Evaluating model robustness in landslide susceptibility mapping using a unified data-consistent framework in northern Thailand
Pichawut Manopkawee, Niti Mankhemthong, Meetaoh Tongsae, Natthaphon Panna · 2026
Read Evaluating model robustness in landslide susceptibility mapping using a unified data-consistent framework in northern Thailand by Pichawut Manopkawee, Niti Mankhemthong, Meetaoh Tongsae, Natthaphon Panna (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13381970.txt.
Description
Pichawut Manopkawee and three co-authors compared five methods for mapping landslide risk in northern Thailand under one shared testing setup in a 2026 study. Published maps often report high accuracy, but differing data and validation habits make results hard to trust or transfer. The team applied every method to the same landslide inventory and the same landscape factors in the Luang Prabang Range.
Random forest proved the most stable and reliable, with an accuracy score of 0.942, followed by a boosted-tree method and two deep learning models. The deep models scored well but wobbled more when data or settings changed. The authors conclude that data structure and settings shape results as much as the choice of algorithm.
Catalog record
| CREATOR | Pichawut Manopkawee, Niti Mankhemthong, Meetaoh Tongsae, Natthaphon Panna |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 91 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |