Invention Application
- Patent Title: A HYBRID DEEP PHYSICS NEURAL NETWORK FOR PHYSICS BASED SIMULATIONS
-
Application No.: US17628610Application Date: 2019-08-30
-
Publication No.: US20220275714A1Publication Date: 2022-09-01
- Inventor: Srinath MADASU , Keshava Prasad RANGARAJAN
- Applicant: LANDMARK GRAPHICS CORPORATION
- Applicant Address: US TX Houston
- Assignee: LANDMARK GRAPHICS CORPORATION
- Current Assignee: LANDMARK GRAPHICS CORPORATION
- Current Assignee Address: US TX Houston
- International Application: PCT/US2019/049181 WO 20190830
- Main IPC: E21B43/16
- IPC: E21B43/16

Abstract:
Aspects of the subject technology relate to systems and methods for predicting physical characteristics of a physical environment using a physical characterization model trained based on simulated states of a modeled physical environment. A physical characterization model can be generated based on a plurality of simulated states of a modeled physical environment. Specifically, the physical characterization model can be trained by mapping simulated spatial properties of the modeled physical environment temporally across the plurality of simulated states of the modeled physical environment. Further, input state data describing one or more input states of a physical environment can be received. One or more physical characteristics of the physical environment can be predicted by applying the physical characterization model to the one or more input states of the physical environment.
Information query