A5028209366- Meteorological Phenomena and Simulations
- Climate variability and models
- Data-Driven Disease Surveillance
- Data Analysis with R
- Heat Transfer and Numerical Methods
- Engineering and Technology Innovations
- Cryospheric studies and observations
- Explainable Artificial Intelligence (XAI)
- Scientific Computing and Data Management
- Oceanographic and Atmospheric Processes
- Statistical Methods and Inference
- COVID-19 epidemiological studies
- Data Quality and Management
- COVID-19 and healthcare impacts
- Computational Physics and Python Applications
University of California, Berkeley
2022-2024
As the COVID-19 outbreak evolves, accurate forecasting continues to play an extremely important role in informing policy decisions. In this paper, we present our continuous curation of a large data repository containing information from range sources. We use develop predictions and corresponding prediction intervals for short-term trajectory cumulative death counts at county-level United States up two weeks ahead. Using January 22 June 20, 2020, combine multiple forecasts using ensembling...
simChef is an R package that empowers data science practitioners to rapidly plan, carry out, and summarize statistical simulation studies in a flexible, efficient, low-code manner.Drawing substantially from the Predictability, Computability, Stability (PCS) framework (Yu & Kumbier, 2020), emphasizes scientific best practices encompassed by PCS removing many of administrative burdens design through: (1) intuitive tidy grammar simulations; (2) powerful abstractions for distributed processing...
Abstract Can the current successes of global machine learning‐based weather simulators be generalized beyond 2‐week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate Emulator (ACE) suggests this is feasible, based upon 10‐year simulations with a network trained on output from physics‐based atmosphere model using grid spacing approximately 110 km forced by repeating annual cycle sea‐surface temperature. Here we show that ACE, without modification, can emulate...
VeridicalFlow is a Python package that simplifies building reproducible and trustworthy data science pipelines using the PCS (predictability-computability-stability) framework (Yu & Kumbier, 2020).It provides users with simple interface for stability analysis, i.e., checking robustness of results from pipeline to various judgement calls made during modeling.This ensures arbitrary by practitioners (e.g., specifying default imputation strategy) do not dramatically alter final conclusions in...
Can the current successes of global machine learning-based weather simulators be generalized beyond two-week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate Emulator (ACE) suggests this is feasible, based upon 10-year simulations trained on a realistic atmosphere model using grid spacing approximately 110~km forced by repeating annual cycle sea-surface temperature. Here we show that ACE, without modification, can emulate another major atmospheric model,...
Can the current successes of global machine learning-based weather simulators be generalized beyond two-week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate Emulator (ACE) suggests this is feasible, based upon 10-year simulations with a network trained on output from physics-based atmosphere model using grid spacing approximately 110 km forced by repeating annual cycle sea-surface temperature. Here we show that ACE, without modification, can emulate...