Publikasi

@conference{Kamal2020,

title = {A preliminary study on machine learning and google earth engine for mangrove mapping},

author = {Muhammad Kamal and Nur Mohammad Farda and Ilham Jamaluddin and Artha Parela and Ketut Wikantika and Lilik B Prasetyo and Bambang Irawan},

url = {https://iopscience.iop.org/article/10.1088/1755-1315/500/1/012038/meta},

doi = {10.1088/1755-1315/500/1/012038},

year  = {2020},

date = {2020-07-03},

volume = {500},

publisher = {IOP Conf. Ser.: Earth Environ. Sci},

abstract = {The alarming rate of global mangrove forest degradation corroborates the need for providing fast, up-to-date and accurate mangrove maps. Conventional scene by scene image classification approach is inefficient and time consuming. The development of Google Earth Engine (GEE) provides a cloud platform to access and seamlessly process large amount of freely available satellite imagery. The GEE also provides a set of the state-of-the-art classifiers for pixel-based classification that can be used for mangrove mapping. This study is an initial effort which is aimed to combine machine learning and GEE for mapping mangrove extent. We used two Landsat 8 scenes over Agats and Timika Papua area as pilot images for this study; path 102 row 64 (2014/10/19) and path 103 row 63 (2013/05/16). The first image was used to develop local training areas for the machine learning classification, while the second one was used as a test image for GEE on the cloud. A total of 838 points samples were collected representing mangroves (244), non-mangroves (161), water bodies (311), and cloud (122) class. These training areas were used by support vector machine classifier in GEE to classify the first image. The classification result show mangrove objects could be efficiently delineated by this algorithm as confirmed by visual checking. This algorithm was then applied to the second image in GEE to check the consistency of the result. A simultaneous view of both classified images shows a corresponding pattern of mangrove forest, which mean the mangrove object has been consistently delineated by the algorithm.},

keywords = {GEE, machine learning, mangrove},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sudhana2020,

title = {Detecting mangrove deforestation using multi land use land cover change datasets: a comparative analysis in Southeast Asia},

author = {Sonny A Sudhana and Anjar D Sakti and Luri N Syahid and Lilik B Prasetyo and Bambang Irawan and Muhammad Kamal and Ketut Wikantika},

url = {https://iopscience.iop.org/article/10.1088/1755-1315/500/1/012014/meta},

doi = {10.1088/1755-1315/500/1/012014},

year  = {2020},

date = {2020-06-01},

volume = {500},

publisher = {IOP Conf. Ser.: Earth Environ. Sci},

abstract = {Mangrove forest grows on tropical coastal areas and has an ecological role for its surrounding environment. Mangrove forest protects the coast from large waves and becomes a habitat for various marine fauna. It stores the highest densities of carbon among any other ecosystem globally. In Southeast Asia, Mangrove forest is highly biodiverse and contributes to the sustainability of the ecosystem. However, based on previous studies, mangrove forests are experiencing deforestation due to high demands of commodities and land use. In this study, we analyzed changes of land cover in Southeast Asia using several global land cover products produced between 2001 and 2012 and their correlation with mangrove deforestation based on Mangrove Forest Watch (CGMFC-21) data. LULC data products applied in this study were ESA CCI LC, MODIS LC, GlobCover. The analysis was carried out by calculating the rate of increase in mangrove deforestation and comparing it with changes in land cover that replaced the mangrove area temporally. The results of this study were land cover classes that replaced mangrove forest areas in the study period. Based on the results it could be concluded that the methods and products used influence the results. There are many sources of data products that might be used for future research, with other methods that are better so that they provide space for future research and development. Our study can be used as a consideration to implement policies that conserve mangrove forest across Southeast Asia.},

keywords = {deforestation, land cover change, mangrove},

pubstate = {published},

tppubtype = {conference}

}

@conference{Prasetyo2019,

title = {Canopy cover of mangrove estimation based on airborne LIDAR & Landsat 8 OLI},

author = {Lilik B Prasetyo and Wim I Nursal and Yudi Setiawan and Yoga Rudianto and Ketut Wikantika and Bambang Irawan},

url = {https://iopscience.iop.org/article/10.1088/1755-1315/335/1/012029},

doi = {10.1088/1755-1315/335/1/012029},

year  = {2019},

date = {2019-10-28},

volume = {335},

publisher = {IOP Conf. Ser.: Earth Environ. Sci},

abstract = {Mangroves are very important ecosystems, because of their economic value and environmental services, including as a habitat for various wildlife species, storing carbon, and protecting land from sea abrasion. Indonesia is known to have large mangrove area and diversity. It is estimated that the area of mangroves in Indonesia in 2015 reached about 3 million hectares, with 15 families, 18 genera, 41 true mangrove species and 116 species of mangrove associations. Unfortunately, the area to continue to decline due to degradation and conversion to other land uses, especially ponds and built up areas. Usually, mangrove degradation assessment is carried out by field survey and relying on Normalized Difference Vegetation Index (NDVI) clustering derived from satellite image data. Field surveys require a large amount of time and cost, meanwhile NDVI clustering is either inaccurate or too rough. Therefore, exploration of another methods are needed. Our result showed that pixel value of Band 5, Band 6, NDVI and PC1 can be used to estimate canopy cover. Regression using quadratic equation is better than linear equations. However, we noticed limitations of optical Landsat 8 OLI data for canopy cover mapping, namely pixel saturation on high canopy cover and high pixel value of bush/shrubs/regrowth that was not always representing high canopy cover.},

keywords = {canopy cover, Landsat, LiDAR, mangrove},

pubstate = {published},

tppubtype = {conference}

}