The improvement in DLCR's performance against the gold standard ground truth over the baseline's performance shows its potential to correct, remap, and fine-tune the mesh-gridded forecasts under the supervision of observations.
Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe.
In this paper, we propose a convolutional variational autoencoder-based stochastic data-driven model that is pre-trained on an imperfect climate model simulation from a 2-layer quasi-geostrophic flow and re-trained, using transfer learning, on a small number of noisy observations from a perfect simulation.
no code implementations • 22 Feb 2022 • Jaideep Pathak, Shashank Subramanian, Peter Harrington, Sanjeev Raja, Ashesh Chattopadhyay, Morteza Mardani, Thorsten Kurth, David Hall, Zongyi Li, Kamyar Azizzadenesheli, Pedram Hassanzadeh, Karthik Kashinath, Animashree Anandkumar
FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor.
We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
As a proof-of-concept, we demonstrate our ML-PDE strategy on a two-dimensional turbulent (Rayleigh Number $Ra=10^9$) Rayleigh-B\'enard Convection (RBC) problem.
We consider the commonly encountered situation (e. g., in weather forecasting) where the goal is to predict the time evolution of a large, spatiotemporally chaotic dynamical system when we have access to both time series data of previous system states and an imperfect model of the full system dynamics.
Our technique leverages the results of a machine learning process for short time prediction to achieve our goal.
We examine the efficiency of Recurrent Neural Networks in forecasting the spatiotemporal dynamics of high dimensional and reduced order complex systems using Reservoir Computing (RC) and Backpropagation through time (BPTT) for gated network architectures.
A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the physical processes governing the dynamics to build an approximate mathematical model of the system.
For the case of the KS equation, we note that as the system's spatial size is increased, the number of Lyapunov exponents increases, thus yielding a challenging test of our method, which we find the method successfully passes.
A scheme that accomplishes this is called an “observer.” We consider the case in which a model of the system is unavailable or insufficiently accurate, but “training” time series data of the desired state variables are available for a short period of time, and a limited number of other system variables are continually measured.