Trustworthiness of Laser-Induced Breakdown Spectroscopy Predictions via Simulation-based Synthetic Data Augmentation and Multitask Learning

no code implementations • 7 Oct 2022 • Riccardo Finotello, Daniel L'Hermite, Celine Quéré, Benjamin Rouge, Mohamed Tamaazousti, Jean-Baptiste Sirven

The procedure is an end-to-end pipeline including the process of synthetic data augmentation, the construction of a suitable robust, homoscedastic, deep learning model, and the validation of its predictions.

Data Augmentation Dimensionality Reduction