{"paper":{"title":"Adaptive mine planning under geological uncertainty: A POMDP framework for sequential decision-making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mine scheduling as a POMDP produces adaptive policies that shrink the expectation-reality gap from 22.3% to 4.6% and raise realized NPV by up to USD44.6M under prior error.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abdellatif Elghali, Hamza Khalifi, Jef Caers, Mostafa Benzaazoua, Yassine Taha","submitted_at":"2026-05-13T15:52:29Z","abstract_excerpt":"Strategic mine production scheduling under geological uncertainty is conventionally formulated as a stochastic optimization problem in which a fixed extraction sequence and routing decisions are computed ex ante. This plan-driven paradigm treats uncertainty as passive: decisions are hedged across geological scenarios, but planning does not anticipate how future observations will inform future decisions. We propose a different perspective by formulating mine scheduling as a Partially Observable Markov Decision Process (POMDP), in which extraction and routing decisions are made sequentially with"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under a statistically consistent prior, the SA-POMDP reduces the expectation-reality gap from 22.3% to 4.6%, improving realized NPV by USD8.4M relative to one-shot stochastic optimization. Under systematic prior misspecification of 10%, the adaptive framework outperforms static planning by up to USD44.6M (36.9%).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the hybrid SA-POMDP architecture (simulated annealing value approximation plus ES-MDA belief updates) yields a policy whose expected value under the true (unknown) geology is accurately estimated without material approximation bias or computational artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hybrid SA-POMDP framework for adaptive mine planning under geological uncertainty reduces the expectation-reality gap from 22.3% to 4.6% and improves realized NPV by up to USD44.6M compared with conventional one-shot stochastic optimization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mine scheduling as a POMDP produces adaptive policies that shrink the expectation-reality gap from 22.3% to 4.6% and raise realized NPV by up to USD44.6M under prior error.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7a814dfda496f73484761deb595b5ad68444781603f4afa4e20140f854ec572c"},"source":{"id":"2605.13702","kind":"arxiv","version":1},"verdict":{"id":"6bf43bb7-8d28-45f6-aebb-269e70f9c013","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:14:21.092076Z","strongest_claim":"Under a statistically consistent prior, the SA-POMDP reduces the expectation-reality gap from 22.3% to 4.6%, improving realized NPV by USD8.4M relative to one-shot stochastic optimization. Under systematic prior misspecification of 10%, the adaptive framework outperforms static planning by up to USD44.6M (36.9%).","one_line_summary":"A hybrid SA-POMDP framework for adaptive mine planning under geological uncertainty reduces the expectation-reality gap from 22.3% to 4.6% and improves realized NPV by up to USD44.6M compared with conventional one-shot stochastic optimization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the hybrid SA-POMDP architecture (simulated annealing value approximation plus ES-MDA belief updates) yields a policy whose expected value under the true (unknown) geology is accurately estimated without material approximation bias or computational artifacts.","pith_extraction_headline":"Mine scheduling as a POMDP produces adaptive policies that shrink the expectation-reality gap from 22.3% to 4.6% and raise realized NPV by up to USD44.6M under prior error."},"references":{"count":16,"sample":[{"doi":"10.1016/j.resourpol.2020.101634","year":2020,"title":"Simultaneous stochastic optimization of production sequence and dynamic cut -off grades in an open pit mining operation","work_id":"1411f6af-bc43-409f-b792-552987950d19","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.asoc.2015.11.038","year":2016,"title":"Global optimization of open pit mining complexes with uncertainty","work_id":"ea39c559-914e-468c-8edc-8c8108ca393c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1080/17480930.2022.2065730","year":2022,"title":"Simultaneous stochastic optimization of mining complexes - mineral value chains: an overview of concepts, examples and comparisons","work_id":"1f59126a-c934-4d96-8c21-11b1e00a0a25","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1007/s11081-012-","year":2013,"title":"Production scheduling with uncertain supply: A new solution to the open pit mining problem","work_id":"c4ab18b3-c7a2-4ee3-af90-c72cc62984dd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.resourpol.2021.102086","year":2021,"title":"Adaptive open -pit mining planning under geological uncertainty","work_id":"05fd255d-5cc1-4a9f-88d6-1d32d038f20f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"4a4d966ebba03649861f8953150fe99c3e0964048111d4fb69b3edefae5cbafe","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}