Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique

Dihkan, Mustafa; Güneroğlu, Nilgün; Karslı, Fevzi; Güneroğlu, Abdulaziz

doi:10.1080/01431161.2013.845317

Cited by 53 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining various classifiers based on a priori knowledge could further enhance the method [105]. Machine learning algorithms using neural network approaches are also evolving and are promising for integration into the methods presented here to potentially improve the results by mapping canopy species [106,107].…”

Section: Discussionmentioning

confidence: 99%

Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

Poortinga¹,

Tenneson²,

Shapiro

et al. 2019

Remote Sensing

118

View full text Add to dashboard Cite

Forests in Southeast Asia are experiencing some of the highest rates of deforestation and degradation in the world, with natural forest species being replaced by cropland and plantation monoculture. In this work, we have developed an innovative method to accurately map rubber and palm oil plantations using fusion of Landsat-8, Sentinel 1 and 2. We applied cloud and shadow masking, bidirectional reflectance distribution function (BRDF), atmospheric and topographic corrections to the optical imagery and a speckle filter and harmonics for Synthetic Aperture Radar (SAR) data. In this workflow, we created yearly composites for all sensors and combined the data into a single composite. A series of covariates were calculated from optical bands and sampled using reference data of the land cover classes including surface water, forest, urban and built-up, cropland, rubber, palm oil and mangrove. This training dataset was used to create biophysical probability layers (primitives) for each class. These primitives were then used to create land cover and probability maps in a decision tree logic and Monte-Carlo simulations. Validation showed good overall accuracy (84%) for the years 2017 and 2018. Filtering for validation points with high error estimates improved the accuracy up to 91%. We demonstrated and concluded that error quantification is an essential step in land cover classification and land cover change detection. Our overall analysis supports and presents a path for improving present assessments for sustainable supply chain analyses and associated recommendations.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

Poortinga¹,

Tenneson²,

Shapiro

et al. 2019

Remote Sensing

118

View full text Add to dashboard Cite

show abstract

“…number of target objects, size of target objects) from both classified and validation maps, and to compare the similarity (Taubenbock et al 2011;Potere et al 2009). Dihkan et al (2013) proposed another pattern-based procedure to assess the accuracy of tea plantation mapping. A fuzzy local matching algorithm (Power, Simms, and White 2001) was introduced to measure the local similarity of patterns between the classified and validation maps.…”

Section: Combination Of Geometric and Thematic Accuraciesmentioning

confidence: 99%

“…One of these is that the samples should be evenly distributed in space in order to represent the entire study area. To ensure spatial balance, a common protocol for sampling, especially when the study area is large, is to first define spatially evenly distributed subareas, and then randomly select sample units from each of the subareas Dihkan et al 2013).…”

Section: Sampling Schemementioning

confidence: 99%

A survey of methods incorporating spatial information in image classification and spectral unmixing

Wang

Shi

Diao

et al. 2016

International Journal of Remote Sensing

View full text Add to dashboard Cite

Over the past decade, the incorporation of spatial information has drawn increasing attention in multispectral and hyperspectral data analysis. In particular, the property of spatial autocorrelation among pixels has shown great potential for improving understanding of remotely sensed imagery. In this paper, we provide a comprehensive review of the state-of-the-art techniques in incorporating spatial information in image classification and spectral unmixing. For image classification, spatial information is accounted for in the stages of pre-classification, sample selection, classifiers, post-classification, and accuracy assessment. With regards to spectral unmixing, spatial information is discussed in the context of endmember extraction, selection of endmember combinations, and abundance estimation. Finally, a perspective on future research directions for advancing spatial-spectral methods is offered.

show abstract

“…LULC maps were created by using surface reflectance values. The classification of satellite images completed by applying Support Vector Machine (SVM) algorithm, which is recently proved to be very effective in separating non-linear features from remotely sensed images (Pal and Mather, 2005;Kavzoğlu and Colkesen, 2009;Duro et al, 2012;Dihkan et al, 2013).…”

Section: Satellite Datamentioning

confidence: 99%

The need for ecosystem-based coastal planning in Trabzon city

Dikhan

Güneroğlu

et al. 2017

International Journal of Environment and Geoinformatics

View full text Add to dashboard Cite

Coastal urbanization problem was emanated from willingness of coastal living. Urban sprawl is one of the most important coastal problems in Turkey as it is in Trabzon city which is known for its natural and historical assets. In order to ensure the sustainability and ecological continuity of the city, an ecosystem based coastal planning is an issue of high priority. Protection and usage balance of the coastal areas could also ensure transition of the natural values to future generations. Trabzon city has been under severe urbanization problem for the last 30 years due to migration from rural to coastal areas of the city. It is thought that recently completed motorway and its service roads accelerated the urbanization on coastal periphery. Therefore, the problem must be resolved as soon as possible to achieve the good environmental status of the coast in the city. Thus, as a solution, DPSIR framework was proposed for systematic evaluation and documentation of the related critical issues by starting with a questionnaire composed of open ended questions for determination of major coastal problems in the city. As a step forward, the problems are quantitatively investigated and confirmed by using remote sensing techniques and census data compiled from TUIK databases. As a result major drivers were defined as "coastal urbanization", "coastal land filling" and "coastal transportation" for the city of Trabzon. It is recommended that single authority (composed of various specialists) must take the responsibility of coastal planning in the region. Moreover, the rights of the municipalities on the coastal zone must urgently be stopped by applying continues independent monitoring. Finally, taxation and land owning policies have to be revised on coastal areas to balance and encourage alternative city planning strategies.

show abstract

Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique

Cited by 53 publications

References 51 publications

Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

A survey of methods incorporating spatial information in image classification and spectral unmixing

The need for ecosystem-based coastal planning in Trabzon city

Contact Info

Product

Resources

About