Land cover classification using Landsat 8 OLI in West Langsa Sub district, Langsa City

Land cover information is needed by various parties as a consideration in controlling land cover changes. The latest land cover information can be obtained using remote sensing techniques in the form of image classification maps. This technique is very effective in monitoring land cover because of its ability to quickly, precisely, and easily provide spatial information on the earth’s surface. The purpose of this study was to classify land cover in West Langsa Sub district, Langsa City using Landsat 8 OLI (Operational Land Imager) imagery. The classification method used in this study is the maximum likelihood classification (MLC) method. There are several considerations of various factors in the MLC method, including the probability of a pixel to be classified into a certain type or class. The results of Landsat 8 OLI image classification in West Langsa Sub district resulted in 6 land cover classes, namely mangrove forests, settlements, rice fields, shrubs, ponds and bodies of water. The largest land cover class is ponds with an area of 1981.54 ha (38.71%) and the smallest land cover is rice fields with an area of 115.58 ha (2.26%) of the total land cover class. Classification accuracy is indicated by the overall accuracy and kappa accuracy of 91.15% and 82.75%, respectively. These results meet the requirements set by the USGS (Overall Accuracy > 85%) and indicate that the Landsat 8 OLI image classification map can be used for various purposes.

Valuasi Dampak Banjir Di Kabupaten Landak, Kalimantan Barat

Banjir merupakan becana yang kerap sekali terjadi pada musim hujan, banjir dapat menyebabkan kehilangan harta benda maupun korban jiwa. Valuasi ekonomi akibat terjadinya banjir adalah salah satu cara yang dapat digunakan untuk menghitung kerugian akibat terjadinya bencana banjir. Tidak adanya kajian mengenai kerentanan dan kerugian ekonomi akibat banjir pada tiga desa di Kecamatan Ngabang yaitu Desa Raja, Hilir Tengah dan Hilir Kantor adalah alasan dilakukannya penelitian ini. Tujuan dilakakukan penelitian ini adalah untuk mengidentifikasi dan menginventarisasi besarnya tingkat kerentanan terhadap banjir yang terjadi dan menghitung valuasi kerugian ekonomi akibat terjadinya bencana banjir. Metode yang digunakan dalam menganalisis kerentanan banjir menggunakan software ArcMap 10.3 adalah Analisa atribut meliputi pemberian skor kelas curah hujan, pemberian skor kelas tutupan lahan, pemberian skor kelas kemiringan lahan, pembobotan dan Analisa AHP. Metode yang digunakan untuk menghitung estimasi kerugian akibat banjir menggunakan metode ECLAC. Hasil yang didapat dalam penelitian ini adalah perubahan tutupan lahan mengalami penurunan dan peningkatan luasan permukiman, pertanian/sawah, dan lahan terbuka/semak, Curah hujan yang tinggi dan kelerengan daerah yang landai menjadi parameter penyebab terjadinya banjir. Pada estimasi nilai kerugian akibat banjir dengan nilai kerugian menggunakan USD dan Emas pada tahun yang ditentukan dengan hasil total kerugian pada tahun 1973 adalah 73,7 Juta dollar, tahun 1989 180 juta dollar, tahun 1994 261 juta dollar, tahun 2000 261juta dollar, tahun 2010 1,1 miliar dollar, dan tahun 2020 1,9 miliar dollar.ABSTRACTFlood is a plan that often occurs in the rainy season, floods can cause loss of property and fatalities. Economic valuation due to flooding is one way that can be used to calculate losses due to flood disasters. The absence of studies on vulnerability and economic losses due to flooding in three villages in Ngabang Subdistrict namely Desa Raja, Hilir Tengah and Hilir Kantor is the reason for this research. The purpose of this study is to identify and inventory the level of vulnerability to floods that occur and calculate the valuation of economic losses due to flood disasters. The methods used in analyzing flood vulnerabilities using ArcMap 10.3 software are attribute analysis including rainfall class scoring, giving land cover class scores, awarding land slope class scores, weighting and AHP Analysis. The method used to calculate the estimated loss due to flooding uses the ECLAC method. The results obtained in this study are changes in land cover experiencing a decrease and increase in the area of settlements, agriculture / rice fields, and open land / bush, high rainfall and marbles of sloping areas become parameters of the cause of flooding. In the estimated value of losses due to floods with the value of losses using USD and Gold in the specified year with the total loss in 1973 was 73.7 million dollars, in 1989 180 million dollars, in 1994 261 million dollars, in 2000 261 million dollars, in 2010 1.1 billion dollars, and in 2020 1.9 billion dollars.

A habitat class to land cover translation model for mapping Area of Habitat of terrestrial vertebrates

Area of Habitat (AOH) is defined as the habitat available to a species, that is, habitat within its range and is produced by subtracting areas of unsuitable land cover and elevation from the range. Habitat associations are documented using the IUCN Habitats Classification Scheme, and unvalidated expert opinion has been used so far to match habitat to land-cover classes generating a source of uncertainty in AOH maps. We develop a data-driven method to translate IUCN habitat classes to land-cover based on point locality data for 6,986 species of terrestrial mammals, birds, amphibians and reptiles. We extracted the land-cover class at each point locality and matched it to the IUCN habitat class(es) assigned to each species occurring there. Then we modelled each land cover class as a function of IUCN habitat using logistic regression models. The resulting odds ratios were used to assess the strength of the association of each habitat land-cover class. We then compared the performance of our data-driven model with those from a published expert knowledge translation table. The results show that some habitats (e.g. forest and desert) could be more confidently assigned to land-cover classes than others (e.g. wetlands and artificial). We calculated the association between habitat classes and land-cover classes as a continuous variable, but to map AOH, which is in the form of a binary presence/absence , it is necessary to apply a threshold of association. This can be chosen by the user according to the required balance between omission and commission errors. We demonstrate that a data-driven translation model and expert knowledge perform equally well, but the model provides greater standardization, objectivity and repeatability. Furthermore, this approach allows greater flexibility in the use of the results and allows uncertainty to be quantified. Our model can be developed regionally or for different taxonomic groups.

Impact of sea level rise on the land cover structure in Southeast Asia

Sea-level rise in Southeast Asia is a consequence of climate change that will affect almost all coastal countries in the region. The results of this phenomenon may have severe consequences, from problems with food production, through mass migration of people, to the threat to unique ecological areas. Hence, the main aim of this research was to investigate the impact of sea level rise on the land cover structure in the region and how it may affect the situation of the countries in the region. For this purpose, GlobCover 2009 data and projections of sea level rise by one meter were used and a multiband raster image was created containing information about the land cover class, country and whether the area is threatened by sea level rise. All calculations have been made on the raster prepared in this way, which shows that 4.4% of South East Asia's areas are at risk of rising sea levels. Finally, the ratio was calculated for each land cover class. This showed the unusual vulnerability of some of the classes to rising sea levels like irrigated croplands and urban areas.

Comparison of Simple Averaging and Latent Class Modeling to Estimate the Area of Land Cover in the Presence of Reference Data Variability

Estimates of the area or percent area of the land cover classes within a study region are often based on the reference land cover class labels assigned by analysts interpreting satellite imagery and other ancillary spatial data. Different analysts interpreting the same spatial unit will not always agree on the land cover class label that should be assigned. Two approaches for accommodating interpreter variability when estimating the area are simple averaging (SA) and latent class modeling (LCM). This study compares agreement between area estimates obtained from SA and LCM using reference data obtained by seven trained, professional interpreters who independently interpreted an annual time series of land cover reference class labels for 300 sampled Landsat pixels. We also compare the variability of the LCM and SA area estimates over different numbers of interpreters and different subsets of interpreters within each interpreter group size, and examine area estimates of three land cover classes (forest, developed, and wetland) and three change types (forest gain, forest loss, and developed gain). Differences between the area estimates obtained from SA and LCM are most pronounced for the estimates of wetland and the three change types. The percent area estimates of these rare classes were usually greater for LCM compared to SA, with the differences between LCM and SA increasing as the number of interpreters providing the reference data increased. The LCM area estimates generally had larger standard deviations and greater ranges over different subsets of interpreters, indicating greater sensitivity to the selection of the individual interpreters who carried out the reference class labeling.

THE USE OF ONLINE WEB-BASED SOFTWARE I-TREE CANOPY AS AN ALTERNATIVE IN SUPPORTING COMMUNITY BASED ZERO DELTA Q PLANNING

Zero Delta Q is a policy to ensure that any additional surface runoff due to development does not further burden the drainage or river system. In case of Zero Delta Q application planning at the community level, a software is needed that can help classify and quantify the existing land cover class in area where the community is located. The purpose of this study is to look at the time needed and reliability of the i-Tree Canopy web-based software online in classifying and quantifying land cover classes on one of the sub-catchments in the Pesanggrahan River Basin. The land cover class is divided into six: trees, grasses / undergrowth plants, open area, water bodies, pavement / road and roof of the building. For comparison, an RBI map is used from the same area to see the extent of each class of land cover. Observation of each point requires an average time of 5.2 ± 1.0 seconds. The difference between direct sub-basin measurements using i-Tree Canopy and detailed analysis results from the RBI map is within the range of 0.41% or 0.36 Ha for each individual class of land cover. For a relatively small study area (under 100 ha) and when supported with reliable internet access, this web-based online software is sufficiently reliable in assisting the application planning process to support Zero Delta Q policy.

A Generalized Zero-Shot Learning Framework for PolSAR Land Cover Classification

Most supervised classification methods for polarimetric synthetic aperture radar (PolSAR) data rely on abundant labeled samples, and cannot tackle the problem that categorizes or infers unseen land cover classes without training samples. Aiming to categorize instances from both seen and unseen classes simultaneously, a generalized zero-shot learning (GZSL)-based PolSAR land cover classification framework is proposed. The semantic attributes are first collected to describe characteristics of typical land cover types in PolSAR images, and semantic relevance between attributes is established to relate unseen and seen classes. Via latent embedding, the projection between mid-level polarimetric features and semantic attributes for each land cover class can be obtained during the training stage. The GZSL model for PolSAR data is constructed by mid-level polarimetric features, the projection relationship, and the semantic relevance. Finally, the labels of the test instances can be predicted, even for some unseen classes. Experiments on three real RadarSAT-2 PolSAR datasets show that the proposed framework can classify both seen and unseen land cover classes with limited kinds of training classes, which reduces the requirement for labeled samples. The classification accuracy of the unseen land cover class reaches about 73% if semantic relevance exists during the training stage.