2020/02/02 by Håkon Hoel, Hoel, Håkon, Gaukhar Shaimerdenova +3
Computer Science · #65C30 #65Y20 #FOS: Mathematics #Numerical Analysis (math.NA) #Target Tracking and Data Fusion in Sensor Networks
paper · pdf · doi:10.48550/arxiv.2002.00480
openalex publication_date 2020/02/02 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
We introduce a new multilevel ensemble Kalman filter method (MLEnKF) which\nconsists of a hierarchy of independent samples of ensemble Kalman filters\n(EnKF). This new MLEnKF method is fundamentally different from the preexisting\nmethod introduced by Hoel, Law and Tempone in 2016, and it is suitable for\nextensions towards multi-index Monte Carlo based filtering methods. Robust\ntheoretical analysis and supporting numerical examples show that under\nappropriate regularity assumptions, the MLEnKF method has better complexity\nthan plain vanilla EnKF in the large-ensemble and fine-resolution limits, for\nweak approximations of quantities of interest. The method is developed for\ndiscrete-time filtering problems with finite-dimensional state space and linear\nobservations polluted by additive Gaussian noise.\n