Pixel and object-based land cover mapping and change detection from 1986 to 2020 for Hungary using histogram-based gradient boosting classification tree classifier

Gudmann, András; Mucsi, László

doi:10.5937/gp26-37720

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ülkemizde arazi örtüsü ve arazi kullanımı artan nüfus ve bunun yanında doğal alanların çeşitli sebep ve şekillerde tahribi ile dinamik bir şekilde değişmektedir. Dünyada ve ülkemizde meydana gelen değişimlerin hızlı, güvenilir ve düşük maliyet ile belirlenmesi ve yerel yönetimlerin hizmetine sunulacak altlık niteliğindeki haritaların üretilmesinde uzaktan algılama ve coğrafi bilgi sistemleri yöntemlerinden sıklıkla faydalanılmaktadır (Güre vd., 2009;Popoyici vd., 2013;Dengiz ve Demirağ, 2014;Gençer vd., 2015;Ateşoğlu, 2016;Bayar ve Karabacak, 2017;Kuru, 2018;Karademir ve Doğan, 2019;Keleş ve Durduran, 2019;Özdeş vd., 2019;Özşahin vd., 2020;Üyük vd., 2020;Polat ve Yalçın, 2020;Kaya vd., 2020;Demir, 2021;Timur vd., 2021;Turan vd., 2021;Türker, 2021;Yeşil ve Güzel, 2021;Gudmann ve Musci, 2022;Nacar ve Karademir, 2022). Bu çalışmanın amacı, Alibeyköy Havzasına ait uydu görüntüleri kullanılarak 2002, 2010 ve 2022 yıllarında arazi örtüsü ve arazi kullanımında meydana gelen değişiklikleri uzaktan algılama (UA) ve CBS teknikleri kullanarak belirlemektir.…”

unclassified

Ali̇beyköy Havzasi Arazi̇ Örtüsü Ve Arazi̇ Kullanimi Zamansal Deği̇şi̇mi̇ni̇n Uzaktan Algilama Yöntemleri̇ İle İncelenmesi̇

SADIK¹,

SARIYILMAZ²

2022

UZALCBS 2022 Sempozyumu

View full text Add to dashboard Cite

INVESTIGATION OF LAND COVER AND LAND USE CHANGE IN ALIBEYKOY BASIN WITH REMOTE SENSING METHODSAlibeyköy basin is one of the 8 important basins that supply water to Istanbul. In this study, the changes in the land cover and land use of the Alibeyköy Basin located in the Alibeyköy district of Eyüpsultan district of Istanbul between 2002, 2010 and 2022 were determined by using remote sensing (UA) techniques and geographic information systems (GIS). For this purpose, firstly, the classification process was carried out and the land cover and land use classes of the study area were determined. In the continuation of the study, Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built-in Index (NDBI) were calculated over satellite images. The results obtained were compared with the classification results of 2002, 2010 and 2022. In the study, Landsat 5 TM for 2002 and 2010 and Landsat 8 OLI for 2022 satellite images were used. The land cover and land use classes of the Alıbeykoy Basin were determined according to the CORINE system. Land cover and land use classes are in 4 classes: forest and semi-natural areas, water bodies, artificial surfaces, and agricultural areas. As a result of the analysis, it was determined that artificial surfaces increased, forest and semi-natural areas and agricultural areas decreased. The reason for the increase in artificial surfaces is thought to be the Istanbul Airport, which was opened in 2018 in the region. It is seen that the changes in and around the Alibeyköy Basin, which is of great importance in the region, can be easily detected by Remote Sensing methods.

show abstract

unclassified

Ali̇beyköy Havzasi Arazi̇ Örtüsü Ve Arazi̇ Kullanimi Zamansal Deği̇şi̇mi̇ni̇n Uzaktan Algilama Yöntemleri̇ İle İncelenmesi̇

SADIK¹,

SARIYILMAZ²

2022

UZALCBS 2022 Sempozyumu

View full text Add to dashboard Cite

show abstract

Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest

Phinzi,

Ngetar,

Pham

et al. 2023

Earth Sci Inform

View full text Add to dashboard Cite

High-resolution sensors onboard satellites are generally reputed for rapidly producing land-use/land-cover (LULC) maps with improved spatial detail. However, such maps are subject to uncertainties due to several factors, including the training sample size. We investigated the effects of different training sample sizes (from 1000 to 12,000 pixels) on LULC classification accuracy using the random forest (RF) classifier. Then, we analyzed classification uncertainties by determining the median and the interquartile range (IQR) of the overall accuracy (OA) values through repeated k-fold cross-validation. Results showed that increasing training pixels significantly improved OA while minimizing model uncertainty. Specifically, larger training samples, ranging from 9000 to 12,000 pixels, exhibited narrower IQRs than smaller samples (1000–2000 pixels). Furthermore, there was a significant variation (Chi2 = 85.073; df = 11; p < 0.001) and a significant trend (J-T = 4641, p < 0.001) in OA values across various training sample sizes. Although larger training samples generally yielded high accuracies, this trend was not always consistent, as the lowest accuracy did not necessarily correspond to the smallest training sample. Nevertheless, models using 9000–11,000 pixels were effective (OA > 96%) and provided an accurate visual representation of LULC. Our findings emphasize the importance of selecting an appropriate training sample size to reduce uncertainties in high-resolution LULC classification.

show abstract

Identification and Landscape Pattern Analysis of Peri-Urban Areas

Shi,

Wang,

Liu

et al. 2024

jengeo

View full text Add to dashboard Cite

The process of peri-urbanization in the context of globalization has become a global phenomenon. Taking Budapest as a case study, this study aims to develop a breakpoint clustering method that combines breakpoint method and spatial clustering to identify peri-urban areas (PUAs). Landscape metrics were used to analyze the structure and characteristics of various landscapes within PUAs. The results indicate that PUAs in Budapest occupy 39.63% of the area, predominantly consisting of artificial surfaces and agricultural land. In PUAs, artificial surfaces are the dominant landscape type, water bodies exhibit high aggregation and strong connectivity, while agricultural areas, forests and semi-natural areas show high fragmentation. The identification and landscape analysis of PUAs will provide significant insights for urban studies and governmental planning.

show abstract

Pixel and object-based land cover mapping and change detection from 1986 to 2020 for Hungary using histogram-based gradient boosting classification tree classifier

Cited by 4 publications

References 20 publications

Ali̇beyköy Havzasi Arazi̇ Örtüsü Ve Arazi̇ Kullanimi Zamansal Deği̇şi̇mi̇ni̇n Uzaktan Algilama Yöntemleri̇ İle İncelenmesi̇

Ali̇beyköy Havzasi Arazi̇ Örtüsü Ve Arazi̇ Kullanimi Zamansal Deği̇şi̇mi̇ni̇n Uzaktan Algilama Yöntemleri̇ İle İncelenmesi̇

Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest

Identification and Landscape Pattern Analysis of Peri-Urban Areas

Contact Info

Product

Resources

About