Just Accepted
A critical review of critical metals in coal and coal-bearing strata Characteristics, enrichment mechanisms, extraction techniques, and strategic significance
LSTM learning enhanced deep cone thickening and paste backfilling for high density tailings: A case study
Multi-criteria decision evaluation of coal gangue resource utilization schemes: A case study of the taigemiao mining area
Integrated backfill planning for sustainable closure of opencast coal mines in India: Case studies and innovative decision support framework
Calculation method of sectional velocity and coal flow based on discrete element simulation for scraper conveyors
more..Machine learning throughout the non-ferrous metal lifecycle: An overview and application advances
Haiyang Liao; Lei Huang; Zhenxing Wang; Zhen Zeng; Xue Jia; Qisheng Huang; Jia Yan; Meng Li; Hongguo Zhang; Zhenxin Chen; Hao LiData-driven machine learning (ML) technologies offer significant advantages throughout the entire lifecycle of non-ferrous metal mineral exploration, smelting processes, resource recovery and circular economy, pollution control and environmental remediation, materials applications and development due to their efficiency and robust analytical capabilities. The integration of ML algorithms such as Random Forest (RF), Convolutional Neural Networks (CNN), and Extreme Gradient Boosting (XGBoost) with reinforcement learning-enabled process control technologies has made substantial contributions to minimizing resource waste. This review summarizes the technological advancements of machine learning techniques in mineral exploration prediction, metallurgical parameter optimization, metal recovery from solid waste, and non-ferrous metal pollution control. Furthermore, we highlight the challenges currently faced in machine learning applications, including data quality and scale issues, the complexity of feature engineering, and poor model interpretability. It also proposes future research priorities focused on optimizing data extraction methods, enhancing model generalization capabilities, and improving interpretability.
Cemented paste backfill: A comparative analysis of global perspectives and Chinese innovations
Aixiang Wu; Tongfei Huang; Zhenqi Wang; Shuairan Shu; Zhuen RuanCemented paste backfill(CPB) is a cornerstone technology for achieving green mining. This paper presents a comparative framework. It contrasts the global perspective with Chinese innovations in CPB development. First, it reviews the evolution of international CPB technology. This includes core equipment such as the deep cone thickener(DCT), high-efficiency mixing, and piston pumps. It also covers foundational theories, such as rheology. This analysis highlights the international model's focus on modularization and standardization. Furthermore, it provides an in-depth analysis of China's unique CPB development path. This path was developed to address"deep, large-scale, and complex" geological conditions. It also meets the strategic demands of the"dual carbon" goals. China's core contribution lies in systems integration—linking mining, processing, backfilling, and solid waste management. This approach emphasizes the synergistic use of multiple sources of solid waste and has spurred technological innovations to address major engineering challenges, such as thickening ultra-fine tailings and transporting them across large height differences in ultra-deep shafts. This study highlights China's progress in CPB technology. It has advanced from"introduction and absorption" to"exporting standards". Finally, the paper outlines the future frontiers for CPB:(1) all-solid-waste-based low-carbon cementitious materials(e.g., geopolymers and carbonation curing); (2) deep backfill design based on thermal-hydrological-mechanical-chemical (THMC) multi-field coupling; and(3) intelligent autonomous systems driven by digital twins.
Towards intelligent perception of flotation processes: A review of froth image analysis methods
Kanghui Zhang; Guobin Zou; Qingkai Wang; Xu Wang; Daoxi Liu; Yang LiuFroth image analysis in flotation processes is a key technology for enabling intelligent perception and closed-loop control in mineral processing. By extracting visual information from multistage flotation cycles, the operating state of the flotation process can be inferred in real time, providing critical decision support for reagent addition, air flow regulation, and pulp level (valve opening) control. This paper systematically reviews the development and research progress of froth image analysis techniques. First, based on the physical behavior of flotation and its process responses, the relationships between froth visual characteristics and production parameters are analyzed. Froth visual characteristics include size, morphology, color, texture, and motion, while production parameters refer to grade, recovery, and operating conditions. From the perspective of visual modeling, froth image features are categorized into static features and dynamic features, representing the spatial characteristics of the froth at specific time points and their temporal evolution, respectively. Static features, particularly froth size, have been analyzed using computer vision approaches such as object detection, semantic segmentation, instance segmentation, density map estimation, and boundary regression. Dynamic features encompass froth motion and other time-dependent behaviors, including flow velocity, breakup rate, stability, and coalescence. These properties are examined using techniques such as flow estimation and object tracking, selected according to the specific dynamic aspect under consideration. Furthermore, this review examines the fusion of froth visual information with flotation process parameters from a time-series modeling perspective. The strengths and limitations of different approaches are highlighted with respect to their feature representation capability, temporal dependency modeling, and practical implementation complexity. Integration with time-series and machine learning approaches enables the prediction of key indicators such as concentrate grade and recovery, and facilitates closed-loop or anticipatory control of flotation variables. Challenges remain in spatiotemporal fusion and robustness under complex industrial conditions, including fluctuating froth behavior, shadows, and reflections. Future directions include leveraging digital twins, large pretrained models, and reinforcement learning to develop adaptive, data-driven control strategies that enhance process efficiency, stability, and sustainability.
High-temperature magnetic sensors for mineral exploration
Zhaozong Zhang; Zilong Zhang; Guo Chen; Meiyong LiaoMagnetic sensing is a non-invasive and cost-effective technique widely used in geophysical mineral exploration, exploiting spatial variations in the Earth's magnetic field to identify subsurface magnetic contrasts. As exploration targets shift toward deeper ore bodies and geothermal environments, the demand for reliable high-temperature magnetic sensors continues to grow. This review examines high-temperature magnetic sensing technologies for mineral exploration, focusing on four major categories of solid-state and miniaturized sensors: fluxgate, Hall effect, magnetoresistive(MR), and microelectromechanical systems(MEMS) sensors. The underlying detection mechanisms, material developments, device architectures, and sensing performance of each technology are discussed. Particular attention is given to material innovations enabling stable operation in harsh environments, including wide-bandgap semiconductors for Hall sensors, advanced magnetic alloys for MR devices, and diamond-based magnetostrictive MEMS structures. Applications across ground, airborne, marine, and borehole platforms are reviewed. Finally, current challenges and future trends are outlined, discussing the increasing role of data-driven approaches for intelligent mineral exploration.
Review on macro-meso mechanical properties and damage mechanism of rock-backfill composite structure
Yuye Tan; Ziyi Zeng; Jinshuo Yang; Jiangwei Liu; Weidong SongThe rock-backfill composite structure is a core load-bearing component in underground metal mines formed by stage open stope subsequent filling. Its stability is critical for safe and efficient mining. Due to significant differences in material compositions, physical properties and mechanical properties between rock and backfill, the damage evolution and failure laws of this composite structure are notably different from those of single-medium structures. This paper systematically reviews the research progress of rock-backfill composite structures in metal mines from macro, meso and micro scales. Macroscopically, laboratory mechanical tests and numerical simulations clarify the synergistic bearing characteristics, stress-strain laws and failure mechanisms of the composite structure. Meso-microscopically, advanced observation technologies reveal the essential damage processes including pore development, micro-crack propagation and particle interaction imbalance. The review identifies key research deficiencies in dynamic mechanical properties, cross-scale correlation and parameter quantitative characterization. Future research trends are proposed focusing on macro-micro method collaboration, dynamic load and multi-field coupling research, and refined damage characterization. This study enriches the mechanical theory system of multi-medium composite structures and provides reliable theoretical support for stope structure optimization, filling ratio design and long-term stability guarantee in underground metal mines.
Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Edit officeCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Expert officeOnline Review
Online Communication with the Editorial Department
Announcement
News
Links
OA Publishing
