Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2
The logging is the leading cause for the reduction in the forest area in the world. At the same time, the number of forest clearcuts continues to grow. However, despite the massive scale, such incidents are difficult to track in time. As a result, huge areas of forests are gradually being cut down....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9241044/ |
| _version_ | 1818839001953468416 |
|---|---|
| author | Kostiantyn Isaienkov Mykhailo Yushchuk Vladyslav Khramtsov Oleg Seliverstov |
| author_facet | Kostiantyn Isaienkov Mykhailo Yushchuk Vladyslav Khramtsov Oleg Seliverstov |
| author_sort | Kostiantyn Isaienkov |
| collection | DOAJ |
| description | The logging is the leading cause for the reduction in the forest area in the world. At the same time, the number of forest clearcuts continues to grow. However, despite the massive scale, such incidents are difficult to track in time. As a result, huge areas of forests are gradually being cut down. Therefore, there is a need for regular and effective monitoring of changes in forest cover. The multitemporal data sources like Copernicus Sentinel-2 allow enhancing the potential of monitoring the Earth's surface and environmental dynamics including forest plantations. In this article, we present a baseline U-Net model for deforestation detection in the forest-steppe zone. Training and evaluation are conducted on our own dataset created on Sentinel-2 imagery for the Kharkiv region of Ukraine (31 400 km<sup>2</sup>). As a part of the research, we present several models with the ability to work with time-dependent imagery. The main contribution of this article is to provide a baseline model for the forest change detection inside Ukraine and improve it adding the ability to use several sequential images as an input of the segmentation model. |
| first_indexed | 2024-12-19T03:47:21Z |
| format | Article |
| id | doaj.art-3f6e12654e1f47d48ec1a6451b91e52f |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-19T03:47:21Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-3f6e12654e1f47d48ec1a6451b91e52f2022-12-21T20:37:06ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-011436437610.1109/JSTARS.2020.30341869241044Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2Kostiantyn Isaienkov0https://orcid.org/0000-0001-5266-7040Mykhailo Yushchuk1Vladyslav Khramtsov2https://orcid.org/0000-0003-1744-7071Oleg Seliverstov3Quantum, Kharkiv, UkraineQuantum, Kharkiv, UkraineQuantum, Kharkiv, UkraineV. N. Karazin Kharkiv National University, SCGIS Ukraine, Kharkiv, UkraineThe logging is the leading cause for the reduction in the forest area in the world. At the same time, the number of forest clearcuts continues to grow. However, despite the massive scale, such incidents are difficult to track in time. As a result, huge areas of forests are gradually being cut down. Therefore, there is a need for regular and effective monitoring of changes in forest cover. The multitemporal data sources like Copernicus Sentinel-2 allow enhancing the potential of monitoring the Earth's surface and environmental dynamics including forest plantations. In this article, we present a baseline U-Net model for deforestation detection in the forest-steppe zone. Training and evaluation are conducted on our own dataset created on Sentinel-2 imagery for the Kharkiv region of Ukraine (31 400 km<sup>2</sup>). As a part of the research, we present several models with the ability to work with time-dependent imagery. The main contribution of this article is to provide a baseline model for the forest change detection inside Ukraine and improve it adding the ability to use several sequential images as an input of the segmentation model.https://ieeexplore.ieee.org/document/9241044/Change detectionconvolutional neural network (CNN)deep learningdeforestationloggingLSTM |
| spellingShingle | Kostiantyn Isaienkov Mykhailo Yushchuk Vladyslav Khramtsov Oleg Seliverstov Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection convolutional neural network (CNN) deep learning deforestation logging LSTM |
| title | Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 |
| title_full | Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 |
| title_fullStr | Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 |
| title_full_unstemmed | Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 |
| title_short | Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2 |
| title_sort | deep learning for regular change detection in ukrainian forest ecosystem with sentinel 2 |
| topic | Change detection convolutional neural network (CNN) deep learning deforestation logging LSTM |
| url | https://ieeexplore.ieee.org/document/9241044/ |
| work_keys_str_mv | AT kostiantynisaienkov deeplearningforregularchangedetectioninukrainianforestecosystemwithsentinel2 AT mykhailoyushchuk deeplearningforregularchangedetectioninukrainianforestecosystemwithsentinel2 AT vladyslavkhramtsov deeplearningforregularchangedetectioninukrainianforestecosystemwithsentinel2 AT olegseliverstov deeplearningforregularchangedetectioninukrainianforestecosystemwithsentinel2 |