Stochastic-constraints method in nonstationary hot-clutter cancellation - Part II: Unsupervised training applications

This paper considers the use of "stochastically constrained" spatial and sp atio-temporal adaptive processing in multimode nonstationary interference ( "hot clutter") mitigation for scenarios that do not allow access to a group of range cells that are free from the backscattered sea/terrain signal ("c old clutter"). Since supervised training methods for interference covarianc e matrix estimation using the cold-clutter-free ranges are inappropriate in this case, we introduce and analyze adaptive routines which can operate on range cells containing a mixture of hot and cold clutter and possible targ ets (unsupervised training samples). Theoretical and simulation results are complemented by surface-wave over-the-horizon data processing, recently co llected during experimental trials in northern Australia.