Mine Economic and Management
Mohamad Reza ameri; Mohammad Mehdi Rajaei; Abuzar Faraji
Abstract
AbstractThis study provides a systematic bibliometric and thematic review of research on risk assessment in the mining industry. The focus is on fuzzy inference systems (FIS), artificial intelligence (AI), and hybrid FIS–AI approaches. A dataset of 1,607 articles from Scopus was analyzed to identify ...
Read More
AbstractThis study provides a systematic bibliometric and thematic review of research on risk assessment in the mining industry. The focus is on fuzzy inference systems (FIS), artificial intelligence (AI), and hybrid FIS–AI approaches. A dataset of 1,607 articles from Scopus was analyzed to identify publication trends, geographic distribution, citation patterns, and key themes. Using the PRISMA protocol, titles and abstracts were screened, and relevant studies were selected for detailed review The results indicate a steady growth in research output over the past decade, reflecting the increasing importance of intelligent systems in addressing uncertainty and complexity in mining operations. Developed countries tend to prioritize AI-driven methods such as machine learning, neural networks, and hybrid systems. In contrast, developing countries place greater reliance on fuzzy logic approaches, particularly in contexts where reliable data are limited. This methodological divergence underscores uneven technological development and highlights the existing knowledge gap across regions. Three main research pillars are identified: safety (39%), operational efficiency (45%), and environmental sustainability (16%). Methodologically, fuzzy approaches dominate (48%), followed by AI (34%) and hybrid methods (18%). These findings confirm the global relevance of AI and FIS in mining risk assessment and emphasize the need for collaboration to close existing gaps.
