“Ensembled transfer learning approach for error reduction in landslide susceptibility mapping of the data scare region”
Ankit Singh, Nitesh Dhiman, K. C. Niraj, Dericks Praise Shukla · 2024
Read “Ensembled transfer learning approach for error reduction in landslide susceptibility mapping of the data scare region” by Ankit Singh, Nitesh Dhiman, K. C. Niraj, Dericks Praise Shukla (2024) 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-11585561.txt.
Description
Ankit Singh and co-authors map landslide risk in data poor mountain districts in 2024 by borrowing knowledge from a data rich one. Making such maps is costly in the Himalayas, where field data are hard to gather.
Two learning models were trained in a source district and then moved to target districts, both alone and mixed with local knowledge. Eleven factors that favor landslides fed the models, after checks for overlap and for how alike the landforms were. For one target, scores rose clearly with the transfer approach for both models. The mixed version did best of all. The authors say transfer learning can cut error where data are scarce.
Catalog record
| CREATOR | Ankit Singh, Nitesh Dhiman, K. C. Niraj, Dericks Praise Shukla |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |