Using Advanced InSAR Techniques and Machine Learning in Google Earth Engine (GEE) to Monitor Regional Black Soil Erosion—A Case Study of Yanshou County, Heilongjiang Province, Northeastern China
Bibliographic record
Abstract
The black soil region experiences complex erosion due to natural processes and intense human activities, leading to soil degradation and adverse ecological and agricultural impacts. However, the complexities involved in quantifying regional erosion poses remarkable challenges in accurately assessing the current status of regional soil erosion for effective soil conservation. To solve this issue, we proposed a new method for monitoring soil erosion using Interferometric synthetic aperture radar (InSAR) technology and machine learning algorithms within the Google Earth Engine platform. The new method not only enables regional-scale monitoring, but also ensures high accuracy in measurement (millimeter-level). The erosion susceptibility of the study area (Yanshou County, Heilongjiang Province, Northeastern China) was also classified using random forest algorithms to refine the monitored and predicted soil erosion. The results indicate that the five-year (2016–2021) deformation in Yanshou County was −11.08 mm, with a significant mean cumulative deformation of −8.08 mm yr−1 occurring in 2017. The driving factor analysis shows that the region was subject to the compound effect of water and freeze–thaw erosion, closely related to crop phenological stages. The susceptibility analysis indicates that 73.3% of the region was susceptible to erosion, with a higher probability in river areas, at high altitudes, and on steep slopes. However, good vegetation cover can reduce the risk of soil erosion to some extent. This study offers a new perspective on monitoring regional soil erosion in the black soil region of China. The proposed method holds potential for future expansion to monitor soil erosion in a larger areas, thereby guiding the strategies development for protection of the agriculturally important black soil.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.001 | 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 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".