Multi-platform remote sensing of nitrogen status and leaching from agricultural fields with random forest regression approach
Bibliographic record
Abstract
Advances in satellite- and drone-based technologies, such as increased spatio-temporal and spectral resolution, in combination with improved computational algorithms, including machine learning, have proven to be useful tools altogether in assessing crop nitrogen (N) status and facilitating precision agriculture. However, it remains challenging to accurately determine in-season crop N status and detach split fertilization from residual soil N prone to losses during (gaseous emissions) and after the growth season (leaching). We conducted a three-year potato field experiment on sandy soil in Denmark (Peng et al. 2021) and determined single-shot in-season plant N uptake (PNU), concentration (PNC) and N nutrition index (NNI; based on the critical N dilution curve). Multispectral data obtained by spaceborne- (Sentinel-2), air- (unmanned aerial vehicle, UAV) and ground (handheld Rapidscan) platforms were correlated with the measured variables, with random forest machine learning regression achieving very high prediction accuracy of < 10kg N ha-1 uncertainty. We also measured nitrate concentration in the soil solution at the end of the root zone, and these measurements showed on average consistently lower values for the split- (16-42 ppm) compared to the full (20-57 ppm) fertilization strategy, with reductions reaching 37% at the peak of the leaching season in November. The approach of accurately detecting plant N requirement and supplying fertilization accordingly, which leaves little substrate of reactive N pool in the soil during and after the growth season is promising for the smart farming industry in the struggle to limit nitrous oxide emissions and N leaching by keeping soil nitrate concentration at low levels. More work should also be done on bridging N deficiency from other abiotic stresses, especially drought, in order to further improve N application recommendation.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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".