Classification of landslide activity based on spaceborne interferometric SAR at the Moselle Valley, Germany

2021 ◽  
Author(s):  
Andre C. Kalia
Keyword(s):  
Time Series ◽  
Clustering Algorithm ◽  
Statistical Tests ◽  
Spatial Density ◽  
Deformation Pattern ◽  
Visual Interpretation ◽  
Landslide Activity ◽  
Spatial Coverage ◽  
Interferometric Sar

<p>Landslide activity is an important information for landslide hazard assessment. However, an information gap regarding up to date landslide activity is often present. Advanced differential interferometric SAR processing techniques (A-DInSAR), e.g. Persistent Scatterer Interferometry (PSI) and Small Baseline Subset (SBAS) are able to measure surface displacements with high precision, large spatial coverage and high spatial sampling density. Although the huge amount of measurement points is clearly an improvement, the practical usage is mainly based on visual interpretation. This is time-consuming, subjective and error prone due to e.g. outliers. The motivation of this work is to increase the automatization with respect to the information extraction regarding landslide activity.</p><p>This study focuses on the spatial density of multiple PSI/SBAS results and a post-processing workflow to semi-automatically detect active landslides. The proposed detection of active landslides is based on the detection of Active Deformation Areas (ADA) and a subsequent classification of the time series. The detection of ADA consists of a filtering of the A-DInSAR data, a velocity threshold and a spatial clustering algorithm (Barra et al., 2017). The classification of the A-DInSAR time series uses a conditional sequence of statistical tests to classify the time series into a-priori defined deformation patterns (Berti et al., 2013). Field investigations and thematic data verify the plausibility of the results. Subsequently the classification results are combined to provide a layer consisting of ADA including information regarding the deformation pattern through time.</p>

scholarly journals Automated classification of Persistent Scatterers Interferometry time series

2013 ◽  
Vol 13 (8) ◽  
pp. 1945-1958 ◽  
Author(s):  
M. Berti ◽  
A. Corsini ◽  
S. Franceschini ◽  
J. P. Iannacone
Keyword(s):  
Time Series ◽  
Linear Time ◽  
Ground Deformation ◽  
Statistical Tests ◽  
Automated Classification ◽  
Linear Quadratic ◽  
Mean Velocity ◽  
Slope Movements ◽  
Persistent Scatterers

Abstract. We present a new method for the automatic classification of Persistent Scatters Interferometry (PSI) time series based on a conditional sequence of statistical tests. Time series are classified into distinctive predefined target trends, such as uncorrelated, linear, quadratic, bilinear and discontinuous, that describe different styles of ground deformation. Our automatic analysis overcomes limits related to the visual classification of PSI time series, which cannot be carried out systematically for large datasets. The method has been tested with reference to landslides using PSI datasets covering the northern Apennines of Italy. The clear distinction between the relative frequency of uncorrelated, linear and non-linear time series with respect to mean velocity distribution suggests that different target trends are related to different physical processes that are likely to control slope movements. The spatial distribution of classified time series is also consistent with respect the known distribution of flat areas, slopes and landslides in the tests area. Classified time series enhances the radar interpretation of slope movements at the site scale, pointing out significant advantages in comparison with the conventional analysis based solely on the mean velocity. The test application also warns against potentially misleading classification outputs in case of datasets affected by systematic errors. Although the method was developed and tested to investigate landslides, it should be also useful for the analysis of other ground deformation processes such as subsidence, swelling/shrinkage of soils, or uplifts due to deep injections in reservoirs.

scholarly journals Automated classification of Persistent Scatterers Interferometry time-series

2013 ◽  
Vol 1 (1) ◽  
pp. 207-246 ◽  
Author(s):  
M. Berti ◽  
A. Corsini ◽  
S. Franceschini ◽  
J. P. Iannacone
Keyword(s):  
Time Series ◽  
Linear Time ◽  
Ground Deformation ◽  
Statistical Tests ◽  
Automated Classification ◽  
Linear Quadratic ◽  
Mean Velocity ◽  
Slope Movements ◽  
Persistent Scatterers

Abstract. We present a new method for the automatic classification of Persistent Scatters Interferometry (PSI) time series based on a conditional sequence of statistical tests. Time series are classified into distinctive predefined target trends (such as uncorrelated, linear, quadratic, bilinear and discontinuous) that describe different styles of ground deformation. Our automatic analysis overcomes limits related to the visual classification of PSI time series, which cannot be carried out systematically for large datasets. The method has been tested with reference to landslides using PSI datasets covering the northern Apennines of Italy. The clear distinction between the relative frequency of uncorrelated, linear and non-linear time series with respect to mean velocity distribution suggests that different target trends are related to different physical processes that are likely to control slope movements. The spatial distribution of classified time series is also consistent with respect the known distribution of flat areas, slopes and landslides in the tests area. Classified time series enhances the radar interpretation of slope movements at the site scale, pointing out significant advantages in comparison with the conventional analysis based solely on the mean velocity. The test application also warns against potentially misleading classification outputs in case of datasets affected by systematic errors. Although the method was developed and tested to investigate landslides, it should be also useful for the analysis of other ground deformation processes such as subsidence, swelling/shrinkage of soils, uplifts due to deep injections in reservoirs.

K-MEANS CLUSTERING ALGORITHM BASED CLASSIFICATION OF SOIL FERTILITY IN NORTH WEST NIGERIA

2020 ◽  
Vol 4 (2) ◽  
pp. 780-787
Author(s):  
Ibrahim Hassan Hayatu ◽  
Abdullahi Mohammed ◽  
Barroon Ahmad Isma’eel ◽  
Sahabi Yusuf Ali
Keyword(s):  
Soil Fertility ◽  
Crop Yield ◽  
Clustering Algorithm ◽  
Soil Samples ◽  
North West ◽  
R Programming ◽  
Available Information ◽  
Northwest Region ◽  
The Relationship

Soil fertility determines a plant's development process that guarantees food sufficiency and the security of lives and properties through bumper harvests. The fertility of soil varies according to regions, thereby determining the type of crops to be planted. However, there is no repository or any source of information about the fertility of the soil in any region in Nigeria especially the Northwest of the country. The only available information is soil samples with their attributes which gives little or no information to the average farmer. This has affected crop yield in all the regions, more particularly the Northwest region, thus resulting in lower food production.  Therefore, this study is aimed at classifying soil data based on their fertility in the Northwest region of Nigeria using R programming. Data were obtained from the department of soil science from Ahmadu Bello University, Zaria. The data contain 400 soil samples containing 13 attributes. The relationship between soil attributes was observed based on the data. K-means clustering algorithm was employed in analyzing soil fertility clusters. Four clusters were identified with cluster 1 having the highest fertility, followed by 2 and the fertility decreases with an increasing number of clusters. The identification of the most fertile clusters will guide farmers on where best to concentrate on when planting their crops in order to improve productivity and crop yield.

scholarly journals Time–frequency time–space LSTM for robust classification of physiological signals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Time Series ◽  
Network Architecture ◽  
Time Series Data ◽  
Short Term Memory ◽  
Physiological Signals ◽  
Series Data ◽  
Time Frequency ◽  
Time Space ◽  
Deep Recurrent Neural Network

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

scholarly journals High-pass filtering artifacts in multivariate classification of neural time series data

2021 ◽  
Vol 352 ◽  
pp. 109080
Author(s):  
Joram van Driel ◽  
Christian N.L. Olivers ◽  
Johannes J. Fahrenfort
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Multivariate Classification ◽  
High Pass

scholarly journals MultiKOC: Multi-One-Class Classifier Based K-Means Clustering

Algorithms ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 134
Author(s):  
Loai Abdallah ◽  
Murad Badarna ◽  
Waleed Khalifa ◽  
Malik Yousef
Keyword(s):  
Clustering Algorithm ◽  
Main Idea ◽  
Molecular Classification ◽  
Positive Sample ◽  
Classification Problems ◽  
Multiple Cancer ◽  
Multiple Tumor ◽  
One Class Classifier ◽  
The Given

In the computational biology community there are many biological cases that are considered as multi-one-class classification problems. Examples include the classification of multiple tumor types, protein fold recognition and the molecular classification of multiple cancer types. In all of these cases the real world appropriately characterized negative cases or outliers are impractical to achieve and the positive cases might consist of different clusters, which in turn might lead to accuracy degradation. In this paper we present a novel algorithm named MultiKOC multi-one-class classifiers based K-means to deal with this problem. The main idea is to execute a clustering algorithm over the positive samples to capture the hidden subdata of the given positive data, and then building up a one-class classifier for every cluster member’s examples separately: in other word, train the OC classifier on each piece of subdata. For a given new sample, the generated classifiers are applied. If it is rejected by all of those classifiers, the given sample is considered as a negative sample, otherwise it is a positive sample. The results of MultiKOC are compared with the traditional one-class, multi-one-class, ensemble one-classes and two-class methods, yielding a significant improvement over the one-class and like the two-class performance.

Sign in / Sign up

Export Citation Format

Share Document