Search Results (39)

Urban pluvial flooding presents growing challenges for disaster risk management, yet most susceptibility studies rely on watershed-based frameworks that inadequately capture the localized dynamics of urban systems. This study proposes a city-scale flood susceptibility modeling framework for Cincinnati, Ohio. Cincinnati was chosen because it is a city with a documented history of severe urban flooding, including a once-in-a-century storm in 2016. Multi-source historical flood data were compiled from NOAA storm event records and crowdsourced reports to enhance spatial coverage. Four machine learning algorithms (Random Forest, Support Vector Machine, XGBoost, and Logistic Regression) were implemented to identify the most effective approach for urban pluvial flood prediction. Random Forest (RF) and Support Vector Machine (SVM) achieved the highest accuracy (0.84) and demonstrated strong discriminatory power. RF was selected as the optimal model because it had a higher AUC (90%) and the lowest RMSE (0.35). To assess generalizability, the RF model was validated on updated land use data and flood records from a 2020 storm event. It demonstrated robust performance (accuracy = 0.89, RMSE = 0.36, precision = 0.75, recall = 1, and AUC = 0.95), despite urban development changes. This study’s novelty lies in combining multi-source flood records with a grid-based machine learning framework and rigorously validating model robustness under evolving urban conditions. The results advance urban pluvial flood susceptibility modeling and offer actionable guidance for evidence-based flood risk management worldwide. Full article

This paper investigates a novel variant of the two-echelon vehicle routing problem (2E-VRP) within the context of modern e-commerce logistics. The model integrates time windows, occasional trucks, occasional drivers, heterogeneous regular vehicles, and two increasingly relevant types of intermediate facilities: transshipment nodes and parcel lockers. Goods are transported from a first-echelon depot to intermediate facilities via occasional trucks and heterogeneous regular trucks, then delivered to customers through occasional drivers and heterogeneous regular riders at the second echelon, or retrieved by customers from designated parcel lockers. Given significant disparities in service scope, vehicle attributes, delivery rules, and cost structures between the two echelons, the crowdsourcing model for the first echelon is redesigned, and new intermediate facilities are incorporated to expand application scenarios and further enhance the operational advantages of the crowdsourcing mode. The objective aims to minimize transportation costs and minimize customer dissatisfaction costs. This study constructed a two-echelon vehicle routing optimization model under the crowdsourcing mode with time windows and intermediate facilities and developed an improved multi-objective sparrow algorithm (IMOSSA) to solve it. Algorithm comparisons and extensive case studies validate the algorithm’s effectiveness and superiority. Scenario analysis investigates the impact of crowdsourced vehicles on routing decisions, experimentally demonstrates the crowdsourcing model’s advantages, and derives practical managerial insights. Full article

In the field of logistics distribution, the two-echelon vehicle routing problem has long been a critical focus. Against the backdrop of global warming, enterprises conducting logistics operations must now prioritize not only delivery costs but also the environmental impact of carbon emissions. To address these challenges, this study integrates occasional drivers into the two-echelon vehicle routing framework, centering on carbon emission reduction. First, Affinity Propagation (AP) clustering is applied to assign customer points to transfer centers. Subsequently, an optimization model is formulated to minimize both vehicle routing costs and carbon emission costs through a collaborative delivery system involving specialized and crowdsourced vehicles. An enhanced Sparrow–Whale Optimization Algorithm (S-WOA) is proposed to solve the model. The algorithm is tested against traditional heuristic methods on three datasets of different scales. Experimental results demonstrate that the two-echelon logistics and distribution model combining specialized vehicles and occasional drivers achieves a significant reduction in total delivery costs compared to models relying solely on specialized vehicles. Further analysis reveals that, with a fixed crowdsourced compensation coefficient, increasing the crowdsourced detour coefficient leads to a decline in total delivery costs. Conversely, when the detour coefficient remains constant, raising the compensation coefficient results in an upward trend in total costs. These insights provide actionable strategies for optimizing cost-efficiency and sustainability in logistics operations. Full article

Centralized UAV logistics controllers can achieve strong navigation performance in controlled settings, but they do not capture key deployment factors in crowdsourcing-enabled emergency logistics, where heterogeneous UAV owners participate with unreliability and dropout, and incentive expenditure and fairness must be accounted for. This paper presents a decentralized crowdsourcing multi-UAV emergency logistics framework on an edge-orchestrated architecture that (i) performs urgency-aware dispatch under distance/energy/payload constraints, (ii) tracks reliability and participation dynamics under stress (unreliable agents and dropout), and (iii) quantifies incentive feasibility via total payment and payment inequality (Gini). We adopt a hybrid decision design in which PPO/DQN policies provide real-time navigation/control, while GA/ACO act as planning-level route refinement modules (not reinforcement learning) to improve global candidate quality under safety constraints. We evaluate the framework in a controlled grid-world simulator and explicitly report stress-matched re-evaluation results under matched stress settings, where applicable. In the nominal comparison, centralized DQN attains high navigation-centric success (e.g., 0.970 ± 0.095) with short reach steps, but it omits incentives by construction, whereas the proposed crowdsourcing method reports measurable payment and fairness outcomes (e.g., payment and Gini) and remains evaluable under unreliability and dropout sweeps. We further provide a utility decomposition that attributes negative-utility regimes primarily to collision-related costs and secondarily to incentive expenditure, clarifying the operational trade-off between mission value, safety risk, and incentive cost. Overall, the results indicate that navigation-only baselines can appear strong when participation economics are ignored, while a deployable crowdsourcing system must explicitly expose incentive/fairness and robustness characteristics under stress. Full article

With the rapid growth of e-commerce and rising demand for faster, reliable last mile delivery, optimizing the spatial layout of terminal logistics facilities is critical. This paper proposes a two-stage location framework for mini-depots and lockers considering spatiotemporal customer demand. In the first stage, Affinity Propagation (AP) clustering identifies candidate mini-depot locations and locker layouts based on temporal and spatial demand characteristics. In the second stage, an Adaptive Heuristic Electric Eel Foraging Optimization (AHEEFO) determines the optimal mini-depot location strategy to minimize total cost. A dataset of 1157 Beijing customer points, including latitude, longitude and demand information, is used for model validation. Results show that Scenario 2, with dispersed demand, outperforms Scenario 1 and traditional strategies in both total cost and customer satisfaction; dispersed demand can be effectively supported via crowdsourced delivery and locker layout, whereas concentrated demand requires more professional courier resources. Comparative experiments reveal AP clustering is more stable, reducing clustering-stage cost by 13.57% compared with K-means, and AHEEFO outperforms other algorithms in cost optimization, computational efficiency, and significance tests under random demand surges. Finally, the sensitivity analysis highlights the effects of different algorithmic and operational parameters, offering valuable insights for both managerial practice and academic research. Full article

Background: Over the past decade, the growth of ecommerce and omnichannel order fulfillment has led to a spike in last-mile delivery services. Last-mile delivery being the most expensive portion of the supply chain has resulted in process improvement initiatives by industry and academia targeting lower operational costs. Methods: In this study, we use simulation to account for the daily randomness regarding order quantities with missed deliveries being rolled over to the next period and attrition of the capacities used to meet the demand for each period. Further, to alleviate the impact on operations due to attrition, we consider the use of automation as a replacement for permanent capacity. Results: From the simulation results, we observe that the negative operational impact of employee turnover can be overcome with a combination of delivery robots and crowdsourcing with a payback period as short as 1.55 years. Conclusions: Optimal resource allocation is further refined by the use of simulation. The use of advanced automation such as robots seems to be a viable option for businesses to lower operational costs for some scenarios. Full article

The importance of Last-Mile Delivery (LMD) in the current economy cannot be overstated, as it is the final and most crucial step in the supply chain between retailers and consumers. In major cities, absent intervention, urban LMD emissions are projected to rise by >30% by 2030 as e-commerce grows (top-100-city “do-nothing” baseline). Sustainable, innovative ground-based solutions for LMD, such as Electric Vehicles, autonomous delivery robots, parcel lockers, pick-up points, crowdsourcing, and freight-on-transit, can revolutionize urban logistics by reducing congestion and pollution while improving efficiency. However, developing these solutions presents challenges in Operations Research (OR), including problem modeling, optimization, and computations. This systematic review aims to provide an OR-centric synthesis of sustainable, ground-based LMD by (i) classifying these innovative solutions across problem types and methods, (ii) linking technique classes to sustainability goals (cost, emissions/energy, service, resilience, and equity), and (iii) identifying research gaps and promising hybrid designs. We support this synthesis by systematically screening 283 records (2010–2025) and analyzing 265 eligible studies. After the gap analysis, the researchers and practitioners are recommended to explore new combinations of innovative solutions for ground-based LMD. While they offer benefits, their complexity requires advanced solution algorithms and decision-making frameworks. Full article

Driven by the green and low-carbon transformation of urban logistics, the integration of crowdsourced delivery and green transportation is considered an important pathway to achieving sustainable last-mile delivery. This study focuses on urban crowdsourced delivery using cargo bikes and develops an extended behavioral model based on the Theory of Planned Behavior (TPB). The model systematically examines the key factors influencing the public’s behavioral intention (BI) to participate as crowdshippers. While retaining the core structure of TPB, the model incorporates external variables—perceived risk (PR), policy support (PS), and infrastructure conditions (IC)—to improve its explanatory power and applicability to real-world delivery scenarios. A questionnaire survey was conducted in South Korea, yielding 600 valid responses. The results indicate that usage attitude and perceived behavioral control exert significant positive effects on BI. PR has a significant negative effect on both attitude and BI. PS indirectly enhances BI by improving attitudes, whereas IC primarily influences BI by strengthening the public’s sense of control. This study not only expands the theoretical explanatory power of the TPB model in the context of green crowdsourced delivery but also provides empirical evidence for policymakers and platform operators. Full article

The rapid growth of e-commerce and surges in shipment volumes have increased the pressure on transport systems, requiring innovations in collaborative logistics where consumers participate in dual roles as receivers and deliverers. However, existing research often addresses these roles in isolation, overlooking the flexibility with which users switch between them. Moreover, the literature has focused predominantly on monetary value in paid crowdsourced or social value in free social delivery, without fully exploring how users perceive value across both models. Addressing these gaps, this study profiles users of collaborative logistics services from both receiver and deliverer perspectives and examines their motivations in paid and unpaid delivery contexts. Based on survey data from 493 participants in Singapore, cluster analysis identified four distinct user segments: hesitators, potential customers, active users, and loyal advocates. The findings indicate that user preferences differ by role, with functional value prioritised in paid delivery and social value more prominent in free models. Free models attract a higher proportion of favourable users, highlighting the significance of non-monetary incentives. This study contributes to the literature by offering an integrated perspective on user roles and value perceptions and provides practical insights for developing more inclusive, community-oriented last-mile logistics solutions. Full article

Driving at night is riskier in terms of crash involvement than it is during the day. Fortunately, it is clearly established that illumination on roadways can reduce the number and severity of nighttime crashes. However, state and municipal departments of transportation (DOTs) lack the available illumination data. Therefore, the objective of this research is threefold, as follows: (i) to develop machine learning models that use readily available roadway characteristic data to predict the severity of nighttime crashes; (ii) determine the effect that illumination has on crash severity; and (iii) develop a tool to assist DOT decision makers in collecting illumination data. To accomplish this objective, we have extracted data from the Texas Department of Transportation (TxDOT) Crash Record Information System (CRIS) database, which was then further split into a training and a test dataset. Then, seven machine learning techniques, namely binary logistic regression, k-nearest neighbors, naïve Bayes, random forest, artificial neural network, Extreme Gradient Boosting (XGBoost), and a Long Short-Term Memory (LSTM) model, were all applied to the unseen test data. The random forest model produced the most promising results by predicting severe crashes with 97.6% accuracy. In addition, we conducted a pilot study to test the collection of illumination data using a light meter. In the future, we aim to complete the development of a smartphone application, which can be used in conjunction with the random forest model presented in this paper, to collect crowdsourced illumination data and predict nighttime crash hotspots. This may assist DOT decision makers to prioritize funding for illumination at the hot spots. Full article

Green logistics has gained significant attention in recent years due to increasing pollution levels and their negative effects. This area of research is crucial as governments and countries worldwide recognize the severity of pollution and its detrimental effects. Despite progress, significant gaps remain due to the lack of advanced models that consider additional factors and the influence of speed on their outcomes. This paper presents a case study on the Volume-based Pollution-Routing Problem with Time Windows (VPRPTW). The objective is to minimize CO${}_2$ emissions and improve customer satisfaction using a fleet of delivery vehicles. We propose a mathematical model and a probabilistic Tabu Search (TS) algorithm to solve the studied VPRPTW. The study revealed a decrease in daily fleet size from 16 to 12, indicating improved operational efficiency. In our study, we evaluate the impact of vehicle speed on fuel consumption and compare the results with a constant route speed to those obtained at varying speeds. Computational experiments reveal a significant difference of over 20% between fixed and variable speed assumptions. Additionally, we confirm that distance alone does not always correlate with energy consumption and CO${}_2$ emissions. This highlights the importance of considering variable speeds in routing problems to assist logistics companies, urban planners, and policymakers achieve more accurate and environmentally friendly transportation solutions. Full article

Motivated by the collaboration of a takeout platform and a crowdsourced delivery platform, we developed a stylized model to explore the interplay between the two platforms’ decisions. We captured the cross-platform network effects of the two complementary platforms, and investigated how the collaboration between the two platforms shapes the optimal prices, platform profits, and social welfare. We found that the takeout platform optimally adopts a subsidy pricing strategy when its commission rate is relatively high. In addition, when the demand-side network effect coefficient increases, the delivery platform optimally raises the shipping fee to trigger a larger supply of drivers. Furthermore, we found that the takeout platform introducing a self-logistics service reduces the subsidy intensity and raises the subsidy threshold. It also reshapes the strategic two-sided pricing to increase the network benefit when the network effect coefficient grows on one side. Specifically, as the supply-side network effect coefficient increases, instead of lowering the delivery price to increase demand and further increase the drivers’ network benefit, the takeout platform optimally raises it under certain conditions. Finally, self-logistics may benefit the takeout platform, while hurting the delivery platform, and it can increase social welfare. Our results, thus, unveil a price regime for platform collaboration and validate the effectiveness of the introduction of self-logistics by takeout platforms. Full article

Background/Objectives. This study aimed to improve machine learning models for diagnosing interstitial cystitis/bladder pain syndrome (IC/BPS) by comparing classical machine learning methods with newer AutoML approaches, utilizing biomarker data and patient-reported outcomes as features. Methods. We applied various machine learning techniques to biomarker data from the previous IP4IC and ICRS studies to predict the presence of IC/BPS, a disorder impacting the urinary bladder. Data were sourced from two nationwide, crowd-sourced collections of urine samples involving 2009 participants. The models utilized included logistic regression, support vector machines, random forests, k-nearest neighbors, and AutoGluon. Results. Expanding the dataset for model training and evaluation resulted in improved performance metrics compared to previously published findings. The implementation of AutoML methods yielded enhancements in model accuracy over classical techniques. The top-performing models achieved a receiver-operating characteristic area under the curve (ROC-AUC) of up to 0.96. Conclusions. This research demonstrates an improvement in model performance relative to earlier studies, with the top model for binary classification incorporating objective urinary biomarker levels. These advancements represent a significant step toward developing a reliable classification model for the diagnosis of IC/BPS. Full article

This study investigates gender-based differences in the satisfaction ranking of riders on real-time crowdsourcing logistics platforms, using online reviews from the Ele.me platform. Quantitative methods, including the frequency ratio-based Analytic Hierarchy Process (AHP), probabilistic linguistic term sets (PLTS), and fuzzy comprehensive evaluation (FCE), were applied to analyze satisfaction differences between men and women riders. The findings reveal an asymmetric pattern in satisfaction preferences: women riders place more emphasis on perceived value, while men riders prioritize service perceived quality. Although both groups rank platform image, product perceived quality, and rider expectations similarly, the importance of these factors varies significantly, indicating an underlying asymmetry in their expectations and values. Women riders express higher satisfaction with platform image, rider expectations, service perceived quality, and product perceived quality, with rider expectations showing the largest difference. Additionally, the multi-criteria decision-making methods used in this study offer insights for optimizing service performance in real-time crowdsourcing logistics platforms, particularly in handling uncertainty and enhancing system adaptability through fuzzy sets. These findings provide a basis for developing gender-specific strategies aimed at enhancing rider satisfaction, minimizing turnover, and improving platform adaptability—contributing to a more inclusive and sustainable logistics supply chain. Full article

Green crowdsourcing mobile applications provide an appropriate supply chain coordination mechanism for deliveries, harnessing benefits for people, profits and the environment. Despite the benefits, the risks and challenges associated with green crowdsourcing undermine the social, economic and sustainability benefits of last mile logistics. We undertook an exploration of the risks of using the green crowdsourcing Dilivari mobile application (App) innovation in South Africa. The study used an exploratory research case study research design. The study included 54 respondents with rich, in-depth knowledge, 49 participants for focus group discussions (FGDs) and five key informant interviews. Our study established security, legal, human and connectivity risks associated with this app. We focused on the risks and challenges in the literature including critical emergent risks in a developing country context, compatibility of technology, load shedding, mobile penetration, and data costs. Furthermore, we highlighted the security risks posed by theft, robberies and terrorism. Full article