scholarly journals AN OBJECT-BASED APPROACH FOR MONITORING THE EVOLUTION OF LANDSLIDE-DAMMED LAKES AND DETECTING TRIGGERING LANDSLIDES IN TAIWAN

2019 ◽  
Vol XLII-3/W8 ◽  
pp. 103-108 ◽  
Author(s):  
Z. Dabiri ◽  
D. Hölbling ◽  
L. Abad ◽  
G. Prasicek ◽  
A.-L. Argentin ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Landsat Imagery ◽  
Contextual Information ◽  
Regional Scale ◽  
Landslide Dam ◽  
Remote Sensing Data ◽  
Time Range ◽  
Channel System ◽  
Object Based ◽  
Elevation Model

<p><strong>Abstract.</strong> In August 2009, Typhoon Morakot caused a record-breaking rainfall in Taiwan. The heavy rainfall triggered thousands of landslides, in particular in the central-southern part of the island. Large landslides can block rivers and can lead to the formation of landslide-dammed lakes. Cascading hazards like floods and debris flows after landslide dam breaches pose a high risk for people and infrastructure downstream. Thus, better knowledge about landslides that significantly impact the channel system and about the resulting landslide-dammed lakes are key elements for assessing the direct and indirect hazards caused by the moving mass. The main objectives of this study are 1) to develop an object-based image analysis (OBIA) approach for semi-automated detection of landslides that caused the formation of landslide-dammed lakes and 2) to monitor the evolution of landslide-dammed lakes based on Landsat imagery. For landslide and lake mapping, primarily spectral indices and contextual information were used. By integrating morphological and hydrological parameters derived from a digital elevation model (DEM) into the OBIA framework, we automatically identified landslide-dammed lakes, and the landslides that likely caused the formation of those lakes, due to the input of large amounts of debris into the channel system. The proposed approach can be adapted to other remote sensing platforms and can be used to monitor the evolution of landslide-dammed lakes and triggering landslides at regional scale after typhoon and heavy rainstorm events within an efficient time range after suitable remote sensing data has been provided.</p>

scholarly journals Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3848
Author(s):  
Wei Cui ◽  
Meng Yao ◽  
Yuanjie Hao ◽  
Ziwei Wang ◽  
Xin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Prior Knowledge ◽  
Contextual Information ◽  
Information Aggregation ◽  
Semantic Segmentation ◽  
Spatial Correlations ◽  
Convolutional Network ◽  
Object Based ◽  
Graph Neural Networks ◽  
Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

scholarly journals Forest areas remote monitoring within the limits of transport objects impact

2021 ◽  
pp. 109-118
Author(s):  
Dmytro Liashenko ◽  
◽  
Dmytro Pavliuk ◽  
Vadym Belenok ◽  
Vitalii Babii ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Spatial Data ◽  
Remote Monitoring ◽  
Forest Cover ◽  
Landsat Imagery ◽  
Remote Sensing Data ◽  
Transport Infrastructure ◽  
Nature Management ◽  
Collecting Methods ◽  
Remote Sensing Methods

The article studies the issues of using remote sensing data for the tasks of ensuring sustainable nature management in the territories within the influence of transport infrastructure objects. Peculiarities of remote monitoring for tasks of transport networks design and in the process of their operation are determined. The paper analyzes the development of modern remote sensing methods (satellite imagery, the use of mobile sensors installed on cars or aircraft). A brief overview of spatial data collecting methods for the tasks of managing the development of territories within the influence of transport infrastructure (roads, railways, etc.) has made. The article considers the experience of using remote sensing technologies to monitor changes in the parameters of forest cover in the Transcarpathian region (Ukraine) in areas near to highways, by use Landsat imagery.

Landscape Biodiversity Characterization in Ecoregion 29 Using MODIS

2013 ◽  
pp. 815-831
Author(s):  
Nitin Kumar Tripathi ◽  
Aung Phey Khant
Keyword(s):  
Climate Change ◽  
Remote Sensing ◽  
Global Warming ◽  
Forest Type ◽  
Regional Scale ◽  
Remote Sensing Data ◽  
Modis Data ◽  
Moderate Resolution ◽  
Landscape Biodiversity

Biodiversity conservation is a challenging task due to ever growing impact of global warming and climate change. The chapter discusses various aspects of biodiversity parameters that can be estimated using remote sensing data. Moderate resolution satellite (MODIS) data was used to demonstrate the biodiversity characterization of Ecoregion 29. Forest type map linked to density of the study area was also developed by MODIS data. The outcome states that remote sensing and geographic information systems can be used in combination to derive various parameters related to biodiversity surveillance at a regional scale.

scholarly journals A Probabilistic Assessment of Soil Erosion Susceptibility in a Head Catchment of the Jemma Basin, Ethiopian Highlands

Geosciences ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. 248 ◽  
Author(s):  
Mariaelena Cama ◽  
Calogero Schillaci ◽  
Jan Kropáček ◽  
Volker Hochschild ◽  
Alberto Bosino ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Soil Erosion ◽  
Remote Sensing Data ◽  
Gully Erosion ◽  
Entropy Model ◽  
Global Issues ◽  
Susceptibility Maps ◽  
Digital Elevation ◽  
Elevation Model ◽  
Color Composite

Soil erosion represents one of the most important global issues with serious effects on agriculture and water quality, especially in developing countries, such as Ethiopia, where rapid population growth and climatic changes affect widely mountainous areas. The Meskay catchment is a head catchment of the Jemma Basin draining into the Blue Nile (Central Ethiopia) and is characterized by high relief energy. Thus, it is exposed to high degradation dynamics, especially in the lower parts of the catchment. In this study, we aim at the geomorphological assessment of soil erosion susceptibilities. First, a geomorphological map was generated based on remote sensing observations. In particular, we mapped three categories of landforms related to (i) sheet erosion, (ii) gully erosion, and (iii) badlands using a high-resolution digital elevation model (DEM). The map was validated by a detailed field survey. Subsequently, we used the three categories as dependent variables in a probabilistic modelling approach to derive the spatial distribution of the specific process susceptibilities. In this study we applied the maximum entropy model (MaxEnt). The independent variables were derived from a set of spatial attributes describing the lithology, terrain, and land cover based on remote sensing data and DEMs. As a result, we produced three separate susceptibility maps for sheet and gully erosion as well as badlands. The resulting susceptibility maps showed good to excellent prediction performance. Moreover, to explore the mutual overlap of the three susceptibility maps, we generated a combined map as a color composite where each color represents one component of water erosion. The latter map yields useful information for land-use managers and planning purposes.

scholarly journals A Soil Moisture Spatial and Temporal Resolution Improving Algorithm Based on Multi-Source Remote Sensing Data and GRNN Model

2020 ◽  
Vol 12 (3) ◽  
pp. 455 ◽  
Author(s):  
Yaokui Cui ◽  
Xi Chen ◽  
Wentao Xiong ◽  
Lian He ◽  
Feng Lv ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Soil Moisture ◽  
Temporal Resolution ◽  
Land Surface ◽  
Regional Scale ◽  
Remote Sensing Data ◽  
The Tibetan Plateau ◽  
Sensing Data ◽  
Spatio Temporal ◽  
Input Variables

Surface soil moisture (SM) plays an essential role in the water and energy balance between the land surface and the atmosphere. Low spatio-temporal resolution, about 25–40 km and 2–3 days, of the commonly used global microwave SM products limits their application at regional scales. In this study, we developed an algorithm to improve the SM spatio-temporal resolution using multi-source remote sensing data and a machine-learning model named the General Regression Neural Network (GRNN). First, six high spatial resolution input variables, including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), albedo, Digital Elevation Model (DEM), Longitude (Lon) and Latitude (Lat), were selected and gap-filled to obtain high spatio-temporal resolution inputs. Then, the GRNN was trained at a low spatio-temporal resolution to obtain the relationship between SM and input variables. Finally, the trained GRNN was driven by the high spatio-temporal resolution input variables to obtain high spatio-temporal resolution SM. We used the Fengyun-3B (FY-3B) SM over the Tibetan Plateau (TP) to test the algorithm. The results show that the algorithm could successfully improve the spatio-temporal resolution of FY-3B SM from 0.25° and 2–3 days to 0.05° and 1-day over the TP. The improved SM is consistent with the original product in terms of both spatial distribution and temporal variation. The high spatio-temporal resolution SM allows a better understanding of the diurnal and seasonal variations of SM at the regional scale, consequently enhancing ecological and hydrological applications, especially under climate change.

scholarly journals Estimation of Snow-Melt Run-Off During Pre-Monsoon Months in Beas Sub-Basin using Satellite Imagery (Abstract)

1987 ◽  
Vol 9 ◽  
pp. 251-251
Author(s):  
K.P. Sharma ◽  
P.K. Garg
Keyword(s):  
Remote Sensing ◽  
Linear Trend ◽  
Landsat Imagery ◽  
Remote Sensing Data ◽  
Snow Accumulation ◽  
Snow Melt ◽  
Monsoon Period ◽  
Similar Work ◽  
Run Off ◽  
Exponential Trend

The increasing demand for water, coupled with the construction of multi-purpose reservoirs to control and regulate snow-melt run-off, requires accurate strearm-flow forecast. For making an accurate prediction of spring run-off, information on the amount of snow accumulation in winter is necessary; this may be achieved through remote-sensing techniques in any inaccessible region.This paper outlines the snow-melt run-off study carried out in a part of Beas basin, India, using Landsat imagery for the years 1973, 1975, 1976, and 1977. The Beas basin lies between long. 76°56' to 77°52'E. and lat. 31°30' to 32°25'N., covering an area about 4900 km2, of which 1400 km2 is permanently covered by snow. The gradual melting of snow accumulated over the catchment area during the winter months is responsible for the perennial character of the Beas River.Photohydrological investigation of the part of the Beas basin up-stream of Barji was carried out and a study was made for the estimation of the snow-melt run-off during the pre-monsoon period in the sub-basin up-stream of Manali. For this purpose, the sub-basin has been divided into permanent and temporary snow-covered zones. The degree-day method and the melt due to rainfall on snow have been used to estimate snow-melt run-off. The routing of snow-melt, after accounting for losses as well as the run-off from the excess rainfall from the permanent and temporary snow-covered areas, has also been done taking the recession coefficient K as 0.90, and the excess rain from the non-snow-covered areas has been assumed to contribute directly to the run-off for that day. Run-off coefficients of 0.595 for rainfall on the snow-covered areas and 0.278 for rainfall on the non-snow-covered areas have been determined.Reference can be made to similar work in India and Pakistan to establish the relationship between the snow cover and the cumulative discharges for the months of March, April, and May of the years 1973, 1975, 1976, and 1977, and an exponential trend was observed with the help of Landsat Imagery. Furthermore, the snow-covered areas as determined from bands 5 and 7 of the Landsat imagery, for the same day, showed a linear trend.The analysis of the results shows that remote-sensing data used in conjunction with conventional methods are likely to improve the accuracy of the snow-melt forecasts in remote areas like the Himalayan catchments.

Sign in / Sign up

Export Citation Format

Share Document