Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines

Petropoulos, George P.; Kontoes, Charalampos; Keramitsoglou, Iphigenia

doi:10.1016/j.jag.2010.06.008

Cited by 106 publications

(50 citation statements)

References 50 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several factors can explain the extensive investigations with Landsat TM, Enhanced Thematic Mapper plus (ETM+) and Operational Land Imager (OLI) data, including a long consistent acquisition record (nearly three decades), a medium spatial resolution (30 m for the optical bands) appropriate for the identification swidden (or burned plots) at the pixel level, a combination of visible, near infrared (NIR), and short-wave infrared (SWIR) bands, and free availability via the Internet since 2008. Therefore, Landsat TM, ETM+ and OLI data are particularly suitable for mapping burned area [104]. However, swidden landscapes were generally considered difficult to map in the past in SEA because of the complex and dynamic feature of swidden farming [54].…”

Section: Satellite Data For Operational Swidden Agriculture Monitoringmentioning

confidence: 99%

“…SVM belongs to linear classifiers and has also gained popularity in the burned area identification with satellite imagery in the last decade. Compared with conventional classification methods, SVM has several advantages in the following aspects [104,134]: (i) dealing with learning problems with a limited number of training sets; (ii) overcoming the pre-determination of optimal threshold; (iii) and dealing with high dimensionality datasets. Especially, the avoidance of setting a critical threshold is undoubtedly a notable improvement in mapping burned area with single-date image.…”

Section: Statistical Theory Based Approachesmentioning

confidence: 99%

“…For example, Cao et al used daily MODIS data to map burn scar using an automatic region growing method based on SVM [134]. Petropoulos et al investigated the potential of combined use of SVM classifier with Landsat TM imagery for delineating burnt area in a Mediterranean setting [104]. Both ANN and SVM are supervised classifiers which classified different land cover types based on training sets.…”

Section: Statistical Theory Based Approachesmentioning

confidence: 99%

See 2 more Smart Citations

A Review of Swidden Agriculture in Southeast Asia

Zhu

Jiang

et al. 2014

Remote Sensing

View full text Add to dashboard Cite

Swidden agriculture is by far the dominant land use system in the mountainous regions of Southeast Asia (SEA). It provides various valuable subsistence products to local farmers, mostly the poor ethnic minority groups. Controversially, it is also closely connected with a number of environmental issues. With the strengthening regional economic cooperation in SEA, swidden agriculture has experienced drastic transformations into other diverse market-oriented land use types since the 1990s. However, there is very limited information on the basic geographical and demographic data of swidden agriculture and the socio-economic and biophysical effects of the transformations. International programs, such as the Reducing Emissions from Deforestation and forest Degradation (REDD), underscore the importance of monitoring and evaluating swidden agriculture and its transition to reduce carbon emission due to deforestation and forest degradation. In this context, along with the accessibility of Landsat historical imagery, remote sensing based techniques will offer an effective way to detect and monitor the locations and extent of swidden agriculture. Many approaches for investigating fire occurrence and burned area can be introduced for swidden agriculture mapping due to the common feature of fire relatedness. In this review paper, four broad approaches involving spectral signatures, phenological characteristics, statistical theory and landscape ecology were summarized for swidden agriculture delineation. Five research priorities about swidden agriculture involving remote sensing techniques, spatial pattern, change, drivers and impacts were proposed accordingly. To our knowledge, a synthesis review on the remote sensing and outlook on swidden agriculture has not been reported yet. This review paper aims to give a comprehensive overview of swidden agriculture studies in the domains of debated definition, trends, remote sensing methods and OPEN ACCESSRemote Sens. 2014, 6 1655 outlook research in SEA undertaken in the past two decades.

show abstract

Section: Satellite Data For Operational Swidden Agriculture Monitoringmentioning

confidence: 99%

Section: Statistical Theory Based Approachesmentioning

confidence: 99%

Section: Statistical Theory Based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Swidden Agriculture in Southeast Asia

Zhu

Jiang

et al. 2014

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…When burned area algorithms are optimized for site level performance, the accuracy can exceed 95% [29,72]. As the target area expands, accuracy often begins to decrease (e.g., 15% to 30% error for burned area) due to variance imposed by local factors [33,73,74].…”

Section: Discussionmentioning

confidence: 99%

Evaluation of the U.S. Geological Survey Landsat Burned Area Essential Climate Variable across the Conterminous U.S. Using Commercial High-Resolution Imagery

et al. 2017

View full text Add to dashboard Cite

The U.S. Geological Survey has produced the Landsat Burned Area Essential Climate Variable (BAECV) product for the conterminous United States (CONUS), which provides wall-to-wall annual maps of burned area at 30 m resolution . Validation is a critical component in the generation of such remotely sensed products. Previous efforts to validate the BAECV relied on a reference dataset derived from Landsat, which was effective in evaluating the product across its timespan but did not allow for consideration of inaccuracies imposed by the Landsat sensor itself. In this effort, the BAECV was validated using 286 high-resolution images, collected from GeoEye-1, QuickBird-2, Worldview-2 and RapidEye satellites. A disproportionate sampling strategy was utilized to ensure enough burned area pixels were collected. Errors of omission and commission for burned area averaged 22 ± 4% and 48 ± 3%, respectively, across CONUS. Errors were lowest across the western U.S. The elevated error of commission relative to omission was largely driven by patterns in the Great Plains which saw low errors of omission (13 ± 13%) but high errors of commission (70 ± 5%) and potentially a region-growing function included in the BAECV algorithm. While the BAECV reliably detected agricultural fires in the Great Plains, it frequently mapped tilled areas or areas with low vegetation as burned. Landscape metrics were calculated for individual fire events to assess the influence of image resolution (2 m, 30 m and 500 m) on mapping fire heterogeneity. As the spatial detail of imagery increased, fire events were mapped in a patchier manner with greater patch and edge densities, and shape complexity, which can influence estimates of total greenhouse gas emissions and rates of vegetation recovery. The increasing number of satellites collecting high-resolution imagery and rapid improvements in the frequency with which imagery is being collected means greater opportunities to utilize these sources of imagery for Landsat product validation.

show abstract

“…There are six machine learning algorithms applied in classifying the satellite image such as Mahalanobis Distance (Chennai et al, 2015), Minimum Distance (Chennai et al, 2015), Maximum Likelihood (Ahmad and Quegan, 2012), Parallelepiped (Lü and Tang, 2012;Vanitha et al, 2013), Neural Network (Ojaghi et al, 2015;Mustapha et al, 2010) and Support Vector Machines (Petropoulos et al, 2011).…”

Section: Image Classificationmentioning

confidence: 99%

Comparison of Classification Techniques on Fused Optical and SAR Images for Shoreline Extraction: A Case Study at Northeast Coast of Peninsular Malaysia

Manaf¹,

Mustapha²,

Sulaiman³

et al. 2016

Journal of Computer Science

View full text Add to dashboard Cite

Shoreline is a very important element to identify exact boundary at the coastal areas of a country. However, in order to identify land-water boundary for a large region using traditional ground survey technique is very time consuming. Alternatively, shoreline can be extracted by using satellite images that minimizes the mapping errors. The trend of extracting shoreline has been shifted from image processing to machine learning and data mining techniques. By using machine learning technique, the satellite images could be classified into land and water classes in order to extract shoreline. However, the result is meaningless if it has cloud and shadow on the water-land boundary. In this study, we compare the accuracy and Kappa Coefficient of six machine learning techniques namely Maximum Likelihood, Minimum Distance, Mahalanobis Distance, Parallelepiped, Neural Network and Support Vector Machines on three type of images; single optical multispectral, single SAR and fused image. A case study for this research is done alongside Tumpat beach, located at the Northeast Coast of Peninsular Malaysia. All the machine learning techniques have been tested on the three types of images. The experimental results show that classification using SVM on single multispectral image has the highest accuracy among all. However, the classified of fused image using SVM is considered much more accurate because it can cater the cloud and shadow problem. Additionally, the classification on 5 and 10 m fused images also tested and the result shows that with the increase of spatial resolution of fused image, the classification accuracy also increases.

show abstract

Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines

Cited by 106 publications

References 50 publications

A Review of Swidden Agriculture in Southeast Asia

A Review of Swidden Agriculture in Southeast Asia

Evaluation of the U.S. Geological Survey Landsat Burned Area Essential Climate Variable across the Conterminous U.S. Using Commercial High-Resolution Imagery

Comparison of Classification Techniques on Fused Optical and SAR Images for Shoreline Extraction: A Case Study at Northeast Coast of Peninsular Malaysia

Contact Info

Product

Resources

About