Murat KURUCA, Dilek Kocuk MATCİ, Ugur AVDAN

The potential of Gokturk 2 satellite images for mapping burnt forest areas

Using remotely sensed data to identify burnt forest areas produces fast, economical, and highly accurate results. Accordingly, in this study we investigate the capabilities of Göktürk-2, Turkey’s national satellite, for mapping burnt forest areas. We compare our results with those obtained from Landsat-8 and Worldview-2 satellite images, which are frequently used for mapping burnt areas. The capabilities of the satellites are compared, in terms of detecting burnt forest areas, using support vector machine (SVM) and rotation forest (RF) classification, which are advanced methods. According to the results of the accuracy analysis, SVM classification gives similar kappa statistics and overall accuracy for Göktürk-2 and Landsat-8 images, while the performance of Worldview-2 shows greater general accuracy. Although there is no significant difference between the two classification methods forLandsat-8 images, SVM gives better results than RF for both Göktürk-2 and Worldview-2. The results of our study show that Göktürk-2 images are an effective source for mapping burnt forest areas.

Keywords:

Göktürk-2, mapping burnt forest area object-based image analysis, rotation forest, support vector machine,

PDF

___

Akar O, 2019, GEOMATIK, V4, P68, DOI [10.29128/geomatik.476668, DOI 10.29128/GEOMATIK.476668]
Anthony G, 2007, ARXIV07093967 .
ARONOFF S, 1982, PHOTOGRAMM ENG REM S, V48, P1299
Ashburn P, 1979, JOHNSON SPACE CTR P, V1
Atak V. O., 2015, HARITA DERGISI, V81, P18
Barbosa PM, 1999, GLOBAL BIOGEOCHEM CY, V13, P933, DOI 10.1029/1999GB900042
Bayburt S, 2009, UYDU GORUNTULERININ .
Bazi Y, 2006, IEEE T GEOSCI REMOTE, V44, P3374, DOI 10.1109/TGRS.2006.880628
Blackburn GA, 1998, INT J REMOTE SENS, V19, P657, DOI 10.1080/014311698215919
Bruzzone L, 2006, IEEE T GEOSCI REMOTE, V44, P3363, DOI 10.1109/TGRS.2006.877950
Cochran W.G., 1967, STAT METHODS .
Colkesen I, 2015, HARITA DERGISI, V154, P9
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
Epting J, 2005, REMOTE SENS ENVIRON, V96, P328, DOI 10.1016/j.rse.2005.03.002
FITZPATRICKLINS K, 1981, PHOTOGRAMM ENG REM S, V47, P343
Foody GM, 2006, REMOTE SENS ENVIRON, V104, P1, DOI 10.1016/j.rse.2006.03.004
Foody GM, 2004, IEEE T GEOSCI REMOTE, V42, P1335, DOI 10.1109/TGRS.2004.827257
Gangkofner UG, 2008, PHOTOGRAMM ENG REM S, V74, P1107, DOI 10.14358/PERS.74.9.1107
Gao Y, 2006, INT J REMOTE SENS, V27, P4039, DOI 10.1080/01431160600702632
Ghosh A, 2014, INT J APPL EARTH OBS, V26, P298, DOI 10.1016/j.jag.2013.08.011
Gitelson AA, 2002, REMOTE SENS ENVIRON, V80, P76, DOI 10.1016/S0034-4257(01)00289-9
Gunn S. R., 1998, ISIS TECH REP, V14, P5
Gurcan I, 2016, 2016 24TH SIGNAL PROCESSING AND COMMUNICATION APPLICATION CONFERENCE (SIU), P2097, DOI 10.1109/SIU.2016.7496185
Hsu C., 2003, PRACTICAL GUIDE SUPP .
Huang C, 2002, INT J REMOTE SENS, V23, P725, DOI 10.1080/01431160110040323
HUETE A R, 1988, Remote Sensing of Environment, V25, P295
Jimenez-Munoz JC, 2009, SENSORS-BASEL, V9, P768, DOI 10.3390/s90200768
Joachims T., 1998, P 10 EUR C MACH LEAR, P137, DOI [10.1007/BFb0026683, DOI 10.1007/BFB0026683]
Kavzolu T, 2010, HARITA DERGISI, V144, P73
Kramer H. J., 2002, OBSERVATION EARTH IT
Ling F, 2015, IEEE GEOSCI REMOTE S, V12, P1963, DOI 10.1109/LGRS.2015.2441135
Liu KH, 2008, COMPUT BIOL MED, V38, P601, DOI 10.1016/j.compbiomed.2008.02.007
Loboda T, 2007, REMOTE SENS ENVIRON, V109, P429, DOI 10.1016/j.rse.2007.01.017
Long TF, 2019, REMOTE SENS-BASEL, V11, DOI 10.3390/rs11050489
Lucas I, 1994, PHOTOGRAMM ENG REMOT, V60, P426
Malinverni ES, 2011, INT J GEOGR INF SCI, V25, P1025, DOI 10.1080/13658816.2011.566569
Melgani F, 2004, IEEE T GEOSCI REMOTE, V42, P1778, DOI 10.1109/TGRS.2004.831865
Meng Ran, 2017, Remote Sensing of Environment, V191, P95, DOI 10.1016/j.rse.2017.01.016
Miller JD, 2002, REMOTE SENS ENVIRON, V82, P481, DOI 10.1016/S0034-4257(02)00071-8
Mountrakis G, 2011, ISPRS J PHOTOGRAMM, V66, P247, DOI 10.1016/j.isprsjprs.2010.11.001
Myint SW, 2011, REMOTE SENS ENVIRON, V115, P1145, DOI 10.1016/j.rse.2010.12.017
PINTY B, 1992, VEGETATIO, V101, P15, DOI 10.1007/BF00031911
Qian YG, 2015, REMOTE SENS-BASEL, V7, P153, DOI 10.3390/rs70100153
Quintano C, 2018, INT J APPL EARTH OBS, V64, P221, DOI 10.1016/j.jag.2017.09.014
Rodriguez JJ, 2006, IEEE T PATTERN ANAL, V28, P1619, DOI 10.1109/TPAMI.2006.211
Roy DR, 2006, IEEE GEOSCI REMOTE S, V3, P112, DOI 10.1109/LGRS.2005.858485
Schroeder W, 2016, REMOTE SENS ENVIRON, V185, P210, DOI 10.1016/j.rse.2015.08.032
Sunar F, 2018, DIGITAL GORUNTU ISLE .
Suwarsono, 2018, MATEC Web of Conferences, V229, DOI 10.1051/matecconf/201822904012
Teke M., 2016, HAVACILIK UZAY TEKNO, V9, P1
TUCKER CJ, 1979, REMOTE SENS ENVIRON, V8, P127, DOI 10.1016/0034-4257(79)90013-0
Van Niel TG, 2005, REMOTE SENS ENVIRON, V98, P468, DOI 10.1016/j.rse.2005.08.011
Vapnik V., 1995, NATURE STAT LEARNING, V325, DOI [10.1007/978-1-4757-2440-0, DOI 10.1007/978-1-4757-2440-0]
Vhengani L, 2015, INT GEOSCI REMOTE SE, P4153, DOI 10.1109/IGARSS.2015.7326740
Waske B, 2007, IEEE T GEOSCI REMOTE, V45, P3858, DOI 10.1109/TGRS.2007.898446
Wu ZT, 2015, PHOTOGRAMM ENG REM S, V81, P143, DOI 10.14358/PERS.81.2.143
Xia JS, 2015, IEEE T GEOSCI REMOTE, V53, P2532, DOI 10.1109/TGRS.2014.2361618
Zhang Y, 2012, INT GEOSCI REMOTE SE, P182, DOI 10.1109/IGARSS.2012.6351607
Zheng Z, 2007, YUNNAN GEOGRAPHIC EN, V20