Roussos Dimitrakopoulos

TL;DR: In this article, a distributed and dynamic programming framework is presented to the mining production rate target tracking of multiple metal mines under financial uncertainty, where a single mine's target tracking is stated as a stochastic optimization problem and the solution is obtained by solving the dynamic program which gives the optimal production rate schedule of each mine as a Markovian feedback control on the price process.

TL;DR: In this article, a stochastic dynamic programming algorithm is employed to define the best policy in terms of metal production targets to follow, depending on the evolution of the related commodity price.

TL;DR: A novel self-learning artificial intelligence algorithm for mining complexes that learns, from its own experience, to adapt the short-term production scheduling decisions by responding to incoming new information is presented.

TL;DR: A mining complex can include multiple mines, stockpiles, waste dumps, and processing facilities as mentioned in this paper, and traditional optimization approaches are often based on sequential optimization of the various compone...

TL;DR: In this paper, a new formulation termed successive cokriging of indicators is presented, which avoids the classic simultaneous solution and related computational problems, while obtaining equivalent results to the impractical simultaneous solution of cok rigging of indicators, as additional data are successively included into the estimation process.