Machine Learning and IoT-Based Approaches to Detect and Predict Rainfall-Triggered Landslides
Bibliographic record
Abstract
Landslides, predominantly triggered by rainfall, pose significant global threats, causing extensive loss of life and severe socio-economic disruptions.Among such calamities, the landslide in Uttarakhand stands as a stark exemplar of the severe repercussions these natural disasters can inflict.This study proposes two sophisticated approaches aimed at the detection and prediction of rainfall-induced landslides.Our initial approach presents a comprehensive analysis of the topographic and hydro-meteorological conditions that catalyzed the catastrophic Kedarnath disaster.This method utilizes an innovative algorithm, validated through machine learning models, in conjunction with an IoT-based application designed to collect critical data necessary for model training and validation.Emphasis is placed on rainfall, identified as a pivotal factor influencing debris flow and lake outbursts during the Kedarnath event.Utilizing the standard deviation of landslide data induced by rainfall from 2013-17, a threshold value was calculated to gauge the severity of such scenarios.The second approach employs a range of machine learning and ensemble learning algorithms to enhance the prediction of rainfall-triggered landslides.These proposed methods were investigated using web-scraped datasets acquired from NASA and IMD portals, with under-sampling and oversampling carried out to mitigate any potential dataset bias.Following extensive exploration and exploitation of diverse learning algorithms, it was inferred that oversampling techniques and the random forest model outperformed alternative models consistently across all performance measures, including Accuracy, Precision, Recall, and F1-Score.
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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 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".