Related Experiment Video
Updated: Jun 12, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
981
Spectral Zones-Based SHAP/LIME: Enhancing Interpretability in Spectral Deep Learning Models Through Grouped Feature
Jhonatan Contreras1,2, Andreea Winterfeld1,2, Juergen Popp1,2
1Institute of Physical Chemistry (IPC) and Abbe Center of Photonics (ACP), Member of the Leibniz Centre for Photonics in Infection Research (LPI), Friedrich Schiller University Jena, Helmholtzweg 4, 07743 Jena, Germany.
Analytical Chemistry
|September 18, 2024
Summary
Explainable AI (XAI) for spectroscopy is improved by analyzing spectral zones instead of individual features. This new method enhances realism and interpretability in deep learning models.
Area of Science:
- Spectroscopy
- Artificial Intelligence
- Machine Learning
Background:
- Interpretability is crucial for complex deep learning models, particularly in spectroscopy.
- Existing Explainable AI (XAI) methods like SHAP and LIME often rely on individual feature perturbations, which can be unrealistic.
- Current XAI literature for spectroscopy primarily focuses on independent feature analysis, neglecting zone analysis.
Purpose of the Study:
- To develop a more realistic and interpretable XAI method for spectroscopy.
- To address the limitations of individual feature perturbation methods in XAI.
- To enhance the understanding of deep learning model behavior in spectroscopic analysis.
Main Methods:
- Developed modified versions of SHAP and LIME to perform group perturbations on spectral zones.
- Implemented an efficient approach for calculating spectral zones in complex spectra.
- Allowed users to define spectral zones based on domain expertise.
Main Results:
- The proposed method enhances the realism and interpretability of XAI in spectroscopy.
- Group perturbations on spectral zones provide more intuitive and physically meaningful explanations.
- Minimized noise in interpretability plots compared to individual feature analysis.
Conclusions:
- Analyzing spectral zones offers a more robust and realistic approach to XAI in spectroscopy.
- Modified LIME and SHAP methods effectively capture the impact of group disturbances.
- The developed XAI technique improves the trustworthiness and applicability of deep learning models in spectroscopic applications.
