OASIS: A Deep Learning Framework for Universal Spectroscopic Analysis Driven by Novel Loss Functions
Not on the map. Why?
Abstract (arXiv)
The proliferation of spectroscopic data across various scientific and engineering fields necessitates automated processing. We introduce OASIS (Omni-purpose Analysis of Spectra via Intelligent Systems), a machine learning (ML) framework for technique-independent, automated spectral analysis, encompassing denoising, baseline correction, and comprehensive peak parameter (location, intensity, FWHM) retrieval without human intervention. OASIS achieves its versatility through models trained on a strategically designed synthetic dataset incorporating features from numerous spectroscopy techniques. Critically, the development of innovative, task-specific loss functions-such as the vicinity peak response (ViPeR) for peak localization-enabled the creation of compact yet highly accurate models from this dataset, validated with experimental data from Raman, UV-vis, and fluorescence spectroscopy. OASIS demonstrates significant potential for applications including in situ experiments, high-throughput optimization, and online monitoring. This study underscores the optimization of the loss function as a key resource-efficient strategy to develop high-performance ML models.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 43 references that are in the map. First posted on arXiv 15 Sep 2025.
Builds on
7 of 43 references.
References · 7
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
- 2021Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationcited by 88
- 2017Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solutioncited by 25
- 2019Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learningcited by 16
- 2019Higher-order total variation approaches and generalisationscited by 14
- 2020High-throughput molecular imaging via deep learning enabled Raman spectroscopycited by 9
- 2024NeurTV: Total Variation on the Neural Domaincited by 7
Built on by
Not cited yet.