscaling and Weather Generation

1Citations
N/AReaders
Get full text

On the Extrapolation of Generative Adversarial Networks for Downscaling Precipitation Extremes in Warmer Climates

1Citations
N/AReaders
Get full text

Projecting future snow changes at kilometer scale for adaptation using machine learning and a CMIP6 multi-model ensemble

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Bailie, T., Koh, Y. S., Rampal, N., & Gibson, P. B. (2024). Quantile-Regression-Ensemble: A Deep Learning Algorithm for Downscaling Extreme Precipitation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, pp. 21914–21922). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v38i20.30193

Readers' Seniority

Tooltip

Lecturer / Post doc 2

40%

PhD / Post grad / Masters / Doc 2

40%

Researcher 1

20%

Readers' Discipline

Tooltip

Business, Management and Accounting 1

25%

Computer Science 1

25%

Engineering 1

25%

Earth and Planetary Sciences 1

25%

Save time finding and organizing research with Mendeley

Sign up for free