Future Mining: Learning for Safety and Security

Details

• Personal Author:
  Rahman, Md Sazedur ; Jewel, Mizanur Rahman ; Madria, Sanjay
• Description:
  Mining industry is rapidly transforming into an AI-driven cyber-physical ecosystem where safety and operational reliability depend on robust perception, resilient communication, trustworthy distributed intelligence and continuous monitoring of miners and equipment. Real-world mining environments impose severe constraints like poor illumination, dust, occlusion, GPS-denied conditions, irregular underground topologies, and intermittent connectivity. These factors degrade perception quality, disrupt situational awareness, impair trajectory prediction and weaken the reliability of distributed learning systems. Emerging cyber-physical threats, including backdoor triggers, sensor spoofing, label-flip attacks and poisoned model updates, further jeopardize operational safety, particularly as mines increasingly adopt autonomous vehicles, humanoid assistance, and federated learning for collaborative intelligence. Moreover, energy-constrained sensors experience uneven and unpredictable battery depletion, creating blind spots in safety coverage and disrupting hazard detection pipelines. This paper presents a vision for a Unified Smart Safety and Security Architecture that integrates multimodal perception, spatial-temporal modeling, secure federated learning, reinforcement learning, DTN-enabled communication and energy-aware sensing into a cohesive safety fabric. We detail five core modules: Miner-finder, Multimodal Situational Awareness, Backdoor Attack Monitor, TrustFED-LFD and IoT-driven Equipment Health Monitoring, addressing critical gaps in miner localization, hazard understanding, model integrity, federated robustness and predictive maintenance. Together, these modules form an end-to-end framework capable of detecting hazards, responding to disasters, guiding miners through obstructed pathways, identifying compromised models or sensors and ensuring the health of mission-critical equipment. By unifying these components, this work outlines a comprehensive research vision for building a futuristic, resilient, proactive and trustworthy intelligent mining system capable of safeguarding miners and maintaining operational continuity under extreme and adversarial conditions. Description provided by NIOSH
• Subjects:
  • Artificial Intelligence
  • Mining
  • Occupational Health
  • Safety
• Keywords:
  • Mining industry; Artificial intelligence; Automation; Sensors; Situational awareness; Hazard communication; Mining engineering; Computer assisted mining; Communications equipment;
  • Author Keywords: Distributed system; DTN communication; energy-aware sensing; machine unlearning; multimodal perception; post-disaster navigation; smart mining
• Source:
  2026 18th International Conference on COMmunication Systems and NETworks (COMSNETS), January 6-10, 2026, Bengaluru, India. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2026 Jan; :473-481
• Series:
  Mining Publications
• ISBN:
  9798331592394
• ISSN:
  2155-2509
• Document Type:
  Text
• Funding:
  Cooperative Agreement
• Genre:
  Proceedings
• Place as Subject:
  Kansas City Region OSHA ; Missouri
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  10 pdf pages
• NIOSHTIC Number:
  nn:20071615
• Contact Point Address:
  Md Sazedur Rahman, Department of Computer Science, Missouri University of Science and Technology, Rolla, MO 65401, USA
• Email:
  mrvfw@mst.edu
• Federal Fiscal Year:
  2026
• NORA Priority Area:
  Mining
• Performing Organization:
  Missouri University of Science and Technology
• Peer Reviewed:
  False
• Start Date:
  20230901
• End Date:
  20270831
• Download URL:
  https://stacks.cdc.gov/view/cdc/259390/cdc_259390_DS1.pdf
• File Type:
  [PDF - 1.88 MB]
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:e6b32aaac05a94e14117bd72b01fa7d3ced57731e4d290559bf4bcda5d4c5ea59a1de75eecdd3d8af520d415b78c71304d1bf066f6e2651356b33c1a4817fd56