Combining proximal and remote sensors for regional soil characterization in rural Haiti
Bibliographic record
Abstract
Agronomic optimization is critical in developing countries, especially where soil resources are constrained. This research, the first of its kind in Haiti, used predictive modeling to relate laboratory-derived physical and chemical soil data to proximal and remotely sensed data collected on 32,949 georeferenced surface soil (0–20 cm) samples in the Arcahaie region. A representative subset of collected samples ( n = 300) was then tested using a litany of predictive models (e.g., random forest, gradient boosting, stacking ensemble, XGBoost) relating the lab-derived to proximally sensed data for the prediction of soil pH, sand, silt, clay, soil organic matter, cation exchange capacity, soil organic carbon, and plant available P, K, Si, Fe, and Cu. Results showed that sand, silt, clay, soil organic carbon, soil organic matter and cation exchange capacity all have predictive R 2 of ≥0.80; predictions of soil texture components and soil organic carbon/organic matter were particularly strong. Other parameters, while still significant, were less robust. The models were used to predict the physical and chemical properties of the full dataset, then spatially interpolated to provide parameter variability maps across the region in support of agronomic optimization. Future research should work to extend the methodology successfully demonstrated herein to other regions of agronomic importance in Haiti and other developing countries. Furthermore, the approaches could be extended to three-dimensional modeling of subsoil properties elucidating optimal soil fertility in the rooting zone.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".