OBJECT BASED BURNED AREA MAPPING WITH RANDOM FOREST ALGORITHM

Utilization of multitemporal remote sensing data among others can be used todetermine thepattern of changes in urban expansion. One of the most important types of cities in urban systems isthe metropolitan urban area that covers several districts and cities. This is because the regiongenerally acts as the capital of the country, the provincial capital, and the center of economicactivities that are national or strategic. Understanding urban expansion at different metropolitanurban levels is important for expanding knowledge in times of urban growth and its impact on theenvironment. Aims in this study are: (1) utilization of multitemporal Landsat data for mapping urbanexpansion patterns, (2) knowing the effectiveness of object-based classification for mapping of urbansettlements and (3) spatiotemporal urban expansion pattern analysis in three metropolitan cities onJava Island.. In this study focused on three metropolitan urban in Java, namely DKI. Jakarta,Surabaya and Semarang. This study utilizing Landsat TM, ETM + and OLI image data to map urbansettlement land cover using object-based classification with Random Forest algorithm. Next,quantifying the typology of urban expansion and compare the spatiotemporal pattern of urbanexpansion during 2005-2015 on the results of land cover mapping. This research has found that (1)object-based classification with Random Forest algorithm is quite effective in terms of time of work tomap urban settlement cover on Landsat digital data having medium spatial resolution; (2) the threeurban metropolia is experiencing rapid and massive development and has a very variedspatiotemporal pattern; (3) Size of the city affect the pattern of urban expansion, followed by rapidexpansion of the region. Larger city size with relatively rapid expansion is more likely to experiencethe edge extension model, while smaller cities tend to develop with outlying models.

Download Full-text

Object-based image classification for burned area mapping of Creus Cape, Spain, using NOAA-AVHRR imagery

Remote Sensing of Environment ◽

10.1016/j.rse.2004.06.006 ◽

2004 ◽

Vol 92 (3) ◽

pp. 409-413 ◽

Cited By ~ 76

Author(s):

Ioannis Z. Gitas ◽

George H. Mitri ◽

Gemma Ventura

Keyword(s):

Image Classification ◽

Burned Area ◽

Noaa Avhrr ◽

Object Based ◽

Burned Area Mapping ◽

Avhrr Imagery

Download Full-text

Object-Based Burned Area Mapping Using Sentinel-2 Imagery and Supervised Learning Guided by Empirical Rules

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss.2019.8900134 ◽

2019 ◽

Cited By ~ 1

Author(s):

Nikos Georgopoulos ◽

Dimitris Stavrakoudis ◽

Ioannis Z. Gitas

Keyword(s):

Supervised Learning ◽

Burned Area ◽

Object Based ◽

Burned Area Mapping ◽

Sentinel 2

Download Full-text

A semi-automated object-oriented model for burned area mapping in the Mediterranean region using Landsat-TM imagery

International Journal of Wildland Fire ◽

10.1071/wf03079 ◽

2004 ◽

Vol 13 (3) ◽

pp. 367 ◽

Cited By ~ 34

Author(s):

G. H. Mitri ◽

I. Z. Gitas

Keyword(s):

Mediterranean Region ◽

Satellite Images ◽

Object Oriented ◽

Landsat Tm ◽

Burned Area ◽

Burned Areas ◽

Object Based ◽

Burned Area Mapping ◽

The Mediterranean ◽

Landsat Tm Imagery

Pixel-based classification methods that make use of the spectral information derived from satellite images have been repeatedly reported to create confusion between burned areas and non-vegetation categories, especially water bodies and shaded areas. As a result of the aforementioned, these methods cannot be used on an operational basis for mapping burned areas using satellite images. On the other hand, object-based image classification allows the integration of a broad spectrum of different object features, such as spectral values, shape and texture. Sophisticated classification, incorporating contextual and semantic information, can be performed by using not only image object attributes, but also the relationship between networked image objects. In this study, the synergy of all these features allowed us to address image analysis tasks that, up until now, have not been possible. The aim of this work was to develop an object-based classification model for burned area mapping in the Mediterranean using Landsat-TM imagery. The object-oriented model developed to map a burned area on the Greek island of Thasos was then used to map other burned areas in the Mediterranean region after the Landsat-TM images had been radiometrically, geometrically and topographically corrected. The results of the research showed that the developed object-oriented model was transferable and that it could be effectively used as an operative tool for identifying and mapping the three different burned areas (~98% overall accuracy).

Download Full-text