An automatic method for burn scar mapping using support vector machines

被引:60
作者
Cao, X. [1 ,3 ]
Chen, J. [1 ]
Matsushita, B. [2 ]
Imura, H. [4 ]
Wang, L. [5 ]
机构
[1] Beijing Normal Univ, Minist Educ China, Key Lab Environm Change & Nat Disaster, Coll Resource Sci & Technol, Beijing 100875, Peoples R China
[2] Univ Tsukuba, Grad Sch Life & Environm Sci, Tsukuba, Ibaraki 3058572, Japan
[3] Nagoya Univ, Grad Sch Engn, Nagoya, Aichi 4648603, Japan
[4] Nagoya Univ, Grad Sch Environm Studies, Nagoya, Aichi 4648603, Japan
[5] SW Texas State Univ, Dept Geog, San Marcos, TX 78666 USA
关键词
SPOT-VEGETATION; SUPERVISED CLASSIFICATION; FOREST-FIRES; TIME-SERIES; AREAS; MODIS; ALGORITHM; INDEXES; IMAGES;
D O I
10.1080/01431160802220219
中图分类号
TP7 [遥感技术];
学科分类号
080201 [机械制造及其自动化];
摘要
Wildfires release large amounts of carbon, smoke and aerosols that strongly impact the global climatic system. Burn scar is an important parameter when modelling the impact of wildfires on the ecosystem and the climatic system. We have developed an automatic burn scar mapping method using daily Moderate Resolution Imaging Spectroradiometer (MODIS) data, in which the Global Environment Monitoring Index (GEMI), a vegetation index VI3T and a new index, GEMI-Burn scar (GEMI-B), were used together to enhance the differences between burned and unburned pixels related to vegetation photosynthesis, surface temperature and vegetation water content, respectively, and an automatic region growing method based on Support Vector Machines (SVMs) was used to classify burn scars without any predefined threshold. A case study was carried out to validate the new method at the border area between Mongolia and China, where a wildfire took place in May 2003. The results show that the burn scar area extracted by the new method is consistent with that from Landsat Thematic Mapper (TM) data with high accuracy. The sound performance of the new technique is due to the following reasons: (1) multiple features of burn scar spectra were combined and used, (2) a reasonable assumption was made stating that the neighbourhoods of active fires (hotspots) are most likely to be burn scars, (3) an SVM classifier was adopted that works well with a small number of training samples, and (4) an iterative classification procedure was developed that is capable of running continuous training for the SVM classifier to deal with the transitionary features of burn scar pixels. The results suggest that the new index GEMI-B and automatic mapping method based on SVMs have the potential to be applied to near real-time burn scar mapping in grassland areas.
引用
收藏
页码:577 / 594
页数:18
相关论文
共 49 条
[1]
Compositing criteria for burned area assessment using multitemporal low resolution satellite data [J].
Barbosa, PM ;
Pereira, JMC ;
Gregoire, JM .
REMOTE SENSING OF ENVIRONMENT, 1998, 65 (01) :38-49
[2]
An algorithm for extracting burned areas from time series of AVHRR GAC data applied at a continental scale [J].
Barbosa, PM ;
Grégoire, JM ;
Pereira, JMC .
REMOTE SENSING OF ENVIRONMENT, 1999, 69 (03) :253-263
[3]
Christensen N.L., 1993, FIRE ENV ECOLOGICAL, P233
[4]
Assessment of multitemporal compositing techniques of MODIS and AVHRR images for burned land mapping [J].
Chuvieco, E ;
Ventura, G ;
Martín, MP ;
Gómez, I .
REMOTE SENSING OF ENVIRONMENT, 2005, 94 (04) :450-462
[5]
Assessment of different spectral indices in the red-near-infrared spectral domain for burned land discrimination [J].
Chuvieco, E ;
Martín, MP ;
Palacios, A .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2002, 23 (23) :5103-5110
[6]
BIOMASS BURNING IN THE TROPICS - IMPACT ON ATMOSPHERIC CHEMISTRY AND BIOGEOCHEMICAL CYCLES [J].
CRUTZEN, PJ ;
ANDREAE, MO .
SCIENCE, 1990, 250 (4988) :1669-1678
[7]
A support vector machine approach for detection of microcalcifications [J].
El-Naqa, I ;
Yang, YY ;
Wernick, MN ;
Galatsanos, NP ;
Nishikawa, RM .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2002, 21 (12) :1552-1563
[8]
Burnt area mapping in Central Africa using ATSR data [J].
Eva, H ;
Lambin, EF .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (18) :3473-3497
[9]
Automatic mapping of surfaces affected by forest fires in Spain using AVHRR NDVI composite image data [J].
Fernandez, A ;
Illera, P ;
Casanova, JL .
REMOTE SENSING OF ENVIRONMENT, 1997, 60 (02) :153-162
[10]
Hotspot and NDVI differencing synergy (HANDS): A new technique for burned area mapping over boreal forest [J].
Fraser, RH ;
Li, Z ;
Cihlar, J .
REMOTE SENSING OF ENVIRONMENT, 2000, 74 (03) :362-376