MULTI-SENSORY DATA INTEGRATION FOR EXTRACTING GEOTECHNICAL PARAMETERS FOR LANDSLIDES HAZARD ASSESSMENT
Bibliographic record
Abstract
Geotechnical engineering is a relatively new discipline that has developed rapidly over the past 30 years. It deals with a wide spectrum of natural geological materials ranging from low strength soils to high strength rocks. Earth movements are common in many parts of the world and, as a result, present serious safety and mortality risk to humans in addition to affecting construction activities. Earth movement can be classified into different categories with landslides as being one of those categories. In order to assess the stability of landslides, different geo-technical parameters are required such as the strike and dip of the discontinuity planes in the potential area. Areas affected by landslides are often inaccessible which makes manual compass and inclinometer measurements challenging because of the danger involved in this operation. Preventing large natural landslides is difficult; however some mitigation is possible and can help to minimize the hazards. Nowadays, 3D modeling of objects can be achieved through either passive or active remote sensing systems. Active sensors, such as Terrestrial Laser Scanning systems (TLS) have been used extensively for quick acquisition of highly accurate three-dimensional point cloud data with high resolution. However, the TLS in some cases has limitations during the data collection due to occlusions, orientation bias and truncation. This research addresses those issues by investigating the possibility of augmenting TLS in the occluded regions through close-range photogrammetry to generate high resolution and dense point cloud using the Semi-Global Matching (SGM) algorithm. By augmenting the two data acquisition methods and registering to a common coordinate system to provide a complete point cloud for the area of interest, any limitations and exposed gaps in the data are filled. Planar segmentation is then carried out to extract the required geotechnical parameters automatically. Four sets of geotechnical parameters have been compared in this research: 1) a set of manual measurements, 2) a set extracted from the TLS data only, 3) a set extracted from the SGM algorithm only, 4) and finally a set extracted from the fused TLS and SGM data. The results showed that the data fusion method provided more accurate results when compared to the results coming from the TLS data and those coming from SGM only. This reveals that the impact of the occluded regions on the calculations of the geotechnical parameters must be considered to achieve the required quality of the estimation process. The proposed method of this research provided high quality measurements for the geotechnical parameters required to assess the landslide hazard, ensured safety, and saved cost and time.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".