Summary of At the Junction Between Deep Learning and Statistics Of Extremes: Formalizing the Landslide Hazard Definition, by Ashok Dahal et al.
At the junction between deep learning and statistics of extremes: formalizing the landslide hazard definition
by Ashok Dahal, Raphaël Huser, Luigi Lombardo
First submitted to arxiv on: 25 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Geophysics (physics.geo-ph); Applications (stat.AP); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a unified model for estimating landslide hazard at the slope unit level, combining spatial information about landslide location, threat, and frequency. The proposed model uses deep learning and extreme-value theory to analyze an inventory of 30 years of observed rainfall-triggered landslides in Nepal. The authors demonstrate that their model can accurately estimate landslide hazard for multiple return periods under different climate change scenarios up to the end of the century. Notably, the results suggest that landslide hazard is likely to increase in the lower Himalayan regions and decrease in the upper Himalayan region under both climate change scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Landslides are a big problem when heavy rain falls on steep slopes. Scientists have been trying to figure out how often landslides happen and where they’re most likely to occur. But it’s hard because there isn’t enough data to work with, especially for really rare events. This paper helps solve that problem by creating a new way to predict landslide risk using computers and math. The team used old data from Nepal to test their method and found it works really well. They also looked at what might happen in the future if the climate changes, and they think some places will get worse while others will get better. |
Keywords
* Artificial intelligence * Deep learning
