Corn and Wheat Plant Identification on Radar and Optical Image Data
Bibliographic record
Abstract
In recent years, prediction, detection, and classification applications have been made in many fields such as agriculture, health, stock market, economy, cybersecurity, etc., in Machine Learning and Artificial Intelligence. These applications are user-friendly and provide fast, high-quality, and accurate results. The advancements in these fields have shown that machine learning and deep learning methods are very useful in classifying large and complex data, especially when human brain and physical power are insufficient. Today's findings suggest there have been promising studies using these models, focused on time- and cost-effective and high-quality products. These studies provide efficiency in agricultural areas, thereby guiding both farmers and policymakers. In addition, the development and widespread implementation of unmanned aerial vehicles (UAVs) accelerated the process of obtaining multispectral aerial images. With the combined use of these technologies and high-speed computer software and hardware for precise and high-quality production in agriculture, it was possible to determine plant species and increase product quality. In this study, a dataset consisting of radar and optical image data was used to classify corn and wheat crops cultivated in agricultural areas. Four different machine learning models, namely Decision Tree (DT), K-Nearest Neighbors (K-NN), Naive Bayes (NB), and Support Vector Machines (SVM), were trained and compared on the dataset consisting of 174 features from Winnipeg, Canada. The dataset has been divided into 80% for training and 20% for testing. According to the results, the SVM model performed the best with the highest accuracy (0.9998) and F1-Score (0.9996), while the NB model performed the worst accuracy (0.9895) and F1-Score (0.9835). The detection of wheat and corn crop types by processing radar and optical image data with machine learning models has shown that other crops in cultivated lands in the Southeastern Anatolia Project (GAP) region can be classified using the same method, which shows the importance of this study.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".