scholarly journals Finding karstic caves and rockshelters in the Inner Asian mountain corridor using predictive modelling and field survey

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245170
Author(s):  
Patrick Cuthbertson ◽  
Tobias Ullmann ◽  
Christian Büdel ◽  
Aristeidis Varis ◽  
Abay Namen ◽  
...  
Keyword(s):  
Minimum Distance ◽  
Supervised Classification ◽  
Predictive Modelling ◽  
Target Area ◽  
Field Surveys ◽  
Landform Classification ◽  
Digital Elevation ◽  
Morphometric Features ◽  
Elevation Model ◽  
Organic Remains

The area of the Inner Asian Mountain Corridor (IAMC) follows the foothills and piedmont zones around the northern limits of Asia’s interior mountains, connecting two important areas for human evolution: the Fergana valley and the Siberian Altai. Prior research has suggested the IAMC may have provided an area of connected refugia from harsh climates during the Pleistocene. To date, this region contains very few secure, dateable Pleistocene sites, but its widely available carbonate units present an opportunity for discovering cave sites, which generally preserve longer sequences and organic remains. Here we present two models for predicting karstic cave and rockshelter features in the Kazakh portion of the IAMC. The 2018 model used a combination of lithological data and unsupervised landform classification, while the 2019 model used feature locations from the results of our 2017–2018 field surveys in a supervised classification using a minimum-distance classifier and morphometric features derived from the ASTER digital elevation model (DEM). We present the results of two seasons of survey using two iterations of the karstic cave models (2018 and 2019), and evaluate their performance during survey. In total, we identified 105 cave and rockshelter features from 2017–2019. We conclude that this model-led approach significantly reduces the target area for foot survey.

Landform classification from a digital elevation model and satellite imagery

Geomorphology ◽  
2008 ◽  
Vol 100 (3-4) ◽  
pp. 453-464 ◽  
Author(s):  
Hossein Saadat ◽  
Robert Bonnell ◽  
Forood Sharifi ◽  
Guy Mehuys ◽  
Mohammad Namdar ◽  
...  
Keyword(s):  
Digital Elevation Model ◽  
Satellite Imagery ◽  
Landform Classification ◽  
Digital Elevation ◽  
Elevation Model

Deep learning-based approach for landform classification from integrated data sources of digital elevation model and imagery

2020 ◽  
Author(s):  
Sijin Li ◽  
Liyang Xiong ◽  
Guoan Tang ◽  
Josef Strobl
Keyword(s):  
Deep Learning ◽  
Loess Plateau ◽  
Data Sources ◽  
The Loess Plateau ◽  
Transitional Area ◽  
Landform Classification ◽  
The Earth ◽  
Digital Elevation ◽  
Elevation Model ◽  
External Forces

<p>Landform classification is one of the most important aspects in geomorphological research, dividing the Earth’s surface into diverse geomorphological types. Thus, an accurate classification of landforms is a key procedure in describing the topographic characteristics of a given area and understanding their inner geomorphological formation processes. However, landform types are not always independent of one another due to the complexity and dynamics of interior and external forces. Furthermore, transitional landforms with gradually changing surface morphologies are widely distributed on the Earth’s surface. With this situation, classifying these complex and transitional landforms with traditional landform classification methods is hard. In this study, a deep learning (DL) algorithm was introduced, aiming at automatically classifying complex and transitional landforms. This algorithm was trained to learn and extract landform features from integrated data sources. These integrated data sources contain different combinations of imagery, digital elevation models (DEMs), and terrain derivatives. The Loess Plateau in China, which contains complex and transitional loess landforms, was selected as the study area for data training. In addition, two sample areas in the Loess Plateau with complex and transitional loess hill and ridge landforms were used to validate the classified landform types by using the proposed DL method. Meanwhile, a comparative analysis between the proposed DL and random forest (RF) methods was also conducted to investigate their capabilities in landform classification. The proposed DL approach can achieve the highest landform classification accuracy of 87% in the transitional area with data combination of DEMs and images. In addition, the proposed DL method can achieve a higher accuracy of landform classification with better defined landform boundaries compared to the RF method. The classified loess landforms indicate the different landform development stages in this area. Finally, the proposed DL method can be extended to other landform areas for classifying their complex and transitional landforms.</p>

scholarly journals A NEW METHOD TO DETECT REGIONS ENDANGERED BY HIGH WIND SPEEDS

2016 ◽  
Vol XLI-B8 ◽  
pp. 59-63
Author(s):  
P. Fischer ◽  
S. Ehrensperger ◽  
T. Krauß
Keyword(s):  
Shuttle Radar Topography Mission ◽  
Boosted Regression Trees ◽  
Slope Aspect ◽  
Maximum Wind ◽  
Wind Speeds ◽  
Landform Classification ◽  
Area Of Interest ◽  
Land Cover Data ◽  
Digital Elevation ◽  
Elevation Model

In this study we evaluate whether the methodology of Boosted Regression Trees (BRT) suits for accurately predicting maximum wind speeds. As predictors a broad set of parameters derived from a Digital Elevation Model (DEM) acquired within the Shuttle Radar Topography Mission (SRTM) is used. The derived parameters describe the surface by means of quantities (e.g. slope, aspect) and quality (landform classification). Furthermore land cover data from the CORINE dataset is added. The response variable is maximum wind speed, measurements are provided by a network of weather stations. The area of interest is Switzerland, a country which suits perfectly for this study because of its highly dynamic orography and various landforms.

scholarly journals A NEW METHOD TO DETECT REGIONS ENDANGERED BY HIGH WIND SPEEDS

2016 ◽  
Vol XLI-B8 ◽  
pp. 59-63
Author(s):  
P. Fischer ◽  
S. Ehrensperger ◽  
T. Krauß
Keyword(s):  
Shuttle Radar Topography Mission ◽  
Boosted Regression Trees ◽  
Slope Aspect ◽  
Maximum Wind ◽  
Wind Speeds ◽  
Landform Classification ◽  
Area Of Interest ◽  
Land Cover Data ◽  
Digital Elevation ◽  
Elevation Model

In this study we evaluate whether the methodology of Boosted Regression Trees (BRT) suits for accurately predicting maximum wind speeds. As predictors a broad set of parameters derived from a Digital Elevation Model (DEM) acquired within the Shuttle Radar Topography Mission (SRTM) is used. The derived parameters describe the surface by means of quantities (e.g. slope, aspect) and quality (landform classification). Furthermore land cover data from the CORINE dataset is added. The response variable is maximum wind speed, measurements are provided by a network of weather stations. The area of interest is Switzerland, a country which suits perfectly for this study because of its highly dynamic orography and various landforms.

scholarly journals Classification Method and Determination of Mountainous Area Types at Township Scales: A Case Study of Yuxi City, Yunnan Province

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Li Wu ◽  
Binggeng Xie ◽  
Xiao Xiao ◽  
Bing Xue ◽  
Jingzhong Li
Keyword(s):  
Yunnan Province ◽  
Classification Method ◽  
Mountainous Area ◽  
Target Area ◽  
Gis Technology ◽  
Ecological Civilization ◽  
Mountain Area ◽  
Digital Elevation ◽  
Elevation Model ◽  
Land Space

The high-resolution regional division of mountainous area types has important scientific significance for promoting precise management of land space and regional sustainable development. At present, the classification method of mountainous area types is mainly at the county level and above, while classifications for towns and villages are nearly nonexistent, which poses a technical challenge for rural revitalization and the construction of ecological civilization in mountainous areas. We used Yuxi city, Yunnan Province, as the target area of this research, which was based on GIS technology and Digital Elevation Model (DEM) data and socioeconomic environmental monitoring data. The most appropriate statistical unit (e.g., 2.8224 km2) for topographic relief was defined, and the study area was divided into six mountain types: flatlands, hills, low mountains, medium-low mountains, midmountains, and subhigh mountains. Based on the township scale, an index system and classification method dominated by the plain comprehensive index were established to carry out mountain area classifications at township scales. The 75 towns of Yuxi city can be classified into 27 plain towns, 23 mountain-plain towns, and 25 mountain towns from an empirical application perspective, which can provide strong data support and a reference basis for studying the evolution characteristics of land use in different geographical spaces and their interrelationships as well as differentiated land space planning and governance.

scholarly journals A geomorphology-based approach for digital elevation model fusion – case study in Danang city, Vietnam

2014 ◽  
Vol 2 (2) ◽  
pp. 403-417 ◽  
Author(s):  
T. A. Tran ◽  
V. Raghavan ◽  
S. Masumoto ◽  
P. Vinayaraj ◽  
G. Yonezawa
Keyword(s):  
Spatial Information ◽  
Thermal Emission ◽  
Accuracy Assessment ◽  
Weighted Averaging ◽  
Normal Vector ◽  
Landform Classification ◽  
Shuttle Radar Topographic Mission ◽  
Digital Elevation ◽  
Elevation Data ◽  
Elevation Model

Abstract. Global digital elevation models (DEM) are considered a source of vital spatial information and find wide use in several applications. The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) Global DEM (GDEM) and Shuttle Radar Topographic Mission (SRTM) DEM offer almost global coverage and provide elevation data for geospatial analysis. However, GDEM and SRTM still contain some height errors that affect the quality of elevation data significantly. This study aims to examine methods to improve the resolution as well as accuracy of available free DEMs by data fusion techniques and evaluating the results with a high-quality reference DEM. The DEM fusion method is based on the accuracy assessment of each global DEM and geomorphological characteristics of the study area. Land cover units were also considered to correct the elevation of GDEM and SRTM with respect to the bare-earth surface. The weighted averaging method was used to fuse the input DEMs based on a landform classification map. According to the landform types, the different weights were used for GDEM and SRTM. Finally, a denoising algorithm (Sun et al., 2007) was applied to filter the output-fused DEM. This fused DEM shows excellent correlation to the reference DEM, having a correlation coefficient R2 = 0.9986, and the accuracy was also improved from a root mean square error (RMSE) of 14.9 m in GDEM and 14.8 m in SRTM to 11.6 m in the fused DEM. The results of terrain-related parameters extracted from this fused DEM such as slope, curvature, terrain roughness index and normal vector of topographic surface are also very comparable to reference data.

scholarly journals Digitalna analiza padina otoka Raba

Geoadria ◽  
2017 ◽  
Vol 12 (1) ◽  
pp. 3
Author(s):  
Mladen Pahernik
Keyword(s):  
Spatial Distribution ◽  
Comparative Analysis ◽  
Network Analysis ◽  
Slope Angle ◽  
Morphometric Parameters ◽  
Digital Elevation ◽  
Morphometric Features ◽  
Gis Environment ◽  
Valley Network ◽  
Elevation Model

The paper analyzes morphometric features of the slopes of Rab Island. Based on the digital elevation model, raster layers were calculated for the values of slope angle, aspect and curvature, as well as valley network, which was grouped using the Strahler method. A comparative analysis of the calculated values of morphometric parameters was conducted in the GIS environment. Spatial distribution of the values of each of the morphometric parameters was correlated to the structural and morphogenetic features of Rab Island. Differences between the slopes features within each of the morphogenetic types of the terrain were ascertained by comparing their morphometric features, and by using the valley network analysis. 

scholarly journals Pemetaan Kesehatan Tanaman Jeruk Dengan Metode Supervised Classification Berdasarkan Hasil Citra Drone

2021 ◽  
Author(s):  
Buyung Al Fanshuri ◽  
◽  
Yunimar ◽  
Keyword(s):  
Digital Elevation Model ◽  
Supervised Classification ◽  
Dense Cloud ◽  
Digital Elevation ◽  
Elevation Model

Luas tanaman jeruk dilaporkan mengalami penurunan di beberapa daerah. Hal tersebut disebabkan oleh beberapa hal, diantaranya serangan penyakit dan kurangnya perawatan. Badan Pusat Statistik (BPS) hanya menyediakan data luasan produksi saja sehingga informasi tentang luasan tanaman yang sakit belum ada. Pemantauan kondisi tanaman dapat menggunakan penginderaan jauh. Penelitian ini bertujuan untuk mengembangkan metode penginderaan jauh dengan drone untuk mendeteksi kesehatan tanaman jeruk. Lokasi percobaan dilakukan di Banyuwangi dengan menggunakan drone phantom 4 dengan kamera RGB. Hasil foto dianalisa menggunakan software agisoft photoscan dalam beberapa tahap, yaitu: align photos, build dense cloud, build digital elevation model, build orthomosaic dan export geotiff. Ratusan foto akan menjadi satu kesatuan gambar dengan proses tersebut. Hasil proses gambar tersebut kemudian di analisa di software QGIS dengan metode Supervised Classification. Percobaan dilakukan pada tanaman muda dan dewasa. Dengan metode tersebut klasifikasi kesehatan tanaman jeruk dewasa dapat dibagi menjadi tiga, yaitu : sehat, sakit dan mati. Hasil ini kemungkinan bias lebih sedikit dibandingkan pada tanaman muda.

Sign in / Sign up

Export Citation Format

Share Document