Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mardani, Morteza, Brenowitz, Noah, Cohen, Yair, Pathak, Jaideep, Chen, Chieh-Yu, Liu, Cheng-Chin, Vahdat, Arash, Nabian, Mohammad Amin, Ge, Tao, Subramaniam, Akshay, Kashinath, Karthik, Kautz, Jan, Pritchard, Mike
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913463481139200
author Mardani, Morteza
Brenowitz, Noah
Cohen, Yair
Pathak, Jaideep
Chen, Chieh-Yu
Liu, Cheng-Chin
Vahdat, Arash
Nabian, Mohammad Amin
Ge, Tao
Subramaniam, Akshay
Kashinath, Karthik
Kautz, Jan
Pritchard, Mike
author_facet Mardani, Morteza
Brenowitz, Noah
Cohen, Yair
Pathak, Jaideep
Chen, Chieh-Yu
Liu, Cheng-Chin
Vahdat, Arash
Nabian, Mohammad Amin
Ge, Tao
Subramaniam, Akshay
Kashinath, Karthik
Kautz, Jan
Pritchard, Mike
contents The state of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis. To address the large resolution ratio, different physics involved at different scales and prediction of channels beyond those in the input data, we employ a two-step approach where a UNet predicts the mean and a corrector diffusion (CorrDiff) model predicts the residual. CorrDiff exhibits encouraging skill in bulk MAE and CRPS scores. The predicted spectra and distributions from CorrDiff faithfully recover important power law relationships in the target data. Case studies of coherent weather phenomena show that CorrDiff can help sharpen wind and temperature gradients that co-locate with intense rainfall in cold front, and can help intensify typhoons and synthesize rain band structures. Calibration of model uncertainty remains challenging. The prospect of unifying methods like CorrDiff with coarser resolution global weather models implies a potential for global-to-regional multi-scale machine learning simulation.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15214
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling
Mardani, Morteza
Brenowitz, Noah
Cohen, Yair
Pathak, Jaideep
Chen, Chieh-Yu
Liu, Cheng-Chin
Vahdat, Arash
Nabian, Mohammad Amin
Ge, Tao
Subramaniam, Akshay
Kashinath, Karthik
Kautz, Jan
Pritchard, Mike
Machine Learning
Atmospheric and Oceanic Physics
The state of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis. To address the large resolution ratio, different physics involved at different scales and prediction of channels beyond those in the input data, we employ a two-step approach where a UNet predicts the mean and a corrector diffusion (CorrDiff) model predicts the residual. CorrDiff exhibits encouraging skill in bulk MAE and CRPS scores. The predicted spectra and distributions from CorrDiff faithfully recover important power law relationships in the target data. Case studies of coherent weather phenomena show that CorrDiff can help sharpen wind and temperature gradients that co-locate with intense rainfall in cold front, and can help intensify typhoons and synthesize rain band structures. Calibration of model uncertainty remains challenging. The prospect of unifying methods like CorrDiff with coarser resolution global weather models implies a potential for global-to-regional multi-scale machine learning simulation.
title Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2309.15214