Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/6472
Title: A Hybrid CNN + Random Forest Approach to Delineate Debris Covered Glaciers Using Deep Features
Authors: Nijhawan R.
Das, Josodhir D.
Balasubramanian R.
Published in: Journal of the Indian Society of Remote Sensing
Abstract: The main aim of this study is to propose a novel hybrid deep learning framework approach for accurate mapping of debris covered glaciers. The framework comprises of integration of several CNNs architecture, in which different combinations of Landsat 8 multispectral bands (including thermal band), topographic and texture parameters are passed as input for feature extraction. The output of an ensemble of these CNNs is hybrid with random forest model for classification. The major pillars of the framework include: (1) technique for implementing topographic and atmospheric corrections (preprocessing), (2) the proposed hybrid of ensemble of CNNs and random forest classifier, and (3) procedures to determine whether a pixel predicted as snow is a cloud edge/shadow (post-processing). The proposed approach was implemented on the multispectral Landsat 8 OLI (operational land imager)/TIRS (thermal infrared sensor) data and Shuttle Radar Topography Mission Digital Elevation Model for the part of the region situated in Alaknanda basin, Uttarakhand, Himalaya. The proposed framework was observed to outperform (accuracy 96.79%) the current state-of-art machine learning algorithms such as artificial neural network, support vector machine, and random forest. Accuracy assessment was performed by means of several statistics measures (precision, accuracy, recall, and specificity). © 2018, Indian Society of Remote Sensing.
Citation: Journal of the Indian Society of Remote Sensing (2018), 46(6): 981-989
URI: https://doi.org/10.1007/s12524-018-0750-x
http://repository.iitr.ac.in/handle/123456789/6472
Issue Date: 2018
Publisher: Springer
Keywords: Classification
CNN
Debris
Glaciers
Random forest
Texture
ISSN: 0255660X
Author Scopus IDs: 57192176367
7202105464
7103127999
Author Affiliations: Nijhawan, R., Department of Earthquake Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Das, J., Department of Earthquake Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Balasubramanian, R., Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Corresponding Author: Nijhawan, R.; Department of Earthquake Engineering, Indian Institute of Technology RoorkeeIndia; email: rahul.deq2014@iitr.ac.in
Appears in Collections:Journal Publications [EQ]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.