Satellite Imagery and AI-Based Detection of Common Waterhemp (AMATU) Infestation in Soybean Fields
Bibliographic record
Abstract
Recent advances in Earth Observation (EO) and artificial intelligence (AI) have enabled scalable solutions for sustainable crop management. In Quebec soybean fields, weeds such as common waterhemp (Amaranthus tuberculatus, AMATU) are spreading rapidly, showing strong resistance to herbicides and threatening crop productivity. To address this challenge, we propose an operational pipeline that combines very highresolution (0.5 m) multispectral Pleiades imagery, ground-verified infestation data, and supervised machine learning. Spectral indices are extracted from four bands, with Random Forest emerging as the most robust model (Accuracy: 0.818, F1-score: 0.821) compared to Gradient Boosting, XGBoost, KNN, SVM, and Linear Regression. SHAP analysis shows that near-infrared (NIR) based measurements are the most important for the model's decisions. The final output is a probability heatmap that highlights true infestation zones with minimal false negatives and limited false positives, mainly in bare soil or dense soybean areas. Results demonstrate that this approach provides a cost-effective, scalable tool for early detection and targeted management of AMATU. These results contribute to reducing herbicide inputs, production costs, and also promote more sustainable agricultural practices.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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 teacher head, 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".