The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume XLIII-B3-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 721–726, 2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 721–726, 2021

  29 Jun 2021

29 Jun 2021


P. Singh, V. Maurya, and R. Dwivedi P. Singh et al.
  • GIS Cell, MNNIT Allahabad, Prayagraj, India

Keywords: Machine Learning, Landslide, GEE, Landsat, Rudraprayag, BHUKOSH

Abstract. Landslide is one of the most common natural disasters triggered mainly due to heavy rainfall, cloud burst, earthquake, volcanic eruptions, unorganized constructions of roads, and deforestation. In India, field surveying is the most common method used to identify potential landslide regions and update the landslide inventories maintained by the Geological Survey of India, but it is very time-consuming, costly, and inefficient. Alternatively, advanced remote sensing technologies in landslide analysis allow rapid and easy data acquisitions and help to improve the traditional method of landslide detection capabilities. Supervised Machine learning algorithms, for example, Support Vector Machine (SVM), are challenging to conventional techniques by predicting disasters with astounding accuracy. In this research work, we have utilized open-source datasets (Landsat 8 multi-band images and JAXA ALOS DSM) and Google Earth Engine (GEE) to identify landslides in Rudraprayag using machine learning techniques. Rudraprayag is a district of Uttarakhand state in India, which has always been the center of attention of geological studies due to its higher density of landslide-prone zones. For the training and validation purpose, labeled landslide locations obtained from landslide inventory (prepared by the Geological Survey of India) and layers such as NDVI, NDWI, and slope (generated from JAXA ALOS DSM and Landsat 8 satellite multi-band imagery) were used. The landslide identification has been performed using SVM, Classification and Regression Trees (CART), Minimum Distance, Random forest (RF), and Naïve Bayes techniques, in which SVM and RF outperformed all other techniques by achieving an 87.5% true positive rate (TPR).