Investigating transformer‐based models for spatial downscaling and correcting biases of near‐surface temperature and wind‐speed forecasts

缩小尺度 数值天气预报 数据同化 气象学 计算机科学 环境科学 风速 图像分辨率 模型输出统计 气候学 人工智能 地理 地质学 降水
作者
Xiaohui Zhong,Du Fei,Lei Chen,Zhibin Wang,Hao Li
出处
期刊:Quarterly Journal of the Royal Meteorological Society [Wiley]
卷期号:150 (758): 275-289 被引量:59
标识
DOI:10.1002/qj.4596
摘要

Abstract High‐resolution and accurate prediction of near‐surface weather parameters based on numerical weather prediction (NWP) models is essential for many downstream and real‐world applications. Traditional dynamical or statistical downscaling methods are insufficient to derive high‐resolution data from operational NWP forecasts, making it essential to devise new approaches. In recent years, an increasing number of researchers have explored the implementations of deep learning (DL) based models for spatial downscaling, motivated by the similarity between the super‐resolution (SR) problem in computer vision (CV) and downscaling. Furthermore, while transformer‐based models have become state‐of‐the‐art models for many SR tasks, they are rarely applied for downscaling of weather forecasts or climate projections. This study adapted transformer‐based models such as SwinIR and Uformer to downscale the temperature at 2 m () and wind speed at 10 m () over Eastern Inner Mongolia, encompassing the area from 39.6–46°N latitude and 111.6–118°E longitude. We used high‐resolution forecast (HRES) data from the European Centre for Medium‐range Weather Forecast (ECMWF) with a spatial resolution of 0.1° as the input and gridded observation data from the China Meteorological Administration (CMA) Land Data Assimilation System (CLDAS) at a spatial resolution of 0.01° as the target. Given that the models use observation data rather than a coarse‐grained version of forecast data as the target, they accomplish both bias correction and spatial downscaling. The results demonstrate that the performance of SwinIR and Uformer is superior to that of two convolutional neural network (CNN) based models (UNet and RCAN). Additionally, we introduced a novel module to extract features of varying resolution from the high‐resolution topography data and applied a multiscale feature fusion module to merge features of different scales, contributing to further enhancement of Uformer's performance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刘思琪发布了新的文献求助10
1秒前
iggyxhjtl完成签到,获得积分10
1秒前
瓶瓶大王完成签到 ,获得积分10
1秒前
傅凡桃完成签到,获得积分10
1秒前
大模型的应助被拉长的砖家采纳,获得10
1秒前
里里完成签到,获得积分10
1秒前
kyhappy_2002完成签到,获得积分10
1秒前
光亮的洙完成签到,获得积分10
2秒前
2秒前
天天向上的应助被路遥知马力采纳,获得10
3秒前
3秒前
榴莲味月饼完成签到 ,获得积分10
3秒前
工作热情仔的应助被xyz采纳,获得100
3秒前
lijiaqi完成签到 ,获得积分10
3秒前
zhi完成签到,获得积分10
4秒前
yu发布了新的文献求助20
4秒前
4秒前
戒骄戒躁完成签到 ,获得积分10
4秒前
认真的小刺猬完成签到,获得积分10
5秒前
5秒前
彭彭完成签到,获得积分10
5秒前
慕青的应助被研友_ZG4ml8采纳,获得10
6秒前
图南完成签到,获得积分10
6秒前
Alex111完成签到,获得积分10
6秒前
橘子完成签到,获得积分20
7秒前
自由灵安完成签到,获得积分10
7秒前
fhn716完成签到,获得积分10
7秒前
7秒前
爱笑的枫叶完成签到,获得积分10
7秒前
7秒前
山楂完成签到,获得积分10
8秒前
科研民工完成签到,获得积分10
8秒前
NexusExplorer的应助被111采纳,获得10
8秒前
合适抽屉完成签到 ,获得积分10
8秒前
名取周一发布了新的文献求助10
9秒前
Owen的应助被小黑球采纳,获得10
10秒前
yunt完成签到 ,获得积分0
10秒前
五六87完成签到,获得积分10
10秒前
hele完成签到,获得积分10
10秒前
TJway发布了新的文献求助10
10秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180146
求助须知:如何正确求助?哪些是违规求助? 9570319
关于积分的说明 21809739
捐赠科研通 7776294
什么是DOI,文献DOI怎么找? 3433266
关于科研通互助平台的介绍 2557483
邀请新用户注册赠送积分活动 2479039