Rock　fragment　movement　during　blasting　operations　is　a　major　cause　of　ore　and　profit　losses　in　hard　rock　open-pit　mines　having　a　complex-orebody.　To　address　this　issue,　a　novel　multilayer　dig-limit　approach,　which　well　considers　blast　movement　in　dig-limit　optimization,　was　proposed　in　this　study　by　combining　machine　learning　techniques　and　practical　heuristic　algorithms.　First,　horizontal　and　vertical　blast-induced　rock　movement　distances　were　predicted　using　a　supervised　learning　model.　Then,　the　movement　direction　of　rock　fragments　was　computed　based　on　the　initiation　sequence.　After　meshing　the　blast　block　into　rock　units,　the　blasted　muckpile　and　post-blast　ore　boundary　were　determined,　providing　a　good　basis　for　dig-limit　determination.　Finally,　the　optimized　dig-limit　with　maximum　profit　can　be　calculated　using　a　practical　heuristic　algorithm.　By　applying　this　method　in　a　case　study,　the　ore　recovery　and　economic　profit　were　improved,　compared　with　manually　drawn　dig-limit　method.　Additionally,　the　impact　of　equipment　size,　number　of　layers　and　powder　factor　on　the　application　of　this　method　was　discussed.　The　obtained　results　indicated　that　ore　and　profit　losses　can　be　reduced　with　a　decreased　equipment　size,　increased　number　of　layers　and　decreased　powder　factor.　©　The　Author(s),　under　exclusive　licence　to　Springer-Verlag　GmbH　Austria,　part　of　Springer　Nature　2024.