Deep learning for Gaussian process tomography model selection using the ASDEX Upgrade SXR system
arXiv:2004.06429 · doi:10.1063/5.0020680
Abstract
Gaussian process tomography (GPT) is a method used for obtaining real-time tomographic reconstructions of the plasma emissivity profile in a tokamak, given some model for the underlying physical processes involved. GPT can also be used, thanks to Bayesian formalism, to perform model selection -- i.e., comparing different models and choosing the one with maximum evidence. However, the computations involved in this particular step may become slow for data with high dimensionality, especially when comparing the evidence for many different models. Using measurements collected by the ASDEX Upgrade Soft X-ray (SXR) diagnostic, we train a convolutional neural network (CNN) to map SXR tomographic projections to the corresponding GPT model whose evidence is highest. We then compare the network's results, and the time required to calculate them, with those obtained through analytical Bayesian formalism. In addition, we use the network's classifications to produce tomographic reconstructions of the plasma emissivity profile, whose quality we evaluate by comparing their projection into measurement space with the existing measurements themselves.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- Weight Uncertainty in Neural Networks
- Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
- Deep learning for plasma tomography using the bolometer system at JET
- Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
- Developement of real time diagnostics and feedback algorithms for JET in view of the next step