Enhanced detection of freeze‒thaw induced landslides in Zhidoi county (Tibetan Plateau, China) with Google Earth Engine and image fusion
Bibliographic record
Abstract
Freeze‒thaw induced landslides (FTILs) in grasslands on the Tibetan Plateau are a geological disaster leading to soil erosion. However, conventional techniques for regional-scale mapping of FTILs are impractical because they are labor-intensive, expensive, and time-consuming. This study focuses on improving FTILs detection by utilizing image fusion-based Google Earth Engine (GEE) and a random forest algorithm. Integration of various data sources, including texture features, index features, spectral features, slope, and vertical‒vertical polarization data, allow automatic detection of the spatial distribution characteristics of FTILs in Zhidoi county, which is located within the Qinghai‒Tibet engineering corridor (QTEC). We employed statistical techniques to elucidate the mechanisms influencing FTILs occurrence. The image fusion method identifies two schemes that achieve high accuracy using a smaller training sample (scheme A: 94.1%; scheme D: 94.5%) compared to other methods (scheme B: 50.0%; scheme C: 95.8%). This approach is effective generating accurate results using only 10% of the training sample size required for other methods. The spatial distribution patterns of FTILs generated for 2021 are similar to those obtained using various other training sample sources, with a primary concentration observed along the central region traversed by the QTEC. The results highlight slope as the most crucial feature in the fusion images, as it accounts for 93% of FTILs occurring on gentle slopes ranging from 0° to 14°. This study provides a theoretical basis and technological reference for the identification, monitoring, prevention and control of FTILs in grasslands, with the potential to benefit grassland ecosystem management, reduce economic losses, and promote grassland 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 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".