Search Results for author:
Found 4 papers, 3 papers with code
Pretraining a Neural Operator in Lower Dimensions
We evaluated the effectiveness of this pretraining strategy in similar PDEs in higher dimensions.
Strategies for Pretraining Neural Operators
Pretraining for partial differential equation (PDE) modeling has recently shown promise in scaling neural operators across datasets to improve generalizability and performance.
Multi-scale Time-stepping of Partial Differential Equations with Transformers
Developing fast surrogates for Partial Differential Equations (PDEs) will accelerate design and optimization in almost all scientific and engineering applications.
Surrogate Modeling of Melt Pool Thermal Field using Deep Learning
In this work, we create three datasets of single-trail processes using Flow-3D and use them to train a convolutional neural network capable of predicting the behavior of the three-dimensional thermal field of the melt pool solely by taking three parameters as input: laser power, laser velocity, and time step.
