Latent Neural Operator for Solving Forward and Inverse PDE Problems
This work addresses computational efficiency and accuracy challenges in solving PDEs for scientific computing applications, representing an incremental improvement over existing neural operator methods.
The authors tackled the high computational cost of neural operators for solving PDEs by introducing the Latent Neural Operator (LNO), which operates in a latent space, resulting in a 50% reduction in GPU memory, 1.8x faster training, and state-of-the-art accuracy on most benchmarks.
Neural operators effectively solve PDE problems from data without knowing the explicit equations, which learn the map from the input sequences of observed samples to the predicted values. Most existing works build the model in the original geometric space, leading to high computational costs when the number of sample points is large. We present the Latent Neural Operator (LNO) solving PDEs in the latent space. In particular, we first propose Physics-Cross-Attention (PhCA) transforming representation from the geometric space to the latent space, then learn the operator in the latent space, and finally recover the real-world geometric space via the inverse PhCA map. Our model retains flexibility that can decode values in any position not limited to locations defined in the training set, and therefore can naturally perform interpolation and extrapolation tasks particularly useful for inverse problems. Moreover, the proposed LNO improves both prediction accuracy and computational efficiency. Experiments show that LNO reduces the GPU memory by 50%, speeds up training 1.8 times, and reaches state-of-the-art accuracy on four out of six benchmarks for forward problems and a benchmark for inverse problem. Code is available at https://github.com/L-I-M-I-T/LatentNeuralOperator.