Depth‐Specific Prediction of Soil Properties In Situ using vis‐NIR Spectroscopy
Bibliographic record
Abstract
Visible‐near infrared (Vis‐NIR) spectroscopy has been used to efficiently and accurately predict various soil properties and has shown potential in digital soil mapping (DSM). Recent developments in three‐dimensional (3D)‐DSM sought additional attention on vis‐NIR spectroscopy. However, environmental and sampling challenges of in situ and depth‐specific measurement of vis‐NIR spectra limited its potential. This paper aims to test the predictive ability and performance of in situ vis‐NIR spectra for various soil physical and chemical properties for the whole soil profile and at different depths. Visible near infrared spectra (397‐ to 2212‐nm wavelength) were continuously collected in situ using Veris P4000 soil profiler at 32 locations down to a 1‐m maximum depth from an agricultural field at Macdonald Farm, McGill University. Soil cores were also collected at the same locations and subsampled at every 10‐cm intervals. A total of 257 samples were measured for a range of soil physical and chemical properties in the laboratory. The total dataset was randomly separated into calibration (70%) and validation dataset (30%). Cubist models were developed to calibrate vis‐NIR spectra against laboratory measured soil properties and evaluated by validation dataset. In addition, two consecutive depths (0–20, 20–40, 40–60, 60–80, and 80–100 cm) were combined for depth‐specific Cubist model fitting which was validated by leave‐one‐out cross validation. Vis‐NIR spectra showed the strongest potential to predict soil organic matter (SOM), water content, and clay content with high accuracy. Other soil properties that were either positively or negatively correlated with SOM, clay, water content were also predicted with good accuracy. Prediction accuracy was found to be independent of soil depth but dependent on the actual values and the range of the soil properties measured. This study clearly showed the potential of vis‐NIR spectroscopy for in situ and depth‐specific prediction of soil properties and gave the new avenue of data collection for 3D‐DSM.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".