Object-Based on Land Cover Classification on LAPAN-A3 Satellite Imagery Using Tree Algorithm (Case Study: Rote Island)

Herawan, Agus; Julzarika, Atriyon; Hakim, Patria Rachman; Anggari, Ega Asti

doi:10.18517/ijaseit.11.6.14200

Cited by 6 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Images from a multispectral camera, LISAT, onboard the third-generation satellite by LAPAN, named LAPAN-A3, were used in a study to perform object-based land cover classification of the Rote Island, using a tree method algorithm [ 62 ]. The results achieved overall classification accuracy of 86% for different classes, including open land, settlements, water bodies and diverse vegetation.…”

Section: Related Workmentioning

confidence: 99%

Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery

Kavran

Mongus

Žalik

et al. 2023

Sensors

View full text Add to dashboard Cite

Multispectral satellite imagery offers a new perspective for spatial modelling, change detection and land cover classification. The increased demand for accurate classification of geographically diverse regions led to advances in object-based methods. A novel spatiotemporal method is presented for object-based land cover classification of satellite imagery using a Graph Neural Network. This paper introduces innovative representation of sequential satellite images as a directed graph by connecting segmented land region through time. The method’s novel modular node classification pipeline utilises the Convolutional Neural Network as a multispectral image feature extraction network, and the Graph Neural Network as a node classification model. To evaluate the performance of the proposed method, we utilised EfficientNetV2-S for feature extraction and the GraphSAGE algorithm with Long Short-Term Memory aggregation for node classification. This innovative application on Sentinel-2 L2A imagery produced complete 4-year intermonthly land cover classification maps for two regions: Graz in Austria, and the region of Portorož, Izola and Koper in Slovenia. The regions were classified with Corine Land Cover classes. In the level 2 classification of the Graz region, the method outperformed the state-of-the-art UNet model, achieving an average F1-score of 0.841 and an accuracy of 0.831, as opposed to UNet’s 0.824 and 0.818, respectively. Similarly, the method demonstrated superior performance over UNet in both regions under the level 1 classification, which contains fewer classes. Individual classes have been classified with accuracies up to 99.17%.

show abstract

Section: Related Workmentioning

confidence: 99%

Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery

Kavran

Mongus

Žalik

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Satelit LAPAN-A3 dimanfaatkan untuk klasifikasi data tutupan lahan (Nugroho et al, 2018) (Herawan et al, 2021). Selain itu citra satelit ini juga dimanfaatkan untuk mengidentifikasi padi menggunakan OBIA (Mukhoriyah dan Kushardono, 2021) (Setiawan et al, 2018).…”

Section: Gambar 1 Satelit Lapan-a3unclassified

Pemanfaatan Satelit Lapan-A3 untuk Pemantauan Bencana Alam

Herawan¹,

Hakim

Anggari

et al. 2022

SNST

View full text Add to dashboard Cite

Sangat penting untuki Indonesia sebagai negara yang rawan bencana untuk memiliki citra satelit sendiri untuk digunakan dalam pemantauan kebencanaan Indonesia. Data satelit LAPAN-A3 telah dipelajari untuk pengamatan bumi dan dapat dimanfaatkan salah satunya untuk pemantauan bencana alam. Dengan ketinggian satelit di orbit rendah dan memiliki swath sebesar 120 kilometer, secara teoritis kamera multispektral satelit LAPAN-A3 memiliki revisit time sebesar 21 hari. Satelit ini membawa sensor multispektral push-broom yang dapat merekam permukaan bumi pada spektrum visible inframerah dan NIR iinframerah dekat. Diluncurkan pada Juni 2016, belum banyak publikasi terkait penggunaan data multispektral LAPAN-A3. Makalah ini bertujuan untuk memaparkan pemanfaatan citra multispektral satelit LAPAN-A3 dalam memantau kebencanaan. Mode operasi yang digunakan untuk memantau bencana dilakukan dengan mode nadir pointing dan off nadir pointing. Hasil memunjukkan satelit LAPAN-A3 telah berhasil mengakuisisi data-data daerah yang mengalami bencana alam salah satunya Erupsi Krakatau dan Bencana di Palu

show abstract

“…Satellites that have mediumresolution cameras (30 m for Landsat-8 and 10 m for Sentinel-2) are widely used for land use and land cover classification [19], [20]. LAPAN-A3 satellite landcover classification has been carried out in research [21]. A tree algorithm was used in this research.…”

Section: Introductionmentioning

confidence: 99%

Assessing the Accuracy of Land Use Classification Using Multi-spectral Camera From LAPAN-A3, Landsat-8 and Sentinel-2 Satellite: A Case Study in Probolinggo-East Java

Anggari,

Herawan,

Hakim

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

The LAPAN-A3 is the third microsatellite generation developed by the Research Center for Satellite Technology. The satellite can be used for land classification, agriculture monitoring, drought monitoring, and land use change. This study aims to classify land use and land cover in the research area. The main image used is LAPAN-A3; the compared images are Landsat-8 and Sentinel-2. Three images were taken on the same day and selected on cloud-free terms. The classification process starts with determining the region of interest (ROI) and the class. The classification is divided into six classes: water, forests, rice fields, settlements, open land, and coastal areas. The classification technique uses supervised learning with the maximum likelihood method. This study used Landsat 8 and Sentinel-2 data to compare the results obtained from LAPAN-A3. The accuracy test results for the LAPAN-A3 and Landsat-8 are 84.7042% and 0.783, respectively. While the accuracy test of LAPAN-A3 and Sentinel-2 is 72.2313%, the kappa value is 0.6394. The classification of two comparisons is quite accurate, with an accuracy of more than 70%. The LA3 classification successfully identifies water and coastal areas. The producer and accuracy is substantiated by comparing the results with both Landsat-8 and Sentinel-2 satellite data, which exhibit an accuracy rate exceeding 85%. Finally, LAPAN-A3 has great potential for classifying land use and land cover when compared to Landsat 8 and Sentinel-2 images, but future research should increase the number of datasets and vary the research area to improve the results.

show abstract

Object-Based on Land Cover Classification on LAPAN-A3 Satellite Imagery Using Tree Algorithm (Case Study: Rote Island)

Cited by 6 publications

References 19 publications

Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery

Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery

Pemanfaatan Satelit Lapan-A3 untuk Pemantauan Bencana Alam

Assessing the Accuracy of Land Use Classification Using Multi-spectral Camera From LAPAN-A3, Landsat-8 and Sentinel-2 Satellite: A Case Study in Probolinggo-East Java

Contact Info

Product

Resources

About