Machine learning and thermodynamics dual-driven precise extraction of critical metals in urban mining

Advancing conceptual understanding of technology adoption decisions in E-waste urban mining sector

Mining is an important industry for the achievement of sustainable development goals (SDGs), but it results in a significant amount of degraded land worldwide, thereby affecting local social and ecological sustainability. Little is known about the extent to which this degraded land adheres to the current SDGs. In this study, based on public geographic information data, the status of SDG 11 (Sustainable Cities and Communities) and SDG 15 (Life on Land) for global mine sites was comprehensively assessed. The results show that (1) the global aggregation index for SDG 11 and 15 in mining areas increased from 23.94 in 2000 to 24.48 in 2020, generally exhibiting a positive trend. (2) For SDG 11, all four indicators indicate improvement, suggesting enhancement of the sustainability of cities and communities surrounding global mined land, as well as urban development, mining activities, and economic growth. In contrast, regarding SDG 15, there were noticeable improvements in the water body area and land reclamation ratio, but the forest coverage ratio and net ecosystem productivity significantly declined, indicating continued stress on ecosystems caused by mining. (3) Less than 1% of mines globally met the green grade in SDG 11, and around 97% were categorized as red grade. For SDG 15, no mines reached the green grade, and at least 99.74% were categorized as red grade mines. (4) Globally, the status has exhibited obvious spatial clustering, and the region with a better status is in the equatorial region. There has been obvious spatial heterogeneity within countries, and mine sites near urban areas have had a better status according to these SDGs. The main influencing factors on the status of mines, according to the SDGs, include the degree of mining disturbance, ecosystem recovery capacity, and urban expansion. Overall, the global status of mines according to the SDGs is far from expectation, indicating a considerable gap from achieving sustainable mining and necessitating efforts to improve human habitats and restore ecosystems in mining areas. Future endeavors should focus on strengthening site specific assessment and long-term monitoring of the global SDGs in mining areas to provide foundational data and scientific evidence for sustainable mining and the realization of SDGs.

Classifying urban mineral resources and reserves for a circular economy.

Granite quarrying, a cornerstone of the construction industry in South India, yields significant economic benefits but poses substantial environmental and social challenges, including land degradation, dust pollution, alternation of the water regime, and harsh working conditions. Rapid urban expansion has escalated granite demand in many countries, intensifying quarrying activities. This trend is particularly pronounced in Bengaluru, India, where rural-urban transformation causes concerns about environmental sustainability and social-ecological consequences of urban resource mining. This study proposes an innovative multi-modal framework to monitor granite quarrying in Bengaluru by combining deep learning with a 2024 dry-season multi-date Sentinel-2 composite for quarry segmentation and UAV SfM-MVS photogrammetry for volumetrics. We benchmark five CNN architectures—U-Net, PSPNet, DeepLabV3 + , FCN, and EMANet. In-area development results peaked with DeepLabV3+ (F1 ≈ 94.6%, IoU ≈ 89.7%), while an external, geographically independent audit established PSPNet as the most robust model (F1 = 93.4% [95% CI 90.8–95.9], IoU = 87.6%) with significantly fewer errors than alternatives (McNemar tests, FDR-adjusted p < 0.001). Applying the best model across the region yielded 252 candidates; 227 quarries were confirmed via field checks and sub-meter imagery, spanning 740 hectares. UAV photogrammetry at the Prasannacharipalya site (0.046 m grid; LoD95 masking), yielded a combined lowering volume of 9 280 051 m³ (acceptance area 97.2%; 95% CI ± 17 864 m³, 0.19%). The satellite-to-UAV pipeline enabled automated, scalable quarry footprint mapping with site-level volumetric quantification, offering actionable evidence for environmental management and oversight of quarrying in the quickly-urbanizing study region.

Abstract The transition from a linear to a circular economy in the building sector is essential to protect resources and reduce environmental impacts. A central strategy of circular construction is reusing existing materials, so-called Urban Mining. However, there is a lack of tools for a systematic search for materials for Urban Mining. This paper shows methods for material scouting for Urban Mining in the German building sector. The focus is on searching for buildings about to be demolished so their materials can potentially be reused. The following methods for searching demolition projects could be identified: (1) Internet research, (2) inquiries to institutions and players in the construction industry, (3) city inspection, and (4) public appeal. As part of a case study, methods 1-3 were used to find demolished buildings within a radius of 50 kilometers around a defined point. A total of 15 potential demolitions have been identified. After further research, the demolition plans for eight buildings could be confirmed through contacting the property owners. Permission for an initial inspection has been granted for two of the properties. The inspection of one property showed contamination with asbestos; further use of the structural components was ruled out. Through a student seminar, the urban mining components of the second property were documented. The analysis of the material scouting methods and the case study’s implementation showed that procuring reused building components is a time-consuming process characterized by uncertainties. This highlights the need to document used materials and building components in ongoing and future projects. Further, sourcing materials and building components must be simplified to scale construction with reused building components.

Abstract The URMIBALI research project aims to develop, within an Urban Mining (UM) framework, a digital method for rapidly acquiring detailed data to inventory and quantify the existing materials deposits in old historic and traditional buildings in the city of Liège. The method’s development follows a bottom-up and interdisciplinary approach, leveraging both six representative study cases, digital documentation technologies commonly used in heritage preservation, and existing historical and archaeological knowledge, including construction techniques and materials. This contribution outlines the various research steps, including a typological analysis of Liège’s building stock built before 1919, a theoretical and quantitative inventory of material deposits in six representative study cases, a theoretical accounting of demolition waste flows generated by energy renovation operations, and the development of a digital method for rapid data acquisition. Additionally, it presents and discusses the results of the theoretical inventory of material deposits.

Abstract Government authorities can play a key role in promoting CE through public procurement, which can help scale resource-efficient strategies in the construction sector. However, they often lack knowledge of circular construction practices, especially about the context potential for urban mining and associated practicable metabolic processes. Therefore, an approach combining pre-demolition and reuse audit models is proposed to evaluate public-owned built assets at the end of their life cycle and suggest CE-oriented compensation measures to be implemented in subsequent construction projects. The paper also presents the results of applying the method to a case study in Lugano: the Ex-Spohr complex. The study identified 56 reusable elements and estimated the outgoing material flows from a hypothetical selective demolition, suggesting offsetting measures achievable in the following municipality projects.

The concept of urban mining refers to the recovery and valorization of valuable resources from urban and industrial waste, contributing to circular economy principles. Within this framework, the present study provides a critical review of alkali-activated binders incorporating bivalve mollusk shells as alternative calcium sources. Shells from oysters, scallops, mussels, clams, cockles, and periwinkles were examined, either in their natural or calcined forms, for use as calcium sources, alkaline activators, or fillers in low-carbon binders. The review evaluates key processing parameters, including precursor composition, type and concentration of alkaline activators, curing conditions, and calcination temperatures, and compares the resulting mechanical, chemical, and microstructural properties. In addition, several studies report applications of these binders in soil stabilization and heavy metal immobilization, demonstrating performances comparable to Portland cement. The findings confirm the technical potential of mollusk shell residues and their contribution to the circular economy by diverting aquaculture waste from landfills and marine environments. Nonetheless, significant knowledge gaps persist, including the limited investigation of non-oyster species, the absence of field-scale studies, and the lack of resource mapping, life cycle, or economic assessments. This synthesis highlights preliminary insights, such as optimal calcination temperatures between 700 and 900 °C and effective combinations with silica and alumina-rich residues. Overall, it outlines a pathway toward transforming an underutilized waste stream into sustainable and technically viable construction materials.

The river source region of the Yellow River Basin is a critical ecological barrier in China, yet it is characterized by extreme environmental vulnerability. Human activities, particularly intensive mining, can severely disrupt the landscape ecosystem and alter its spatial patterns. The aim of this study is to conduct a comprehensive landscape ecological risk assessment, analyzing the spatial differentiation and driving factors of these risks to ensure regional ecological security. Employing high-resolution remote sensing technology, a comprehensive assessment of landscape ecological risk in the river source region of the Yellow River Basin was conducted based on the 2020 mining development status. The landscape ecological risk index (ERIk) was applied to evaluate risk distribution patterns, while the Geodetector model implemented in R was utilized to identify and analyze key driving factors. The results were as follows: (1) The study area exhibited an elevated landscape ecological risk. (2) Anthropogenic disturbances, such as urban construction, residential activities, and mining, combined with a widespread cropland distribution, degraded alpine grasslands, and high landscape fragility, were identified as major contributors to the elevated landscape ecological risk in the study area. (3) Habitat quality and population density remain the most significant factors driving the spatial differentiation of landscape ecological risk, and their interaction strongly governs the spatial distribution of such risk. In contrast, mining development intensity is not a dominant factor influencing the spatial heterogeneity of landscape ecological risk at the regional scale in the study area. This assessment reveals the extent of ecological risk associated with mining and other human activities and its key drivers.

Recently, geospatial artificial intelligence (GeoAI) has risen as a set of essential technologies for urban mobility pattern mining and understanding. However, traditional deep learning models are constrained by their high data dependency and limited interpretability. This study introduces the Knowledge-Driven Semantic Tree (KD-ST) model, a novel GeoAI framework that integrates structured semantic descriptions with graph-based learning to enhance geospatial modeling on e-scooter ridership classification. By incorporating a street knowledge structure into the GeoAI model architecture, KD-ST bridges the gap between purely data-driven methods and knowledge-informed urban analytics, improving classification performance and model transparency. We conducted case studies in four major U.S. cities, including Austin, Phoenix, Denver, and Washington, D.C., to evaluate the proposed KD-ST model’s performance. The proposed model outperformed baseline models by 12.1% to 156.5% as for the F1 score. Moreover, to enhance transparency and reliability, key internal parameters were extracted to visualize and analyze the learned hierarchical knowledge structure. Results indicate that domain knowledge provides useful information for the design of deep learning models and improves model performance. Furthermore, the model achieved higher transferability among cities with more similar urban contexts, which provides valuable insights for e-scooter planners on model choice.

There is an increasing demand for consistent methods and tools to quantify biodiversity footprints: the magnitude of biodiversity loss associated with all direct and indirect impacts associated with a given human activity or economic actor. Here, we present the intactness-based biodiversity impact factors (IBIF) dataset: a consistent set of country-level impact factors that can be used to attribute losses in local terrestrial biodiversity intactness to emissions and resource use associated with production or consumption in a given country. We used the GLOBIO biodiversity model and its mean species abundance (MSA) metric to obtain these impact factors for 234 countries and five environmental pressures: CO2 emissions, NH3 emissions, NOx emissions, land use (urban land, cropland, pasture, forest plantations and mines) and roads. IBIF includes impact factors for vascular plants, warm-blooded vertebrates (birds & mammals) and both species groups combined. The dataset can be used to quantify the biodiversity footprints of current products, industrial sectors or consumers, in support of policy- and decision-making aimed at halting or reversing biodiversity loss.

The relentless pace of industrialisation and globalisation has precipitated the rapid depletion of surface mineral deposits, presenting a formidable challenge to conventional mining operations and exerting a detrimental impact on their profitability. This depletion, coupled with the escalating demand for minerals, has driven prices to unprecedented highs, thereby inflating operating costs across various industries. Traditional surface and underground mining methods, struggling to meet burgeoning demands, contribute significantly to environmental degradation and substantial energy consumption. In response to these challenges, this study advocates for a paradigm shift from conventional mining methods and mineral resources toward untapped alternatives that hold the potential for enhanced economic viability and sustainability. Utilising environmentally friendly techniques and adopting more economical approaches becomes paramount in addressing the pressing demands of the current era and securing resources for future generations. This short review examines potential alternative mineral resources and the associated mining methods, including fluidised mining, deep-sea mining, brine mining, urban mining, in-situ and heap leaching, and space mining. A meticulous evaluation of the state-of-the-art technologies developed for these unconventional methods is conducted, including an assessment of their respective advantages and disadvantages. Finally, the study deliberates on the prospects of each approach, elucidating their potential contributions to alleviating the global metal crisis. This research provides insights that can inform sustainable mining practices and guide the industry toward a more environmentally responsible and economically viable future. The urgency of such a transition is underscored by the need to address the challenges posed by conventional mining and ensure the availability of mineral resources for generations to come.

Abstract China’s booming truck industry has led to a rapid rise in end-of-life trucks, yet only one-third are formally recycled. Here we estimate the resource, economic, and decarbonization potential of end-of-life trucks in China through 2050 using a dynamic population balance model. Our analysis shows the annual amount of end-of-life trucks will increase nine-fold to 53 million metric tons by 2050. The economic benefit from these materials is projected to reach 44 billion United States dollars, adjusted for inflation. Furthermore, urban mining of aluminum, iron, and copper can reduce carbon emissions by up to 58 million metric tons in 2050 compared to primary production. These findings provide quantitative support for urban mining policies to advance decarbonization, particularly in economies with fossil fuel-dominated power grids.

Land use/land cover (LULC) change is a key driving factor influencing the dynamics of terrestrial ecosystem carbon storage. In high-groundwater-level coal resource-based cities (HGCRBCs), the interplay of urban expansion, mining disturbances, and land reclamation makes the carbon storage evolution process more complex. This study takes Jining, Zaozhuang, and Heze cities in Shandong Province as the research area and constructs a coupled analytical framework of “mining–reclamation–carbon storage” by integrating the Patch-generating Land Use Simulation (PLUS), Probability Integral Method (PIM), InVEST, and Grey Multi-Objective Programming (GMOP) models. It systematically evaluates the spatiotemporal characteristics of carbon storage changes from 2000 to 2020 and simulates the carbon storage responses under different development scenarios in 2030. The results show that: (1) From 2000 to 2020, the total carbon storage in the region decreased by 31.53 Tg, with cropland conversion to construction land and water bodies being the primary carbon loss pathways, contributing up to 89.86% of the total carbon loss. (2) Among the 16 major LULC transition paths identified, single-process drivers dominated carbon storage changes. Specifically, urban expansion and mining activities individually accounted for nearly 70% and 8.65% of the carbon loss, respectively. Although the reclamation path contributed to a recovery of 1.72 Tg of carbon storage, it could not fully offset the loss caused by mining. (3) Future scenario simulations indicate that the ecological conservation scenario yields the highest carbon storage, while the economic development scenario results in the lowest. Mining activities generally lead to approximately 3.5 Tg of carbon loss, while post-mining reclamation can restore about 72% of the loss.

Subterranean ecosystems represent some of the most unique and fragile habitats on Earth, yet they remain poorly understood and highly vulnerable to human-induced disturbances. Despite their ecological significance, these systems are rarely integrated into conservation planning, and surface-level protected areas alone are insufficient to safeguard their biodiversity. In southeastern Brazil, a karst landscape spanning approximately 1200 km2, recognized as the region with the highest cave density in South America (approximately 2600 caves), is under increasing pressure from urban expansion, agriculture, and mining, all of which threaten the ecological integrity of subterranean habitats. This study sought to identify caves of high conservation priority by integrating species richness of non-troglobitic invertebrates, occurrence of troglobitic species, presence of endemic troglobitic taxa, and the degree of anthropogenic impacts, using spatial algebra and polygon-based mapping approaches. Agriculture and exotic forestry plantations (54%) and mining operations (15%) were identified as the most prevalent disturbances. A total of 32 troglobitic species were recorded, occurring in 63% of the 105 surveyed caves. Notably, seven caves alone harbor 25% of the region's known cave invertebrate diversity and encompass 50% of its cave-restricted species. The findings highlight the global significance of this spot of subterranean biodiversity and reinforce the urgent need for targeted conservation measures. Without immediate action to mitigate unsustainable land use and resource exploitation, the persistence of these highly specialized communities is at imminent risk.

IntroductionThe circular economy as a resource sustainability strategy is both established and contentious in and beyond academia. This paper contributes to the growth-critical scholarship on circularity, starting from the premise that circular economic diversity is both a function of, and is required for, an economy beyond growth-dependencies. Exploring the question what this diverse circularity might look like on the ground, our paper inventories the wide range of circular activities and relationships taking place in a not-for-profit maker cooperative in Belgium and studies their main characteristics.MethodologyWe deploy the diverse economies (DE) framework, which presents us with theoretical concepts and qualitative-ethnographic methods (long-term observation, participation, depth interviews) that enable the study and classification of economic activity. It is designed to broaden the scope of the ‘circular economic’ by including non-market and informal practices.ResultsWe found that many of the circular activities we observed (repairing, urban mining, reusing, dismantling, maintaining) are often overlooked in the literature on CE strategies, tend to involve a wider variety of materials than in the for-profit CE (unruly left-over materials, outdated furniture, bicycle components typically discarded), and occur within a wider range of economic dynamics (including informal and non-monetary encounters). We also identified four characteristics that pattern these diverse activities and relations: diversified material value and purpose, redefined work, social embeddedness, and resilience in the face of precarity.DiscussionBased on these results, we make the case that a diversified circular economy might be crucial for our collective wellbeing in critical futures: it includes more diverse actors, is more materially creative, includes a wider skill-set and is more tethered to local community approaches to provisioning. Lastly, the paper highlights why and how structural barriers related to spatial planning and financial investment need to be overcome in order to support diverse circularities.

The anthropogenic material in-use stocks accumulated in products, buildings, and infrastructure are essential for satisfying basic human demands and ensuring well-being. They drive global resource demand and environmental impacts while representing valuable resource reservoirs for potential recycling through urban mining. A high-resolution understanding of global material in-use stocks was achieved by integrating reconciled night-time light imageries with national stock data on primary construction materials, including steel, aluminum, and cement. The integration enabled the estimates of global stocks from 2000 to 2019 at a 500 × 500 m grid resolution. The updated dataset mitigated saturation and blooming effects in prior satellite data compared to previous datasets, offering refined temporal and geographical representations despite some regional variations. The refined results systematically elucidate the spatiotemporal dynamics of material accumulation worldwide, highlighting distribution discrepancies between and within cities. The comprehensive database serves as a helpful resource for supporting waste management, circular economy, spatial planning, urban sustainability, and climate change mitigation efforts across various geographical scales.

The economic recovery of anodes in lithium‐ion batteries remains challenging due to their low value. Here, the study presents a cross‐sector battery‐plastic co‐upcycling strategy that transforms spent graphite anodes into bifunctional photothermal catalysts for efficient Polyethylene terephthalate (PET) depolymerization. Upon reaction with ethylene glycol (EG), lithiated graphite spontaneously enables copper foil detachment, graphite regeneration, and in situ formation of organolithium species (C2H4O2Li2‐xHx). The resulting catalyst system achieves 95% PET conversion and 64.6% BHET yield within 15 minutes under 0.71 W/cm2 sunlight. Mechanistically, a synergistic effect between solid electrolyte interphase (SEI)‐derived Li2CO3/Li2O and organolithium intermediates significantly accelerates glycolysis. Techno‐economic modeling for a 90 000 ton/year facility reveals a minimum selling price of $0.956/kg for BHET and annual energy savings of 5.039 × 1011 kJ. This work highlights a scalable, low‐cost approach to integrate battery and plastic waste recycling, offering a new paradigm for sustainable urban mining and circular polymer economy.

The rapid deployment of solar photovoltaic (PV) systems has created a growing challenge in managing end-of-life panels. While many studies project future recycling potential, they are often limited by the lack of data on existing distributed PV installations. To address this need, we developed SolarScope, an open-source model that integrates computer vision (CV) with dynamic material flow analysis (dMFA) to automatically identify distributed PV panel areas and evaluate the urban mining potential. By leveraging satellite imagery and Vision Transformer (ViT) models, SolarScope achieves an Area under the Receiver Operating Characteristic Curve (AUROC) of 0.93 for classification and a Dice Similarity Coefficient (Dice) score of 0.90 for segmenting distributed PV installations. A case study in Kamakura, Japan, demonstrates the model's transferability and its ability to support material recovery assessments at fine spatial scales. We present a methodological framework that combines CV with dMFA to bottom-up estimate the regional material stock and recycling potential of distributed PV systems, providing a scalable solution to overcome data limitations in conventional material flow analysis and contributing to circular economy advancement.