首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 31 毫秒
1.
It is easy for a multi-layered perception (MLP) to fit a stratified spatial interpolation pattern whose form is close to open surface; while it is easy for a radial basis function network (RBFN) to fit a pocket (radial) spatial interpolation pattern whose form is close to closed surface. However, in the real world, the spatial interpolation pattern may consist of stratified and pocket patterns. Neither MLP nor RBFN can fit the pattern easily. To combine their advantages to fit the complex hybrid spatial interpolation patterns, in this article we propose a novel neural network, MLP–RBFN hybrid network (MRHN), whose hidden layer contains sigmoid and Gaussian units at the same time. Although there are two kinds of processing units in MRHN, in this study we used the principle of minimizing the error sum of squares to derive the supervised learning rules for all the network parameters. This research took rainfall distribution in Taiwan as a case study. The results show that (1) the prediction error of the testing dataset outside the training dataset demonstrated that MRHN was the most accurate among the three networks, RBFN was the next best, and MLP was the worst; (2) the MLP model seriously underestimated the values of high observed rainfall; (3) over-learning may be a serious shortcoming of using RBFN in spatial interpolation applications; (4) MRHN may have better generalization learning capacity than RBFN in spatial interpolation applications.  相似文献   

2.
Calibration and validation of models predicting urban growth have been largely developed using internal variables. Further investigation is required to improve model’s calibration and validation mixing internal and external variables. To reach this objective, a spatial zoning approach simulating long-term expansion of Mashhad, the second largest city of Iran, was presented in this study. Spatial zoning approaches distinguish local-scale urban dynamics in districts with different socioeconomic characteristics. Thiessen polygons were used to identify districts with different morphology and functional attributes. Urban growth was subsequently simulated for each district using a Multi-Layer Perceptron (MLP) neural network and Markov chains (MC) analysis. MLP and MC algorithms were respectively used to derive transition maps from non-urban to urban use of land and to determine spatial evolution of built-up areas at the metropolitan scale. Results of simulations based on spatial zoning were compared with outcomes of traditional urban growth models. Spatial zoning improved significantly model’s accuracy in respect to more traditional simulation modes. The approach proposed here is appropriate when simulating land-use changes under discontinuous urban expansion.  相似文献   

3.
Property valuation studies often use classical statistics techniques. Among these techniques, the Artificial Neural Networks are the most applied, overcoming the inflexibility and the linearity of the hedonic models. Other researchers have used Geostatistics techniques, specifically the Kriging Method, for interpreting spatial-temporal variability and to predict housing unit prices. The innovation of this study is to highlight how the Kriging Method can help to better understand the urban environment, improving the results obtained by classical statistics. This study presents two different methods that share the general objective of extracting information regarding a city’s housing from datasets. The procedures applied are Ordinary Kriging (Geostatistics) and Multi-Layer Perceptron algorithm (Artificial Neural Networks). These methods were used to predict housing unit prices in the municipality of Pozuelo de Alarcon (Madrid). The implementation of both methods provides us with the urban characteristics of the study area and the most significant variables related to price. The main conclusion is that the Ordinary Kriging models and the Neural Networks models, applied to predicting housing unit prices are necessary methodologies to improve the information obtained in classical statistical techniques.

Abbreviations: ANN: Artificial Neural Networks; OK: ordinary Kriging; MLP: multi-layer perceptron  相似文献   

4.
Recently, researchers have introduced deep learning methods such as convolutional neural networks (CNN) to model spatio-temporal data and achieved better results than those with conventional methods. However, these CNN-based models employ a grid map to represent spatial data, which is unsuitable for road-network-based data. To address this problem, we propose a deep spatio-temporal residual neural network for road-network-based data modeling (DSTR-RNet). The proposed model constructs locally-connected neural network layers (LCNR) to model road network topology and integrates residual learning to model the spatio-temporal dependency. We test the DSTR-RNet by predicting the traffic flow of Didi cab service, in an 8-km2 region with 2,616 road segments in Chengdu, China. The results demonstrate that the DSTR-RNet maintains the spatial precision and topology of the road network as well as improves the prediction accuracy. We discuss the prediction errors and compare the prediction results to those of grid-based CNN models. We also explore the sensitivity of the model to its parameters; this will aid the application of this model to network-based data modeling.  相似文献   

5.
Understanding the complexity of urban expansion requires an analysis of the factors influencing the spatial and temporal processes of rural–urban land conversion. This study aims at building a statistical land conversion model to assist in understanding land use change patterns. Specifically, GIS coupled with a logistic regression model and exponential smoothing techniques is used for exploring the effects of various factors on land use change. These factors include population density, slope, proximity to roads, and surrounding land use, and their influence on land use change is studied for generating a predictive model. Methods to reduce spatial autocorrelation in a logistic regression framework are also discussed. Primarily, an optimal sampling scheme that can eliminate spatial autocorrelation while maintaining adequate samples to allow the model to achieve the comparable accuracy as the spatial autoregressive model is developed. Since many of the previous studies on modeling the spatial complexity of urban growth ignored temporal complexity, a modified exponential smoothing technique is employed to produce a smoothed model from a series of bi‐temporal models obtained from different time periods. The proposed model is validated using the multi‐temporal land use data in New Castle County, DE, USA. It is demonstrated that our approach provides an effective option for multi‐temporal land use change modeling and the modeling results help interpret the land use change patterns.  相似文献   

6.
ABSTRACT

Cellular automata (CA) models are in growing use for land-use change simulation and future scenario prediction. It is necessary to conduct model assessment that reports the quality of simulation results and how well the models reproduce reliable spatial patterns. Here, we review 347 CA articles published during 1999–2018 identified by a Scholar Google search using ‘cellular automata’, ‘land’ and ‘urban’ as keywords. Our review demonstrates that, during the past two decades, 89% of the publications include model assessment related to dataset, procedure and result using more than ten different methods. Among all methods, cell-by-cell comparison and landscape analysis were most frequently applied in the CA model assessment; specifically, overall accuracy and standard Kappa coefficient respectively rank first and second among all metrics. The end-state assessment is often criticized by modelers because it cannot adequately reflect the modeling ability of CA models. We provide five suggestions to the method selection, aiming to offer a background framework for future method choices as well as urging to focus on the assessment of input data and error propagation, procedure, quantitative and spatial change, and the impact of driving factors.  相似文献   

7.
从内容、空间尺度、时间维、综合程度、建模方式、复杂程度和数学方法等方面对目前的城市模型进行了系统的分类。论述了城市模型研究的发展趋势：模型研究内容日益丰富和多元化;从静态模拟到动态模拟发展;从子系统模拟向综合系统模拟发展;遥感和GIS的应用以及与城市模型的集成。对城市模型研究的未来发展进行了展望,认为未来的城市模型开发应基于综合方法的思想,注重加强城市基本理论和多学科交叉研究,强调城市模拟的动态性和综合性。充分借助遥感与GIS等技术手段进行研究。  相似文献   

8.
ABSTRACT

Spatial interpolation is a traditional geostatistical operation that aims at predicting the attribute values of unobserved locations given a sample of data defined on point supports. However, the continuity and heterogeneity underlying spatial data are too complex to be approximated by classic statistical models. Deep learning models, especially the idea of conditional generative adversarial networks (CGANs), provide us with a perspective for formalizing spatial interpolation as a conditional generative task. In this article, we design a novel deep learning architecture named conditional encoder-decoder generative adversarial neural networks (CEDGANs) for spatial interpolation, therein combining the encoder-decoder structure with adversarial learning to capture deep representations of sampled spatial data and their interactions with local structural patterns. A case study on elevations in China demonstrates the ability of our model to achieve outstanding interpolation results compared to benchmark methods. Further experiments uncover the learned spatial knowledge in the model’s hidden layers and test the potential to generalize our adversarial interpolation idea across domains. This work is an endeavor to investigate deep spatial knowledge using artificial intelligence. The proposed model can benefit practical scenarios and enlighten future research in various geographical applications related to spatial prediction.  相似文献   

9.
Urban multiple land use change (LUC) modelling enables the realistic simulation of LUC processes in complex urban systems; however, such modelling suffers from technical challenges posed by complicated transition rules and high spatial heterogeneity when predicting the LUC of a highly developed area. Tree-based methods are powerful tools for addressing this task, but their predictive capabilities need further examination. This study integrates tree-based methods and cellular automata to simulate multiple LUC processes in the Greater Tokyo Area. We examine the predictive capability of 4 tree-based models – bagged trees, random forests, extremely randomised trees (ERT) and bagged gradient boosting decision trees (bagged GBDT) – on transition probability prediction for 18 land use transitions derived from 8 land use types. We compare the predictive power of a tree-based model with multi-layer perceptron (MLP) and among themselves. The results show that tree-based models generally perform better than MLP, and ERT significantly outperforms the three other tree-based models. The outstanding predictive performance of ERT demonstrates the advantages of introducing bagging ensemble and a high degree of randomisation into transition probability modelling. In addition, through variable importance evaluation, we found the strongest explanatory powers of neighbourhood characteristics for all land use transitions; however, the size of the impacts depends on the neighbourhood land use type and the neighbourhood size. Furthermore, socio-economic and policy factors play important roles in transitions ending with high-rise buildings and transitions related to industrial areas.  相似文献   

10.
While there are extensive studies of urban 2D forms, research on the varying geometric features and spatial distribution patterns of urban 3D spaces is comparatively rare. In this paper, we propose a coupled model, known as BPANN-CBRSortCA, which is based on a back propagation artificial neural network (BPANN) and case-based reasoning technology with sort cellular automaton (CBRSortCA) to simulate future urban building heights and their spatial distribution. BPANN–CBRSortCA uses BPANN to predict the vertical extrusion of building heights and uses CBRSortCA to simulate horizontal urban expansion. The BPANN–CBRSortCA model is innovative because of its capabilities to simultaneously project urban growth in the vertical and horizontal dimensions. The proposed model also overcomes the limitations of the traditional cellular automata models that cannot simulate ‘diffused’ urban expansion. This research used Wuhan City as a case study to simulate vertical and horizontal urban expansion from 2015 to 2025. The results showed the following: (1) in the next 10 years, new build-up will mainly appear along the edge of Hongshan and Hanyang Districts or will occupy bare land in the form of ‘filling’ and (2) the tallest buildings will be mainly located to the south of East Lake in Hongshan District and on undeveloped land within the city. These simulation results can provide a reference for future urban planning.  相似文献   

11.
《Urban geography》2013,34(2):259-272
Africa's urban population growth has been especially rapid, averaging about 5% per year over the past two decades. As a result, many urban areas have experienced dramatic growth that is seriously outstripping the capacity of most cities to provide adequate services for their residents. Although population growth and urbanization rates in Africa have slowed recently due to a number of factors including HIV/AIDS, urban growth is still expected to double by 2030, leading to dramatic sprawl with serious environmental and social consequences. Using Nairobi as an example of a rapidly urbanizing African city, we studied the dynamics of land use and land cover change using satellite data and addressed the need for models and urban management tools that can guide sustainable urban planning policies. Cellular Automata, which integrate biophysical factors with dynamic spatial modeling, are used in this study. The model was calibrated and tested using time series of urbanized areas derived from land use/cover maps, produced from remotely sensed imagery, with future urban growth projected to 2030. Model assessment results showed high levels of accuracy, indicating that simulation findings were realistic, thereby confirming the effectiveness of the model. Results further showed that the model is a useful and effective tool to foresee the spatial consequences of planning policies in the context of many African cities. The forecast for Nairobi showed unsustainable sprawl.  相似文献   

12.
上海市提出“五大新城”发展战略,新城建设迈入了面向“独立的综合性节点城市”的新阶段。基于2001、2010和2018年全行业企业总部—分支机构数据,论文构建了上海大都市圈内区县尺度的城市网络,利用社会网络分析方法刻画城市网络整体特征及五大新城网络地位的格局演变,并通过空间计量模型对相关影响因素作实证分析。研究发现：① 上海大都市圈的城市网络呈现从以上海中心城区为核心的单极结构向多极结构转变的趋势,强联系仍然主要发生在各级市域内部,市际行政边界对网络联系具有较强的阻碍;② 五大新城仍未呈现“节点城市”的中心性特征但具备了一定的独立性,距离成为“独立的综合性节点城市”仍有一段距离;③ 创新能力对新城入度和中介中心性的影响显著增强,新城在提升中心性的过程中也更加注重环境质量的提升,交通基础设施建设在提升五大新城的中心性中扮演着越来越重要的角色。此外,城市人口规模、政策优惠与公共服务完善程度也对新城中心性有着相对持续稳定的正向影响。论文从企业网络这一视角切入,为将五大新城建设为上海大都市圈内“独立的综合性节点城市”提供政策建议。  相似文献   

13.
区域尺度城市增长时空动态模型及其在京津唐都市圈应用   总被引：3，自引：0，他引：3  
Dynamic urban expansion simulation at regional scale is one of the important re-search methodologies in Land Use/Cover Change (LUCC) and global environmental change influenced by urbanization.However,previous studies indicate that the single urban expan-sion simulation for future scenarios at local scale cannot meet the requirements for charac-terizing and interpreting the interactive mechanisms of regional urbanization and global en-vironmental 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 character-istics 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 ex-pansion will shift quickly from Beijing metropolis to the periphery of Tianjin and Tangshan city along coastal belt.  相似文献   

14.
对统计型人口数据进行格网形式的空间化可更直观地展示人口的空间分布,但不同的人口空间化建模方法和不同的格网尺度在表达人口空间化结果方面存在差异。本文在人口特征分区的基础上,引入DMSP/OLS夜间灯光对城镇用地进行再分类,采用多元统计回归和地理加权回归方法(GWR),开展人口统计数据空间化多尺度模型研究,生成1 km、5 km和10 km等3个尺度的2010年安徽省人口空间数据,并对3个尺度下2个模型结果进行精度评价与比较。结果表明：人口空间数据精度不仅与建模所用方法关系密切,还受到建模格网尺度大小的影响。基于多元统计回归方法的模型估计人口数与实际人口的平均相对误差值随着尺度的增加而降低,而基于GWR方法获得的人口空间数据误差值随着尺度的增加而升高。整体来看,基于GWR方法的1 km研究尺度的人口空间数据平均相对误差最低(22.31%)。区域地形地貌条件与人口空间数据误差有较强的关联,地貌类型复杂的山区人口空间数据误差较大。  相似文献   

15.
论文通过对230家“新三板”文化产业挂牌企业总部—分支机构关联数据的收集、整理和分析,对文化产业视角下中国城市网络的空间结构特征进行研究,比较文化产业城市网络与其他类型城市网络的差异性,并探索影响文化产业城市网络空间格局的经济社会因素。结果表明：① 中国文化产业挂牌企业地理分布呈现出地域分散但数量集中的特点,城市网络空间分布高度不均衡,并未表现出常见的“菱形结构”;② 网络核心节点以东中部发达城市以及少数具有特殊资源的城市为主,多数城市的对外输出能力有限;③ 城市网络扩散以核心节点城市间的等级扩散为主,邻近城市间的扩散效应不明显,同时本地网络(即城市内部网络)对文化企业组织结构的贡献度低于跨地域网络;④ 不同类型文化产业在网络结构上表现出较为明显的差异,反映其市场需求和发展条件的不同;⑤ 地方政府作用和城市产业结构是影响中国文化产业企业布局和网络格局形成的重要因素,其他社会经济因素的作用则较为不明显,反映出中国文化产业的独特性。  相似文献   

16.
董冠鹏  张航  郭雨臣 《地理研究》2023,42(2):495-513
在经济全球化、区域一体化的背景下,城市发展动力由内部功能集聚转向外部关系协调,城市间的关联作用愈发重要,成为“城市的第二本质”。通过文献计量分析,发现空间计量模型逐渐成为城市网络外部性定量测度的主要方法之一。从研究设计角度,空间计量模型作为城市网络外部性的定量建模工具,存在至少两方面的问题：城市网络外部性的非对称效应和城市网络的多尺度问题。本文结合城市网络外部性测度与建模,首先阐述如何规范地解读空间计量模型参数及其与网络外部性测度的对应关系;其次基于蒙特卡洛模拟实验论证非对称城市网络外部性和多尺度城市网络外部性的建模方法。研究表明：(1)忽视城市网络外部性中潜在的非对称效应会显著降低模型参数估计的准确性,本文开发的非对称空间效应模型（Asymmetric Spatial Econometric Model,ASEM）可以准确识别网络外部性的非对称效应,给出更加准确的参数估计;(2)忽略现实存在的多尺度网络效应,只在单一尺度对网络效应建模会造成参数估计失真,而空间多尺度统计模型（Hierarchical Spatial Autoregressive model,HSAR）为多尺度网络外部...  相似文献   

17.
空间认同:城市空间研究转向中的知识前沿、趋势与启发   总被引：1，自引：2，他引：1  
郭文 《地理科学》2019,39(4):587-595
中国城市化进程的快速发展,促使人们不断解构、调整和重构对城市空间的认同,这是城市化发展中不容忽视的新问题。以Web of Science（WoS）为数据源,对国外城市空间认同研究进行了分析和知识再现。研究发现：① 城市空间认同是人们对城市发展中社会经济认同、文化认同、集体认同、身份认同与情感认同的集合。作为重要的国民意识,城市空间认同主题是国外学者关注的重要领域,对该领域研究的本质上是对城市空间实践中人文主义空间诉求的知识表征;② 在2008~2017年的国外城市空间认同研究中,美国、英国、澳大利亚等国家具有明显优势,国际合作研究网络主要在美洲-欧洲、欧洲-澳洲,以及澳洲-欧美之间;国外城市空间认同研究高被引文献注重对“空间多中心性”“地方与连续性”“城市社区”“城市公民身份”“空间绅士化”“地方主义”等方面的讨论。③ 未来研究更加倾向在“认同”“空间”“城市”“地理”“政治”“地方”,以及“社区”等新主题方面。相比较而言,国内对城市空间认同的研究较为欠缺,随着中国城市空间实践不断推向纵深阶段,需要强化城市空间认同研究的“理论自觉”。  相似文献   

18.
ABSTRACT

Cellular automata (CA) are effective tools for simulating urban dynamics. Coupling top-down and bottom-up CA models are often used to address macro-scale demand and micro-scale allocation in the simulation of urban dynamics. However, those models typically ignore spatial differences in terms of the coupling process between macro-scale demand and micro-scale allocation. Herein, a novel approach for combining top-down and bottom-up strategies based on simulating urban dynamics is proposed. An optimizing strategy was used to predict the parameter of the inverse S-shaped function of future urban land use pattern and further deduce urban land increment within each concentric ring. The maximum probability transformation rule was incorporated into the CA model to address the micro-scale allocation. Wuhan was selected to test the performance of the proposed approach, and the conventional and the proposed approaches were compared. The results demonstrated that the proposed approach can not only retain the model’s accuracies but also better simulate the macro morphology of urban development dynamics and generate more realistic urban dynamic pattern in the urban sub-center and fringe regions. The proposed coupling approach can also be used to generate different development scenarios. The approach is expected to provide new perspectives for coupling top-down and bottom-up CA models in modeling urban expansion.  相似文献   

19.
Understanding the relationship between vegetation and climate is essential for predicting the impact of climate change on broad-scale landscape processes. Utilizing vegetation indicators derived from remotely sensed imagery, we present an approach to forecast shifts in the future distribution of vegetation. Remotely sensed metrics representing cumulative greenness, seasonality, and minimum cover have successfully been linked to species distributions over broad spatial scales. In this paper we developed models between a historical time series of Advanced Very High Resolution Radiometer (AVHRR) satellite imagery from 1987 to 2007 at 1 km spatial resolution with corresponding climate data using regression tree modeling approaches. We then applied these models to three climate change scenarios produced by the Canadian Centre for Climate Modeling and Analysis (CCCma) to predict and map productivity indices in 2065. Our results indicated that warming may lead to increased cumulative greenness in northern British Columbia and seasonality in vegetation is expected to decrease for higher elevations, while levels of minimum cover increase. The Coast Mountains of the Pacific Maritime region and high elevation edge habitats across British Columbia were forecasted to experience the greatest amount of change. Our approach provides resource managers with information to mitigate and adapt to future habitat dynamics. Forecasting vegetation productivity levels presents a novel approach for understanding the future implications of climate change on broad scale spatial patterns of vegetation.  相似文献   

20.
快速城市化阶段济南城市空间扩展及驱动力研究   总被引：2，自引：0，他引：2  
王成新  窦旺胜  程钰  刘凯 《地理科学》2020,40(9):1513-1521
基于济南市1992年、2000年、2010年、2018年Landsat遥感影像数据，借助ArcGIS、ENVI等图像分析工具，提取济南城市建成区，从扩展速度、强度、分形维数、紧凑度、重心转移等方面探究济南城市空间扩展的时空变化过程、特征，运用地理加权逻辑回归方法对济南城市空间扩展驱动力进行分析。结果表明：① 济南城市空间扩展经历“中强低速”“高强中速”“低强高速”3个阶段，城市形态趋于稳定，城市形状呈现东西向条带状分布格局，紧凑度较差；② 1992—2018年济南城市空间向E、NEE、NE方向扩展最为显著，扩展方式以外延扩张与内部填充为主，城市空间分布重心东移态势明显；③ 济南城市空间扩展受多重驱动因子影响，主驱动因子为距城市建成区距离、距主要公路距离、地区生产总值、城镇化率、人口密度等。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号