A two-stage stochastic programming model for collaborative asset protection routing problem enhanced with machine learning: a learning-based matheuristic algorithm

In this paper, a two-stage stochastic mathematical model is developed for an asset protection routing problem under wildfire. The main aim of study to reduce the negative impact Some parameters, such as travel and service times, obtaining profit by protecting asset, upper bounds time windows, are considered parameters. Generating proper scenarios uncertain parameters has large on accuracy obtained solutions. Therefore, artificial neural networks employed extract possible according previous actual wildfire events. cannot be solved exact solvers instances, so two matheuristic algorithms proposed in solve reasonable time. first algorithm, set feasible routes generated based heuristic approach, then route-based used obtain final solution. Also, another algorithm adaptive neighbourhood search (ALNS) proposed. decisions determined using ALNS while other achieved solving intermediate model. numerical analysis confirms efficiency both algorithms; however, performs more efficiently.