Prediction and monitoring of soil pH using field reflectance spectroscopy and time-series Sentinel-2 remote sensing imagery
Bibliographic record
Abstract
Soil pH is an important property that is widely used in soil and environmental sciences. Remote sensing imagery could significantly improve the prediction efficiency and has the advantage of periodic monitoring. To investigate and monitor soil pH efficiently, time-series Sentinel-2 remote sensing imagery was used for predicting and monitoring of soil pH. The study area selected was Qian’an County, Jilin Province, China. A total of 141 soil samples were collected, and their reflectance spectra were measured in situ. Time-series Sentinel-2 images were acquired for 2022 to 2024. The field reflectance spectra were used to develop a prediction model and examine the sensitivity of the prediction to the spectral sampling interval. Genetic algorithm (GA) and partial least squares regression (PLSR) were adopted for model calibration using the full spectral range of the field reflectance spectra, and multiple linear regression (MLR) was adopted to calibrate the prediction model using multispectral datasets. In prediction of soil pH using the full spectral range, root mean square error (RMSE) and coefficient of determination (R 2 ) values are 0.29 and 0.87. In the prediction using multispectral datasets, the optimal RMSE and R 2 values were 0.45 and 0.70 for the prediction using identified important spectral bands of the field reflectance spectra and 0.45 and 0.69 for the prediction using simulated Sentinel-2 spectra. A six-band prediction model developed using simulated Sentinel-2 spectra was selected to predict and monitor soil pH using time-series Sentinel-2 remote sensing images. The generated pH maps depicted the spatial distribution of soil pH, and the predicted values were comparable to those obtained by chemical analysis in the variation range. Spatial variations in soil pH from 2022 to 2024 were revealed with pH maps generated from time-series remote sensing images. This study provides an alternative for the rapid prediction and monitoring of soil pH using Sentinel-2 remote sensing imagery. • Important spectral bands for the prediction of soil pH remain relatively stable. • The sensitivity of soil pH prediction to spectral sampling interval is moderate. • Sentinel-2 remote sensing imagery can be used for predicting soil pH. • Short-wave infrared spectral bands help improve the prediction of soil pH. • Time-series Sentinel-2 images achieve the monitoring of soil pH over time.
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 | 0.001 |
| 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 | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".