EGU23-1957, updated on 22 Feb 2023
https://doi.org/10.5194/egusphere-egu23-1957
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Building Vulnerability Assessment using Artificial Intelligence forLandslide Susceptibility Zone in Champawat District, India 

Yaggesh Sharma1,2,3, Arun Tyagi1, Mukat Lal Sharma1, Priyanka Sharma1, and Ashish Aggarwal3
Yaggesh Sharma et al.
  • 1Indian Institute of Technology Roorkee, Department of Earthquake Engineering, India (yaggeshsharma24@gmail.com)
  • 2Water Engineering and Management, Asian Institute of Technology, Pathumthani, Thailand -12120
  • 3Department of Petroleum Engineering & Earth Sciences, University of Petroleum & Energy Studies, Dehradun, India- 248007

The evaluation of the vulnerability of society aroused to landslide-related tragedy is an enlarged
topic. Few studies talk about this issue and limited research has been carried out on the
relationship between landslides and their potential impact on buildings and infrastructure.
Uttarakhand Province in India is a highly landslide-prone area in the Himalayan region. The
present study focused on assessing the building vulnerability for the landslide susceptibility zone
in the Champawat district of Uttarakhand state. The building footprint areas are identified by
using an image segmentation algorithm in artificial intelligence. Moreover, the landslide-prone
zone was identified based on the historical and recent information collected from various
authenticated sources and the field investigations made on the recent landslides whereas, more
than ten landslide causative parameters/landslide conditioning factors (LCF) have been used to
generate a susceptibility map. The frequency ratio method has been applied to carry out the
susceptibility zone in the entire study area. Most buildings are found in dangerous areas that are
highly correlated by using published and in-situ datasets.
Keywords: Landslide Susceptibility Zone, Artificial Intelligence, Vulnerability, Building Footprints

How to cite: Sharma, Y., Tyagi, A., Sharma, M. L., Sharma, P., and Aggarwal, A.: Building Vulnerability Assessment using Artificial Intelligence forLandslide Susceptibility Zone in Champawat District, India , EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-1957, https://doi.org/10.5194/egusphere-egu23-1957, 2023.