Surface-Enhanced Raman Spectroscopy–Machine Learning for Multiplex Naphthenic Acid Profiling in Water
Bibliographic record
Abstract
Naphthenic acids (NAs) contribute to the toxicity of vast industrial effluents and present a considerable risk to aquatic ecosystems. This study presents a sensitive, data-driven approach to the detection and quantification of diverse NAs in water, leveraging surface-enhanced Raman spectroscopy (SERS) and machine learning (ML). Our methodology employs highly uniform silver (Ag) nanoparticles, dispersed in NA-containing water with a cationic surfactant added to enhance acid–nanoparticle interactions and boost SERS signals. The detection limits were as low as 10 –4 to 10 –5 M for eight distinct NA types across three groups, encompassing classical linear, cyclic, and heteroatom-containing NAs (sulfur and nitrogen). SERS spectral data were rigorously utilized to train machine learning models. For single acid identification, a random forest (RF) model demonstrated an 86.3% classification accuracy via 7-fold cross-validation. Furthermore, ridge regression models, trained on fast Walsh-Hadamard transformed (FWHT) spectra, scaling, and principal component analysis (PCA), yielded remarkable average R 2 values of 99.5% for the concentration prediction of most acids. To address the complexities of acid mixture samples, a Siamese convolutional neural network (SNN) was developed to accurately identify multiple acid types within complex samples by comparing mixture spectral fingerprints with individual acid reference fingerprints, achieving an overall identification accuracy of 95%. The model’s reliability in multilabel acid detection is further corroborated by averaged F1 scores of approximately 95%. This work emphatically demonstrates the suitability of SERS spectroscopy, utilizing colloidal silver nanoparticles and machine learning algorithms, for the simultaneous identification and quantification of multiple NAs in complex samples. This method eliminates the need for extraction or separation, offering a proof of concept for the sensitive detection of naphthenic acids in environmental samples.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".