“…This paper deals with offline nonlinear state estimation in a bounded-error context (see e.g., [1], [5], [11], [17], [8], [22]), but here, we shall consider fleeting data, i.e., fugitive data that can appear at some given dates. More formally, a state estimation problem with fleeting data can be represented by a classical state equation with some visibility conditions: ẋ (t) = f (x (t) , t) + b(t) h (x (t)) = 0 ⇒ g (x (t)) ∈ W (t)…”