Improving Landslide-Event Inventories Using High-Fidelity Lidar Change Detection in Eastern Kentucky
Bibliographic record
Abstract
Following spatially expansive landslide events, rapid remote sensing data acquisition is perhaps the most efficient means of capturing the nature and extent of landsliding. This is particularly true in the Appalachian Mountains of eastern North America, where high annual rainfall, humidity, and vegetation can obscure landslide features within a single growing season. In July 2022, a convective rainfall event with an annual exceedance probability of 0.1–0.2% caused record-breaking flooding and widespread landslides throughout about 1,800 km2 of the Appalachian Plateau in eastern Kentucky. In the immediate weeks following the storm, field and remote-sensing reconnaissance mapping by the Kentucky Geological Survey identified approximately 1,065 landslides triggered during the event. In January 2023, the state of Kentucky acquired a lidar dataset over the impacted region, complimenting previous acquisitions from 2012 and 2017. We used point cloud alignment and surface-normal comparison techniques to compare 2012 and 2017 lidar point clouds to post-storm 2023 point clouds. This resulted in a lidar change detection dataset with a limit of detection of +/- 13 cm over an area of 1,800 km2. By using this dataset as a basis for our inventorying, we are finding more numerous and smaller landslides compared to state-of-practice mapping methods (e.g., aerial photo interpretation, hillshade comparisons, field-based inspections). Additionally, we can compute statistics on volume balance within landslides, thereby providing insight into landslide mechanics at scale that is difficult to impossible to understand without such data. Inventorying is ongoing, however, as of January 2025, we have inventoried over 2,000 landslides that occurred between 2017-2023 in 10% of the impacted area. This presentation will discuss how high-fidelity lidar change detection methods influence landslide inventory mapping, statistical characterizations of the landslide event, and ongoing efforts to advance AI-driven landslide inventory mapping.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".