Investigating species composition in a temperate grassland using Unmanned Aerial Vehicle-acquired imagery
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Species composition has been studied extensively in different ecosystems for investigating biodiversity and evaluating ecosystem health conditions. Remote sensing imagery is an important data source for investigating species composition, owing to its large spatial coverage and continuous data acquisition. However, commonly-used remote sensing images acquired by satellite (e.g., Landsat, Quickbird) or airplane have a spatial resolution lower than 0.5m, and are thus not capable of resolving characteristically small features. This poses a particular challenge in grassland ecosystems, since grassland species are typically small in size and highly mixed. Unmanned Aerial Vehicle (UAV) is an emerging technology in recent decades that can acquire imagery with ultra-high spatial resolution (sub-decimeter). Therefore, UAV-acquired imagery facilitates fine-scale species classification. This study classified two UAV-acquired images obtained at different times during the vegetation-growing cycle for species investigation in a temperate grassland. The classification approach utilized in this process was object-oriented classification, which is capable of identifying ground covers using spectral, spatial, and textural information. Classification and Regression Tree (CART) was applied for feature selection, which is an essential step in determining optimal features for classifiers. The dominant species in the study area were classified with an overall accuracy higher than 80%. Spatial and temporal variations of dominant species were analyzed, and their potential influencing factors (e.g., topographic condition, soil moisture) were also examined. Challenges of using UAV-acquired imagery and the object-oriented technique for species classification were summarized at the end of this paper.
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.
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 it