A Hybrid Knowledge System for Mine Rehabilitation Decision Support Using Relational Filtering and Semantic Retrieval in a Community-Curated Case Repository

Authors

  • Vancho Adjiski Goce Delcev University https://orcid.org/0000-0001-6401-6835
  • Jindřich Šancer VSB – TUO
  • Peter Schwendner Zurich University of Applied Sciences
  • Luka Crnogorac University of Belgrade
  • Kemajl Zeqiri University "Isa Boletini"
  • Václav Zubíček VSB – TUO
  • Stefan Moellerherm University of Applied Science

DOI:

https://doi.org/10.17794/rgn.2027.1.1

Keywords:

Mine rehabilitation, post-mining land use, decision-support system, semantic retrieval, community-curated database

Abstract

Mine closure and post-mining repurposing require tools that connect practitioners with relevant rehabilitation examples across fragmented case evidence. This study transforms the Recovery of Mining District Network (REMINDNET) Work Group 3 (WG3) best-practices spreadsheet into a hybrid knowledge system combining structured relational filtering with lexical and semantic retrieval. From 149 submissions, the workflow produced a curated dataset of 130 unique cases from 21 countries, with validated WGS84 coordinates, standardised metadata, a controlled 12-category multi-label vocabulary, and reproducible `case_card` and `retrieval_text` representations. The system was evaluated using 25 natural-language benchmark queries and a relevance definition based on category overlap within structured constraints. The dataset is dominated by socially oriented and relatively low-impact reuse pathways, especially Community & culture, Non-intensive recreation, Conversion & ecosystem services, and Education & research. Co-occurrence and subgroup analyses show that mine type, operational status, ore type, and geography shape thematic case profiles, supporting their use as decision-support filters. In retrieval evaluation, both term frequency-inverse document frequency (TF-IDF) and embedding-based ranking improved over a filters-only random baseline, confirming that ranked search adds value after structured filtering. Filtered embeddings achieved the highest macro-average early-ranking scores, including Precision at 5 (P@5 = 0.768) and normalized Discounted Cumulative Gain at 10 (nDCG@10 = 0.810), but paired query-level tests did not show a statistically reliable advantage over filtered TF-IDF at the current benchmark scale. The strongest supported gain was the benefit of structured filtering for the embedding workflow. Overall, a relational-plus-semantic architecture can make community-curated knowledge on mine rehabilitation easier to search, compare, and interpret.

Downloads

Additional Files

Published

2026-10-26

Issue

Vol. 42 No. 1 (2027): Forthcoming Issue: No. 82

Section

Mining

License

Copyright (c) 2026 Vancho Adjiski, Jindřich Šancer, Peter Schwendner, Luka Crnogorac, Kemajl Zeqiri, Václav Zubíček, Stefan Moellerherm

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Creative Commons-BY

Authors who publish with this journal agree to the following terms:

In agreeing this form, you certify that:

  1. You read the ethical codex of the RGN zbornik available at journal web.
  2. You submitted work is your original work, and has not previously been published and does not include any form of plagiarism.
  3. You own copyright in the submitted work, and are therefore permitted to assign the licence to publish to RGN zbornik.
  4. Your submitted work contains no violation of any existing copyright or other third party right or any material of an obscene, libellous or otherwise unlawful nature.
  5. You have obtained permission for and acknowledged the source of any illustrations, diagrams or other material included in the work of which you are not the copyright owner.
  6. You have taken due care to ensure the accuracy of the work, and that, to the best of your knowledge, there are no false statements made within it.
  7. All co-authors of this submitted work are aware of, and in agreement with, the terms of this licence and that the submitted manuscript has been approved by these authors.

 

Publication licence

You retain copyright in your submitted work, according to journal license policy (CC-BY). By signing this form you agree that RGN zbornik may publish it under the publication licence. In summary the licence allows the following:

Anyone is free:

  • To copy, distribute, display, and perform the work.
  • To make derivative works.

 

Under the following conditions:

  • The original author must always be given credit.
  • The work may not be used for commercial purposes.
  • If the work is altered, transformed, or built upon, the resulting work may only be distributed under a licence identical to this one.

 

Exceptions to the licence

In addition to publishing the work printed under the above licence, RGN zbornik will also enable the work to be visible online.

The journal editorial can change the licence rules anytime but it cannot retroactively restrict author(s) rights.

 

How to Cite

Adjiski, V., Šancer, J., Schwendner, P., Crnogorac, L., Zeqiri, K., Zubíček, V., & Moellerherm, S. (2026). A Hybrid Knowledge System for Mine Rehabilitation Decision Support Using Relational Filtering and Semantic Retrieval in a Community-Curated Case Repository. Rudarsko-geološko-Naftni Zbornik, 42(1), Article in Press. https://doi.org/10.17794/rgn.2027.1.1