From clustering to ensemble clustering in GNSS velocities: A Meta CLustering-based approach

Seda Özarpacı; Batuhan Kılıç; Mehmet Köküm; Uğur Doğan

Makale detayları

From clustering to ensemble clustering in GNSS velocities: A Meta CLustering-based approach

Yazarlar:

Seda Özarpacı | Batuhan Kılıç | Mehmet Köküm | Uğur Doğan

Yayıncı:

Gumushane University

Ana Başlıklar:

Mühendislik

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 3, pp.661-674

Belge Tipi:

Makale

Yayın Tarihi:

7/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001295856

pISSN:

2146-538X

Anahtar kelimeler:

Özet:

 Although there are different approaches and models to understand and interpret the structures in crustal deformations, one of them is the block modeling method. Using block modeling, one can determine plate movements, parameters such as slip rates, locking depths or Euler poles on faults. However, the accuracy of the block modeling results is related to how well the block boundaries are determined. One of the most important steps of block modeling is the detection of block boundaries and clustering can be used as a tool for this. Cluster analysis assigns data to similar groups based on similarities and differences in the data subject to clustering. In this study, Türkiye was determined as the study area. In this context, we utilized the ensemble clustering algorithm to cluster recent Global Navigation Satellite Systems GNSS velocity field in Türkiye and determine block boundaries. Current GNSS velocity field, which consists of 78 survey and 22 continuous type GNSS data processed together, used for clustering analysis for the first time in this study. Before clustering, we employed three different methods - Davies-Bouldin, Gap statistics, and Silhouette - to determine the optimal number cluster number that best fit to GNSS velocity field of clusters. Then, k-means, HAC, and spectral clustering techniques were then applied to cluster current GNSS velocities. Finally, we utilized the Meta-Clustering Algorithm MCLA as an ensemble clustering technique to cluster the horizontal components of the current velocity domain and present our findings.

 Although there are different approaches and models to understand and interpret the structures in crustal deformations, one of them is the block modeling method. Using block modeling, one can determine plate movements, parameters such as slip rates, locking depths or Euler poles on faults. However, the accuracy of the block modeling results is related to how well the block boundaries are determined. One of the most important steps of block modeling is the detection of block boundaries and clustering can be used as a tool for this. Cluster analysis assigns data to similar groups based on similarities and differences in the data subject to clustering. In this study, Türkiye was determined as the study area. In this context, we utilized the ensemble clustering algorithm to cluster recent Global Navigation Satellite Systems GNSS velocity field in Türkiye and determine block boundaries. Current GNSS velocity field, which consists of 78 survey and 22 continuous type GNSS data processed together, used for clustering analysis for the first time in this study. Before clustering, we employed three different methods - Davies-Bouldin, Gap statistics, and Silhouette - to determine the optimal number cluster number that best fit to GNSS velocity field of clusters. Then, k-means, HAC, and spectral clustering techniques were then applied to cluster current GNSS velocities. Finally, we utilized the Meta-Clustering Algorithm MCLA as an ensemble clustering technique to cluster the horizontal components of the current velocity domain and present our findings.

 Although there are different approaches and models to understand and interpret the structures in crustal deformations, one of them is the block modeling method. Using block modeling, one can determine plate movements, parameters such as slip rates, locking depths or Euler poles on faults. However, the accuracy of the block modeling results is related to how well the block boundaries are determined. One of the most important steps of block modeling is the detection of block boundaries and clustering can be used as a tool for this. Cluster analysis assigns data to similar groups based on similarities and differences in the data subject to clustering. In this study, Türkiye was determined as the study area. In this context, we utilized the ensemble clustering algorithm to cluster recent Global Navigation Satellite Systems GNSS velocity field in Türkiye and determine block boundaries. Current GNSS velocity field, which consists of 78 survey and 22 continuous type GNSS data processed together, used for clustering analysis for the first time in this study. Before clustering, we employed three different methods - Davies-Bouldin, Gap statistics, and Silhouette - to determine the optimal number cluster number that best fit to GNSS velocity field of clusters. Then, k-means, HAC, and spectral clustering techniques were then applied to cluster current GNSS velocities. Finally, we utilized the Meta-Clustering Algorithm MCLA as an ensemble clustering technique to cluster the horizontal components of the current velocity domain and present our findings.

 Kıtasal deformasyonları anlayabilmek ve yorumlayabilmek için farklı yaklaşımlar ve modeller bulunmakta olup, bunlardan biri de blok modelleme yöntemidir. Blok modelleme yardımıyla plaka hareketleri, kayma hızları, faylardaki kilitlenme derinlikleri, Euler kutbu gibi parametreler belirlenebilmektedir. Ancak, blok sınırları ne kadar iyi belirlenirse, modelleme sonuçları o kadar gerçeğe yaklaşmaktadır. Blok modellemenin en önemli adımlarından biri blok sınırlarının tespiti olup, kümeleme işlemi bunun için bir araç olarak kullanılabilmektedir. Kümeleme analizi, kümelemeye konu verideki benzerlik ve farklılıklara dayanarak veriyi benzer gruplara atamaktadır. Bu çalışmada, çalışma alanı olarak Türkiye belirlenmiştir. Bu kapsamda Türkiyenin en güncel Küresel Navigasyon Uydu Sistemi Global Navigation Satellite Systems  GNSS hız alanı topluluk kümeleme algoritması ile kümelenmiş ve bu hız alanına uygun blok sınırları belirlenmiştir. Türkiye için 22si sürekli ve 78i kampanya tipi verilerden oluşan GNSS gözlemlerinin birarada değerlendirilerek güncellenmiş hız alanı ilk defa bu çalışma ile kümelenmiştir. Kümeleme öncesinde üç ayrı yöntemle, Davies-Bouldin, Gap gap istatistiği ve Silhouette ile, veriye en iyi uyum sağlayan optimum küme sayısı GNSS hız alanına en uygun küme sayısı tespit edilmiştir. Daha sonra, k-ortalamalar, HAC ve spektral kümeleme teknikleri kullanılarak güncel GNSS hızları kümelenmiştir. Son olarak, Meta-Kümeleme Algoritması Meta-CLustering Algorithm - MCLA olan topluluk kümeleme tekniği ile güncel hız alanı yatay bileşenleri kümelenmiş ve sonuçlar paylaşılmıştır.

Makale detayları

From clustering to ensemble clustering in GNSS velocities: A Meta CLustering-based approach

Yazarlar:

Seda Özarpacı | Batuhan Kılıç | Mehmet Köküm | Uğur Doğan

Yayıncı:

Gumushane University

Ana Başlıklar:

Mühendislik

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 3, pp.661-674

Belge Tipi:

Makale

Yayın Tarihi:

7/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001295856

pISSN:

2146-538X

Determining block boundaries

GNSS

Current velocity field

Clustering

Meta-ClusteringBlok sınırlarının belirlenmesi

GNSS

Güncel hız alanı

Kümeleme

Meta-Kümeleme

Sayı

Makale detayları

Yazarlar: Seda Özarpacı | Batuhan Kılıç | Mehmet Köküm | Uğur Doğan

Yayıncı: Gumushane University

Ana Başlıklar: Mühendislik

Dergi: Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 3, pp.661-674

Belge Tipi: Makale

Yayın Tarihi: 7/2023

Belge Dili: Türkçe

Document ID (Org No.): 2001295856

pISSN: 2146-538X

Sayı

Yazarlar:

Seda Özarpacı | Batuhan Kılıç | Mehmet Köküm | Uğur Doğan

Yayıncı:

Gumushane University

Ana Başlıklar:

Mühendislik

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 3, pp.661-674

Belge Tipi:

Makale

Yayın Tarihi:

7/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001295856

pISSN:

2146-538X