A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment
Recent improvements in the spatial, temporal, and spectral resolution of satellite images necessitate (semi-)automated classification and information extraction approaches. Therefore, we developed an integrated fuzzy object-based image analysis and deep learning (FOBIA-DL) approach for monitoring th...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2021-11-01
|
Series: | GIScience & Remote Sensing |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/15481603.2021.2000350 |
_version_ | 1797679019451219968 |
---|---|
author | Bakhtiar Feizizadeh Keyvan Mohammadzade Alajujeh Tobia Lakes Thomas Blaschke Davoud Omarzadeh |
author_facet | Bakhtiar Feizizadeh Keyvan Mohammadzade Alajujeh Tobia Lakes Thomas Blaschke Davoud Omarzadeh |
author_sort | Bakhtiar Feizizadeh |
collection | DOAJ |
description | Recent improvements in the spatial, temporal, and spectral resolution of satellite images necessitate (semi-)automated classification and information extraction approaches. Therefore, we developed an integrated fuzzy object-based image analysis and deep learning (FOBIA-DL) approach for monitoring the land use/cover (LULC) and respective changes and compared it to three machine learning (ML) algorithms, namely the support vector machine (SVM), random forest (RF), and classification and regression tree (CART). We investigated LULC impacts on drought by analyzing Landsat satellite images from 1990 to 2020 for the Urmia Lake area in northern Iran. In the FOBIA-DL approach, following the initial segmentation steps, object features were identified for each LULC class. We then derived their respective attributes using fuzzy membership functions and deep convolutional neural networks (DCNNs), a deep learning method. The Fuzzy Synthetic Evaluation and Dempster-Shafer Theory (FSE-DST) also applied to validate and carryout the spatial uncertainties. Our results indicate that the FOBIA-DL, with an accuracy of 90.1% to 96.4% and a spatial certainty of 0.93 to 0.97, outperformed the other approaches, closely followed by the SVM. Our results also showed that the integration of Fuzzy-OBIA and DCNNs could improve the strength and robustness of the OBIA’s decision rules, while the FSE-DST approach notably improved the spatial accuracy of the object-based classification maps. While object-based image analysis (OBIA) is already considered a paradigm shift in GIScience, the integration of OBIA with fuzzy and deep learning creates more flexibility and robust OBIA decision rules for image analysis and classification. This research integrated popular data-driven approaches and developed a novel methodology for image classification and spatial accuracy assessment. From the environmental perspective, the results of this research support lake restoration initiatives by decision-makers and authorities in applications such as drought mitigation, land use management and precision agriculture programs. |
first_indexed | 2024-03-11T23:08:19Z |
format | Article |
id | doaj.art-51431c306f594f10a7de5652a1b19311 |
institution | Directory Open Access Journal |
issn | 1548-1603 1943-7226 |
language | English |
last_indexed | 2024-03-11T23:08:19Z |
publishDate | 2021-11-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | GIScience & Remote Sensing |
spelling | doaj.art-51431c306f594f10a7de5652a1b193112023-09-21T12:43:07ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262021-11-015881543157010.1080/15481603.2021.20003502000350A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessmentBakhtiar Feizizadeh0Keyvan Mohammadzade Alajujeh1Tobia Lakes2Thomas Blaschke3Davoud Omarzadeh4University of TabrizUniversity of TabrizHumboldt University of BerlinUniversity of SalzburgUniversity of TabrizRecent improvements in the spatial, temporal, and spectral resolution of satellite images necessitate (semi-)automated classification and information extraction approaches. Therefore, we developed an integrated fuzzy object-based image analysis and deep learning (FOBIA-DL) approach for monitoring the land use/cover (LULC) and respective changes and compared it to three machine learning (ML) algorithms, namely the support vector machine (SVM), random forest (RF), and classification and regression tree (CART). We investigated LULC impacts on drought by analyzing Landsat satellite images from 1990 to 2020 for the Urmia Lake area in northern Iran. In the FOBIA-DL approach, following the initial segmentation steps, object features were identified for each LULC class. We then derived their respective attributes using fuzzy membership functions and deep convolutional neural networks (DCNNs), a deep learning method. The Fuzzy Synthetic Evaluation and Dempster-Shafer Theory (FSE-DST) also applied to validate and carryout the spatial uncertainties. Our results indicate that the FOBIA-DL, with an accuracy of 90.1% to 96.4% and a spatial certainty of 0.93 to 0.97, outperformed the other approaches, closely followed by the SVM. Our results also showed that the integration of Fuzzy-OBIA and DCNNs could improve the strength and robustness of the OBIA’s decision rules, while the FSE-DST approach notably improved the spatial accuracy of the object-based classification maps. While object-based image analysis (OBIA) is already considered a paradigm shift in GIScience, the integration of OBIA with fuzzy and deep learning creates more flexibility and robust OBIA decision rules for image analysis and classification. This research integrated popular data-driven approaches and developed a novel methodology for image classification and spatial accuracy assessment. From the environmental perspective, the results of this research support lake restoration initiatives by decision-makers and authorities in applications such as drought mitigation, land use management and precision agriculture programs.http://dx.doi.org/10.1080/15481603.2021.2000350integrated approachfuzzy object-basedeep learning cnnmachine learning algorithmsspatial uncertaintyland use/coverchange detectionurmia lake |
spellingShingle | Bakhtiar Feizizadeh Keyvan Mohammadzade Alajujeh Tobia Lakes Thomas Blaschke Davoud Omarzadeh A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment GIScience & Remote Sensing integrated approach fuzzy object-base deep learning cnn machine learning algorithms spatial uncertainty land use/cover change detection urmia lake |
title | A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment |
title_full | A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment |
title_fullStr | A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment |
title_full_unstemmed | A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment |
title_short | A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment |
title_sort | comparison of the integrated fuzzy object based deep learning approach and three machine learning techniques for land use cover change monitoring and environmental impacts assessment |
topic | integrated approach fuzzy object-base deep learning cnn machine learning algorithms spatial uncertainty land use/cover change detection urmia lake |
url | http://dx.doi.org/10.1080/15481603.2021.2000350 |
work_keys_str_mv | AT bakhtiarfeizizadeh acomparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT keyvanmohammadzadealajujeh acomparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT tobialakes acomparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT thomasblaschke acomparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT davoudomarzadeh acomparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT bakhtiarfeizizadeh comparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT keyvanmohammadzadealajujeh comparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT tobialakes comparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT thomasblaschke comparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment AT davoudomarzadeh comparisonoftheintegratedfuzzyobjectbaseddeeplearningapproachandthreemachinelearningtechniquesforlandusecoverchangemonitoringandenvironmentalimpactsassessment |