Field-Scale Detection of Crop Seeding Date Using Sentinel-1 Coherence Time Series
Bibliographic record
Abstract
Seeding date plays a crucial role in crop monitoring and yield estimation. Traditional methods, which estimate seeding dates by observing phenological stages such as the start of the season and back-calculating, are often affected by environmental and management variations. Detecting seeding dates directly from field changes before and after seeding offers a simpler and more robust alternative. However, existing approaches face challenges in accurately and efficiently determining seeding dates at the field scale. This study proposes a novel method for estimating seeding dates using Sentinel-1 constellation interferometric synthetic aperture radar (InSAR) coherence time series. The method identifies seeding activities by detecting changes in InSAR coherence caused by soil disturbances during seeding and applies thresholding and decision rules to analyze the time series. It also addresses practical challenges, such as successive seeding operations and reseeding due to adverse weather. Additionally, the method leverages the partial overlapping orbital footprints of Sentinel-1 to integrate data from multiple orbits, improving the reliability and accuracy of seeding date estimation. Applied to 89 and 79 experimental corn fields in 2019 and 2020 near London, Ontario, Canada, the method achieved RMSEs ranging from 5.99 to 9.89 days for individual orbits, outperforming the benchmark method. Integrating data from two orbits further reduced the RMSE to 6.74 days in 2019 and 5.59 days in 2020. When tested on over 1,000 soybean fields and 2,000 corn fields in 2019 and 2020, the method demonstrated strong agreement with local agricultural progress reports.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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".