pith. sign in

arxiv: 2604.13385 · v1 · submitted 2026-04-15 · 💻 cs.NE · cs.AI

On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem

Ishara Hewa Pathiranage , Aneta Neumann This is my paper

Pith reviewed 2026-05-10 12:35 UTC · model grok-4.3

classification 💻 cs.NE cs.AI
keywords evolutionary optimizationdynamic environmentschance constraintsopen pit miningmulti-objective optimizationchange responsestochastic valuesscheduling
0
0 comments X

The pith

A diversity-based change response mechanism enables evolutionary algorithms to outperform baselines in solving the dynamic chance-constrained open-pit mine scheduling problem.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper aims to show that evolutionary optimization can effectively address open-pit mine scheduling when block economic values are uncertain and mining capacities change over time. It proposes treating the problem as bi-objective, maximizing expected profit while minimizing variance, and introduces a specific response to dynamics by repairing infeasible plans and adding diverse feasible ones. If effective, this would mean better adaptive scheduling tools for mining operations facing real-world variability, reducing risk in profit forecasts compared to static or separately handled uncertainty approaches.

Core claim

The authors formulate the open-pit mine scheduling as a dynamic chance-constrained problem with stochastic values and varying capacities, and demonstrate through experiments on six instances that their diversity-based change response mechanism, when integrated into multi-objective evolutionary algorithms, consistently produces superior solutions in terms of expected discounted profit and its standard deviation across varying levels of uncertainty and change frequencies, compared to a re-evaluation baseline.

What carries the argument

The diversity-based change response mechanism, which detects changes and repairs a subset of infeasible solutions while injecting additional feasible solutions to maintain diversity in the population.

If this is right

  • The approach allows simultaneous optimization of profit expectation and risk under both uncertainty and dynamics.
  • Four multi-objective evolutionary algorithms benefit from the mechanism when applied to mine scheduling.
  • Performance holds across different uncertainty levels and frequencies of capacity changes.
  • Outperformance is shown on six standard mining instances.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar mechanisms could extend to other dynamic optimization problems with constraints that change, like resource allocation in varying markets.
  • Future work might explore predicting capacity changes to proactively adjust rather than reactively repair.
  • The bi-objective formulation could be expanded to include additional risk measures or environmental objectives in mining.

Load-bearing premise

That repairing infeasible solutions and injecting new feasible ones after capacity changes does not bias the search or add prohibitive computational cost while preserving effective optimization progress.

What would settle it

If on additional test instances with more frequent or extreme capacity changes the diversity-based method shows no improvement or worse performance than the baseline re-evaluation strategy in terms of the bi-objective metrics, the effectiveness claim would be challenged.

Figures

Figures reproduced from arXiv: 2604.13385 by Aneta Neumann, Ishara Hewa Pathiranage.

Figure 1
Figure 1. Figure 1: Dynamic changes in mining and processing capacities over six periods under 30 dynamic changes. Each [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
read the original abstract

Open-pit mine scheduling is a complex real world optimization problem that involves uncertain economic values and dynamically changing resource capacities. Evolutionary algorithms are particularly effective in these scenarios, as they can easily adapt to uncertain and changing environments. However, uncertainty and dynamic changes are often studied in isolation in real-world problems. In this paper, we study a dynamic chance-constrained open-pit mine scheduling problem in which block economic values are stochastic and mining and processing capacities vary over time. We adopt a bi-objective evolutionary formulation that simultaneously maximizes expected discounted profit and minimizes its standard deviation. To address dynamic changes, we propose a diversity-based change response mechanism that repairs a subset of infeasible solutions and introduces additional feasible solutions whenever a change is detected. We evaluate the effectiveness of this mechanism across four multi-objective evolutionary algorithms and compare it with a baseline re-evaluation-based change-response strategy. Experimental results on six mining instances demonstrate that the proposed approach consistently outperforms the baseline methods across different uncertainty levels and change frequencies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper studies the dynamic chance-constrained open-pit mine scheduling problem with stochastic block values and time-varying capacities. It formulates the problem as a bi-objective optimization task maximizing expected discounted profit while minimizing its standard deviation, and proposes a diversity-based change-response mechanism that repairs infeasible solutions and injects additional feasible ones upon capacity changes. Experiments on six mining instances compare this mechanism embedded in four MOEAs against a re-evaluation baseline, claiming consistent outperformance across uncertainty levels and change frequencies.

Significance. If the performance claims hold under rigorous validation, the work provides a concrete algorithmic contribution to evolutionary dynamic optimization with chance constraints, addressing a practically relevant combination of uncertainty and dynamism that is rarely treated jointly. The empirical focus on real-world mining instances and the explicit handling of capacity changes via diversity maintenance are strengths that could inform future applications in stochastic scheduling.

major comments (3)
  1. [Experimental Results] The central claim of consistent outperformance rests on the diversity-based repair-plus-injection mechanism, yet the experimental comparison does not isolate the injection step from the repair step; without an ablation that disables injection while retaining repair (or vice versa), it remains possible that the measured advantage arises from direct population manipulation rather than improved evolutionary adaptation to new capacities.
  2. [Problem Formulation and Approach] The bi-objective mean-variance formulation is presented as a proxy for the chance-constrained capacities, but no post-hoc verification (e.g., Monte-Carlo sampling of capacity satisfaction rates) is reported to confirm that the returned solutions actually meet the original probabilistic requirements at the tested uncertainty levels; this leaves the uncertainty-handling claim indirect.
  3. [Experimental Results] No statistical significance tests (Wilcoxon, Friedman, or equivalent) or effect-size measures are described for the hypervolume or feasibility comparisons across the six instances, uncertainty levels, and change frequencies; without these, the assertion of 'consistent outperformance' cannot be distinguished from random variation.
minor comments (2)
  1. [Abstract] The abstract states that four MOEAs are used but does not name them; the specific algorithms and their parameter settings should be stated explicitly in the abstract or early in the introduction.
  2. [Experimental Setup] Details on instance generation (block model sizes, uncertainty distributions, capacity change schedules) and exact wall-clock overhead measurements after each change are absent, limiting reproducibility.

Simulated Author's Rebuttal

3 responses · 0 unresolved

Thank you for the constructive comments on our manuscript. We address each major comment below and indicate the revisions planned to strengthen the work.

read point-by-point responses

  1. Referee: [Experimental Results] The central claim of consistent outperformance rests on the diversity-based repair-plus-injection mechanism, yet the experimental comparison does not isolate the injection step from the repair step; without an ablation that disables injection while retaining repair (or vice versa), it remains possible that the measured advantage arises from direct population manipulation rather than improved evolutionary adaptation to new capacities.

    Authors: We agree that an ablation isolating the repair and injection components would clarify their individual contributions. In the revised manuscript we will add experiments comparing the full mechanism against a repair-only variant and an injection-only variant on the same instances, keeping all other algorithmic settings fixed. revision: yes

  2. Referee: [Problem Formulation and Approach] The bi-objective mean-variance formulation is presented as a proxy for the chance-constrained capacities, but no post-hoc verification (e.g., Monte-Carlo sampling of capacity satisfaction rates) is reported to confirm that the returned solutions actually meet the original probabilistic requirements at the tested uncertainty levels; this leaves the uncertainty-handling claim indirect.

    Authors: The mean-variance formulation is used as a standard proxy for chance constraints. To provide direct evidence, we will add Monte-Carlo post-hoc verification in the revision, reporting empirical capacity-satisfaction rates for the final solutions across the tested uncertainty levels. revision: yes

  3. Referee: [Experimental Results] No statistical significance tests (Wilcoxon, Friedman, or equivalent) or effect-size measures are described for the hypervolume or feasibility comparisons across the six instances, uncertainty levels, and change frequencies; without these, the assertion of 'consistent outperformance' cannot be distinguished from random variation.

    Authors: We will incorporate statistical testing in the revision by applying the Wilcoxon signed-rank test for pairwise comparisons and the Friedman test with Nemenyi post-hoc analysis, together with effect-size reporting, for hypervolume and feasibility results across all instances, uncertainty levels, and change frequencies. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical algorithmic evaluation on external instances

full rationale

The paper proposes an algorithmic diversity-based change response for a dynamic chance-constrained open-pit mine scheduling problem and evaluates it experimentally against baselines on six mining instances. No mathematical derivation, prediction, or uniqueness theorem is claimed that reduces to fitted parameters or self-citations by construction. The bi-objective mean-variance formulation and repair/injection mechanism are presented as design choices, with performance claims resting on external test data rather than internal definitions or self-referential loops. This is a standard empirical study with no load-bearing self-citation chain or self-definitional reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical axioms, free parameters, or invented entities are described in the abstract; the work relies on standard evolutionary algorithm operators and chance-constraint handling from prior literature.

pith-pipeline@v0.9.0 · 5469 in / 1033 out tokens · 28708 ms · 2026-05-10T12:35:31.031496+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

40 extracted references · 40 canonical work pages

  1. [1]

    Pro- duction scheduling for strategic open pit mine planning: a mixed-integer programming approach.Operations Research, 68(5):1425–1444, 2020

    Orlando Rivera-Letelier, Daniel Espinoza, Marcos Goycoolea, Eduardo Moreno, and Gonzalo Muñoz. Pro- duction scheduling for strategic open pit mine planning: a mixed-integer programming approach.Operations Research, 68(5):1425–1444, 2020

    work page 2020

  2. [2]

    Aggregation heuristic for the open-pit block scheduling problem.European Journal of Operational Research, 249(3):1169– 1177, 2016

    Enrique Jélvez, Nelson Morales, Pierre Nancel-Penard, Juan Peypouquet, and Patricio Reyes. Aggregation heuristic for the open-pit block scheduling problem.European Journal of Operational Research, 249(3):1169– 1177, 2016. ISSN 0377-2217

    work page 2016

  3. [3]

    Coello Coello

    Saber Elsayed, Ruhul Sarker, Daryl Essam, and Carlos A. Coello Coello. Evolutionary approach for large-scale mine scheduling.Information Sciences, 523:77–90, 2020

    work page 2020

  4. [4]

    Multi-objective evolutionary optimization for large-scale open pit mine scheduling

    Ishara Hewa Pathiranage and Aneta Neumann. Multi-objective evolutionary optimization for large-scale open pit mine scheduling. InIEEE Congress on Evolutionary Computation, pages 1–8. IEEE, 2024

    work page 2024

  5. [5]

    Open pit mine production schedule optimization using a hybrid of maximum-flow and genetic algorithms.Applied Soft Computing, 81:105507, 2019

    Amol Paithankar and Snehamoy Chatterjee. Open pit mine production schedule optimization using a hybrid of maximum-flow and genetic algorithms.Applied Soft Computing, 81:105507, 2019. ISSN 1568-4946

    work page 2019

  6. [6]

    Snehamoy Chatterjee and Roussos Dimitrakopoulos. Production scheduling under uncertainty of an open-pit mine using lagrangian relaxation and branch-and-cut algorithm.International Journal of Mining, Reclamation and Environment, 34(5):343–361, 2020

    work page 2020

  7. [7]

    Open-pit mining complex optimization under uncertainty with integrated cut-off grade based destination policies.Resources Policy, 70:101875, 2021

    Amol Paithankar, Snehamoy Chatterjee, and Ryan Goodfellow. Open-pit mining complex optimization under uncertainty with integrated cut-off grade based destination policies.Resources Policy, 70:101875, 2021. ISSN 0301-4207

    work page 2021

  8. [8]

    Production phase and ultimate pit limit design under commodity price uncertainty.European Journal of Operational Research, 248(2):658–667,

    Snehamoy Chatterjee, Manas Ranjan Sethi, and Mohammad Waqar Ali Asad. Production phase and ultimate pit limit design under commodity price uncertainty.European Journal of Operational Research, 248(2):658–667,

    work page

  9. [9]

    A stochastic particle swarm based model for long term production planning of open pit mines considering the geological uncertainty

    Seyyed-Omid Gilani, Javad Sattarvand, Mohsen Hajihassani, and Shahrum Shah Abdullah. A stochastic particle swarm based model for long term production planning of open pit mines considering the geological uncertainty. Resources Policy, 68:101738, 2020

    work page 2020

  10. [10]

    A differential evolution based approach for the production scheduling of open pit mines with or without the condition of grade uncertainty.Applied Soft Computing, 66:428–437, 2018

    Asif Khan and Christian Niemann-Delius. A differential evolution based approach for the production scheduling of open pit mines with or without the condition of grade uncertainty.Applied Soft Computing, 66:428–437, 2018

    work page 2018

  11. [11]

    Heuristic strategies for solving complex interacting stockpile blending problem with chance constraints

    Yue Xie, Aneta Neumann, and Frank Neumann. Heuristic strategies for solving complex interacting stockpile blending problem with chance constraints. InProceedings of the Genetic and Evolutionary Computation Con- ference, page 1079–1087. ACM, 2021

    work page 2021

  12. [12]

    Improving confidence in evolutionary mine scheduling via uncertainty discounting

    Michael Stimson, William Reid, Aneta Neumann, Simon Ratcliffe, and Frank Neumann. Improving confidence in evolutionary mine scheduling via uncertainty discounting. InIEEE Congress on Evolutionary Computation, pages 1–10. IEEE, 2023

    work page 2023

  13. [13]

    Evolutionary bi-objective opti- mization for the dynamic chance-constrained knapsack problem based on tail bound objectives

    Hirad Assimi, Oscar Harper, Yue Xie, Aneta Neumann, and Frank Neumann. Evolutionary bi-objective opti- mization for the dynamic chance-constrained knapsack problem based on tail bound objectives. InEuropean Conference on Artificial Intelligence, volume 325, pages 307–314. IOS Press, 2020

    work page 2020

  14. [14]

    Runtime analysis of randomized search heuristics for dynamic graph coloring

    Jakob Bossek, Frank Neumann, Pan Peng, and Dirk Sudholt. Runtime analysis of randomized search heuristics for dynamic graph coloring. InGenetic and Evolutionary Computation Conference, page 1443–1451. ACM,

    work page

  15. [15]

    Using 3-objective evolutionary algorithms for the dynamic chance constrained knapsack problem

    Ishara Hewa Pathiranage, Frank Neumann, Denis Antipov, and Aneta Neumann. Using 3-objective evolutionary algorithms for the dynamic chance constrained knapsack problem. InProceedings of the Genetic and Evolution- ary Computation Conference, page 520–528. ACM, 2024

    work page 2024

  16. [16]

    Multi-objective evolutionary algorithms with sliding window se- lection for the dynamic chance-constrained knapsack problem

    Kokila Kasuni Perera and Aneta Neumann. Multi-objective evolutionary algorithms with sliding window se- lection for the dynamic chance-constrained knapsack problem. InProceedings of the Genetic and Evolutionary Computation Conference, page 223–231. ACM, 2024. ISBN 9798400704949

    work page 2024

  17. [17]

    Single- and multi-objective evolutionary algorithms for the knapsack problem with dynamically changing constraints.Theoretical Computer Science, 924:129–147,

    Vahid Roostapour, Aneta Neumann, and Frank Neumann. Single- and multi-objective evolutionary algorithms for the knapsack problem with dynamically changing constraints.Theoretical Computer Science, 924:129–147,

    work page

  18. [18]

    10 On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem

    ISSN 0304-3975. 10 On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem

    work page

  19. [19]

    Chance-constrained programming.Management science, 6(1):73–79, 1959

    Abraham Charnes and William W Cooper. Chance-constrained programming.Management science, 6(1):73–79, 1959

    work page 1959

  20. [20]

    Minimum spanning trees made easier via multi-objective optimization

    Frank Neumann and Ingo Wegener. Minimum spanning trees made easier via multi-objective optimization. Natural Computing: An International Journal, 5(3):305–319, 2006. ISSN 1567-7818

    work page 2006

  21. [21]

    3-objective pareto optimization for problems with chance constraints

    Frank Neumann and Carsten Witt. 3-objective pareto optimization for problems with chance constraints. In Proceedings of the Genetic and Evolutionary Computation Conference, page 731–739. ACM, 2023. ISBN 9798400701191

    work page 2023

  22. [22]

    Advanced mine optimisation under un- certainty using evolution

    William Reid, Aneta Neumann, Simon Ratcliffe, and Frank Neumann. Advanced mine optimisation under un- certainty using evolution. InProceedings of the Genetic and Evolutionary Computation Conference Companion, pages 1605–13. ACM, 2021

    work page 2021

  23. [23]

    Pareto optimization for subset selec- tion with dynamic cost constraints.Artificial Intelligence, 302:103597, 2022

    Vahid Roostapour, Aneta Neumann, Frank Neumann, and Tobias Friedrich. Pareto optimization for subset selec- tion with dynamic cost constraints.Artificial Intelligence, 302:103597, 2022. ISSN 0004-3702

    work page 2022

  24. [24]

    The chance constrained travelling thief problem: Problem formulations and algorithms

    Thilina Pathirage Don, Aneta Neumann, and Frank Neumann. The chance constrained travelling thief problem: Problem formulations and algorithms. InProceedings of the Genetic and Evolutionary Computation Conference. ACM, 2024

    work page 2024

  25. [25]

    Sliding window bi-objective evolutionary algorithms for optimizing chance-constrained monotone submodular functions

    Xiankun Yan, Aneta Neumann, and Frank Neumann. Sliding window bi-objective evolutionary algorithms for optimizing chance-constrained monotone submodular functions. InParallel Problem Solving from Nature – PPSN XVIII, LNCS, pages 20–35. Springer, 2024

    work page 2024

  26. [26]

    Optimising monotone chance-constrained submodular functions using evolutionary multi-objective algorithms

    Aneta Neumann and Frank Neumann. Optimising monotone chance-constrained submodular functions using evolutionary multi-objective algorithms. InParallel Problem Solving from Nature, PPSN XVI, 2020, Proceed- ings, Part I, volume 12269, pages 404–417. Springer, 2020

    work page 2020

  27. [27]

    Optimizing monotone chance-constrained submodular functions using evolutionary multiobjective algorithms.Evolutionary Computation, 33(3):363–393, 2025

    Aneta Neumann and Frank Neumann. Optimizing monotone chance-constrained submodular functions using evolutionary multiobjective algorithms.Evolutionary Computation, 33(3):363–393, 2025

    work page 2025

  28. [28]

    Kalyanmoy Deb, Udaya Bhaskara Rao N., and S. Karthik. Dynamic multi-objective optimization and decision- making using modified NSGA-II: A case study on hydro-thermal power scheduling. InEvolutionary Multi- Criterion Optimization, pages 803–817. Springer Berlin Heidelberg, 2007. ISBN 978-3-540-70928-2

    work page 2007

  29. [29]

    Multi-objective evolutionary approaches for the knapsack problem with stochastic profits

    Kokila Kasuni Perera, Frank Neumann, and Aneta Neumann. Multi-objective evolutionary approaches for the knapsack problem with stochastic profits. InParallel Problem Solving from Nature – PPSN XVIII, LNCS, pages 116–132. Springer, 2024

    work page 2024

  30. [30]

    On the use of bi-objective evolutionary algorithms for the stochas- tic multiple knapsack problem under dynamic constraints

    Ishara Hewa Pathiranage and Aneta Neumann. On the use of bi-objective evolutionary algorithms for the stochas- tic multiple knapsack problem under dynamic constraints. InProceedings of the Genetic and Evolutionary Com- putation Conference. ACM, 2026. To appear

    work page 2026

  31. [31]

    Minelib: A library of open pit mining problems.Annals of Operations Research, 206:93–114, 07 2013

    Daniel Espinoza, Marcos Goycoolea, Eduardo Moreno, and Alexandra Newman. Minelib: A library of open pit mining problems.Annals of Operations Research, 206:93–114, 07 2013

    work page 2013

  32. [32]

    Evolutionary algorithms for limiting the effect of uncertainty for the knapsack problem with stochastic profits

    Aneta Neumann, Yue Xie, and Frank Neumann. Evolutionary algorithms for limiting the effect of uncertainty for the knapsack problem with stochastic profits. InParallel Problem Solving from Nature – PPSN XVII, pages 294–307. Springer International Publishing, 2022

    work page 2022

  33. [33]

    Evolutionary dynamic multi-objective optimisation: A survey.ACM Computing Surveys, 55(4), 2022

    Shouyong Jiang, Juan Zou, Shengxiang Yang, and Xin Yao. Evolutionary dynamic multi-objective optimisation: A survey.ACM Computing Surveys, 55(4), 2022

    work page 2022

  34. [34]

    MOEA/D: A multiobjective evolutionary algorithm based on decomposition.IEEE Transactions on Evolutionary Computation, 11(6):712–731, 2007

    Qingfu Zhang and Hui Li. MOEA/D: A multiobjective evolutionary algorithm based on decomposition.IEEE Transactions on Evolutionary Computation, 11(6):712–731, 2007

    work page 2007

  35. [35]

    K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2):182–197, 2002

    work page 2002

  36. [36]

    SMS-EMOA: Multiobjective selection based on domi- nated hypervolume.European Journal of Operational Research, 181(3):1653–1669, 2007

    Nicola Beume, Boris Naujoks, and Michael Emmerich. SMS-EMOA: Multiobjective selection based on domi- nated hypervolume.European Journal of Operational Research, 181(3):1653–1669, 2007. ISSN 0377-2217

    work page 2007

  37. [37]

    SPEA2: Improving the strength pareto evolutionary algo- rithm.TIK report, 103, 2001

    Eckart Zitzler, Marco Laumanns, and Lothar Thiele. SPEA2: Improving the strength pareto evolutionary algo- rithm.TIK report, 103, 2001

    work page 2001

  38. [38]

    Bi-objective evolutionary optimization for large-scale open pit mine scheduling problem under uncertainty with chance constraints.arXiv, 2511.08275, 2025

    Ishara Hewa Pathiranage and Aneta Neumann. Bi-objective evolutionary optimization for large-scale open pit mine scheduling problem under uncertainty with chance constraints.arXiv, 2511.08275, 2025

    work page arXiv 2025

  39. [39]

    Gurobi optimizer reference manual, 2024

    LLC Gurobi Optimization. Gurobi optimizer reference manual, 2024. URLhttps://www.gurobi.com

    work page 2024

  40. [40]

    Corder and Dale I

    Gregory W. Corder and Dale I. Foreman.Nonparametric statistics for non-statisticians: A step-by-step approach. John Wiley & Sons, 2014. 11

    work page 2014