Comparison of laser-induced breakdown spectroscopy, colour sensing, as well as visible, near-infrared, and mid-infrared spectroscopy to predict soil properties
Bibliographic record
Abstract
• Seven different instruments to predict soil properties using the same samples were compared. • Soil properties included P, K, Ca, Mg, Al, buffer pH, pH, SOM, and CEC. • LIBS and Vis-NIR sensor systems produced results with relatively lower uncertainties. • Several prediction models, all for CEC, yielded relatively accurate predictions. • Neither instrument was able to overperform commercial labs for P, pH, Mg, and SOM. Seven spectroscopic instruments’ ability to predict nine soil chemical properties [ i.e. , extractable phosphorus (P), extractable potassium (K), calcium (Ca), magnesium (Mg), aluminum (Al), soil pH (pH), buffer pH (BpH), soil organic matter (SOM) and cation exchange capacity (CEC)] were assessed using a diverse set of 798 air-dried and compressed soil samples from Southern Quebec. The instruments varied in terms of spectral range and resolution [ e.g ., colour/visible (Vis), visible and near-infrared (Vis-NIR), mid-infrared (MIR), and laser-induced breakdown spectroscopy (LIBS)], complexity, and interaction with the target. The performance of these instruments was compared using relevant test statistics derived from partial least squares regression (PLSR) models, such as the root mean squared error of prediction (RMSE P ) and the coefficient of determination (R 2 ) for simple linear regressions between sensor measurements and soil test reference values. Analysis of the LIBS spectra produced the lowest RMSE P values for P, K, Mg, Ca, pH, BpH, and SOM, while two Vis-NIR instruments yielded prediction models with the lowest RMSE P for Al and CEC. Overall, prediction models were relatively accurate for Ca, Mg, Al, SOM, and CEC (R 2 = 0.70–0.81), and less certain for P, pH, BpH, and K (R 2 = 0.53–0.65).
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 | 0.003 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".