arXiv subjects

Yingkai Sha

Publications and source records attributed to Yingkai Sha.

10 recordsLinked to original sources

arXiv2026

Kilometer-Scale AI Downscaling of Atlantic Hurricanes with Generative Ensembles

This study presents an AI-based dynamical downscaling system for Tropical Cyclones (TCs). The system incorporates an AI-based limited-area model that downscales 3-hourly low-resolution boundary forcings into hourly high-resolution fields autoregressively, and a diffusion model that converts the outputs into ensembles of hazard-relevant variables. The system is trained on the regridded CONUS404 data with ERA5 forcings, and is evaluated on 20 TCs in 2020--2024. Verification shows stable downscaling performance across Atlantic hurricane seasons, with energy spectra closely matching the CONUS404 reference. The system is also verified to produce skillful TC-relevant weather extremes, largely improved over a deterministic AI baseline. The system performs well with forcing data from other models (GDAS/FNL) and can produce detailed eyewall, rainband, and landfall structures in TC case studies. The study provides a good example of how AI-based dynamical downscaling systems can be designed to resolve small-scale extreme weather events.

physics.ao-ph↗

arXiv2026

Hard conservation correctors can hide a degrading model when training autoregressive emulators

AI weather and climate emulators increasingly incorporate physical principles into their formulation. One approach is to apply hard correctors that modify network outputs so that global mass, water, or energy budgets close. Prior work introduced such training-time correctors in the CREDIT framework and reported reduced precipitation bias and improved stability. Motivated by those results, we fine-tuned a global atmosphere emulator with a water-budget corrector, using the corrected prediction in the supervised loss and evaluating through post-correction budget closure. By that measure, training appeared successful. Every delivered field closed the moisture budget to machine precision. However, raw precipitation developed a growing global low bias over 18 training epochs, while the required correction increased from about 2% to roughly 24%. The cause is a scale degeneracy. A uniform change in raw precipitation amplitude is offset by a compensating change in the correction factor, leaving the corrected field, and therefore the supervised loss, unchanged. This invariance removes the restoring force on raw precipitation amplitude, allowing other training pressures to drive drift. Two changes recovered stable behavior. We supervised the pre-correction prediction and penalized its raw budget imbalance, while the hard correction remained in place for the delivered field. The required correction returned to less than 1% within the next epoch. A controlled 2x2 ablation showed that the runaway occurred only when corrected-output supervision was combined with no imbalance penalty. Exact post-correction closure therefore says little about whether the raw model has learned the budget. When a corrector removes information from the loss, the raw fields and the applied correction need to be tracked.

physics.ao-ph↗

arXiv2026

AI-Based Regional Emulation for Kilometer-Scale Dynamical Downscaling

An AI-based Limited-Area Model (LAM) is developed for dynamical downscaling over the Southern Great Plains and the southeastern United States, with strong generalization abilities under diverse boundary conditions. The model is trained using 0.25-degree, 3-hourly ERA5 as forcings and CONUS404 as targets in 1980--2019, producing 4-km, hourly dynamical downscaling outputs; it is also connected to a post-processing model to derive additional diagnostic variables. The model is evaluated across multiple forcing datasets, time periods, and climate regimes. For present-day downscaling in the 2021--2024 water years, the model produces stable multi-year simulations with no unrealistic drift; its deterministic verification scores are comparable to other weather-forecasting-oriented AI models. The model also generalizes robustly to a 1.0-degree, 6-hourly non-ERA5 forcing dataset, yielding only minor performance changes. Frontal cyclone and hurricane case studies further demonstrate that the model reconstructs realistic, interpretable weather-scale dynamical and thermodynamic structure from coarse boundary information. The AI-based LAM is further tested by downscaling 30-year global climate model runs in 1980--2010 and 2070--2100, and climate model ensembles in 2025-2027. In this application, the model remains stable at hourly downscaling frequencies for all 30 years and effectively captures future climate-change signals, indicating meaningful generalization across different climate regimes. When downscaling ensembles, the model produces well-posed ensemble distributions without collapsing the ensemble spread. Overall, the AI-based LAM of this study offers good downscaling performance and generalization abilities. It provides a practical and transferable example of adapting AI weather prediction models for regional climate applications.

physics.ao-ph↗

arXiv2025

Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts

Improving the skill of medium-range (3-8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather forecasts, specifically from the Pangu-Weather model, for improved severe weather guidance. Unlike traditional post-processing methods that use a dense neural network to predict the probability of severe weather using discrete forecast samples, our method treats forecast lead times as sequential ``tokens'', enabling the transformer to learn complex temporal relationships within the evolving atmospheric state. We compare this approach against post-processing of the Global Forecast System (GFS) using both a traditional dense neural network and our transformer, as well as configurations that exclude convective parameters to fairly evaluate the impact of using the Pangu-Weather AI model. Results demonstrate that the transformer-based post-processing significantly enhances forecast skill compared to dense neural networks. Furthermore, AI-driven forecasts, particularly Pangu-Weather initialized from high resolution analysis, exhibit superior performance to GFS in the medium-range, even without explicit convective parameters. Our approach offers improved accuracy, and reliability, which also provides interpretability through feature attribution analysis, advancing medium-range severe weather prediction capabilities.

physics.ao-ph↗

arXiv2025

CAMulator: Fast Emulation of the Community Atmosphere Model

We introduce CAMulator version 1, an auto-regressive machine-learned (ML) emulator of the Community Atmosphere Model version 6 (CAM6) that simulates the next atmospheric state given the prescribed sea surface temperatures and incoming solar radiation. CAMulator explicitly conserves global dry air mass, moisture, and total atmospheric energy while remaining numerically stable over indefinite climate integrations. It successfully reproduces the annual CAM6 climatology and key modes of climate variability, including the El Ni\~no-Southern Oscillation, the North Atlantic Oscillation, and the Pacific-North American pattern, with slightly muted variability. When forced with sea surface temperature (SST) outside the training distribution, CAMulator exhibits a systematic cold bias in high-latitude regions, particularly in boreal winter, likely due to the absence of interactive land and sea ice. Nonetheless, CAMulator achieves these results with a 350 times speedup over CAM6, making it an efficient alternative for generating large ensembles.

physics.ao-ph↗

arXiv2025

Investigating the use of terrain-following coordinates in AI-driven precipitation forecasts

Artificial Intelligence (AI) weather prediction (AIWP) models often produce ``blurry'' precipitation forecasts. This study presents a novel solution to tackle this problem -- integrating terrain-following coordinates into AIWP models. Forecast experiments are conducted to evaluate the effectiveness of terrain-following coordinates using FuXi, an example AIWP model, adapted to 1.0 degree grid spacing data. Verification results show a largely improved estimation of extreme events and precipitation intensity spectra. Terrain-following coordinates are also found to collaborate well with global mass and energy conservation constraints, with a clear reduction of drizzle bias. Case studies reveal that terrain-following coordinates can represent near-surface winds better, which helps AIWP models in learning the relationships between precipitation and other prognostic variables. The result of this study suggests that terrain-following coordinates are worth considering for AIWP models in producing more accurate precipitation forecasts.

physics.ao-ph↗

arXiv2025

Improving AI weather prediction models using global mass and energy conservation schemes

Artificial Intelligence (AI) weather prediction (AIWP) models are powerful tools for medium-range forecasts but often lack physical consistency, leading to outputs that violate conservation laws. This study introduces a set of novel physics-based schemes designed to enforce the conservation of global dry air mass, moisture budget, and total atmospheric energy in AIWP models. The schemes are highly modular, allowing for seamless integration into a wide range of AI model architectures. Forecast experiments are conducted to demonstrate the benefit of conservation schemes using FuXi, an example AIWP model, modified and adapted for 1.0-degree grid spacing. Verification results show that the conservation schemes can guide the model in producing forecasts that obey conservation laws. The forecast skills of upper-air and surface variables are also improved, with longer forecast lead times receiving larger benefits. Notably, large performance gains are found in the total precipitation forecasts, owing to the reduction of drizzle bias. The proposed conservation schemes establish a foundation for implementing other physics-based schemes in the future. They also provide a new way to integrate atmospheric domain knowledge into the design and refinement of AIWP models.

physics.ao-ph↗

arXiv2024

Community Research Earth Digital Intelligence Twin (CREDIT)

Recent advancements in artificial intelligence (AI) for numerical weather prediction (NWP) have significantly transformed atmospheric modeling. AI NWP models outperform traditional physics-based systems, such as the Integrated Forecast System (IFS), across several global metrics while requiring fewer computational resources. However, existing AI NWP models face limitations related to training datasets and timestep choices, often resulting in artifacts that reduce model performance. To address these challenges, we introduce the Community Research Earth Digital Intelligence Twin (CREDIT) framework, developed at NSF NCAR. CREDIT provides a flexible, scalable, and user-friendly platform for training and deploying AI-based atmospheric models on high-performance computing systems. It offers an end-to-end pipeline for data preprocessing, model training, and evaluation, democratizing access to advanced AI NWP capabilities. We demonstrate CREDIT's potential through WXFormer, a novel deterministic vision transformer designed to predict atmospheric states autoregressively, addressing common AI NWP issues like compounding error growth with techniques such as spectral normalization, padding, and multi-step training. Additionally, to illustrate CREDIT's flexibility and state-of-the-art model comparisons, we train the FUXI architecture within this framework. Our findings show that both FUXI and WXFormer, trained on six-hourly ERA5 hybrid sigma-pressure levels, generally outperform IFS HRES in 10-day forecasts, offering potential improvements in efficiency and forecast accuracy. CREDIT's modular design enables researchers to explore various models, datasets, and training configurations, fostering innovation within the scientific community.

cs.AI↗

arXiv2024

Improving ensemble extreme precipitation forecasts using generative artificial intelligence

An ensemble post-processing method is developed to improve the probabilistic forecasts of extreme precipitation events across the conterminous United States (CONUS). The method combines a 3-D Vision Transformer (ViT) for bias correction with a Latent Diffusion Model (LDM), a generative Artificial Intelligence (AI) method, to post-process 6-hourly precipitation ensemble forecasts and produce an enlarged generative ensemble that contains spatiotemporally consistent precipitation trajectories. These trajectories are expected to improve the characterization of extreme precipitation events and offer skillful multi-day accumulated and 6-hourly precipitation guidance. The method is tested using the Global Ensemble Forecast System (GEFS) precipitation forecasts out to day 6 and is verified against the Climate-Calibrated Precipitation Analysis (CCPA) data. Verification results indicate that the method generated skillful ensemble members with improved Continuous Ranked Probabilistic Skill Scores (CRPSSs) and Brier Skill Scores (BSSs) over the raw operational GEFS and a multivariate statistical post-processing baseline. It showed skillful and reliable probabilities for events at extreme precipitation thresholds. Explainability studies were further conducted, which revealed the decision-making process of the method and confirmed its effectiveness on ensemble member generation. This work introduces a novel, generative-AI-based approach to address the limitation of small numerical ensembles and the need for larger ensembles to identify extreme precipitation events.

physics.ao-ph↗

arXiv2023

Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model

An ensemble post-processing method is developed for the probabilistic prediction of severe weather (tornadoes, hail, and wind gusts) over the conterminous United States (CONUS). The method combines conditional generative adversarial networks (CGANs), a type of deep generative model, with a convolutional neural network (CNN) to post-process convection-allowing model (CAM) forecasts. The CGANs are designed to create synthetic ensemble members from deterministic CAM forecasts, and their outputs are processed by the CNN to estimate the probability of severe weather. The method is tested using High-Resolution Rapid Refresh (HRRR) 1--24 hr forecasts as inputs and Storm Prediction Center (SPC) severe weather reports as targets. The method produced skillful predictions with up to 20% Brier Skill Score (BSS) increases compared to other neural-network-based reference methods using a testing dataset of HRRR forecasts in 2021. For the evaluation of uncertainty quantification, the method is overconfident but produces meaningful ensemble spreads that can distinguish good and bad forecasts. The quality of CGAN outputs is also evaluated. Results show that the CGAN outputs behave similarly to a numerical ensemble; they preserved the inter-variable correlations and the contribution of influential predictors as in the original HRRR forecasts. This work provides a novel approach to post-process CAM output using neural networks that can be applied to severe weather prediction.

cs.LG↗