Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia
Wildland fire is one of the most causes of deforestation, and it has an important impact on atmospheric emissions, notably CO<sub>2</sub>. It occurs almost every year in Indonesia, especially during the dry season. Therefore, it is necessary to identify the burned areas from remote sensi...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Data |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5729/7/6/78 |
| _version_ | 1797488355611508736 |
|---|---|
| author | Yudhi Prabowo Anjar Dimara Sakti Kuncoro Adi Pradono Qonita Amriyah Fadillah Halim Rasyidy Irwan Bengkulah Kurnia Ulfa Danang Surya Candra Muhammad Thufaili Imdad Shadiq Ali |
| author_facet | Yudhi Prabowo Anjar Dimara Sakti Kuncoro Adi Pradono Qonita Amriyah Fadillah Halim Rasyidy Irwan Bengkulah Kurnia Ulfa Danang Surya Candra Muhammad Thufaili Imdad Shadiq Ali |
| author_sort | Yudhi Prabowo |
| collection | DOAJ |
| description | Wildland fire is one of the most causes of deforestation, and it has an important impact on atmospheric emissions, notably CO<sub>2</sub>. It occurs almost every year in Indonesia, especially during the dry season. Therefore, it is necessary to identify the burned areas from remote sensing images to establish the zoning map of areas prone to wildland fires. Many methods have been developed for mapping burned areas from low-resolution to medium-resolution satellite images. One of the popular approaches for mapping tasks is a deep learning approach using U-Net architecture. However, it needs a large amount of representative training data to develop the model. In this paper, we present a new dataset of burned areas in Indonesia for training or evaluating the U-Net model. We delineate burned areas manually by visual interpretation on Landsat-8 satellite images. The dataset is collected from some regions in Indonesia, and it consists of 227 images with a size of 512 × 512 pixels. It contains one or more burned scars or only the background and its labeled masks. The dataset can be used to train and evaluate the deep learning model for image detection, segmentation, and classification tasks related to burned area mapping. |
| first_indexed | 2024-03-10T00:01:56Z |
| format | Article |
| id | doaj.art-038c8543d6e54b28a2b23ae4e6f418f2 |
| institution | Directory Open Access Journal |
| issn | 2306-5729 |
| language | English |
| last_indexed | 2024-03-10T00:01:56Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Data |
| spelling | doaj.art-038c8543d6e54b28a2b23ae4e6f418f22023-11-23T16:14:50ZengMDPI AGData2306-57292022-06-01767810.3390/data7060078Deep Learning Dataset for Estimating Burned Areas: Case Study, IndonesiaYudhi Prabowo0Anjar Dimara Sakti1Kuncoro Adi Pradono2Qonita Amriyah3Fadillah Halim Rasyidy4Irwan Bengkulah5Kurnia Ulfa6Danang Surya Candra7Muhammad Thufaili Imdad8Shadiq Ali9National Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaRemote Sensing and Geographic Information Science Research Group, Faculty of Earth Sciences and Technology, Institut Teknologi Bandung, Bandung 40132, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaNational Research and Innovation Agency (BRIN), Jakarta 13220, IndonesiaDepartment of Physics, University of Indonesia, Depok City 16424, IndonesiaWildland fire is one of the most causes of deforestation, and it has an important impact on atmospheric emissions, notably CO<sub>2</sub>. It occurs almost every year in Indonesia, especially during the dry season. Therefore, it is necessary to identify the burned areas from remote sensing images to establish the zoning map of areas prone to wildland fires. Many methods have been developed for mapping burned areas from low-resolution to medium-resolution satellite images. One of the popular approaches for mapping tasks is a deep learning approach using U-Net architecture. However, it needs a large amount of representative training data to develop the model. In this paper, we present a new dataset of burned areas in Indonesia for training or evaluating the U-Net model. We delineate burned areas manually by visual interpretation on Landsat-8 satellite images. The dataset is collected from some regions in Indonesia, and it consists of 227 images with a size of 512 × 512 pixels. It contains one or more burned scars or only the background and its labeled masks. The dataset can be used to train and evaluate the deep learning model for image detection, segmentation, and classification tasks related to burned area mapping.https://www.mdpi.com/2306-5729/7/6/78datasetburned areadeep learningU-NetLandsat-8remote sensing |
| spellingShingle | Yudhi Prabowo Anjar Dimara Sakti Kuncoro Adi Pradono Qonita Amriyah Fadillah Halim Rasyidy Irwan Bengkulah Kurnia Ulfa Danang Surya Candra Muhammad Thufaili Imdad Shadiq Ali Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia Data dataset burned area deep learning U-Net Landsat-8 remote sensing |
| title | Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia |
| title_full | Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia |
| title_fullStr | Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia |
| title_full_unstemmed | Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia |
| title_short | Deep Learning Dataset for Estimating Burned Areas: Case Study, Indonesia |
| title_sort | deep learning dataset for estimating burned areas case study indonesia |
| topic | dataset burned area deep learning U-Net Landsat-8 remote sensing |
| url | https://www.mdpi.com/2306-5729/7/6/78 |
| work_keys_str_mv | AT yudhiprabowo deeplearningdatasetforestimatingburnedareascasestudyindonesia AT anjardimarasakti deeplearningdatasetforestimatingburnedareascasestudyindonesia AT kuncoroadipradono deeplearningdatasetforestimatingburnedareascasestudyindonesia AT qonitaamriyah deeplearningdatasetforestimatingburnedareascasestudyindonesia AT fadillahhalimrasyidy deeplearningdatasetforestimatingburnedareascasestudyindonesia AT irwanbengkulah deeplearningdatasetforestimatingburnedareascasestudyindonesia AT kurniaulfa deeplearningdatasetforestimatingburnedareascasestudyindonesia AT danangsuryacandra deeplearningdatasetforestimatingburnedareascasestudyindonesia AT muhammadthufailiimdad deeplearningdatasetforestimatingburnedareascasestudyindonesia AT shadiqali deeplearningdatasetforestimatingburnedareascasestudyindonesia |