Optimizing image-based soil organic matter prediction: Effects of illumination type and intensity
Bibliographic record
Abstract
• Device-specific illumination thresholds revolutionize digital soil color measurement accuracy. • CIE La*b* and CIE Lu*v* color spaces outperform RGB features in soil organic matter prediction. • Smartphones achieve optimal performance at 300–500 lux, digital cameras at 400–600 lux. • Warm lighting provides superior stability compared to natural light at moderate intensities. • Random Forest models excel in calibration while SVM models show stronger validation performance. Image-based soil organic matter (SOM) prediction has emerged as a promising approach for rapid soil assessment, but illumination variations significantly impact measurement reliability. This study provides a comprehensive analysis of illumination effects on soil color measurements and develops an optimized framework for image acquisition across different devices and lighting conditions. Soil samples ( n = 500) collected from southern Ontario, Canada were imaged under six illumination levels (100–900 lux) using both natural daylight (> 5000 k), representing cool lighting condition, and warm lighting (2700–3000 K) to simulate typical indoor condition. Images were captured using a smartphone (iPhone 14 Pro) and digital camera (Sony α7 III), with systematic evaluation of color feature stability and prediction accuracy. Mixed-model analysis revealed device-specific optimal illumination ranges for effective image feature extraction, with smartphones performing best between 300–500 lux (RMSE=0.232, CCC=0.892) and digital cameras maintaining stability up to 600 lux (RMSE=0.173, CCC=0.931). Color features from opponent-based color spaces (CIE La*b* and CIE Lu*v*) demonstrated superior stability and consistency compared to those from additive color spaces (RGB and HSV), which encode color through separate channels rather that perceptual opponent relationship. Warm lighting provided more consistent results at lower illumination levels, while natural lighting showed greater stability at higher intensities. Random Forest machine learning models achieved optimal performance under moderate illumination levels (400–500 lux) for both devices. The findings establish quantitative relationships between illumination parameters and prediction accuracy, advancing the development of reliable image-based soil analysis methods by addressing critical gaps in illumination control and feature stability.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".