scholarly journals Channel network identification from high-resolution DTM: a statistical approach

2010 ◽  
Vol 7 (6) ◽  
pp. 9327-9365
Author(s):  
G. Sofia ◽  
P. Tarolli ◽  
F. Cazorzi ◽  
G. Dalla Fontana

Abstract. A statistical approach to LiDAR derived topographic attributes for the automatic extraction of channel network is presented in this paper. The basis of this approach is to use statistical descriptors to identify channel where terrain geometry denotes significant convergences. Two case study areas of different morphology and degree of organization are used with their 1 m LiDAR Digital Terrain Models (DTMs). Topographic attribute maps (curvature and openness) for different window sizes are derived from the DTMs in order to detect surface convergences. For the choice of the optimum kernel size, a statistical analysis on values distributions of these maps is carried out. For the network extraction, we propose a three-step method based (a) on the normalization and overlapping of openness and minimum curvature in order to highlight the more likely surface convergences, (b) a weighting of the upslope area according to such normalized maps in order to identify drainage flow paths and flow accumulation consistent with terrain geometry, (c) the z-score normalization of the weighted upslope area and the use of z-score values as non-subjective threshold for channel network identification. As a final step for optimal definition and representation of the whole network, a noise-filtering and connection procedure is applied. The advantage of the proposed methodology, and the efficiency and accurate localization of extracted features are demonstrated using LiDAR data of two different areas and comparing both extractions with field surveyed networks.

2011 ◽  
Vol 15 (5) ◽  
pp. 1387-1402 ◽  
Author(s):  
G. Sofia ◽  
P. Tarolli ◽  
F. Cazorzi ◽  
G. Dalla Fontana

Abstract. A statistical approach to LiDAR derived topographic attributes for the automatic extraction of channel network and for the choice of the scale to apply for parameter evaluation is presented in this paper. The basis of this approach is to use distribution analysis and statistical descriptors to identify channels where terrain geometry denotes significant convergences. Two case study areas with different morphology and degree of organization are used with their 1 m LiDAR Digital Terrain Models (DTMs). Topographic attribute maps (curvature and openness) for various window sizes are derived from the DTMs in order to detect surface convergences. A statistical analysis on value distributions considering each window size is carried out for the choice of the optimum kernel. We propose a three-step method to extract the network based (a) on the normalization and overlapping of openness and minimum curvature to highlight the more likely surface convergences, (b) a weighting of the upslope area according to these normalized maps to identify drainage flow paths and flow accumulation consistent with terrain geometry, (c) the standard score normalization of the weighted upslope area and the use of standard score values as non subjective threshold for channel network identification. As a final step for optimal definition and representation of the whole network, a noise-filtering and connection procedure is applied. The advantage of the proposed methodology, and the efficiency and accurate localization of extracted features are demonstrated using LiDAR data of two different areas and comparing both extractions with field surveyed networks.


Author(s):  
Atsushi Nagamachi ◽  
Takahiro Tsukahara

Abstract We tested Artificial Neural Networks (ANNs) to predict a fully-developed turbulent channel flow of a viscoelastic fluid in preparation for elucidating flow phenomenon and solving the difficulty in DNS (Direct Numerical Simulation) due to numerical instability of the viscoelastic fluid. Two kinds of ANNs (multi-layer perceptron (MLP) and U-Net) were trained using DNS data to predict conformation stress from given instantaneous field. The MLP showed accurate predictions and predictions got better with z-score normalization. ANN predicted accurately in near-wall region having coherent structures. In addition, we demonstrated that ANN get the nonlinear relationship between velocity gradient and viscoelastic stress partially.


Author(s):  
Mingyue Wu ◽  
Ran Wang ◽  
Yang Hu ◽  
Mengjiao Fan ◽  
Yufan Wang ◽  
...  

This study examined the reliability of a tennis stroke classification and assessment platform consisting of a single low-cost MEMS sensor in a wrist-worn wearable device, smartphone, and computer. The data that was collected was transmitted via Bluetooth and analyzed by machine learning algorithms. Twelve right-handed male elite tennis athletes participated in the study, and each athlete performed 150 strokes. The results from three machine learning algorithms regarding their recognition and classification of the real-time data stream were compared. Stroke recognition and classification went through pre-processing, segmentation, feature extraction, and classification with Support Vector Machine (SVM), including SVM without normalization, SVM with Min–Max, SVM with Z-score normalization, K-nearest neighbor (K-NN), and Naive Bayes (NB) machine learning algorithms. During the data training process, 10-fold cross-validation was used to avoid overfitting and suitable parameters were found within the SVM classifiers. The best classifier was achieved when C = 1 using the RBF kernel function. Different machine learning algorithms’ classification of unique stroke types yielded highly reliable clusters within each stroke type with the highest test accuracy of 99% achieved by SVM with Min–Max normalization and 98.4% achieved using SVM with a Z-score normalization classifier.


2016 ◽  
Author(s):  
Paul Bigelow ◽  
Lee Benda ◽  
Sarah Pearce

Abstract. Erosion and sedimentation pose ubiquitous problems for land and watershed managers, requiring delineation of sediment sources and sinks across landscapes. However, the technical complexity of many spatially explicit erosion models precludes their use by practitioners. To address this critical gap, we demonstrate a contemporary use of applied geomorphometry through a straightforward GIS analysis of sediment sources in the San Francisco Bay Area in California, USA, designed to support erosion reduction strategies. Using 2 m LiDAR DEMs, we delineated the entire river network in the Arroyo Mocho watershed (573 km2) at the scale of ~30 m segments and identified incised landforms using a combination of hillslope gradient and planform curvature. Chronic erosion to the channel network was estimated based on these topographic attributes and the density and size of vegetation, and calibrated to sediment gage data, providing a spatially explicit estimate of sediment yield from incised channels across the basin. Rates of erosion were summarized downstream through the channel network, revealing patterns of sediment supply at the reach scale. Erosion and sediment supply were also aggregated to subbasins, allowing comparative analyses at the scale of tributaries. The erosion patterns delineated using this approach provide land use planners with a robust framework to design erosion reduction strategies. More broadly, the study demonstrates a modern analysis of important geomorphic processes affected by land use that is easily applied by agencies to solve common problems in watersheds, improving the integration between science and environmental management.


2016 ◽  
Vol 4 (3) ◽  
pp. 531-547 ◽  
Author(s):  
Paul Bigelow ◽  
Lee Benda ◽  
Sarah Pearce

Abstract. Erosion and sedimentation pose ubiquitous problems for land and watershed managers, requiring delineation of sediment sources and sinks across landscapes. However, the technical complexity of many spatially explicit erosion models precludes their use by practitioners. To address this critical gap, we demonstrate a contemporary use of applied geomorphometry through a straightforward GIS analysis of sediment sources in the San Francisco Bay Area in California, USA, designed to support erosion reduction strategies. Using 2 m lidar digital elevation models, we delineated the entire river network in the Arroyo Mocho watershed (573 km2) at the scale of  ∼  30 m segments and identified incised landforms using a combination of hillslope gradient and planform curvature. Chronic erosion to the channel network was estimated based on these topographic attributes and the size of vegetation, and calibrated to sediment gage data, providing a spatially explicit estimate of sediment yield from incised channels across the basin. Rates of erosion were summarized downstream through the channel network, revealing patterns of sediment supply at the reach scale. Erosion and sediment supply were also aggregated to subbasins, allowing comparative analyses at the scale of tributaries. The erosion patterns delineated using this approach provide land use planners with a robust framework to design erosion reduction strategies. More broadly, the study demonstrates a modern analysis of important geomorphic processes affected by land use that is easily applied by agencies to solve common problems in watersheds, improving the integration between science and environmental management.


2019 ◽  
Vol 4 (1) ◽  
pp. 78
Author(s):  
Darnisa Azzahra Nasution ◽  
Hidayah Husnul Khotimah ◽  
Nurul Chamidah

Abstrak— Rentang nilai yang tidak seimbang pada setiap atribut dapat mempengaruhi kualitas hasil data mining. Untuk itu diperlukan adanya praproses data. Praproses ini diharapkan dapat meningkatkatkan keakuratan hasil dari pengklasifikasian dataset wine. Metode praproses yang digunakan adalah transformasi data dengan normalisasi. Ada tiga cara yang dilakukan dalam transformasi data dengan normalisasi, yaitu min-max normalization, z-score normalization, dan decimal scaling. Data yang telah diproses dari setiap metode normalisasi akan dibandingan untuk melihat hasil akurasi terbaik klasifikasi dengan menggunakan algoritama K-NN. K yang digunakan dalam perbandingan adalah 1, 3, 5, 7, 9, 11. Sebelum dilakukan pengklasifikasian dataset wine yang telah dinormalisasi dibagi menjadi data uji dan data latih dengan k-fold cross validation. Pembagian data menggunakan k sama dengan 10. Hasil pengujian klasifikasi dengan algoritma K-NN menunjukkan, bahwa akurasi terbaik terletak pada dataset wine yang telah dinormalisasi menggunakan metode min-max normalization dengan K = 1 sebesar 65,92%. Rata-rata yang diperoleh, yaitu 59,68%. Keywords— Normalisasi, K-fold cross validation, K-NN


2020 ◽  
Vol 13 (6) ◽  
pp. 3025
Author(s):  
Ronaldo Ferreira Maganhotto ◽  
Luis Claudio De PAula Souza ◽  
Jairo Calderari De Oliveira Junior ◽  
Marciel Lohmann

O consumo dos recursos naturais trouxe à tona questionamentos sobre o que pode ser feito para evitar prejuízos cada vez maiores à natureza. Sendo assim, as Unidades de Conservação (UCs) passam a exercer papel primordial no processo de proteção ambiental. Soma-se a isso o plano de manejo, instrumento que estabelece o zoneamento da UC e as normas que devem presidir o uso da área. Nesse contexto, este trabalho objetivou propor o zoneamento ambiental da REBIO das Araucárias a partir do processamento de atributos topográficos e das suas correlações com o uso do solo. Para tanto, foram gerados diversos atributos topográficos derivados do Modelo Digital do Terreno (MDT). Como resultados, verificou-se que a utilização dos atributos topográficos possibilitou o entendimento das informações pedológicas e de limitação de uso (susceptibilidade ambiental). Logo, para o zoneamento, realizou-se tabulação cruzada entre a Limitação de Uso e o Uso do Solo, sendo delineadas as Zonas de Manejo da unidade. Environmental zoning proposal for the Araucária Biological Reserve based on topographic attributes A B S T R A C TThe consumption of natural resources has raised questions about what can be done to avoid increasing damage to nature. Thus, Conservation Units (PAs) play a major role in the process of environmental protection. Add to this the management plan, an instrument that establishes the zoning of the CU and the norms that should govern the use of the area. In this context, this work aimed to propose the environmental zoning of REBIO das Araucárias from the processing of topographic attributes and their correlations with land use. For this, several topographic attributes derived from the Digital Terrain Model (DTM) were generated. As results, it was verified that the use of the topographic attributes made possible the understanding of the pedological information and of limitation of use (environmental susceptibility). Therefore, for the zoning, a cross-tabulation was performed between the Use Limitation and the Land Use, and the Management Areas of the unit were delineated.Keywords: Geotechnology; Topographic Attributes; Protected Áreas.


2020 ◽  
Vol 15 (02) ◽  
pp. 201-219
Author(s):  
José Guilherme de Oliveira ◽  
Alexei Nowatzki ◽  
Leonardo José Cordeiro Santos

A região noroeste do estado do Paraná ao longo dos últimos 50 anos vem sofrendo diversos impactos decorrentes de processos erosivos lineares, ravinas e voçorocas principalmente. A ocorrência desses processos está associada a dois fatores: o histórico de ocupação da região, bem como as características pedológicas locais, principalmente a textura dos solos e sua distribuição nas vertentes. O método adotado para o mapeamento de suscetibilidade é uma adaptação do proposto por Crepani et al. (2001). Esse autor define que a suscetibilidade de uma área é definida pela soma das vulnerabilidades dos componentes do meio físico. Para a realização do trabalho foram selecionados os atributos topográficos declividade e perfil de curvatura; na pedologia, as tipologias de solo. Os resultados foram discretizados em 5 classes: Muito baixa, baixa, média, alta e muito alta suscetibilidade. As áreas de suscetibilidade a erosão Alta e Muito alta, representam 24% do município, sendo que nessas porções se concentram 26% das erosões, o tipo de solo em conjunto com as características topográficas fazem essa área mais propicia naturalmente a ocorrência dos processos erosivos. A classe de moderada suscetibilidade a erosão representam cerca de 40% do município e 54% das feições erosivas se concentra nessa unidade. Palavras-chave: Erosão; Modelo Digital de Terreno; Álgebra de Mapas.   USE OF TOPOGRAPHIC ATTRIBUTES IN THE EROSIVE SUSCEPTIBILITY MAPPING IN THE RURAL AREA OF THE MUNICIPALITY OF PARANAVAÍ – PR Abstract The northwest region of the state of Paraná over the last 50 years has suffered several impacts and consequences of linear erosives, ravines and gullies mainly. The occurrence of these processes is mainly associated with two factors: the occupation history of the region, as well as local soil characteristics, mainly the soil texture and a distribution of soils along the slopes. The methodology adopted for the mapping of susceptibility to erosion follows a line of thought developed by Crepani et al. (2001). This proposal defines that the vulnerability of an area is defined by the sum of the vulnerabilities of the components of the physical environment. For the accomplishment of the methodology were selected, to represent the geomorphology, the topographic attributes: slope, curvature plane and profile; for pedology, soil typologies were selected.  The results were discretized in 5 classes, from environments less susceptible to the most susceptible.  The areas of susceptibility to erosion High and Very high, summed represent 24% of the municipality, being that in these portions it concentrates 26% of the area of the erosions, once in these areas the type of soil together with the topographic characteristics make it  more propitious to the occurrence of linear erosive processes.The moderate susceptibility to erosion class represent about 40% of the municipality and 54% of the area of ​​erosive features is concentrated in this unit. Keywords: Erosions; Digital Terrain Model; Map Algebra.   UTILIZACIÓN DE ATRIBUTOS TOPOGRÁFICOS EN EL MAPEO DE SUSCEPTIBILIDAD EROSIVA EN EL ÁREA RURAL DEL MUNICIPIO DE PARANAVAÍ – PR Resumen  La región noroeste del estado de Paraná en los últimos 50 años viene sufriendo impactos producto de procesos erosivos lineales, regueros y cárcavas principalmente. La ocurrencia de estos procesos está asociada a dos factores: el modo de ocupación de la región y las características pedológicas locales, principalmente la textura de los suelos y su distribución en las vertientes. El método adoptado para el mapeo de susceptibilidad es una adaptación del propuesto por Crepani et al. (2001). Este autor especifica que la susceptibilidad de un área está definida por la suma de las vulnerabilidades de los componentes del medio físico. Para realizar este trabajo fueron seleccionados los atributos topográficos declividad y perfil de curvatura; en la pedología, las tipologías de suelo. Los resultados fueron representados en 5 clases: muy baja, baja, media, alta y muy alta susceptibilidad. Las áreas de susceptibilidad a erosión alta y muy alta, representan el 24% del municipio, sumado a ello en esas porciones se concentran el 26% de las erosiones, por lo tanto el tipo de suelo en conjunto con las características topográficas hacen de esas áreas las más propicias naturalmente a la ocurrencia de procesos erosivos. La clase de moderada susceptibilidad a erosión representa cerca del 40% del municipio y el 54% de los rasgos erosivos se concentran en esa unidad. Palabras claves: Erosión; Modelo Digital del Terreno; Álgebra del Mapas.


2012 ◽  
Vol 1 (1) ◽  
pp. 81-85 ◽  
Author(s):  
Michał Sobala ◽  
Barbara Czajka

Abstract Digital Terrain Model (DTM) and maps based on it, are very valuable tool in investigations of distribution of cultural landscape elements. Connection DTM with a digital land cover maps, clearly illustrate factors determinate location of various landscape elements. The paper presents the applicability of Digital Terrain Model to detect the influence of topographic attributes on landscape elements distribution and to determinate the landscape’s structure in the different altitudinal zones. Presented results, are the effect of the first phase of cultural landscape elements distribution research and they are starting point to look for other factors which could effect on structure of the landscape.


Sign in / Sign up

Export Citation Format

Share Document