Clustering of GNSS Velocities Using Unsupervised Machine Learning in the Southeastern Tibetan Plateau: Block Identification and the Dominance of Sinistral-slip Faults

Previous studies have constrained the fault slip rates and block geometries of the SoutheasternTibetan Plateau (SETP) with contradictory results due to complex deformation patterns, limited datasets, and subjective choices of block boundaries. In this work, we address the issue of uncertain block geometries by employing an unsupervised machine learning (Euler pole clustering) algorithm that automatically resolves regions that behave as rigid blocks (clusters) using ~1000 GNSS velocity vectors. The optimal clustering results, determined by F-test and Euler-vector overlap analyses, indicate 4 elongated blocks exist in the SETP that are approximately parallel and delineated by a set of arcuate sinistral-slip faults. Our clustering results redefine the kinematicsof the SETP region with new block definitions which elucidate the dominance of sinistral-slipfaults.