Mapping China’s mangroves based on an object-oriented classification of Landsat imagery

Jia, Mingming; Wang, Zongming; Li, Lin; Song, Kaishan; Chunying, Ren; Liu, Bo; Mao, Dehua

doi:10.1007/s13157-013-0449-2

Cited by 76 publications

(44 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Consequently, small sample sizes of reference samples are typical [16,35,56,57]. In this study, only 718 samples were collected over the MPMNR, among which 80% were used for training the classifiers and 20% for validation and accuracy assessment (see Table 2).…”

Section: Factors Affecting Accuracy Assessmentmentioning

confidence: 99%

Potential of Combining Optical and Dual Polarimetric SAR Data for Improving Mangrove Species Discrimination Using Rotation Forest

et al. 2018

Self Cite

View full text Add to dashboard Cite

Classification of mangrove species using satellite images is important for investigating the spatial distribution of mangroves at community and species levels on local, regional and global scales. Hence, studies of mangrove deforestation and reforestation are imperative to support the conservation of mangrove forests. However, accurate discrimination of mangrove species remains challenging due to many factors such as data resolution, species number and spectral confusion between species. In this study, three different combinations of datasets were designed from Worldview-3 and Radarsat-2 data to classify four mangrove species, Kandelia obovate (KO), Avicennia marina (AM), Acanthus ilicifolius (AI) and Aegiceras corniculatum (AC). Then, the Rotation Forest (RoF) method was employed to classify the four mangrove species. Results indicated the benefits of dual polarimetric SAR data with an improvement of accuracy by 2-3%, which can be useful for more accurate large-scale mapping of mangrove species. Moreover, the difficulty of classifying different mangrove species, in order of increasing difficulty, was identified as KO < AM < AI < AC. Dual polarimetric SAR data are recognized to improve the classification of AI and AC species. Although this improvement is not remarkable, it is consistent for all three methods. The improvement can be particularly important for large-scale mapping of mangrove forest at the species level. These findings also provide useful guidance for future studies using multi-source satellite data for mangrove monitoring and conservation.

show abstract

Section: Factors Affecting Accuracy Assessmentmentioning

confidence: 99%

Potential of Combining Optical and Dual Polarimetric SAR Data for Improving Mangrove Species Discrimination Using Rotation Forest

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…An object-based approach, i.e., eCognition Developer 8.64 [37][38][39], was chosen due to its known advantages over pixel-based methods with respect to high spatial resolution land-cover classification [40][41][42][43], as for example the "salt-and-pepper" effect was avoided and object features were fully utilized. Land-use/cover information for the year 2010 was extracted via the following steps: After a "trial-and-error" method, the meaningful and homogeneous objects was segmented using multiresolution segmentation method, with the parameters of scale, shape, and compactness of 15, 0.1, and 0.5, respectively [44,45]. Then, the objects was exported from eCognition and 2000 random samples was selected by means of "the Creat Random Points" tool in Arcgis 10.0 and the land use attributes of selected samples was assigned by visual interpretation.…”

Section: Classification System and Interpretationmentioning

confidence: 99%

Assessing the Role of Policies on Land-Use/Cover Change from 1965 to 2015 in the Mu Us Sandy Land, Northern China

Wang

2017

Sustainability

View full text Add to dashboard Cite

Policy has long been considered one of the major driving forces for land-use/cover change. However, research on the interactions between land-use/cover change (LUCC) and relevant policies remains limited. The agropastoral ecotone is a typical area of policy implementation and LUCC. Therefore, this study integrates the use of multisource and multiresolution remote sensing and topographic and field-based datasets for the case of the Mu Us Sandy Land (MUSL) in northern China. The research aim was to quantify LUCC from 1965 to 2015 and describe the relationship between policy changes and land-use types during three stages: the stage of the Great Cultural Revolution, the stage of the modernization of the economy, and the stage of the Great Ecological Project. The results indicated that land use was affected by different national policies because of the national approach to land use during different periods. In the stage of the Great Cultural Revolution, the amount of cultivated land increased, and the environment deteriorated under the influence of leftists. In the stage of the modernization of the economy, vegetation coverage improved after the initial damage, and cultivated and artificial surfaces also increased. In the stage of the Great Ecological Project, cultivated land and unused land decreased, and woodland and sparse vegetation increased with the implementation of the Grain for Green Project (GGP). However, cultivated land increased but wood land and sparse vegetation decreased significantly by the end of the GGP. The coverage of artificial surfaces increased and grasslands decreased due to the encroachment of artificial surfaces into grasslands.

show abstract

“…Mangroves store more organic material, including organic pollutants, than other coastal systems (Zhang et al, 2004), but are highly threated by land-use-change (Lovelock et al, 2011;Valiela et al, 2001) due to the large scale conversion to aquaculture areas Jia et al, 2014;Murdiyarso et al, 2015;Pendleton et al, 2012). Global mangrove deforestation rates are frequently cited to be 1e2% p.a.…”

Section: Pop Mass Inventory In Mangrovesmentioning

confidence: 99%

Profiles and inventories of organic pollutants in sediments from the central Beibu Gulf and its coastal mangroves

2016

View full text Add to dashboard Cite

Mapping China’s mangroves based on an object-oriented classification of Landsat imagery

Cited by 76 publications

References 24 publications

Potential of Combining Optical and Dual Polarimetric SAR Data for Improving Mangrove Species Discrimination Using Rotation Forest

Potential of Combining Optical and Dual Polarimetric SAR Data for Improving Mangrove Species Discrimination Using Rotation Forest

Assessing the Role of Policies on Land-Use/Cover Change from 1965 to 2015 in the Mu Us Sandy Land, Northern China

Profiles and inventories of organic pollutants in sediments from the central Beibu Gulf and its coastal mangroves

Contact Info

Product

Resources

About