Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images
Urban forests globally face severe degradation due to human activities and natural disasters, making deforestation an urgent environmental challenge. Remote sensing technology and very-high-resolution (VHR) bitemporal satellite imagery enable change detection (CD) for monitoring forest changes. Howe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4285 |
| _version_ | 1797581895211417600 |
|---|---|
| author | Aisha Javed Taeheon Kim Changhui Lee Jaehong Oh Youkyung Han |
| author_facet | Aisha Javed Taeheon Kim Changhui Lee Jaehong Oh Youkyung Han |
| author_sort | Aisha Javed |
| collection | DOAJ |
| description | Urban forests globally face severe degradation due to human activities and natural disasters, making deforestation an urgent environmental challenge. Remote sensing technology and very-high-resolution (VHR) bitemporal satellite imagery enable change detection (CD) for monitoring forest changes. However, deep learning techniques for forest CD concatenate bitemporal images into a single input, limiting the extraction of informative deep features from individual raw images. Furthermore, they are developed for middle to low-resolution images focused on specific forests such as the Amazon or a single element in the urban environment. Therefore, in this study, we propose deep learning-based urban forest CD along with overall changes in the urban environment by using VHR bitemporal images. Two networks are used independently: DeepLabv3+ for generating binary forest cover masks, and a deeply supervised image fusion network (DSIFN) for the generation of a binary change mask. The results are concatenated for semantic CD focusing on forest cover changes. To carry out the experiments, full scene tests were performed using the VHR bitemporal imagery of three urban cities acquired via three different satellites. The findings reveal significant changes in forest covers alongside urban environmental changes. Based on the accuracy assessment, the networks used in the proposed study achieved the highest F1-score, kappa, IoU, and accuracy values compared with those using other techniques. This study contributes to monitoring the impacts of climate change, rapid urbanization, and natural disasters on urban environments especially urban forests, as well as relations between changes in urban environment and urban forests. |
| first_indexed | 2024-03-10T23:13:07Z |
| format | Article |
| id | doaj.art-2838bd71ae334c81b8f5e98e7d58e1a3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:13:07Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2838bd71ae334c81b8f5e98e7d58e1a32023-11-19T08:47:02ZengMDPI AGRemote Sensing2072-42922023-08-011517428510.3390/rs15174285Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite ImagesAisha Javed0Taeheon Kim1Changhui Lee2Jaehong Oh3Youkyung Han4Department of Civil Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Civil Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Civil Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Civil Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaDepartment of Civil Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaUrban forests globally face severe degradation due to human activities and natural disasters, making deforestation an urgent environmental challenge. Remote sensing technology and very-high-resolution (VHR) bitemporal satellite imagery enable change detection (CD) for monitoring forest changes. However, deep learning techniques for forest CD concatenate bitemporal images into a single input, limiting the extraction of informative deep features from individual raw images. Furthermore, they are developed for middle to low-resolution images focused on specific forests such as the Amazon or a single element in the urban environment. Therefore, in this study, we propose deep learning-based urban forest CD along with overall changes in the urban environment by using VHR bitemporal images. Two networks are used independently: DeepLabv3+ for generating binary forest cover masks, and a deeply supervised image fusion network (DSIFN) for the generation of a binary change mask. The results are concatenated for semantic CD focusing on forest cover changes. To carry out the experiments, full scene tests were performed using the VHR bitemporal imagery of three urban cities acquired via three different satellites. The findings reveal significant changes in forest covers alongside urban environmental changes. Based on the accuracy assessment, the networks used in the proposed study achieved the highest F1-score, kappa, IoU, and accuracy values compared with those using other techniques. This study contributes to monitoring the impacts of climate change, rapid urbanization, and natural disasters on urban environments especially urban forests, as well as relations between changes in urban environment and urban forests.https://www.mdpi.com/2072-4292/15/17/4285deep learningtransfer learningforest cover change detectionvery high resolution (VHR)DeepLabv3+deeply supervised image fusion network (DSIFN) |
| spellingShingle | Aisha Javed Taeheon Kim Changhui Lee Jaehong Oh Youkyung Han Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images Remote Sensing deep learning transfer learning forest cover change detection very high resolution (VHR) DeepLabv3+ deeply supervised image fusion network (DSIFN) |
| title | Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images |
| title_full | Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images |
| title_fullStr | Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images |
| title_full_unstemmed | Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images |
| title_short | Deep Learning-Based Detection of Urban Forest Cover Change along with Overall Urban Changes Using Very-High-Resolution Satellite Images |
| title_sort | deep learning based detection of urban forest cover change along with overall urban changes using very high resolution satellite images |
| topic | deep learning transfer learning forest cover change detection very high resolution (VHR) DeepLabv3+ deeply supervised image fusion network (DSIFN) |
| url | https://www.mdpi.com/2072-4292/15/17/4285 |
| work_keys_str_mv | AT aishajaved deeplearningbaseddetectionofurbanforestcoverchangealongwithoverallurbanchangesusingveryhighresolutionsatelliteimages AT taeheonkim deeplearningbaseddetectionofurbanforestcoverchangealongwithoverallurbanchangesusingveryhighresolutionsatelliteimages AT changhuilee deeplearningbaseddetectionofurbanforestcoverchangealongwithoverallurbanchangesusingveryhighresolutionsatelliteimages AT jaehongoh deeplearningbaseddetectionofurbanforestcoverchangealongwithoverallurbanchangesusingveryhighresolutionsatelliteimages AT youkyunghan deeplearningbaseddetectionofurbanforestcoverchangealongwithoverallurbanchangesusingveryhighresolutionsatelliteimages |