A method can include providing a trained neural network; providing a set of production values where the set includes, for example, a cumulative production value for an interval, an average production value for the interval, a first production value for the interval and a last production value for the interval; and predicting at least one production value for a subsequent interval based at least in part on the trained neural network and the provided set of production values. Various other apparatuses, systems, methods, etc., are also disclosed.