A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery
Fine-scale land use and land cover (LULC) data in a mining area are helpful for the smart supervision of mining activities. However, the complex landscape of open-pit mining areas severely restricts the classification accuracy. Although deep learning (DL) algorithms have the ability to extract infor...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/6/2089 |
id |
doaj-b439b3ba198f407cb108e72b724ded68 |
---|---|
record_format |
Article |
spelling |
doaj-b439b3ba198f407cb108e72b724ded682021-03-17T00:06:41ZengMDPI AGSensors1424-82202021-03-01212089208910.3390/s21062089A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS ImageryMeng Li0Zhuang Tang1Wei Tong2Xianju Li3Weitao Chen4Lizhe Wang5Faculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaFine-scale land use and land cover (LULC) data in a mining area are helpful for the smart supervision of mining activities. However, the complex landscape of open-pit mining areas severely restricts the classification accuracy. Although deep learning (DL) algorithms have the ability to extract informative features, they require large amounts of sample data. As a result, the design of more interpretable DL models with lower sample demand is highly important. In this study, a novel multi-level output-based deep belief network (DBN-ML) model was developed based on Ziyuan-3 imagery, which was applied for fine classification in an open-pit mine area of Wuhan City. First, the last DBN layer was used to output fine-scale land cover types. Then, one of the front DBN layers outputted the first-level land cover types. The coarse classification was easier and fewer DBN layers were sufficient. Finally, these two losses were weighted to optimize the DBN-ML model. As the first-level class provided a larger amount of additional sample data with no extra cost, the multi-level output strategy enhanced the robustness of the DBN-ML model. The proposed model produces an overall accuracy of 95.10% and an F1-score of 95.07%, outperforming some other models.https://www.mdpi.com/1424-8220/21/6/2089remote sensingdeep learningfine-scale classificationdeep belief networksopen-pit miningZiyuan-3 imagery |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Meng Li Zhuang Tang Wei Tong Xianju Li Weitao Chen Lizhe Wang |
spellingShingle |
Meng Li Zhuang Tang Wei Tong Xianju Li Weitao Chen Lizhe Wang A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery Sensors remote sensing deep learning fine-scale classification deep belief networks open-pit mining Ziyuan-3 imagery |
author_facet |
Meng Li Zhuang Tang Wei Tong Xianju Li Weitao Chen Lizhe Wang |
author_sort |
Meng Li |
title |
A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery |
title_short |
A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery |
title_full |
A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery |
title_fullStr |
A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery |
title_full_unstemmed |
A Multi-Level Output-Based DBN Model for Fine Classification of Complex Geo-Environments Area Using Ziyuan-3 TMS Imagery |
title_sort |
multi-level output-based dbn model for fine classification of complex geo-environments area using ziyuan-3 tms imagery |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-03-01 |
description |
Fine-scale land use and land cover (LULC) data in a mining area are helpful for the smart supervision of mining activities. However, the complex landscape of open-pit mining areas severely restricts the classification accuracy. Although deep learning (DL) algorithms have the ability to extract informative features, they require large amounts of sample data. As a result, the design of more interpretable DL models with lower sample demand is highly important. In this study, a novel multi-level output-based deep belief network (DBN-ML) model was developed based on Ziyuan-3 imagery, which was applied for fine classification in an open-pit mine area of Wuhan City. First, the last DBN layer was used to output fine-scale land cover types. Then, one of the front DBN layers outputted the first-level land cover types. The coarse classification was easier and fewer DBN layers were sufficient. Finally, these two losses were weighted to optimize the DBN-ML model. As the first-level class provided a larger amount of additional sample data with no extra cost, the multi-level output strategy enhanced the robustness of the DBN-ML model. The proposed model produces an overall accuracy of 95.10% and an F1-score of 95.07%, outperforming some other models. |
topic |
remote sensing deep learning fine-scale classification deep belief networks open-pit mining Ziyuan-3 imagery |
url |
https://www.mdpi.com/1424-8220/21/6/2089 |
work_keys_str_mv |
AT mengli amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT zhuangtang amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT weitong amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT xianjuli amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT weitaochen amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT lizhewang amultileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT mengli multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT zhuangtang multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT weitong multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT xianjuli multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT weitaochen multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery AT lizhewang multileveloutputbaseddbnmodelforfineclassificationofcomplexgeoenvironmentsareausingziyuan3tmsimagery |
_version_ |
1724219033536954368 |