Greenhouse Mapping and Crop Type Classification for Small-Scale Farms Using Airborne Laser Scanning
Bibliographic record
Abstract
The increasing frequency of extreme climatic events has resulted in significant crop losses, prompting many farmers to adopt greenhouses as a climate adaptation strategy. Greenhouses, constructed with transparent materials to allow sunlight penetration, are widely used for high-quality vegetable and fruit cultivation. These structures have both upper and lower layers; airborne laser scanning can penetrate the upper plastic layer and detect crop in the lower layer. This study analyzed 222 small-scale greenhouses in Taiwan, covering a total area of 1,443 ha. ALS data were used to derive four indices: normalized digital surface model, first echo intensity, laser penetration index, and surface roughness. These indices were used to classify greenhouse areas using a support vector machine, achieving an overall accuracy of 87.32% and an F1-score of 0.93. A cloth simulation filter was then applied to separate point data into upper and lower layers, enabling the removal of upper-layer points. Greenhouse area crops were further classified into bare ground, tall crops, low-lying crops, and mixed crops, with 199 greenhouse areas correctly identified and an overall accuracy of 92.56%. The F1-scores for each crop class ranged from 0.87 to 0.97. This method accurately reflected actual cultivation conditions within the GAs.
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 | 0.000 |
| 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".