Supply Risk Research Articles

Integrating machine learning and deep learning for enhanced supplier risk prediction

The importance of anticipating and preventing disruptions is underscored by the increased operational complexity and vulnerability caused by advancements in supply chain management (SCM). This has spurred interest in integrating machine learning (ML) and deep learning (DL) into supply chain risk management (SCRM). In this paper, we introduce a tailored method using ML and DL to improve SCRM by predicting supplier failures, thus boosting efficiency and resilience in SC operations. Our method involves five phases focused on classifying and predicting supplier failures in non-conforming deliveries. This involves forecasting failure quantities and estimating total disruption costs. Initially, data from an automotive company is selected, and appropriate potential features and algorithms are selected, performance metric aligns with case study objectives, facilitating method evaluation are used such as: Precision, recall, F1-score, and accuracy metrics assess classification models, while Mean Squared Error (MSE) is used for regression tasks. Finally, an experimental design optimizes models, assessing success rates of various algorithms and their parameters within the chosen feature space. Experimental results underscore the success of our methodology in model development. In the classification task, the Random Forest (RF) classifier achieved 86% accuracy. When combined with the Gradient Boosting classifier, the ensemble exhibited enhanced accuracy, highlighting the complementary strengths of both algorithms and their synergistic impact, surpassing the performance of RF, Support Vector Regression (SVR), k-Nearest Neighbors (KNN), and Artificial Neural Network (ANN). Noteworthy is the performance in regression tasks, where Linear Regression, ANN, and RF Regressor displayed exceptionally low MSE compared to other models.

A critical review of machine learning applications in supply chain risk management

This article examines the transformative role of Machine Learning (ML) in Supply Chain Risk Management (SCRM), emphasizing its ability to enhance risk prediction and mitigation through real-time, data-driven insights. It demonstrates how ML applications like demand forecasting, inventory optimization, supplier risk assessment, and fraud detection improve supply chain resilience by analyzing large datasets to identify patterns, predict risks, and recommend proactive actions. However, the article also highlights key challenges, including data quality, availability, and privacy issues, which limit the effectiveness of ML models. Integrating ML with legacy systems poses additional technical and financial difficulties, particularly for smaller businesses. High implementation costs and scalability constraints further hinder widespread adoption. Ethical concerns, such as data bias and privacy, still need to be explored, raising questions about responsible ML use in supply chains. Future research should address these gaps by improving data governance frameworks for accuracy and privacy, developing scalable ML models suited to various supply chain environments, and exploring synergies with technologies like blockchain and the Internet of Things (IoT). These advancements will help realize ML’s full potential, fostering more agile, transparent, and resilient supply chains capable of navigating complex global risks. By tackling these challenges, ML can shift SCRM from reactive to proactive, ensuring long-term operational continuity and a competitive edge in the evolving global market.

Information model for assessing the impact of tactical material procurement risks on order fulfillment in make-to-order manufacturing

Manufacturing businesses are showing increased interest in the issue of supply risks for materials and components. In recent decades, numerous studies and reviews have been published on the subject of supply chain risks. However, most research examines the global impact of risks on business as a whole and proposes a multi-level procedure for identifying, assessing, and developing risk mitigation measures, which should be carried out in advance with the involvement of specialists and experts. Nevertheless in maketo-order manufacturing, it is important to assess the risks of material supply for individual production orders, at the same time taking into account constant changes in production state and supply chains. The problem of assessing the risks of material supply gets even more complicated at enterprises with a high mix of manufactured products. To solve the above-mentioned problems, the authors propose an automated model for risks evaluation. The model is implemented as a component of the enterprise's information system (ERP) and uses data from the technological, production, inventory, and logistics modules to calculate the probability of deviation in order fulfillment time from the planned schedule due to potential disruptions in material supply chains. When executing the model, it analyzes the production's material requirements in both volumetric and calendar terms, inventory levels, and the condition of supply channels. The risks of delayed delivery for each material are expressed as the standard deviation of the delivery date from the planned date and are calculated by composing the risks for segments (elements) of the supply chain, the risks for which are, in turn, calculated based on performance data accumulated in the logistics module, with the possibility of introducing correction coefficients and expert evaluations. The overall risk of order material supply is determined by summing up the delivery risks of individual materials, expressed as the corresponding standard deviations. The model's results can be used for managerial decision-making in production and procurement or for communicating expected order fulfillment times to customers. The model has been tested at an enterprise in the electrical engineering industry.

Design of Blockchain and Strategic Financing Service under the Platform Economy

The capital constrains and uncertainties in supply disruptions faced by small and medium-sized suppliers pose critical challenges for the development of e-commerce platforms. In response, platforms have begun offering direct financing (PDF) to their suppliers alongside traditional bank credit financing (BCF). Within the private (consortium) blockchain, the platform and the supplier (and the bank) achieve consensus on financial smart contract, enabling the execution of flexible contracts tailored to suppliers’ risk profile. We develop a game-theoretic model to examine the terms of smart contracts in different blockchains and further investigate the platform's optimal blockchain design. We find that PDF serves to safeguard the platform's commission income from high-interest BCF. Our analysis reveals that PDF is more likely to be provided to a risky supplier within the consortium blockchain, contrasting with outcomes observed within the private blockchain. As a result, the platform and the supplier could reach win-win, or win-lose outcomes within the private blockchain; while within the consortium blockchain, they tend to result in win-win or lose-win outcomes. Such incentive conflict could potentially hinder blockchain adoption. Our findings further provide the managerial insights guiding the platform's blockchain design: adopting consortium blockchain under moderate market potential and low or high supplier's risk, and adopting private blockchain otherwise. Furthermore, we consider the supplier's endogenous effort on reducing risk, and numerically demonstrate that blockchain may encourage or discourage the supplier's effort. Our research complements previous studies by investigating the interaction between the PDF provision and blockchain structures under uncertain supply disruption risk.

Research on OEM/ODM supply chain decision-making considering supply risk

Research on OEM/ODM supply chain decision-making considering supply risk

Integrating risk management in implementing circular economy principles in the healthcare sector: a case study from Indonesia

Purpose The purpose of this study is to explore the integration of risk management and circular economy (CE) principles within the healthcare sector to promote sustainability and resilience. Specifically, the study aims to demonstrate how risk management can support the transition to a circular economy in healthcare supply chains. By integrating risk management practices with CE principles, healthcare organizations can identify potential risks and opportunities associated with circular initiatives. Design/methodology/approach This study adopts a qualitative research approach, using a case study methodology with semi-structured interviews conducted at primary care facilities to understand the application of CE principles in practice. The study uses fuzzy logic methods to assess and mitigate risks associated with strategies promoting CE principles. Additionally, key performance indicators are identified to evaluate the effectiveness and enhance the resilience of these strategies within healthcare supply chains. Findings The study highlights the critical role of robust risk management strategies in facilitating the transition to a circular economy within healthcare organizations. Primary care facilities, which are critical to frontline healthcare delivery, are particularly vulnerable to product shortages due to supply risks. This study focuses on critical protective equipment, specifically latex gloves and assesses operational risks, including supply, demand and environmental risks, using a fuzzy logic-based model. Import delays were found to be a moderate risk, typically occurring once a year. The research highlights critical KPIs for a successful CE transition within healthcare supply chains, such as on-time delivery and service quality, which are directly related to the risk of supply chain disruption. In addition, the study highlights the significant impact of other CE strategies on healthcare supply chains, including localized production and manufacturing, innovation in product development, reverse logistics, closed-loop supply chains and the adoption of lean principles. Practical implications This study provides valuable insights for healthcare organizations to optimize resource efficiency, reduce waste and promote circularity in their operations. By implementing the proposed solutions and focusing on the identified KPIs, organizations can develop strategies to achieve sustainability goals and enhance resilience in healthcare supply chains. Originality/value This study contributes to the literature by demonstrating the application of risk management in facilitating the transition to a circular economy in the healthcare sector. The use of fuzzy logic methodology offers a novel approach to assessing and mitigating risks associated with critical product failures in supply chain activities. The study’s findings provide practical guidance for healthcare organizations seeking to integrate circular economy principles and improve sustainability performance.

Developing resilience strategies amid supply chain risks in the automotive industry: A stakeholder theory perspective

AbstractManaging automotive supply chain risks contributes to achieving sustainability goals, including ensuring business continuity, maintaining production and delivery schedules, and reducing environmental impact. Therefore, this study aims to investigate the risks confronting the supply chain in the automotive industry through the moderating effect of reactive and proactive resilience strategies. The stakeholder theory perspective was used in this study to examine supply chain risk in the automotive industry. A quantitative method was employed, resulting in 157 valid responses. The results reveal that demand risk had the most significant effect on auto dealer performance, followed by logistics/transportation, production, and supply risk. Notably, proactive resilience strategies were found to significantly impact the relationship between risk and performance. The findings underscore the importance of proactive measures in mitigating the performance impacts of supply chain risk. This study contributes a theoretical framework by identifying four major supply chain risks and seven proactive and 12 reactive strategies. In addition, the study was conducted through the lens of stakeholder theory, emphasizing the importance of suppliers, manufacturers, and dealers cooperating to establish a reliable supply chain.

Urban Sprawl and Imbalance between Supply and Demand of Ecosystem Services: Evidence from China’s Yangtze River Delta Urban Agglomerations

The contradiction between ecological resource protection and urban sprawl in urban agglomeration areas is becoming more and more prominent, facing a serious imbalance between the supply and demand of ecosystem services. To analyze the impact of urban agglomeration expansion on regional ecosystem services, based on multi-source data, an assessment model of supply and demand of ecosystem services for water conservation, carbon sequestration, soil conservation and crop production was constructed. With the help of value transformation model and spatial analysis method, this paper explores the risk of ecosystem service supply and demand imbalance faced by the Yangtze River Delta urban agglomeration in the process of expansion. This study found that the supply capacity of ecosystem services in the YRDUA has continued to decline at the spatial pixel scale; ecosystem service value deficits are a common problem in the YRDUA, with cities around Taihu Lake, such as Shanghai and Suzhou, being the most serious; the value surplus areas are concentrated in the southern cities, such as Xuancheng and Chizhou, but the balance between the supply of and demand for ecosystem services in these cities is also facing a challenge as the cities are expanding. This study analyzed the spatial pattern changes in the Yangtze River Delta region in the context of urban sprawl from the perspective of ecosystem service supply and demand, which helps to clarify the changing ecosystem service dynamics of the region and guide the formulation of urban planning policies and to achieve a balance between ecological supply and demand as well as sustainable development.

Sustainability inspired fabrication of next generation neurostimulation and cardiac rhythm management electrodes via reactive hierarchical surface restructuring

Over the last two decades, platinum group metals (PGMs) and their alloys have dominated as the materials of choice for electrodes in long-term implantable neurostimulation and cardiac rhythm management devices due to their superior conductivity, mechanical and chemical stability, biocompatibility, corrosion resistance, radiopacity, and electrochemical performance. Despite these benefits, PGM manufacturing processes are extremely costly, complex, and challenging with potential health hazards. Additionally, the volatility in PGM prices and their high supply risk, combined with their scarce concentration of approximately 0.01 ppm in the earth’s upper crust and limited mining geographical areas, underscores their classification as critical raw materials, thus, their effective recovery or substitution worldwide is of paramount importance. Since postmortem recovery from deceased patients and/or refining of PGMs that are used in the manufacturing of the electrodes and microelectrode arrays is extremely rare, challenging, and highly costly, therefore, substitution of PGM-based electrodes with other biocompatible materials that can yield electrochemical performance values equal or greater than PGMs is the only viable and sustainable solution to reduce and ultimately substitute the use of PGMs in long-term implantable neurostimulation and cardiac rhythm management devices. In this article, we demonstrate for the first time how the novel technique of “reactive hierarchical surface restructuring” can be utilized on titanium—that is widely used in many non-stimulation medical device and implant applications—to manufacture biocompatible, low-cost, sustainable, and high-performing neurostimulation and cardiac rhythm management electrodes. We have shown how the surface of titanium electrodes with extremely poor electrochemical performance undergoes compositional and topographical transformations that result in electrodes with outstanding electrochemical performance.

Microwave-assisted alkaline fusion followed by water-leaching for the selective extraction of the refractory metals tungsten, niobium and tantalum from low-grade ores and tailings

The refractory metals tungsten, tantalum and niobium are considered critical raw materials in Europe. Diversifying the supply of such materials, for instance by recovering refractory metals from local low-grade ore materials could reduce their supply risks. However, the extraction processes require to be efficient with a low energy and material consumption and a minimal environmental impact. In this work, microwave (MW) assisted alkaline fusion was explored to extract tungsten from scheelite containing ore materials with different grades (high to very low) and tantalum and niobium from a columbite-tantalite [(Fe,Mn)(Nb,Ta)2O6] concentrate. During the fusion process scheelite was converted into soluble alkali tungstate salts [Na2WO4, K2WO4 and/or K3Na(WO4)2] and the reaction temperature could be lowered to 150–200 °C by fusion with a low-melting eutectic alkali salt system of an 1:1 (m/m) NaOH:KOH mixture. The application of MW-assisted heating allowed for fast and volumetric heating, thereby lowering reaction times to 10 min – 30 min. After fusion, tungsten was extracted by a simple water leaching step leading to extraction efficiencies ranging from 77 % to 97 %. Noteworthily, also P, S and As, which all form soluble oxyanions were extracted from the studied materials. Extraction of niobium and tantalum was also achieved though MW-assisted alkaline fusion as an alternative to acidic fluorine-based hydrometallurgical processes. MW-assisted heating allowed for a fast conversion of the (Fe,Mn)(Nb,Ta)2O6 into alkali tantalate and niobate salts. Under optimal conditions, MW-assisted fusion with KOH (salt:sample = 3:1 (m/m)) at 400 °C for 10 min leached ca. 74 %–88 % of tantalum and 77 %–86 % of niobium into water (L/S=10) at 40 °C for 120 min, while the main matrix elements Mn and Fe displayed limited dissolution (<4%). Due to the low solubility of sodium tantalate and niobate salts in water, MW-assisted alkaline fusion in an eutectic NaOH:KOH mixture followed by water leaching was not efficient.

Risks of sanitation and water supply in Pontianak City poorer areas settlements

Abstract The availability of sufficient and safe drinking water is one of the criteria for a settlement to be declared as a poorer area. Areas declared as poorer areas by the city government have water supply problems that require intervention. The Sanitation Risk Index is calculated using a questionnaire on households regarding sanitation conditions and water supply. This research examines the relationship between the Sanitation Risk Index and its effect on water use, as well as the strategies implemented to reduce sanitation risks in water supply in poorer areas in Pontianak City, West Kalimantan. The city of Pontianak is located downstream of Kapuas River. Many settlements grow along riverbanks and require clean water and adequate sanitation facilities. This study began with an assessment of sanitation conditions and clean water supply with a sanitation risk assessment using a questionnaire in poorer areas. The results of the questionnaire led to calculation of the Sanitation Risk Index (IRS). Descriptive and statistical analyses show the relationship between IRS and water supply. In obtaining the water supply strategy carried out here, it was found that more than 50% of the population uses refillable water for drinking; however, rainwater and river water are still used by poorer area settlements for daily activities. The sanitation risk index was 350, indicating the influence of sanitation risk on the quality and supply of water in Pontianak City poorer area settlements. There are urgent problems that must be resolved in the clean water supply sector in the studied poorer areas.

Optimizing Market Efficiency through Blue Economy: Supply Chain and Risk Analysis of Tuna Fisheries in South Coastal East Java

Optimizing Market Efficiency through Blue Economy: Supply Chain and Risk Analysis of Tuna Fisheries in South Coastal East Java

Will future copper resources and supply be adequate to meet the net zero emission goal?

The fact that in recent times mineral exploration has been disappointing and that transition to clean energy to achieve net zero emission by 2050 will place extraordinary pressure on copper demand, are beyond dispute. The critical question is to what extent will copper supply be capable of satisfying growing demand in a net zero future. Reality is that global copper resources have been growing significantly and steadily for decades despite increasing mine production. Besides, with dwindling exploration discoveries, this increase is primarily attributable to expansion of the resources of existing deposits through a combination of better progressive delineation and re-assessment of classification of resources in response to economic and technological changes, the so-called Australasian Joint Ore Reserves Committee (JORC) ‘modifying factors’. Analysis of MinEx Consulting's global mineral deposit database indicates that just the resources of deposits discovered since 2010 have been growing at estimated Compound Annual Growth Rates (CAGRs) in the range 7.5% to 15.5%, but greater additional tonnage is associated with deposits discovered before 2010. The result is that tens of millions of tonnes of copper are added to the inventory each year, notwithstanding increasing production and mounting Environmental, Social and Governance (ESG) pressure sterilising some deposits. In essence, copper supply shortages are unlikely to result from depletion of copper resources but rather from possible inadequacy of mining and processing capacity. Geopolitical supply risk is also low compared to some other critical metals (e.g., Co and Ni) on account of the large number and geographical dispersion of copper deposits. Increases in price due to a perception of impending scarcity will ensure that future capacity will, at a minimum, continue to grow along its historical 3% CAGR. In addition, it will create strong incentives for above-trend capacity utilisation and improvement in recycling collection and recovery. This will be followed by acceleration of expansion of capacity at many existing mines, and development of deposits at the advanced feasibility stage, releasing copper to market at lower capital cost and on shorter timeframes than exploring for and developing new mines. Estimates of possible levels of above-trend increments in capacity for the various components of the current copper endowment show that, while shortages may occur, they will not be as serious as currently generally expected. This does not mean that net zero emission may not be delayed beyond 2050, but it is more likely that it may be delayed by a range of other constrains and impediments unrelated to availability of copper, and that such delays may give copper supply breathing time.

ESG Performance and its Impact of on Corporate Performance: Take China Everbright Bank as an Example

This paper has investigated China Everbright Bank (CEB)’s performance on ESG and analyzed the impact of ESG performance on CEB’s financial outcome. During the reported period, CEB has been performing well on ESG, especially on social perspective. From environmental perspective, CEB took proactive steps to mitigate its negative environmental impact. This included reducing emission by strictly conduct regulation within the company, assessing environmental risks associated with key industries and clients and setting rules on energy conservation. The bank also prioritized compliance with environmental standards, pollution control, and ecological protection in its credit approval processes. From social perspective, CEB has been actively promoting democracy and equality in employment by combating various discrimination, and continuously ensuring employee welfare besides wages, such as health care and skill training. Regarding governance, CEB has adopted strict supervision on its supply chain, strengthening the management of the procurement process by establishing an intelligent procurement platform. It has also emphasized supplier risk management. Considering the financial metrics of CEB in last years, the study suggests that the long-term profitability, operational capacity and growth potential of CEB have been positively affected, while the market value and the solvency are not. The paper concludes that ESG criteria can be considered as a reliable tool in business evaluation of potential and sustainability, therefore incorporated into business operation and investment.

White phosphorus production by a carbothermic reduction of upcycled crude phosphoric acid

White phosphorous is a critically important material in manufacturing semiconductors and advanced pharmaceuticals. However, white phosphorus is produced by only four countries using the huge energy-consuming electric arc furnace process. These four countries have resorted to banning or restricting their exports causing a supply risk for white phosphorus for many industrialized countries.To meet the white phosphorous supply risk, the never-existing white phosphorous production process has been developed by applying the carbothermic reduction of P2O5 gas provided by the thermal decomposition of phosphoric acid. The novel process can produce semiconductor-grade high-purity white phosphorous from crude phosphoric acid recovered from secondary phosphorous resources.By supplying phosphoric acid in the form of small droplets, we have achieved continuous operation of white phosphorus production, which was previously impossible, and brings production efficiency to an industrial level. This process could significantly reduce the supply risk for countries that rely entirely on imported white phosphorus.

Resilient water infrastructure partnerships in institutionally complex systems face challenging supply and financial risk tradeoffs

As regions around the world invest billions in new infrastructure to overcome increasing water scarcity, better guidance is needed to facilitate cooperative planning and investment in institutionally complex and interconnected water supply systems. This work combines detailed water resource system ensemble modeling with multiobjective intelligent search to explore infrastructure investment partnership design in the context of ongoing canal rehabilitation and groundwater banking in California. Here we demonstrate that severe tradeoffs can emerge between conflicting goals related to water supply deliveries, partnership size, and the underlying financial risks associated with cooperative infrastructure investments. We show how hydroclimatic variability and institutional complexity can create significant uncertainty in realized water supply benefits and heterogeneity in partners’ financial risks that threaten infrastructure investment partnership viability. We demonstrate how multiobjective intelligent search can design partnerships with substantially higher water supply benefits and a fraction of the financial risk compared to status quo planning processes. This work has important implications globally for efforts to use cooperative infrastructure investments to enhance the climate resilience and financial stability of water supply systems.

Competing buyers’ investment and ordering strategies under supply disruption

Supply chain disruptions can be costly and disruptive, and reducing supplier uncertainty through investments can be an effective strategy for mitigating these risks. In this study, we explore ordering and investment strategies in a downstream competitive environment, considering supply uncertainty. We consider two buyers ordering from a single supplier and competing in a Cournot market. Buyers must balance investment benefits against costs when making investment decisions. We find that without downstream competition, a relatively low investment proportion can yield a “win-win” outcome. Under downstream competition, an increased number of investors does not necessarily lead to higher supplier reliability. When both buyers invest at a high ratio, the significant decline in order quantities may results in lower supplier reliability. When there is only one investing buyer in the market, even though the competitor may benefit from spillover reliability enhancement — free-riding, the buyer may also be willing to provide an investment subsidy to improve the supplier’s reliability. When both buyers invest at a moderate ratio, downstream competition may benefit all supply chain members. Moreover, increasing wholesale price differentiation and endogenous investment ratios can effectively reduce free-riding behavior of the non-investing buyer. These findings have practical implications for supply chain managers aiming to reduce supply risks and allocate investment resources efficiently.

Ecosystem Services’ Supply–Demand Assessment and Ecological Management Zoning in Northwest China: A Perspective of the Water–Food–Ecology Nexus

The coordinated development of the water–food–ecology (WFE) nexus is a practical issue that has to be addressed urgently for northwest China’s (WTL) sustainable development. Optimizing the linkage relationship and accomplishing the rational distribution of resources from the perspective of the supply and demand for ecosystem services (ESSD) are imperative. Thus, in this study, a numerical indicator system for ESSD from the perspective of the WFE nexus was constructed with the incorporation of the water and carbon footprint. Based on this premise, the ecological management zoning method was enhanced by integrating supply and demand risks, and optimization suggestions were proposed for various zones. The results showed that (1) carbon sequestration (CS), food production (FP), and water yield (WY) supply and demand significantly increased between 2000 and 2021. High ESSDs were concentrated in the west side of northwest China. Maize, wheat, cotton, vegetables, and garden fruits had a higher demand for ecosystem services (ESs). (2) The three ESSDs were bound in a synergistic relationship. The synergy between supply exhibited significant spatial heterogeneity, while the synergies between demand showed similar distribution patterns. (3) Regarding quantity matching, the supply for FP and CS surpassed demand, while the WY supply could not meet the demand. The three ESs’ supply and demand deficits rose. Ecological supply–demand ratio (ESDR) regional differentiation for the three ESs was apparent. Regarding spatial matching, FP and CS concentrated on low supply–low demand, while WY focused on high supply–high demand. FP risk was concentrated in Qaidam Basin, whereas WY risk was mostly in Hexi inland river basin (HX), the Yellow River Basin area (HH), and both sides of the “Qice line”. (4) The ecological management zones were formed by integrating WTL’s three dominant weak functional zones, four categorized strategy regions, and four governance models. This study can serve as a scientific benchmark for regional ecological management, which is significant in ensuring northwest China’s water, food, and ecological safety.

Sustainable purchasing supply management assessment in construction supply chains: a design science research approach

Purpose In response to multiple disruptions, the purchasing supply management (PSM) function in construction supply chain management (CSCM) has gained prominence due to stakeholder pressures, dynamic market conditions and the need to adhere to complex sustainability, safety and health regulations and standards. However, there is a noticeable absence of empirical research on measuring and mitigating PSM vulnerabilities, especially considering the distinct challenges faced by large engineer-to-order project-oriented manufacturers. To address these issues, the purpose of this study is to develop and test a novel method to assist companies in construction supply chains in assessing and managing risks associated with sustainable procuring and sourcing materials. Design/methodology/approach Grounded in the literature gaps on construction PSM and a real case supply chain, the research uses the design science research (DSR) approach to develop an integrated method for assessing PSM strategies in this sector. The method integrates three essential purchasing dimensions: supply risks, profit impact and sustainability risks of materials, supported by nine subdimensions. Empirical validation took place within a multinational European construction company based in Denmark. Findings Findings from the supplier–buyer relationships confirmed that the developed method allows for the identification of the key components that significantly impact supplier–buyer relationships, profitability and sustainability. The research further suggests that construction supply chain managers and purchasing practitioners can use the proposed method to evaluate PSM, thus enabling them to make more informed decisions. Practical implications Through the utilization of the proposed artifact, construction companies can take a more proactive approach to address PSM uncertainties, thereby enhancing their competitiveness in dynamic construction supply chains. Originality/value The research contributes to bridging the theory and practice, providing valuable assistance for construction companies assessing and managing the PSM and supply risks within global construction value chains. This paper provides original insights for the CSCM, aiding in adopting competitive PSM strategies to improve overall supply chain performance.

Leaching of Rare Earths from End-of-Life NdFeB Magnets with Citric Acid Using Full Factorial Design, Response Surface Methodology, and Artificial Neural Network Analysis

In recent years, the increasing demand and rising prices of rare earth elements (REEs), along with their attendant supply risk (about 95% of these elements are supplied by China), have led the European Commission to consider REEs as critical raw materials. Developing and optimizing processes for recovering REEs from secondary sources such as NdFeB magnets is fundamental in this context. A novel method to recover REEs by leaching with citric acid and subsequently separating these elements using the solvent extraction method has been introduced. Therefore, this research investigates the leaching efficiency of REEs, Fe, and B from NdFeB magnets. A full factorial design, with 18 experimental setups, was conducted to optimize the citric acid concentration (1–3 mol/L), leaching time (1–3 h), and solid–liquid ratio (5–10%wt./vol.). All tests were carried out at room temperature and 150 rpm. Different optimizations (response surface methodology (RSM) and artificial neural network (ANN) analysis) are used to maximize the REEs’ leaching efficiency. RSM resulted in a maximum extraction yield of total rare earth elements (TREEs) of about 89% in the investigated experimental plan. This result is similar to that for ANN analysis (about 86%), but more accurate than that for RSM. In fact, for the ANN, an overall R-value higher than 0.99 was obtained. This result indicates that the developed ANN can be used as an accurate model for estimating the leaching efficiencies of REEs from NdFeB magnets.