AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Yingpeng, Yu, Weijiang, Zheng, Fudan, Huang, Dan, Xiao, Nong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913222805684224
author Wen, Yingpeng
Yu, Weijiang
Zheng, Fudan
Huang, Dan
Xiao, Nong
author_facet Wen, Yingpeng
Yu, Weijiang
Zheng, Fudan
Huang, Dan
Xiao, Nong
contents Previous post-processing studies on rainfall forecasts using numerical weather prediction (NWP) mainly focus on statistics-based aspects, while learning-based aspects are rarely investigated. Although some manually-designed models are proposed to raise accuracy, they are customized networks, which need to be repeatedly tried and verified, at a huge cost in time and labor. Therefore, a self-supervised neural architecture search (NAS) method without significant manual efforts called AdaNAS is proposed in this study to perform rainfall forecast post-processing and predict rainfall with high accuracy. In addition, we design a rainfall-aware search space to significantly improve forecasts for high-rainfall areas. Furthermore, we propose a rainfall-level regularization function to eliminate the effect of noise data during the training. Validation experiments have been performed under the cases of \emph{None}, \emph{Light}, \emph{Moderate}, \emph{Heavy} and \emph{Violent} on a large-scale precipitation benchmark named TIGGE. Finally, the average mean-absolute error (MAE) and average root-mean-square error (RMSE) of the proposed AdaNAS model are 0.98 and 2.04 mm/day, respectively. Additionally, the proposed AdaNAS model is compared with other neural architecture search methods and previous studies. Compared results reveal the satisfactory performance and superiority of the proposed AdaNAS model in terms of precipitation amount prediction and intensity classification. Concretely, the proposed AdaNAS model outperformed previous best-performing manual methods with MAE and RMSE improving by 80.5\% and 80.3\%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16046
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts
Wen, Yingpeng
Yu, Weijiang
Zheng, Fudan
Huang, Dan
Xiao, Nong
Machine Learning
Artificial Intelligence
Atmospheric and Oceanic Physics
Previous post-processing studies on rainfall forecasts using numerical weather prediction (NWP) mainly focus on statistics-based aspects, while learning-based aspects are rarely investigated. Although some manually-designed models are proposed to raise accuracy, they are customized networks, which need to be repeatedly tried and verified, at a huge cost in time and labor. Therefore, a self-supervised neural architecture search (NAS) method without significant manual efforts called AdaNAS is proposed in this study to perform rainfall forecast post-processing and predict rainfall with high accuracy. In addition, we design a rainfall-aware search space to significantly improve forecasts for high-rainfall areas. Furthermore, we propose a rainfall-level regularization function to eliminate the effect of noise data during the training. Validation experiments have been performed under the cases of \emph{None}, \emph{Light}, \emph{Moderate}, \emph{Heavy} and \emph{Violent} on a large-scale precipitation benchmark named TIGGE. Finally, the average mean-absolute error (MAE) and average root-mean-square error (RMSE) of the proposed AdaNAS model are 0.98 and 2.04 mm/day, respectively. Additionally, the proposed AdaNAS model is compared with other neural architecture search methods and previous studies. Compared results reveal the satisfactory performance and superiority of the proposed AdaNAS model in terms of precipitation amount prediction and intensity classification. Concretely, the proposed AdaNAS model outperformed previous best-performing manual methods with MAE and RMSE improving by 80.5\% and 80.3\%, respectively.
title AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts
topic Machine Learning
Artificial Intelligence
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2312.16046