scholarly journals INTEGRATING GEO-SPATIAL DATA FOR REGIONAL LANDSLIDE SUSCEPTIBILITY MODELING IN CONSIDERATION OF RUN-OUT SIGNATURE

2016 ◽  
Vol XLI-B8 ◽  
pp. 89-93
Author(s):  
J.-S. Lai ◽  
F. Tsai ◽  
S.-H. Chiang
Keyword(s):  
Random Forests ◽  
Spatial Data ◽  
Landslide Susceptibility ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Digital Terrain Model ◽  
Landslide Inventory ◽  
Terrain Model ◽  
Susceptibility Modeling ◽  
Causative Factors

This study implements a data mining-based algorithm, the random forests classifier, with geo-spatial data to construct a regional and rainfall-induced landslide susceptibility model. The developed model also takes account of landslide regions (source, non-occurrence and run-out signatures) from the original landslide inventory in order to increase the reliability of the susceptibility modelling. A total of ten causative factors were collected and used in this study, including aspect, curvature, elevation, slope, faults, geology, NDVI (Normalized Difference Vegetation Index), rivers, roads and soil data. Consequently, this study transforms the landslide inventory and vector-based causative factors into the pixel-based format in order to overlay with other raster data for constructing the random forests based model. This study also uses original and edited topographic data in the analysis to understand their impacts to the susceptibility modeling. Experimental results demonstrate that after identifying the run-out signatures, the overall accuracy and Kappa coefficient have been reached to be become more than 85 % and 0.8, respectively. In addition, correcting unreasonable topographic feature of the digital terrain model also produces more reliable modelling results.

scholarly journals INTEGRATING GEO-SPATIAL DATA FOR REGIONAL LANDSLIDE SUSCEPTIBILITY MODELING IN CONSIDERATION OF RUN-OUT SIGNATURE

2016 ◽  
Vol XLI-B8 ◽  
pp. 89-93
Author(s):  
J.-S. Lai ◽  
F. Tsai ◽  
S.-H. Chiang
Keyword(s):  
Random Forests ◽  
Spatial Data ◽  
Landslide Susceptibility ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Digital Terrain Model ◽  
Landslide Inventory ◽  
Terrain Model ◽  
Susceptibility Modeling ◽  
Causative Factors

This study implements a data mining-based algorithm, the random forests classifier, with geo-spatial data to construct a regional and rainfall-induced landslide susceptibility model. The developed model also takes account of landslide regions (source, non-occurrence and run-out signatures) from the original landslide inventory in order to increase the reliability of the susceptibility modelling. A total of ten causative factors were collected and used in this study, including aspect, curvature, elevation, slope, faults, geology, NDVI (Normalized Difference Vegetation Index), rivers, roads and soil data. Consequently, this study transforms the landslide inventory and vector-based causative factors into the pixel-based format in order to overlay with other raster data for constructing the random forests based model. This study also uses original and edited topographic data in the analysis to understand their impacts to the susceptibility modeling. Experimental results demonstrate that after identifying the run-out signatures, the overall accuracy and Kappa coefficient have been reached to be become more than 85 % and 0.8, respectively. In addition, correcting unreasonable topographic feature of the digital terrain model also produces more reliable modelling results.

scholarly journals Geoinformation technologies in the process of terrain slope detection in the area of Fruska Gora with reference to potential development of slope processes

2012 ◽  
Vol 92 (4) ◽  
pp. 51-62
Author(s):  
Ivana Badnjarevic ◽  
Miro Govedarica ◽  
Dusan Jovanovic ◽  
Vladimir Pajic ◽  
Aleksandar Ristic
Keyword(s):  
High Risk ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Satellite Image ◽  
Digital Terrain Model ◽  
Terrain Model ◽  
Digital Terrain ◽  
Geoinformation Technologies ◽  
Terrain Slope ◽  
Sensing Technology

This research aims to describe the analysis of geoinformation technologies and systems and its usage in detection of terrain slope with reference to timely detection and mapping sites with a high risk of slope movement and activation of landslides. Special attention is referred to the remote sensing technology and data acquisition. In addition to acquisition, data processing is performed: the production of digital terrain model, calculating of the vegetation index NDVI (Normalized Difference Vegetation Index) based on satellite image and analyses of pedology maps. The procedures of processing the satellite images in order to identify locations of high risk of slope processes are described. Several factors and identifiers are analyzed and used as input values in automatic processing which is performed through a unique algorithm. Research results are presented in raster format. The direction of further research is briefly defined.

scholarly journals Drone technology for identification of healing forest spot at Kampung Cisamaya Mount Ciremai National Park

2021 ◽  
Vol 918 (1) ◽  
pp. 012040
Author(s):  
H Ramdan
Keyword(s):  
Forest Ecosystem ◽  
Psychological Health ◽  
Spatial Data ◽  
National Park ◽  
Vegetation Index ◽  
Digital Terrain Model ◽  
Physical Parameters ◽  
Vegetation Density ◽  
Terrain Model ◽  
Research Activities

Abstract Reconnecting people to nature through healing activities in the forest ecosystem is important. Various studies have shown that forest ecosystems dominated by tree vegetation have positive impacts on physical and psychological health. Not all locations in the forest ecosystem are suitable for healing forests (HF), but their suitability should be identified. Land slope, vegetation density, and easiness access to the site are some physical parameters of the land which are indicators for the development of HF site. Identification of suitable HF spots can be identified using drone technology and GIS. The research objective was the use of drones equipment in identifying potential sites for HF activities. The research site was Kampung Cisamaya in Mount Ciremai National Park. The type of drone used was the Phantom 4 Pro Obsidian equipped with a 20-megapixel RGB camera. The stages of research activities were data acquisition, processing, and analyzing from drone spatial data. Vegetation density was determined through GRVI (Green-Red Vegetation Index), while drone data analyzed the slope classification by DTM (Digital Terrain Model). The accessibility to the location was analyzed through data from the spatial map of the Kuningan Regency. The results found that the use of drones was effective in evaluating the suitability spots for HF activities. From this study can be concluded that the Cisamaya area was suitable for the development of HF activities due to physical parameters of flat to gentle slopes (0-15%), having dense vegetation, as well as the easiness access by people.

scholarly journals Landslide Susceptibility Evaluation Using Hybrid Integration of Evidential Belief Function and Machine Learning Techniques

Water ◽  
2019 ◽  
Vol 12 (1) ◽  
pp. 113 ◽  
Author(s):  
Yang Li ◽  
Wei Chen
Keyword(s):  
Landslide Susceptibility ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Characteristic Curve ◽  
Slope Angle ◽  
Classification And Regression Tree ◽  
Machine Learning Techniques ◽  
Susceptibility Map ◽  
Prediction Ability ◽  
Susceptibility Modeling

In this study, Random SubSpace-based classification and regression tree (RSCART) was introduced for landslide susceptibility modeling, and CART model and logistic regression (LR) model were used as benchmark models. 263 landslide locations in the study area were randomly divided into two parts (70/30) for training and validation of models. 14 landslide influencing factors were selected, such as slope angle, elevation, aspect, sediment transport index (STI), topographical wetness index (TWI), stream power index (SPI), profile curvature, plan curvature, distance to rivers, distance to road, soil, normalized difference vegetation index (NDVI), land use, and lithology. Finally, the hybrid RSCART model and two benchmark models were applied for landslide susceptibility modeling and the receiver operating characteristic curve method is used to evaluate the performance of the model. The susceptibility is quantitatively compared based on each pixel to reveal the system spatial pattern between susceptibility maps. At the same time, area under ROC curve (AUC) and landslide density analysis were used to estimate the prediction ability of landslide susceptibility map. The results showed that the RSCART model is the optimal model with the highest AUC values of 0.852 and 0.827, followed by LR and CART models. The results also illustrate that the hybrid model generally improves the prediction ability of a single landslide susceptibility model.

scholarly journals Landslide susceptibility analysis by means of event-based multi-temporal landslide inventories

2015 ◽  
Vol 3 (2) ◽  
pp. 1137-1173 ◽  
Author(s):  
C. M. Tseng ◽  
C. W. Lin ◽  
W. D. Hsieh
Keyword(s):  
Landslide Susceptibility ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Landslide Inventory ◽  
Weight Of Evidence ◽  
Slope Aspect ◽  
Susceptibility Map ◽  
Study Region ◽  
Landslide Occurrence ◽  
Susceptibility Analysis

Abstract. This study uses landslide inventory of a single typhoon event and Weight of Evidence (WOE) analysis to establish landslide susceptibility map of the Laonung River in southern Taiwan. Eight factors including lithology, elevation, slope, slope aspect, landform, Normalized Difference Vegetation Index (NDVI), distance to geological structure, and distance to stream are used to evaluate the susceptibility of landslide. Effect analysis and the assessment of grouped factors showed that lithology, slope, elevation, and NDVI are the dominant factors of landslides in the study area. Landslide susceptibility analysis with these four factors achieves over 90% of the AUC (area under curve) of the success rate curve of all eight factors. Four landslide susceptibility models for four typhoons from 2007 to 2009 are established, and each model is cross validated. Results indicate that the best model should be constructed by using landslide inventory close to the landslide occurrence threshold and should reflect the most common spatial rainfall pattern in the study region for ideal simulation and validation results. The prediction accuracy of the best model in this study reached 90.2%. The two highest susceptibility categories (very high and high levels) cover around 80% of the total landslides in the study area.

scholarly journals Mapping the Groundwater Level and Soil Moisture of a Montane Peat Bog Using UAV Monitoring and Machine Learning

2021 ◽  
Vol 13 (5) ◽  
pp. 907
Author(s):  
Theodora Lendzioch ◽  
Jakub Langhammer ◽  
Lukáš Vlček ◽  
Robert Minařík
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Spatial Data ◽  
Groundwater Level ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Sampling Strategy ◽  
Peat Bog ◽  
Strong Impact ◽  
Ground Truth Data

One of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs) and RGB, multispectral, and thermal orthoimages reflecting topomorphometry, vegetation, and surface temperature information generated from drone mapping. We used 34 predictors to feed the random forest (RF) algorithm. The predictor selection, hyperparameter tuning, and performance assessment were performed with the target-oriented leave-location-out (LLO) spatial cross-validation (CV) strategy combined with forward feature selection (FFS) to avoid overfitting and to predict on unknown locations. The spatial CV performance statistics showed low (R2 = 0.12) to high (R2 = 0.78) model predictions. The predictor importance was used for model interpretation, where temperature had strong impact on GWL and SM, and we found significant contributions of other predictors, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model yielded high-quality results and where predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data with no knowledge about these environments. The AOA method is well suited and unique for planning and decision-making about the best sampling strategy, most notably with limited data.

Landslide inventory mapping and landslide susceptibility modeling assessment on the SW flank of Pico de Orizaba volcano, Puebla-Veracruz, Mexico

2013 ◽  
Vol 57 (3) ◽  
pp. 371-385 ◽  
Author(s):  
Gabriel Legorreta Paulín ◽  
Marcus Bursik ◽  
María Teresa Ramírez-Herrera ◽  
Trevor Contreras ◽  
Michael Polenz ◽  
...  
Keyword(s):  
Landslide Susceptibility ◽  
Landslide Inventory ◽  
Susceptibility Modeling ◽  
Pico De Orizaba Volcano

scholarly journals Changes in a hydrographic network of the Słowiński National Park in terms of photogrammetric analyses

2017 ◽  
Vol 21 (4) ◽  
pp. 197-204
Author(s):  
Maciej Góraj ◽  
Marcin Kucharski ◽  
Krzysztof Karsznia ◽  
Izabela Karsznia ◽  
Jarosław Chormański
Keyword(s):  
Spatial Data ◽  
National Park ◽  
Laser Scanning ◽  
Digital Terrain Model ◽  
Aerial Photographs ◽  
Terrain Model ◽  
Digital Terrain ◽  
Protected Natural Area ◽  
Water Courses ◽  
Hydrographic Network

AbstractThe main objective of this study is to evaluate the changes in the hydrographic network of Słowiński National Park. The authors analysed the changes occurring in the drainage network due to limited maintenance in this legally protected natural area. To accomplish this task, elaborations prepared on the basis of aerial photographs were used: an orthophoto map from 1996, hyperspectral imaging from June 2015, and a digital terrain model based on airborne laser scanning (ALS) from June 2015. These spatial data resources enabled the digitisation of the water courses for which selected hydro-morphological features had been defined. As a result of analysing the differences of these features, a quality map was elaborated which was then subjected to interpretation, and the identified changes were quantified in detail.

scholarly journals CONCEPTUAL MODEL OF AGROECOLOGICAL PROPERTIES OF LAND. SEQUENCES

2021 ◽  
pp. 80-87
Author(s):  
В.К. Каличкин ◽  
Р.А. Корякин ◽  
К.Ю. Максимович ◽  
Р.Р. Галимов ◽  
Н.А. Чернецкая
Keyword(s):  
Spatial Data ◽  
Digital Terrain Model ◽  
Knowledge Bases ◽  
Sequence Diagrams ◽  
Land Area ◽  
Modeling Tools ◽  
Intelligence System ◽  
Terrain Model ◽  
Logical Language ◽  
In The Beginning

Рассмотрен процесс создания последовательностей при описании предметных областей на формально-логическом языке UML. Использование последовательностей основано на понятии «источник данных», введённом авторами на основе предыдущего этапа концептуализации предметной области «агроэкологические свойства земель» – диаграммы классов. В классе начала связи выбирается один из комплектов атрибутов, в классе конца связи – один из методов (запрос), соответствующий этому комплекту. Многократно применяя этот подход при различных значениях атрибутов центрального класса, получается массив данных (в том числе пространственных). Атрибуты являются связующим звеном между создаваемой моделью, методами, потоками данных и запросов системы, так как, с одной стороны, они входят в состав классов, участвующих в сценариях диаграмм последовательностей, а с другой – принадлежат к внешней оболочке модели. На примерах движения информации, необходимой для расчетов гидротермического коэффициента Селянинова и степени проявления эрозии для рабочего участка, построены диаграммы последовательностей «ГидротермическийКоэффициент» и «СтепеньПроявленияЭрозии». Данные для диаграмм последовательностей формируются с помощью геоинформационных систем (географические координаты рабочего участка, цифровая модель рельефа) и справочно-информационного портала «Погода и климат». Предлагаемый подход даёт возможность автоматического построения баз знаний на основе двух концептуальных понятий: «источники данных» и «последовательности». Структурирование и формализация знаний позволяет осуществить переход от набора информации к знаниям и последующему их графическому отображению. Визуализация помогает наглядно отобразить связи между классами, которые могут быть не очевидны. Становится доступной возможность последующей оценки жизнеспособности модели, ее проектирования в симбиозе с использованием инструментов для имитационного моделирования, а также математических методов анализа и обработки информации. Данные диаграммы используются для построения и верификации созданных подсистем в процессе прямого и обратного проектирования аграрной интеллектуальной системы. The process of creating sequences while describing subdicipline in the formal-logical language UML is considered. The sequences usage is based on the concept of a "data source". It was deduced by the authors on the basis of the previous step of subdicipline conceptualization «agroecological lands properties» - class diagrams. In the beginning link's class, one of the attribute set is selected, in the ending class - one of the adequate to this set methods (query). The result of repeated application this approach, with different values of the attributes of the central class, is a database (including spatial data). Attributes mediate the created model, methods, data streams and system requests, as, on the one hand, they are among the classes involved in sequence diagrams scripting, and on the other - belong to the outer shell of the model. Sequences diagrams were constructed by the examples of the information flow necessary for calculating the Selyaninov hydrothermal index and the degree of erosion for the working land area. These diagrams are "HydrothermalIndexQuery" and "ErosionDegreeQuery". Data for sequence diagrams is generated by Geological Information System (geographic coordinates of the working land area, digital terrain model) and the reference-information gateway “Weather and Climate". The proposed approach makes it possible to build knowledge bases with the scope of two concepts: "data sources" and "sequence" automatically. Knowledge structuralizasion and formalization allows produce a shift from collecting information to knowledge and its subsequent graphical image. Visualization helps to demonstrably provide insight into classes' connections that may occur not to be obvious. The possibility of subsequent estimate of model consistency, its creation process using simulation modeling tools, as well as mathematical analysis methods and processing of data becomes more accessible. Diagrams' data is used for sybsystem construction and verification. These parts of a whole system were created in the process of forward and reverse engineering agricultural intelligence system.

scholarly journals Statistical and expert-based landslide susceptibility modeling on a national scale applied to North Macedonia

2019 ◽  
Vol 11 (1) ◽  
pp. 750-764
Author(s):  
Ivica Milevski ◽  
Slavoljub Dragićević ◽  
Matija Zorn
Keyword(s):  
Information System ◽  
Geographic Information System ◽  
Analytical Hierarchy Process ◽  
Landslide Susceptibility ◽  
Cross Validation ◽  
Landslide Inventory ◽  
National Scale ◽  
Landslide Occurrence ◽  
Susceptibility Modeling ◽  
Hierarchy Process

Abstract This article presents a Geographic Information System (GIS) assessment of Landslide Susceptibility Zonation (LSZ) in North Macedonia. Because of the weak landslide inventory, statistical method (frequency ratio) is combined with Analytical Hierarchy Process (AHP). In this study, lithology, slope, plan curvature, precipitations, land cover, distance from streams, and distance from roads were selected as precondition factors for landslide occurrence. There are two advantages of the approach used. The first is the possibility of comparing of the results and cross-validation between the statistical and expert based methods with an indication of the advantages and drawbacks of each of them. The second is the possibility of better weighting of precondition factors for landslide occurrence, which can be useful in cases of weak landslide inventory. The final result shows that in the case of weak landslide inventory, LSZmap created with the combination of both models provide better overall results than each model separately.

Sign in / Sign up

Export Citation Format

Share Document