Optimizing potato yield mapping and prediction: Integrating satellite-based remote sensing and machine learning for sustainable agriculture
Bibliographic record
Abstract
Precision agriculture and sustainable farming require crop yield prediction and mapping. PEI is a major Canadian potato producer. However, PEI potato yield prediction research is limited. This highlights a literature gap and the need for improved data-driven precision agriculture in PEI. High-resolution satellite imagery and machine learning (ML) enable field-scale crop yield mapping. This study investigated the potential of high-resolution multispectral imagery and ML for potato yield prediction. The study focused on four plots in PEI during the 2021 and 2022 growing seasons. Potato crop yield data collected using a combined harvester and manual digging were analyzed to model yield using Sentinel-2A and PlanetScope imagery. For both sensors, vegetation indices (NDVI, GNDVI, SAVI, and EVI) and spectral bands chosen for their application in crop growth monitoring were retrieved and incorporated into ML models. The cloud computing platform, Google Earth Engine (GEE), was used to evaluate and compare the performance of three ML algorithms, which are random forest regression (RFR), classification and regression trees (CART) and gradient tree boosting (GTB). Overall, the performance of all three models was satisfactory in yield prediction with both sensors. However, GTB with Sentinel-2A and harvester data gave slightly higher estimation accuracy with R 2 values of 0.71–0.78, RMSE values of 2.82–5.96 t/ha, and MAE values of 2.33–4.2 t/ha. Hence, the approach used in this study provides real-time seasonal yield prediction maps on a field scale, which will help the farmers identify the targeted areas for variable rate application, leading to resource efficiency and sustainability.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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".