TY - JOUR
T1 - Deep convolutional neural networks for surface coal mines determination from sentinel-2 images
AU - Madhuanand, L.
AU - Sadavarte, P.
AU - Visschedijk, A.J.H.
AU - Denier van der Gon, H.A.C.
AU - Aben, I.
AU - Osei, F.B.
N1 - Funding Information:
This research is partly supported through the GALES (Gas Leaks from Space) project (Grant 15597) by the Dutch Technology Foundation, which is part of the Netherlands Organisation for Scientific Research (NWO) and is partly funded by the Ministry of Economic Affairs, The Netherlands. We thank Dr Janot Tokaya (TNO) for helping with the preliminary application over a larger part of India and discussion.
Publisher Copyright:
© 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2021
Y1 - 2021
N2 - Coal is a principal source of energy and the combustion of coal supplies around one-third of the global electricity generation. Coal mines are also an important source of CH4 emissions, the second most important greenhouse gas. Monitoring CH4 emissions caused by coal mining using earth observation will require the exact location of coal mines. This paper aims to determine surface coal mines from satellite images through deep learning techniques by treating them as a land use/land cover classification task. This is achieved using Convolutional Neural Networks (CNN) that has proven to be capable of complex land use/land cover classification tasks. With a list of known coal mine locations from various countries, a training dataset of “Coal Mine” and “No Coal Mine” image patches is prepared using Sentinel-2 satellite images with 13 spectral bands. Various pre-trained CNN network architectures (VGG, ResNet, DenseNet) are trained and validated with our prepared coal mine dataset of 3500 “Coal Mine” and 3000 “No Coal Mine” image patches. After several experiments with the VGG network combined with transfer learning is found to be an optimal model for this task. Classification accuracy of 98% has been achieved for the validation dataset of the pre-trained VGG architecture. The model produces more than 95% overall accuracy when tested on unseen satellite images from different countries outside the training dataset and evaluated against visual classification.
AB - Coal is a principal source of energy and the combustion of coal supplies around one-third of the global electricity generation. Coal mines are also an important source of CH4 emissions, the second most important greenhouse gas. Monitoring CH4 emissions caused by coal mining using earth observation will require the exact location of coal mines. This paper aims to determine surface coal mines from satellite images through deep learning techniques by treating them as a land use/land cover classification task. This is achieved using Convolutional Neural Networks (CNN) that has proven to be capable of complex land use/land cover classification tasks. With a list of known coal mine locations from various countries, a training dataset of “Coal Mine” and “No Coal Mine” image patches is prepared using Sentinel-2 satellite images with 13 spectral bands. Various pre-trained CNN network architectures (VGG, ResNet, DenseNet) are trained and validated with our prepared coal mine dataset of 3500 “Coal Mine” and 3000 “No Coal Mine” image patches. After several experiments with the VGG network combined with transfer learning is found to be an optimal model for this task. Classification accuracy of 98% has been achieved for the validation dataset of the pre-trained VGG architecture. The model produces more than 95% overall accuracy when tested on unseen satellite images from different countries outside the training dataset and evaluated against visual classification.
KW - ITC-ISI-JOURNAL-ARTICLE
KW - ITC-GOLD
UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2021/isi/madhuanand_dee.pdf
U2 - 10.1080/22797254.2021.1920341
DO - 10.1080/22797254.2021.1920341
M3 - Article
VL - 54
SP - 296
EP - 309
JO - European Journal of Remote Sensing
JF - European Journal of Remote Sensing
SN - 2279-7254
IS - 1
ER -