Integration of synthetic aperture radar and optical satellite data for corn biomass estimation
Bibliographic record
Abstract
Efforts to use satellites to monitor the condition and productivity of crops, although extensive, can be challenging to operationalize at field scales in part due to low frequency revisit of higher resolution space-based sensors, in the context of an actively growing crop canopy. The presence of clouds and cloud shadows further impedes the exploitation of high resolution optical sensors for operational monitoring of crop development. The objective of this research was to present an option to facilitate greater temporal observing opportunities to monitor the accumulation of corn biomass, by integrating biomass products from Synthetic Aperture Radar (SAR) and optical satellite sensors. To accomplish this integration, a transfer function was developed using a Neural Network algorithm to relate estimated corn biomass from SAR to that estimated from optical data. With this approach, end users can exploit biomass products to monitor corn development, regardless of the source of satellite data.•The Water Cloud Model (WCM) was calibrated or parametrized for horizontal transmit and horizontal received (HH) and horizontal transmit and vertical received (HV) C-band SAR backscatter using a least square algorithm.•Biomass and volumetric soil moisture were estimated from dual-polarized RADARSAT-2 images without any ancillary input data.•A feed forward backpropagation Neural Network algorithm was trained as a transfer function between the biomass estimates from RADARSAT-2 and the biomass estimates from RapidEye.
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 | 0.000 | 0.001 |
| 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".