US-12619001-B2 - Regionalized climate models using physics-informed neural networks

US12619001B2US 12619001 B2US12619001 B2US 12619001B2US-12619001-B2

Abstract

A method, a computer system, and a computer program product for regionalized climate models is provided. Embodiments of the present invention may include selecting a class of a reduced order model. Embodiments of the present invention may include building a neural network in a reduced order space. Embodiments of the present invention may include recovering full state dynamics. Embodiments of the present invention may include training a model. Embodiments of the present invention may include providing an output.

Inventors

Etienne Eben Vos
Campbell D Watson
Alberto Costa Nogueira Junior
Bianca Zadrozny
Komminist Weldemariam

Assignees

INTERNATIONAL BUSINESS MACHINES CORPORATION

Dates

Publication Date: 20260505
Application Date: 20210423

Claims (15)

1 . A method for creating improved regionalized climate models using physics-informed neural networks in a latent space, the method comprising: selecting a class of a reduced order model, the reduced order model a physics-informed neural network for reduced order modeling, the reduced order model including an encoder, a decoder, and physics informed-constraints; building a neural network in a reduced order space; recovering full state dynamics using the decoder of the reduced order model, recovering the full state dynamics including selecting a loss function for a full order space, the loss function related to the built neural network; training a model using ontologies or knowledge graphs, the model trained to predict weather or provide climate statistics; and providing an output.
2 . The method of claim 1 , wherein the class is selected based on physics of the data.
3 . The method of claim 1 , wherein a loss function is selected for the reduced order space based on physics of the data.
4 . The method of claim 1 , wherein recovering the full state dynamics includes selecting physical constraints based on known partial differential equations that govern a weather system or a climate system.
5 . The method of claim 1 , wherein the output provides a summarization of the model based on deriving an interpretation of a cause and an effect from the latent space.
6 . The method of claim 1 , wherein the neural network is associated with hyperparameters, the hyperparameters selected using a hyperparameter optimization software framework.
7 . A computer system for creating improved regionalized climate models using physics-informed neural networks in a latent space, comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising: selecting a class of a reduced order model, the reduced order model a physics-informed neural network for reduced order modeling, the reduced order model including an encoder, a decoder, and physics informed-constraints; building a neural network in a reduced order space; recovering full state dynamics using the decoder of the reduced order model, recovering the full state dynamics including selecting a loss function for a full order space, the loss function related to the built neural network; training a model using ontologies or knowledge graphs, the model trained to predict weather or provide climate statistics; and providing an output.
8 . The computer system of claim 7 , wherein the class is selected based on physics of the data.
9 . The computer system of claim 7 , wherein a loss function is selected for the reduced order space based on physics of the data.
10 . The computer system of claim 7 , wherein recovering the full state dynamics includes selecting physical constraints based on known partial differential equations that govern a weather system or a climate system.
11 . The computer system of claim 7 , wherein the output provides a summarization of the model based on deriving an interpretation of a cause and an effect from the latent space.
12 . A computer program product for creating improved regionalized climate models using physics-informed neural networks in a latent space, comprising: one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more computer-readable tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising: selecting a class of a reduced order model, the reduced order model a physics-informed neural network for reduced order modeling, the reduced order model including an encoder, a decoder, and physics informed-constraints; building a neural network in a reduced order space; recovering full state dynamics using the decoder of the reduced order model, recovering the full state dynamics including selecting a loss function for a full order space, the loss function related to the built neural network; training a model using ontologies or knowledge graphs, the model trained to predict weather or provide climate statistics; and providing an output.
13 . The computer program product of claim 12 , wherein the class is selected based on physics of the data.
14 . The computer program product of claim 12 , wherein a loss function is selected for the reduced order space based on physics of the data.
15 . The computer program product of claim 12 , wherein recovering the full state dynamics includes selecting physical constraints based on known partial differential equations that govern a weather system or a climate system.

Description

BACKGROUND The present invention relates generally to the field of computing, and more particularly to machine learning. Extreme weather changes and impacts on the climate are increasing in the amount of changes that are occurring and in the complexity of weather patterns. Climate extremes can affect weather conditions and climate variability, both of which can have significant impacts on businesses and regions. SUMMARY Embodiments of the present invention disclose a method, a computer system, and a computer program product for regionalized climate models. Embodiments of the present invention may include selecting a class of a reduced order model. Embodiments of the present invention may include building a neural network in a reduced order space. Embodiments of the present invention may include recovering full state dynamics. Embodiments of the present invention may include training a model. Embodiments of the present invention may include providing an output. BRIEF DESCRIPTION OF THE DRAWINGS These and other objects, features and advantages of the present invention will become apparent from the following detailed description of illustrative embodiments thereof, which is to be read in connection with the accompanying drawings. The various features of the drawings are not to scale as the illustrations are for clarity in facilitating one skilled in the art in understanding the invention in conjunction with the detailed description. In the drawings: FIG. 1 illustrates a networked computer environment according to at least one embodiment; FIG. 2 is a block diagram of example architecture for building a regionalized climate model using physics-informed neural networks in the latent space according to at least one embodiment; FIG. 3 is an operational flowchart illustrating a process for building a regionalized climate model using physics-informed neural networks in the latent space according to at least one embodiment; FIG. 4 is a block diagram of internal and external components of computers and servers depicted in FIG. 1 according to at least one embodiment; FIG. 5 is a block diagram of an illustrative cloud computing environment including the computer system depicted in FIG. 1, in accordance with an embodiment of the present disclosure; and FIG. 6 is a block diagram of functional layers of the illustrative cloud computing environment of FIG. 5, in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION Detailed embodiments of the claimed structures and methods are disclosed herein, however, it can be understood that the disclosed embodiments are merely illustrative of the claimed structures and methods that may be embodied in various forms. This invention may, however, be embodied in many different forms and should not be construed as limited to the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this invention to those skilled in the art. In the description, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the presented embodiments. As previously described, extreme weather changes and impacts on the climate are increasing in the amount of changes that are occurring and in the complexity of weather patterns. Climate extremes can affect weather conditions and climate variability, both of which can have significant impacts on businesses and regions. Higher-fidelity regional climate models now exist, such as models with 1-10 km grid spacing, that offer some improvement to local climates. However, the current models have some critical issues, such as systematic errors in global climate models propagated into regional climate models due to a requirement of calibration of many model parameters. Another issue may include computational expenses that make the models impractical for high-impact climate resilience studies that require large sets of forecasts for uncertainty quantification and confidence scoring. Surrogate models for fluid dynamics exist but these models present a unique challenge due to compressibility and having phase changes, such as from a gaseous state of water to a liquid state of water with resulting energy transfers. The fluid dynamics and phase changes are significantly more complicated than an incompressible Navier-Stokes computation. Current surrogate models for complex fluid flows, such as sparse identification of nonlinear dynamics (SINDy) make assumptions about or need to know the governing equations of the physical phenomenon that limits the model's applicability to very complex systems. Physics-informed machine learning or artificial intelligence regional climate models solve computationally extensive calculations and cost a significant amount of money to build and operate. However, the current regional climate models may have unresolved issues, some include limitations on the model grid resoluti