Ensemble
Kalman filter
§Replace xk, Pk from the full KF
with an ensemble
of xk,i, i=1,É,Nens
§Add
dynamic noise consistent with Qk to xk,i when propagating;
add measurement noise
consistent with Rk to measurements when updating, initial
ensemble has a spread
consistent with P0
§When
needed in KF equations, Pk replaced with
§Replace
matrix multiplications with sums of dot products
§Good for
non-Gaussian distributions
