Search

As high-speed rail (HSR) and air transportation developed rapidly in the last decade, their coopetition and interactional relationship has reshaped China's urban networks. Based on HSR and flight schedule data from 2009 to 2019, this paper constructs a weighted network to compare China's urban networks and their evolution, and employs machine learning to investigate the potential determinants. The results indicated that both networks tend toward polarization in the overall distribution and that the structure of urban networks under HSR networks is more hierarchical. That of HSR networks gradually forms a corridor structure along the trunk lines, while that of airline networks mainly shows a diamond spatial structure with Beijing, Shanghai, Guangzhou, and Chengdu as the cores. As for the evolution of urban networks, geographical factors, per capita GDP, and the tourism function of cities have more important impacts on that of HSR networks, while the network's topological structure and education resources have a greater impact on that of airline networks. Some socioeconomic attributes, such as urban administrative level, population, and the proportion of tertiary industry, have similar and limited influences on the two networks. • The paper constructed a comparative analysis on the evolution of China's urban networks during the last decade. • Employing machine learning to investigate the potential determinants. • The study examined the distinct attributes of the evolution and structure of high-speed rail and airline networks. • The study contrasts the determinants influencing the evolution of high-speed rail and airline networks at the city level. [ABSTRACT FROM AUTHOR]

The development and functional perfection of urban areas have led to increasingly severe fire risks in recent decades. Previous urban fire risk assessment methods relied on subjective judgment, rough data collection, simple linear statistical methods, etc. These drawbacks can lead to low robustness of evaluation and inadequate generalization ability. To resolve these problems, this paper selects the indicator and regression models based on the high-resolution data of the spatial distribution characteristics of Longquanyi distinct in Chengdu, China. and proposes an integrated machine learning algorithm for fire risk assessment. Firstly, the kernel density analysis is used to map the fourteen urban characteristics related to fire risks. The contributions of these indicators (characteristics) to fire risk and its corresponding index are determined by Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and eXtreme Gradient Boosting (XGBoost). Then, the spatial correlation of fire risks is determined through Moran's I, and the spatial distribution pattern of indicator weights is clarified through the raster coefficient space analysis. Finally, with these selected indicators, we test the regression performance with a backpropagation neural network (BPNN) algorithm and a geographically weighted regression (GWR) model. The results indicate that numerical variables are more suitable than dummy variables for estimating micro-scale fire risks. The main factors with a high contribution are all numerical variables, including roads, gas pipelines, GDP, hazardous chemical enterprises, petrol and charging stations, cultural heritage protection units, assembly occupancies, and high-rise buildings. The machine learning algorithm integrating RF and BPNN shows the best performance (R2 = 0.97), followed by the RF-GWR integrated algorithm (R2 = 0.87). Compared with previous methods, this algorithm reduces the subjectivity of the traditional assessment models and shows the ability to automatically obtain the key indicators of urban fire risks. Hence, this new approach provides us with a more robust tool for assessing the future fire safety level in urban areas. [ABSTRACT FROM AUTHOR]

Predicting and understanding travellers' mode choices is crucial to developing urban transportation systems and formulating traffic demand management strategies. Machine learning (ML) methods have been widely used as promising alternatives to traditional discrete choice models owing to their high prediction accuracy. However, a significant body of ML methods, especially the branch of neural networks, is constrained by overfitting and a lack of model interpretability. This study employs a neural network with feature selection for predicting travel mode choices and Shapley additive explanations (SHAP) analysis for model interpretation. A dataset collected in Chengdu, China was used for experimentation. The results reveal that the neural network achieves commendable prediction performance, with a 12% improvement over the traditional multinomial logit model. Also, feature selection using a combined result from two embedded methods can alleviate the overfitting tendency of the neural network, while establishing a more robust model against redundant or unnecessary variables. Additionally, the SHAP analysis identifies factors such as travel expenditure, age, driving experience, number of cars owned, individual monthly income, and trip purpose as significant features in our dataset. The heterogeneity of mode choice behaviour is significant among demographic groups, including different age, car ownership, and income levels. [ABSTRACT FROM AUTHOR]

Natural environmental factors and human activity intensity factors, the two main factors that affect the spatial and temporal distribution of PM2.5 concentration near the surface, have different mechanisms of action on PM2.5 concentration. In this paper, a GTWR-XGBoost two-stage sequential hybrid model is proposed aiming at detecting the expression of spatiotemporal heterogeneity in the traditional machine learning retrieval model of PM2.5 concentration and the difficulty of expressing the complex nonlinear relationship in the statistical regression model. In the first stage, the natural environmental factors are used to predict PM2.5 concentration with spatiotemporal characteristics by collinearity diagnosis method and Geographically and Temporally Weighted Regression method (GTWR). In the second stage, the simulation results in the first stage and the natural factors eliminated through LUR stepwise regression in the first stage are into the XGBoost model together with the human activity intensity factors in the buffer zone with the best correlation coefficient of PM2.5, and finally the temporal and spatial distribution of PM2.5 concentration. Taking the Chengdu Chongqing Economic Circle as an example, the proposed model is used to retrieve PM2.5 concentration and compared with the single GTWR, XGBoost, and coupling model published recently. The experimental results show that the R2, RMSE, and MAE of the GTWR-XGBoost two-stage model cross-validation are 0.92, 5.44 ug·m−3, and 4.12 ug·m−3, respectively. Compared with the above single models, R2 increased by 0.01 and 0.12, and MAE decreased by more than 0.11 and 3.1, respectively. Compared with the coupling model published recently, R2 is increased by 0.02, and MAE is reduced by more than 0.4. In addition, the PM2.5 concentration in Chengdu Chongqing showed obvious seasonal temporal and spatial changes, and the influence ratios of natural environmental factors and human activity intensity activities factors on PM2.5 were 0.66 and 0.34. The results show that the GTWR-XGBoost two-stage Model can not only describe the heterogeneity and objectively reflect the complex nonlinear relationship between the phenomenon and the influencing factors, but also enhance the interpretability of the phenomenon when simulating the spatiotemporal distribution characteristics of PM2.5 concentration. [ABSTRACT FROM AUTHOR]

A variety of Chinese textual operational text data has been recorded during the operation and maintenance of the high-speed railway catenary system. Such defect text records can facilitate defect detection and defect severity analysis if mined efficiently and accurately. Therefore, in this context, this paper focuses on a specific problem in defect text mining, which is to efficiently extract defect-relevant information from catenary defect text records and automatically identify catenary defect severity. The specific task is transformed into a machine learning problem for defect text classification. First, we summarize the characteristics of catenary defect texts and construct a text dataset. Second, we use BERT to learn defect texts and generate word embedding vectors with contextual features, fed into the classification model. Third, we developed a deep text categorization network (DTCN) to distinguish the catenary defect level, considering the contextualized semantic features. Finally, the effectiveness of our proposed method (BERT-DTCN) is validated using a catenary defect textual dataset collected from 2016 to 2018 in the China Railway Administration in Chengdu, Lanzhou, and Hengshui. Moreover, BERT-DTCN outperforms several competitive methods in terms of accuracy, precision, recall, and F 1 -score value. [ABSTRACT FROM AUTHOR]

Emission inspection of motor vehicles (emission inspection) is a crucial player in solving the problem of motor vehicle exhaust pollution, and research on the features affecting emission inspection results and their importance is a basis for optimizing the environmental management of motor vehicles. However, there is no study on the multi-feature impact analysis of the emission inspection results. This hinders the emission inspection from playing a better guiding role in the policy formulation of motor vehicle management. In this paper, the ensemble learning algorithm and interpretable machine learning theory are used. Nineteen feature indicators and over 400,000 vehicle mass analysis system (VMAS) detection data in Chengdu were selected from the emission inspection database to construct prediction models for emission inspection results. Moreover, the factors affecting emission inspection results and their ranks by importance were also obtained. The results revealed that the environment has a strong influence on the outcomes from emission inspections (accounting for about one-third of the total effect). Besides, the following eight feature indicators displayed great effects on emission inspection results in sequence: emission inspection agency (18.38%), world manufacturer code (15.01%), vehicle usage days (9.60%), transmission type (9.41%), accumulated mileage (9.21%), emission standard (5.82%), temperature (5.54%), and driving mode (5.50%). In this study, prediction models for emission inspection results are established, and the results are interpreted based on the interpretable machine learning theory. It is considered that more attention should be paid to the effect of inspection differences among emission inspection agencies on fairness, as well as the effects of differences in world manufacturer and transmission type on vehicle deterioration in future research. The supervision of emission inspection agencies, training of inspectors, elimination of obsolete vehicles, and government-guided purchase should be strengthened. This study provides empirical support for optimizing the formulation of motor vehicle environmental management policies. Implications: Emission inspection of motor vehicles (emission inspection) is a crucial player in solving the problem of motor vehicle exhaust pollution. In this work, prediction models for emission of motor vehicles inspection results are established. The results revealed that following eight feature indicators displayed great effects on emission inspection results in sequence: emission inspection agency (18.38%), world manufacturer code (15.01%), vehicle usage days (9.60%), transmission type (9.41%), accumulated mileage (9.21%), emission standard (5.82%), temperature (5.54%), and driving mode (5.50%). It is considered that more attention should be paid to the effect of inspection differences among emission inspection agencies on fairness, as well as the effects of differences in world manufacturer and transmission type on vehicle deterioration in future research. The supervision of emission inspection agencies, training of inspectors, elimination of obsolete vehicles, and government-guided purchase should be strengthened. This study provides empirical support for optimizing the formulation of motor vehicle environmental management policies. [ABSTRACT FROM AUTHOR]

Accurate travel time prediction between two locations is one of the most substantial services in transport. In travel time prediction, origin–destination (OD) method is more challenging since it has no intermediate trajectory points. This paper puts forward a deep learning-based model, called Gated Spatial–Temporal Attention (GSTA), to optimize the OD travel time prediction. While many trip features are available, their relations and particular contributions to the output are usually unknown. To give our model the flexibility to select the most relevant features, we develop a feature selection module with an integration unit and a gating mechanism to pass or suppress the trip feature based on its contribution. To capture spatial–temporal dependencies and correlations in the short and long term, we propose a new pair-wise attention mechanism with spatial inference and temporal reasoning. In addition, we adapt and integrate multi-head attention to improve model performance in case of sophisticated dependencies in long term. Extensive experiments on two large taxi datasets in New York City, USA, and Chengdu, China demonstrate the superiority of our model in comparison with other models. [ABSTRACT FROM AUTHOR]

Nowadays, S‐band weather radars are designed to observe weather conditions within large area. However, S‐band radars suffer from large blind zone at low elevation and fixed scan strategy so that they are not efficient for surveillance of convective weathers such as tornado. Networked X‐band weather radars are thereby proposed to overcome this issue. One key problem of networked radar is to automatically determine the type and the precise position of convective cells that are worthwhile to detect. In this paper, a tailor‐made framework is proposed to automatically find the convective cells and retrieve information of them from reflectivity product of networked X‐band weather radars. The framework consists of three substeps: convection pixel retrieval by Back Propagation Neural Network (BPNN), convection cell construction by Density‐Based Spatial Clustering of Applications with Noise (DBSCAN), and convection cell classification by Convolutional Neural Network (CNN). Evaluation results show that the proposed algorithm is capable to identify isolated single‐cell and multicell convective storms from the reflectivity image accurately. Therefore, the proposed framework is capable to provide information for networked X‐band weather radars so that they can track harmful convective weathers. The proposed framework has been embedded in the meteorological command and control (MCC) center of networked X‐band radar system in Chengdu. Plain Language Summary: Weather radar is significant in modern meteorological observation system. Recently, networked X‐band weather radars are attractive because it provides an efficient way to detect and track harmful convective weather such as tornadoes. One of the most difficult tasks of networked X‐band weather radars is to automatically determine clouds that are possible to endanger our regular live. It is not an easy mission because clouds are notoriously changeable, and the time resolution of our weather radars is relative low. In this paper, we propose an algorithm to challenge this problem by utilizing machine learning methods. According to the evaluation results, our algorithm is accurate and computational efficient, and it has been embedded into the networked X‐band radar system in Chengdu, China. Key Points: A framework of region‐of‐interest detection and classification is proposed for networked X‐band weather radar systemReal‐time machine learning‐based algorithms are introduced to achieve accurate identification with simple inputThe framework is subjectively and objectively evaluated in a networked X‐band radar system located in Chengdu, China [ABSTRACT FROM AUTHOR]

Short-term metro passenger flow forecasting is an essential component of intelligent transportation systems (ITS) and can be applied to optimize the passenger flow organization of a station and offer data support for metro passenger flow early warning and system management. LSTM neural networks have recently achieved remarkable recent in the field of natural language processing (NLP) because they are well suited for learning from experience to predict time series. For this purpose, we propose an empirical mode decomposition (EMD)-based long short-term memory (LSTM) neural network model for predicting short-term metro inbound passenger flow. The EMD algorithm decomposes the original sequential passenger flow into several intrinsic mode functions (IMFs) and a residual. Selected IMFs that are strongly correlated with the original data can be obtained via feature selection. The selected IMFs and the original data are integrated into inputs for LSTM neural networks, and a single LSTM prediction model and an EMD-LSTM hybrid forecasting model are developed. Finally, historical real automatic fare collection (AFC) data from metro passengers are collected from Chengdu Metro to verify the validity of the proposed EMD-LSTM prediction model. The results indicate that the proposed EMD-LSTM hybrid forecasting model outperforms the LSTM, ARIMA and BPN models. [ABSTRACT FROM AUTHOR]

The spatial heterogeneity and temporal variability of traffic in urban environments make traffic emissions inference challenging. To address this challenge, this study introduces a novel geographical context-based approach utilizing high-resolution taxi GPS data, incorporating multidimensional contextual factors such as road data, points of interest (POI), weather data, and population density. The proposed method can enhance the precision of traffic emissions inference compared to conventional macroscopic estimation techniques. To overcome the issue of missing data in traffic emissions inference from taxi data, three ensemble machine learning algorithms—Random Forest, Gradient Boosting Decision Trees (GBDT), and eXtreme Gradient Boosting (XGBoost)—are employed. These algorithms efficiently handle a substantial volume of taxi GPS data, achieving reduced computational time and model complexity. The proposed framework establishes localized models for each road segment, taking into consideration both geographical and external features that characterize the urban environment. This localized modeling contributes significantly to a more profound understanding of traffic dynamics. A thorough comparative analysis is conducted to assess the performance of the proposed method. Results indicate that incorporating multidimensional urban features is advantageous for traffic speed inference. Among the ensemble learning models, Random Forest outperforms others when dealing with a small missing rate or limited sample size, while XGBoost exhibits superior performance for larger missing rates or substantial sample sizes. Additionally, an analysis of the feature importance in traffic speed highlights that road network features are the most significant factors, followed by temporal characteristics, spatial attributes, POI data, and weather information. Finally, leveraging inferred traffic speed and volume information, emissions from large-scale urban road traffic are inferred based on the COPERT model. In contrast to methods relying on complex, multi-source data for emission estimation, our approach utilizes simple and easily accessible data, enabling precise estimation of emissions on a large-scale spatiotemporal basis. [ABSTRACT FROM AUTHOR]

In the realm of daily activity planning, precise weather forecasting services hold paramount significance. However, the prevalent dissemination of weather forecasts through conventional channels like radio, television, and the internet often yields only generalized regional predictions. This limitation contributes to diminished forecast reach, inadequate accuracy, and a lack of individualization, thwarting the effective distribution of meteorological insights and inhibiting the fulfillment of personalized forecast demands. Addressing these concerns, our study proposes a personalized weather forecasting approach that harnesses machine learning techniques and leverages the 5G messaging platform. By amalgamating projected user travel data, we augment personalized weather reports and extend user coverage to achieve tailored, timely, and high-quality weather services. Concretely, our research commences with an extensive analysis of large-scale user travel behavior data to extract pertinent travel attributes. Subsequently, we construct a user's future location prediction model—dubbed the Loc-PredModel—by employing the Extreme Gradient Boosting (XGBoost) algorithm to forecast users' trip destinations and arrival times. Anchored in the anticipated outcomes of user travel behavior, personalized weather data reports are formulated. Experimental results underscore the Loc-PredModel's remarkable predictive prowess, demonstrating a root mean squared error (RMSE) value of 0.208 and a coefficient of determination (R2) value of 0.935, affirming its efficacy in prognosticating users' trip destinations and arrival times. Furthermore, our 5G message-driven platform, rooted in intelligent personalized meteorological services, underwent testing within Chengdu city and garnered positive user feedback. Our research effectively surmounts the limitations of conventional weather forecasting platforms by furnishing users with more precise and customized weather information predicated on behavioral analysis and the 5G information ecosystem. This study not only advances the theoretical groundwork of intelligent meteorology but also offers invaluable insights and guidance for future advancement. By providing users with a more personalized and timely intelligent meteorological service experience, our approach exhibits transferability, with the research methodology and model potentially extendable nationwide or even on a larger scale beyond the study's Chengdu-based scope. [ABSTRACT FROM AUTHOR]

• The GHG emissions of Chengdu Metro were calculated using the LCA framework. • A WOA-DELM prediction model for Chengdu Metro GHG emissions was developed. • The effectiveness of the model was verified with other algorithm models. • The rough calculation formulas for GHG emissions of Chengdu Metro were obtained. With the mass construction of urban subways, the global greenhouse gas (GHG) emissions have been on the rise. This paper provides statistical evidence to support the infrastructure of subway emissions reduction through a study of GHG emissions during the construction stage of 6 stations and 7 sections of Chengdu Metro Line 18. Using the emission coefficient method, the GHG emissions from building material production, transportation and site construction in subway stations and shield sections were calculated, and a subway GHG emissions prediction model dependent on deep extreme learning machine (DELM) with whale optimization algorithm (WOA) was established(i.e., WOA-DELM). Compared with some optimized DELMs, namely wind driven optimizer (WDO) -DELM, grey wolf optimizer (GWO) -DELM, particle swarm optimizer (PSO) -DELM, artificial bee colony (ABC) -DELM, multi verse optimizer (MVO) -DELM, and atom search optimizer (ASO) -DELM, and some non-optimized algorithm models, namely back propagation neural network (BPNN), kernel extreme learning machine (KELM) and DELM, the correlation consistency of WOA-DELM algorithm prediction results (0.757) was found to be slightly higher. Through sensitivity analysis of the main input variables of subway GHG emissions with the WOA-DELM algorithm model, it was determined that the key influencing factors of station GHG emissions prediction were the station length and the depth of track surface, with relative change rates of corresponding variables of GHG emissions at 30.1% and 23.1% respectively. Finally, a rough prediction formula of GHG emissions from Chengdu Metro stations and shield sections were fitted based on the key influencing factors of GHG emissions. This study provides a practical and effective reference for reducing GHG emissions in subway construction and operation. [ABSTRACT FROM AUTHOR]

Accurate traffic status prediction is of great importance to improve the security and reliability of the intelligent transportation system. However, urban traffic status prediction is a very challenging task due to the tight symmetry among the Human–Vehicle–Environment (HVE). The recently proposed spatial–temporal 3D convolutional neural network (ST-3DNet) effectively extracts both spatial and temporal characteristics in HVE, but ignores the essential long-term temporal characteristics and the symmetry of historical data. Therefore, a novel spatial–temporal 3D residual correlation network (ST-3DRCN) is proposed for urban traffic status prediction in this paper. The ST-3DRCN firstly introduces the Pearson correlation coefficient method to extract a high correlation between traffic data. Then, a dynamic spatial feature extraction component is constructed by using 3D convolution combined with residual units to capture dynamic spatial features. After that, based on the idea of long short-term memory (LSTM), a novel architectural unit is proposed to extract dynamic temporal features. Finally, the spatial and temporal features are fused to obtain the final prediction results. Experiments have been performed using two datasets from Chengdu, China (TaxiCD) and California, USA (PEMS-BAY). Taking the root mean square error (RMSE) as the evaluation index, the prediction accuracy of ST-3DRCN on TaxiCD dataset is 21.4%, 21.3%, 11.7%, 10.8%, 4.7%, 3.6% and 2.3% higher than LSTM, convolutional neural network (CNN), 3D-CNN, spatial–temporal residual network (ST-ResNet), spatial–temporal graph convolutional network (ST-GCN), dynamic global-local spatial–temporal network (DGLSTNet), and ST-3DNet, respectively. [ABSTRACT FROM AUTHOR]

Due to multiple comorbid illnesses, polypharmacy, and age-related changes in pharmacokinetics and pharmacodynamics in older adults, the prevalence of potentially inappropriate medications (PIMs) is high, which affects the quality of life of older adults. Building an effective warning model is necessary for the early identification of PIMs to prevent harm caused by medication in geriatric patients. The purpose of this study was to develop a machine learning-based model for the warning of PIMs in older Chinese outpatients. This retrospective study was conducted among geriatric outpatients in nine tertiary hospitals in Chengdu from January 2018 to December 2018. The Beers criteria 2019 were used to assess PIMs in geriatric outpatients. Three problem transformation methods were used to tackle the multilabel classification problem in prescriptions. After the division of patient prescriptions into the training and test sets (8:2), we adopted six widely used classification algorithms to conduct the classification task and assessed the discriminative performance by the accuracy, precision, recall, F1 scores, subset accuracy (ss Acc), and Hamming loss (hm) of each model. The results showed that among 11,741 older patient prescriptions, 5816 PIMs were identified in 4038 (34.39%) patient prescriptions. A total of 41 types of PIMs were identified in these prescriptions. The three-problem transformation methods included label power set (LP), classifier chains (CC), and binary relevance (BR). Six classification algorithms were used to establish the warning models, including Random Forest (RF), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), CatBoost, Deep Forest (DF), and TabNet. The CC + CatBoost model had the highest accuracy value (97.83%), recall value (89.34%), F1 value (90.69%), and ss Acc value (97.79%) with a good precision value (92.18%) and the lowest hm value (0.0006). Therefore, the CC + CatBoost model was selected to predict the occurrence of PIM in geriatric Chinese patients. This study's novelty establishes a warning model for PIMs in geriatric patients by using machine learning. With the popularity of electronic patient record systems, sophisticated computer algorithms can be implemented at the bedside to improve medication use safety in geriatric patients in the future. [ABSTRACT FROM AUTHOR]

Rapid urbanization has brought along with it many environmental and social problems such as ecosystem damage and traffic congestion. Therefore, forecasting the trend of urban expansion and providing a reasonable urban planning basis for government departments have become the focus of researchers. An artificial neural network (ANN) can be used to consider spatial nonstationarity when obtaining the changing characteristics of urban land types. Therefore, in this study, we use cellular automata (CA) based on ANN (ANN-CA) to simulate and forecast urban expansion and discuss the parameter sensitivity of the model in detail. In addition, we propose a new Urban Expansion Early Warning Indicator system to warn about the deterioration of future land distribution patterns. Chengdu is selected as the study area, and the study period is from 2000 to 2020. The results showed the following: (1) The best accuracy was achieved when the neighborhood size is 7 × 7 and the number of model iterations is 250, and overall accuracy (OA), Kappa coefficient, and figure of merit (FOM) are 91.47%, 0.855, and 0.354, respectively; (2) ANN-CA is more suitable for predicting the urban expansion of Chengdu than CA based on logistic regression (LR-CA) and CA based on decision tree (DT-CA). Compared with the worst performance model, the score of OA increased by 6.23%, that of kappa increased by 0.062, and that of FOM increased by 0.056. (3) According to the current development trend, artificial built-up areas will increase substantially. The comprehensive evaluation results of the morphology effect, ecological effect, and intensity effect of urban expansion predict severe early warning for Jinniu District, Qingyang District, and Wuhou District by 2030. [ABSTRACT FROM AUTHOR]

• Built environment factors have strong non-linear effects on the ridesplitting ratio. • Gradient Boosting Decision Trees model is used to analyze the effects. • Distance to the city center is the most important among built environment factors. • Land use diversity and road density also have strong impacts on ridesplitting ratios. • Non-linear thresholds of built environment factors are identified to guide the planning. Ridesplitting, a form of ridesourcing services that matches riders with similar routes to the same driver, is a high occupancy travel mode that can bring considerable benefits. However, the current ratio of ridesplitting in the ridesourcing services is relatively low and its influencing factors remain unrevealed. Therefore, this paper uses a machine learning method, gradient boosting decision tree (GBDT) model, to explore the nonlinear effects of built environment on the ridesplitting ratio of origin–destination pairs (census tract to census tract). The GBDT model also provides the relative importance ranking of all the built environment factors. The results indicate that distance to city center, land use diversity and road density are the key influencing factors of ridesplitting ratio. In addition, the non-linear thresholds of built environment factors are identified based on partial dependence plots, which could provide policy implications for the government and transportation network companies to promote ridesplitting. [ABSTRACT FROM AUTHOR]

• A dynamic graph neural network for OD demand prediction. • Proposed the k- TNEAT algorithm to capture evolutionary patterns of dynamic OD graphs. • A topology representation method to jointly consider multi-source traffic data. • The methods are evaluated in two real-world ride-hailing datasets. The ride-hailing service platforms have grown tremendously around the world and attracted a wide range of research interests. A key to ride-hailing service platforms is how to realize accurate and reliable demand prediction. However, most of the existing studies focus on the region-level demand prediction while only a few attempts to address the problem of origin–destination (OD) demand prediction. In this paper, from the graph aspects, we construct the dynamic OD graphs to describe the ride-hailing demand data. We propose a novel neural architecture named the Dynamic Node-Edge Attention Network (DNEAT) to address the unique challenges of OD demand prediction from the demand generation and attraction perspectives. Different from previous studies, in DNEAT, we develop a new neural layer, named k -hop temporal node-edge attention layer (k -TNEAT), to capture the temporal evolution of node topologies in dynamic OD graphs instead of the pre-defined relationships among regions. We evaluate our model on two real-world ride-hailing demand datasets (from Chengdu, China, and New York City). The experiment results show that the proposed model outperforms six baseline models and is more robust to demand data with high sparsity. [ABSTRACT FROM AUTHOR]

• Providing drivers with future ridesourcing trip demand predictions can reduce trip-level deadheading. • Drivers act on high expected demand information by waiting in place for the next rider. • Machine learning for future demand prediction and trips assignment by minimizing the empty vehicle mileage. • The analysis leverages sample data from ridesourcing services operating in US and China. • Average deadhead mileage reduction ranges from 53% to 82% for ridesourcing operations per trip. Ridesourcing services provide alternative mobility options in several cities. Their market share has grown exponentially due to the convenience they provide. The use of such services may be associated with car-light or car-free lifestyles. However, there are growing concerns regarding their impact on urban transportation operations performance due to empty, unproductive miles driven without a passenger (commonly referred to as deadheading). This paper is motivated by the potential to reduce deadhead mileage of ridesourcing trips by providing drivers with information on future ridesourcing trip demand. Future demand information enables the driver to wait in place for the next rider's request without cruising around and contributing to congestion. A machine learning model is employed to predict hourly and 10-minute future interval travel demand for ridesourcing at a given location. Using future demand information, we propose algorithms to (i) assign drivers to act on received demand information by waiting in place for the next rider, and (ii) match these drivers with riders to minimize deadheading distance. Real-world data from ridesourcing providers in Austin, TX (RideAustin) and Chengdu, China (DiDi Chuxing) are leveraged. Results show that this process achieves 68%–82% and 53%–60% reduction of trip-level deadheading miles for the RideAustin and DiDi Chuxing sample operations respectively, under the assumption of unconstrained availability of short-term parking. Deadheading savings increase slightly as the maximum tolerable waiting time for the driver increases. Further, it is observed that significant deadhead savings per trip are possible, even when a small percent of the ridesourcing driver pool is provided with future ridesourcing demand information. [ABSTRACT FROM AUTHOR]

The Model Output Statistics (MOS) model is a dynamic statistical weather forecast model based on multiple linear regression technology. It is greatly affected by the selection of parameters and predictors, especially when the weather changes drastically, or extreme weather occurs. We improved the traditional MOS model with the machine learning method to enhance the capabilities of self-learning and generalization. Simultaneously, multi-source meteorological data were used as the input to the model to improve the data quality. In the experiment, we selected the four areas of Nanjing, Beijing, Chengdu, and Guangzhou for verification, with the numerical weather prediction (NWP) products and observation data from automatic weather stations (AWSs) used to predict the temperature and wind speed in the next 24 h. From the experiment, it can be seen that the accuracy of the prediction values and speed of the method were improved by the ML-MOS. Finally, we compared the ML-MOS model with neural networks and support vector machine (SVM), the results show that the prediction result of the ML-MOS model is better than that of the above two models. [ABSTRACT FROM AUTHOR]

The tradeoff between engineering costs and water treatment of the artificial lake system has a significant effect on engineering decision-making. However, decision-makers have little access to scientific tools to balance engineering costs against corresponding water treatment. In this study, a framework integrating numerical modeling, surrogate models and multi-objective optimization is proposed. This framework was applied to a practical case in Chengdu, China. A water quality model (MIKE21) was developed, providing training datasets for surrogate modeling. The Artificial Neural Network (ANN) and Support Vector Machine (SVM) were utilized for training surrogate models. Both surrogate models were validated with the coefficient of determinations (R2) greater than 0.98. SVM performed more stably with limited training data sizes while ANN demonstrated higher accuracies with more training samples. The multi-objective optimization model was developed using the genetic algorithm, with targets of reducing both engineering costs and target aquatic pollutant concentrations. An optimal target concentration after treatment was identified, characterized by the ammonia concentration (1.3 mg/L) in the artificial lake. Furthermore, scenarios with varying water quality in the upstream river were evaluated. Given the assumption of deteriorated upstream water quality in the future, the optimal proportion of pre-treatment in the total costs is increasing. [ABSTRACT FROM AUTHOR]