Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part II: Daily Precipitation

Statistical downscaling (SD) derives localized information from larger-scale numerical models. Convolutional neural networks (CNNs) have learning and generalization abilities that can enhance the downscaling of gridded data (Part I of this study experimented with 2-m temperature). In this research,...

Full description

Saved in:
Bibliographic Details
Published in:Journal of applied meteorology and climatology 2020-12, Vol.59 (12), p.2075-2092
Main Authors: Sha, Yingkai, Gagne, David John, West, Gregory, Stull, Roland
Format: Article
Language:English
Subjects:
Aggregation
Artificial neural networks
Bias
Climate
Climatology
Complex variables
Daily precipitation
Datasets
Deep learning
Disaggregation
Elevation
Error correction
Gauges
Hydrology
Mathematical models
Neural networks
Numerical models
Precipitation
Resolution
Semantic segmentation
Statistical analysis
Watersheds
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Statistical downscaling (SD) derives localized information from larger-scale numerical models. Convolutional neural networks (CNNs) have learning and generalization abilities that can enhance the downscaling of gridded data (Part I of this study experimented with 2-m temperature). In this research, we adapt a semantic-segmentation CNN, called UNet, to the downscaling of daily precipitation in western North America, from the low resolution (LR) of 0.25° to the high resolution (HR) of 4-km grid spacings. We select LR precipitation, HR precipitation climatology, and elevation as inputs; train UNet over the subset of the south- and central-western United States using Parameter–Elevation Regressions on Independent Slopes Model (PRISM) data from 2015 to 2018, and test it independently in all available domains from 2018 to 2019. We proposed an improved version of UNet, which we call Nest-UNet, by adding deep-layer aggregation and nested skip connections. Both the original UNet and Nest-UNet show generalization ability across different regions and outperform the SD baseline (bias-correction spatial disaggregation), with lower downscaling error and more accurate fine-grained textures. Nest-UNet also shares the highest amount of information with station observations and PRISM, indicating good ability to reduce the uncertainty of HR downscaling targets.
ISSN:1558-8424
1558-8432
DOI:10.1175/JAMC-D-20-0058.1