Advancing Soil and Environmental Analysis with Dual-Wavelength Raman Spectroscopy and Machine Learning 
Bibliographic record
Abstract
Advanced environmental measurements require versatile, high-throughput methodologies that can analyze complex and heterogeneous systems. Raman spectroscopy presents a promising solution as an optical measurement technique, owing to its minimal sample preparation requirements, real-time and non-destructive measurements, and its potential for field deployment. However, its adoption in environmental applications has been limited by challenges such as fluorescence interference and sample heterogeneity. Here, we describe a dual-wavelength Raman spectroscopy approach that overcomes these challenges, enabling precise and reliable measurements of soil. Central to our approach is a custom Shifted-Excitation Raman Difference Spectroscopy (SERDS) instrument, which integrates advanced optical design, signal processing, and machine-learning multivariate analysis. We utilize our SERDS methodology to measure soil organic carbon (SOC) in agricultural soils and tire wear particles. By leveraging custom spectral collection strategies and signal processing tools, such as common-mode rejection (CMR) along with hyperspectral data fusion techniques, we effectively mitigate fluorescence interference, particle size variations, and nonlinear optical behavior in soils for accurate SOC and tire wear quantification. Nonlinear machine-learning regression techniques, including tree-based models and a custom Partial Least Squares Regression algorithm, enhance predictive accuracy and validate the methodology. While the measurement of SOC and tire wear particles in soil highlight the potential of our SERDS methodology in advancing real-time and high-throughput soil measurements, its versatility extends to a broad range of environmental sensing applications, including water quality monitoring, pollutant detection, and the analysis of complex environmental systems. This research presents an in-depth examination of the design and implementation of the SERDS instrument and methodology, showcasing its potential for advancing environmental measurement and its adaptability for addressing a wide range of analytical challenges in environmental science.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".