基于Kriging遗传算法的高速公路应急车道管控优化

针对如何在不同交通流状况下有效提高高速公路运行效率和降低安全风险的问题,提出基于Kriging代理模型的遗传算法优化应急车道管控策略。结合应急车道开放策略的时空特性设计数学优化模型,通过引入Kriging代理模型,结合遗传算法搭建优化框架,采用仿真软件获取数据训练代理模型,以此求解带有开放时间和开放空间双重约束的总行程时间与总碰撞暴露时间最小化问题。对车道控制时间与空间变量的变化频次进行了约束,并对目标函数中效率与安全指标权重变化对优化结果的影响进行了分析。实验表明:该优化方法使路网总行程时间减小14.9%,碰撞暴露时间减小44.2%,控制效果提升。

Integration of Neural Networks and Cellular Automata for Urban Planning

This paper presents a new type of cellular automa ta (CA) model for the simulation of alternative land development using neural netw orks for urban planning. CA models can be regarded as a planning tool because th ey can generate alternative urban growth. Alternative development patterns can b e formed by using different sets of parameter values in CA simulation. A critica l issue is how to define parameter values for realistic and idealized simulation . This paper demonstrates that neural networks can simplify CA models but genera te more plausible results. The simulation is based on a simple three-layer netw ork with an output neuron to generate conversion probability. No transition rule s are required for the simulation. Parameter values are automatically obtained f rom the training of network by using satellite remote sensing data. Original tra ining data can be assessed and modified according to planning objectives. Altern ative urban patterns can be easily formulated by using the modified training dat a sets rather than changing the model.

DeepRadiation:An intelligent augmented reality platform for predicting urban energy performance just through 360 panoramic streetscape images utilizing various deep learning models

Urban energy simulation is critical for understanding and managing energy performance in cities.In this research,we design a novel framework called DeepRadiation,to enable automatic urban environmental performance prediction.By incorporating deep learning strategies,DeepRadiation predicts solar radiation on an urban scale using just panoramic streetscape images without any 3D modeling and simulation.New York City was chosen as the case study for this research.DeepRadiation is comprised of three different deep learning models organized into two stages.The first stage,named DeepRadiation modeling,serves as the framework's brain.At this stage,solar radiation analysis was performed using a Pix2Pix model,a type of conditional generative adversarial networks(GANs).After extracting GIS data and performing energy simulation analysis to prepare the dataset,the Pix2Pix model was trained on 10000 paired panoramic depth images of streetscapes with only building blocks and related panoramic images of streetscapes with only solar radiation analysis.Two GAN generator evaluation measures named qualitative evaluation and quantitative evaluation were used to validate the trained Pix2Pix model.Both demonstrated high levels of accuracy(qualitative evaluation:93%,quantitative evaluation:89%).DeepRadiation application as the DeepRadiation's sescond stage is the framework's eyes.At this stage,two convolutional neural network(CNN)models(DeepLabv3 and MiDaS)were used to perform computer vision tasks on panoramic streetscape images,such as semantic segmentation and depth estimation.The DeepRadiation application stage allows urban designers,architects,and urban policymakers to use the DeepRadiation framework and experience the final output via augmented reality.

Simulating dynamic urban expansion at regional scale in Beijing-Tianjin-Tangshan Metropolitan Area

Dynamic urban expansion simulation at regional scale is one of the important research methodologies in Land Use/Cover Change （LUCC） and global environmental change influenced by urbanization. However, previous studies indicate that the single urban expansion simulation for future scenarios at local scale cannot meet the requirements for characterizing and interpreting the interactive mechanisms of regional urbanization and global environmental change. This study constructed a regional Dynamic Urban Expansion Model （Reg-DUEM） suitable for different scenarios by integrating the Artificial Neural Network （ANN） and Cellular Automaton （CA） model. Firstly we analyzed the temporal and spatial characteristics of urban expansion and acquired a prior knowledge rules using land use/cover change datasets of Beijing-Tianjin-Tangshan metropolitan area. The future urban expansion under different scenarios is then simulated based on a baseline model, economic models, policy models and the structural adjustment model. The results indicate that Reg-DUEM has good reliability for a non-linear expansion simulation at regional scale influenced by macro-policies. The simulating results show that future urban expansion patterns from different scenarios of the metropolitan area have the tremendous spatio-temporal differences. Future urban expansion will shift quickly from Beijing metropolis to the periphery of Tianjin and Tangshan city along coastal belt.

Incorporation of intra-city human mobility into urban growth simulation:A case study in Beijing

The effective modeling of urban growth is crucial for urban planning and analyzing the causes of land-use dynamics.As urbanization has slowed down in most megacities,improved urban growth modeling with minor changes has become a crucial open issue for these cities.Most existing models are based on stationary factors and spatial proximity,which are unlikely to depict spatial connectivity between regions.This research attempts to leverage the power of real-world human mobility and consider intra-city spatial interaction as an imperative driver in the context of urban growth simulation.Specifically,the gravity model,which considers both the scale and distance effects of geographical locations within cities,is employed to characterize the connection between land areas using individual trajectory data from a macro perspective.It then becomes possible to integrate human mobility factors into a neural-network-based cellular automata(ANN-CA)for urban growth modeling in Beijing from 2013 to 2016.The results indicate that the proposed model outperforms traditional models in terms of the overall accuracy with a 0.60%improvement in Cohen’s Kappa coefficient and a 0.41%improvement in the figure of merit.In addition,the improvements are even more significant in districts with strong relationships with the central area of Beijing.For example,we find that the Kappa coefficients in three districts(Chaoyang,Daxing,and Shunyi)are considerably higher by more than 2.00%,suggesting the possible existence of a positive link between intense human interaction and urban growth.This paper provides valuable insights into how fine-grained human mobility data can be integrated into urban growth simulation,helping us to better understand the human-land relationship.

Dynamic simulation of urban water metabolism under water environmental carrying capacity restrictions

A revised concept for urban water metabolism （UWM） is presented in this study to address the inadequacies in current research on UWM and the problems associated with the traditional urban water metabolic process. Feedback loops can be analyzed to increase the water environmental carrying capacity （WECC） of the new urban water metabolism system （UWMS） over that of a traditional UWMS. An analysis of the feedback loops of an UWMS was used to construct a system dynamics （SD） model for the system under a WECC restriction. Water metabolic processes were simulated for different scenarios using the Tongzhou District in Beijing as an example. The results for the newly developed UWM case showed that a water environment of Tongzhou District could support a population of 1.1926 × 106, an irrigation area of 375.521 km2, a livestock of 0.7732 × 106, and an industrial value added of ￥193.14 × 109 （i.e. about US$28.285 × 109） in 2020. A sensitivity analysis showed that the WECC could be improved to some extent by constructing new sewage treatment facilities or by expanding the current sewage treatment facilities, using reclaimed water and improving the water circulation system.

Multi-agent system simulation for urban policy design:open space land use change problem

Multi-agent system(MAS)models have been increasingly applied to the simulation of complex phenomena in different areas,providing successful and credible results.Citizens behavior related to a specific urban activity(i.e.,recreation activities in a park,using bicycle for mobility purposes)can be modeled as an agent(actor)with several affinities and preferences which are dependent on aspects that affect the activity.A particular application of a MAS approach is in area of urban policy design,in which policies should be designed considering citizens needs,preferences and behavior.Once an open space in a city is available(i.e.,an industry is moved to an industrial area),a land use policy should contribute to identify the new use for the urban space.There are different land use policies that can be applied depending on which services or facilities must be empowered in the city.It is important to identify the correct policy in order to satisfy present citizens needs but considering also the future needs in a social changing context.A socio-technological simulation model has been developed to allow citizens to get a better understanding of the urban problem,its dynamics and explore the sustainability of the different solutions.,enhancing citizens to participate in the urban decisions through new technologies(i.e.,e-participation).This paper illustrates an open space MAS simulation model for land use design policies in which citizens can check their opinion and get a better understanding of the different choices and its acceptability by the community considering not only present neighborhood profiles,but also future neighborhood configurations.It is the first step before the development of the final software including a user friendly interface to let citizens with different cultural profiles to perform simulations as an essential and neutral tool to reach consensus during the decision-making process in urban policy design.

Simulating multiple urban land use changes by integrating transportation accessibility and a vector-based cellular automata:a case study on city of Toronto

The accessibility provided by the transportation system plays an essential role in driving urban growth and urban functional land use changes.Conventional studies on land use simulation usually simplified the accessibility as proximities and adopted the grid-based simulation strategy,leading to the insufficiencies of characterizing spatial geometry of land parcels and simulating subtle land use changes among urban functional types.To overcome these limita-tions,an Accessibility-interacted Vector-based Cellular Automata(A-VCA)model was proposed for the better simulation of realistic land use change among different urban functional types.The accessibility at both local and zonal scales derived from actual travel time data was considered as a key driver of fine-scale urban land use changes and was integrated into the vector-based CA simulation process.The proposed A-VCA model was tested through the simulation of urban land use changes in the City of Toronto,Canada,during 2012-2016.A vector-based CA without considering the driving factor of accessibility(VCA)and a popular grid-based CA model(Future Land Use Simulation,FLUS)were also implemented for compar-isons.The simulation results reveal that the proposed A-VCA model is capable of simulating fine-scale urban land use changes with satisfactory accuracy and good morphological feature(kappa=0.907,figure of merit=0.283,and cumulative producer’s accuracy=72.83%±1.535%).The comparison also shows significant outperformance of the A-VCA model against the VCA and FLUS models,suggesting the effectiveness of the accessibility-interactive mechanism and vector-based simulation strategy.The proposed model provides new tools for a better simula-tion of fine-scale land use changes and can be used in assisting the formulation of urban and transportation planning.

Simulated impacts of 3D urban morphology on urban transportation in megacities: case study in Beijing

Urban morphology and morphology change and their impacts on urban transportation have been studied extensively in planar urban space.The essential feature of urban space,however,is its three-dimensionality(3D),and few studies have been conducted from a 3D perspective,overly limiting the accuracy of studies on the relationships between urban morphology and transportation.The aim of this paper is to simulate the impacts of 3D urban morphologies on urban transportation under the Digital Earth framework.On the basis of the principle that population distribution and movement are largely confined by 3D urban morphologies,which affect transportation,high spatial resolution remote sensing imagery and a thematic vector data-set were used to extract urban morphology and transportation-related variables.With a combination of three research methods-factor analysis,spatial regression analysis and Euclidean allocation-we provide an effective method to construct a simulation model.The paper indicates three general results.First,building capacity in the urban space has the most significant impact on traffic condition.Second,obvious urban space otherness,reflecting both use density characteristics and functional character-istics of urban space,mostly results in heavier traffic flow pressure.Third,no single morphology density indicator or single urban structure indicator can reflect its contribution to the pressure of traffic flow directly,but a combination of these different indicators has the ability to do so.

A multi process value-based reinforcement learning environment framework for adaptive traffic signal control

Realising adaptive traffic signal control(ATSC)through reinforcement learning(RL)is an important means to easetraffic congestion.This paper finds the computing power of the central processing unit(CPU)cannot fully usedwhen Simulation of Urban MObility(SUMO)is used as an environment simulator for RL.We propose a multi-process framework under value-basedRL.First,we propose a shared memory mechanism to improve exploration efficiency.Second,we use the weight sharing mechanism to solve the problem of asynchronous multi-process agents.We also explained the reason shared memory in ATSC does not lead to early local optima of the agent.Wehave verified in experiments the sampling efficiency of the 10-process method is 8.259 times that of the single process.The sampling efficiency of the 20-process method is 13.409 times that of the single process.Moreover,the agent can also converge to the optimal solution.