Memory-based parameterization with differentiable solver: Application to Lorenz '96
Mohamed Aziz Bhouri1, Pierre Gentine1
1Department of Earth and Environmental Engineering, Columbia University, New York, New York 10027, USA.
Chaos (Woodbury, N.Y.)
|July 6, 2023
Summary
New memory-based neural networks improve weather and climate models by better representing small-scale processes. This approach enhances prediction accuracy and stability, overcoming limitations of current machine learning parameterizations.
Area of Science:
- Atmospheric Science
- Climate Modeling
- Machine Learning
Background:
- Physical parameterizations represent unresolved subgrid processes in climate models.
- Machine learning parameterizations show promise but struggle with process stochasticity.
Purpose of the Study:
- To develop a novel memory-based neural network parameterization to address stochasticity and improve prediction accuracy.
- To enhance the stability and non-instantaneous response of closures in climate models.
Main Methods:
- Implemented memory-based neural networks with a differentiable solver.
- Applied the new parameterization to the Lorenz '96 model with coarse temporal resolution.
Main Results:
- The memory-based parameterization demonstrated skillful forecasts over long time horizons.
- Achieved improved prediction accuracy and stability compared to instantaneous parameterizations.
Conclusions:
- Memory-based parameterizations offer a promising solution for closure problems in climate modeling.
- This approach can reduce uncertainties associated with stochastic processes.
Related Concept Videos
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
81
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
81
01:13Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
96
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
96
01:21Linear Approximation in Time Domain
107
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
107
01:17Ampere-Maxwell's Law: Problem-Solving
676
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
676
01:24One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
582
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
582
01:26Linear Approximation in Frequency Domain
115
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
115