A hybrid time series analysis-genetic algorithm-support vector machine model for enhanced landslide prediction
Bibliographic record
Abstract
Landslide prediction is a critical task for ensuring public safety and preventing economic loss in regions prone to such natural disasters. Traditional models for landslide prediction often lack accuracy and precision because of the intricate interactions between various factors that lead to landslide events. To tackle this issue, we introduce an innovative hybrid approach for landslide prediction that combines Time Series Analysis (TSA), Genetic Algorithm (GA), and Support Vector Machine (SVM). TSA decomposes landslide displacement data into trend, seasonal, and residual components, improving the clarity of the data. GA optimizes the hyperparameters of SVM, ensuring the most effective application of the SVM. Finally, the SVM is trained on detrended data, producing a model capable of accurately predicting future landslides. Our experimental outcomes manifest that the TSA-GA-SVM model we advanced performs far better than the individual TSA and SVM models when it comes to forecasting landslide displacement. The hybrid model achieved a mean absolute error of 0.15 m compared to 0.42 m for TSA and 0.38 m for SVM alone. Sensitivity analysis revealed that increasing GA population size improved model stability, while higher mutation rates led to more variable predictions. The model showed good generalization ability, performing well across different regions and under various geological and hydrological conditions. This research not only advances the state of the art in landslide prediction but also provides a practical tool for authorities to implement in their disaster prevention and management strategies.
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 | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".