Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy
This work addresses robust, low-footprint classification for autonomous Raman spectroscopy in exploration scenarios like Mars rovers, though it is incremental in applying existing CNNs to this domain.
The paper tackled the problem of interpreting raw Raman spectra distorted by fluorescence baselines and peak shifts for autonomous instruments, achieving advances such as baseline-independent classification with compact CNNs surpassing traditional methods, robustness to Raman shifts up to 30 cm⁻¹, and up to 11% accuracy improvement with only 10% labels using semi-supervised techniques.
Autonomous Raman instruments on Mars rovers, deep-sea landers, and field robots must interpret raw spectra distorted by fluorescence baselines, peak shifts, and limited ground-truth labels. Using curated subsets of the RRUFF database, we evaluate one-dimensional convolutional neural networks (CNNs) and report four advances: (i) Baseline-independent classification: compact CNNs surpass $k$-nearest-neighbors and support-vector machines on handcrafted features, removing background-correction and peak-picking stages while ensuring reproducibility through released data splits and scripts. (ii) Pooling-controlled robustness: tuning a single pooling parameter accommodates Raman shifts up to $30 \,\mathrm{cm}^{-1}$, balancing translational invariance with spectral resolution. (iii) Label-efficient learning: semi-supervised generative adversarial networks and contrastive pretraining raise accuracy by up to $11\%$ with only $10\%$ labels, valuable for autonomous deployments with scarce annotation. (iv) Constant-time adaptation: freezing the CNN backbone and retraining only the softmax layer transfers models to unseen minerals at $\mathcal{O}(1)$ cost, outperforming Siamese networks on resource-limited processors. This workflow, which involves training on raw spectra, tuning pooling, adding semi-supervision when labels are scarce, and fine-tuning lightly for new targets, provides a practical path toward robust, low-footprint Raman classification in autonomous exploration.