Snow and cloud discrimination using convolutional neural networks

D. Varshney; P. K. Gupta; C. Persello; B. R. Nikam

doi:10.5194/isprs-annals-IV-5-59-2018

Snow and cloud discrimination using convolutional neural networks

D. Varshney, P. K. Gupta, C. Persello, B. R. Nikam

Research output: Contribution to journal › Conference article › peer-review

4 Scopus citations

Abstract

Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.

Original language	English
Pages (from-to)	59-63
Number of pages	5
Journal	ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Volume	4
Issue number	5
DOIs	https://doi.org/10.5194/isprs-annals-IV-5-59-2018
State	Published - Nov 15 2018
Externally published	Yes
Event	2018 ISPRS TC V Mid-Term Symposium on Geospatial Technology - Pixel to People - Dehradun, India Duration: Nov 20 2018 → Nov 23 2018

Access to Document

10.5194/isprs-annals-IV-5-59-2018

Cite this

@article{dd3cf37ec3d3464bb27c9ed5a1ab124d,

title = "Snow and cloud discrimination using convolutional neural networks",

abstract = "Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.",

author = "D. Varshney and Gupta, {P. K.} and C. Persello and Nikam, {B. R.}",

note = "Publisher Copyright: {\textcopyright} 2018 Authors.; 2018 ISPRS TC V Mid-Term Symposium on Geospatial Technology - Pixel to People ; Conference date: 20-11-2018 Through 23-11-2018",

year = "2018",

month = nov,

day = "15",

doi = "10.5194/isprs-annals-IV-5-59-2018",

language = "English",

volume = "4",

pages = "59--63",

journal = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",

issn = "2194-9042",

number = "5",

}

TY - JOUR

T1 - Snow and cloud discrimination using convolutional neural networks

AU - Varshney, D.

AU - Gupta, P. K.

AU - Persello, C.

AU - Nikam, B. R.

PY - 2018/11/15

Y1 - 2018/11/15

N2 - Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.

AB - Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.

UR - http://www.scopus.com/inward/record.url?scp=85057631256&partnerID=8YFLogxK

U2 - 10.5194/isprs-annals-IV-5-59-2018

DO - 10.5194/isprs-annals-IV-5-59-2018

M3 - Conference article

AN - SCOPUS:85057631256

SN - 2194-9042

VL - 4

SP - 59

EP - 63

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

IS - 5

T2 - 2018 ISPRS TC V Mid-Term Symposium on Geospatial Technology - Pixel to People

Y2 - 20 November 2018 through 23 November 2018

ER -

Snow and cloud discrimination using convolutional neural networks

Abstract

Access to Document

Other files and links

Fingerprint

Cite this