Rising customer demands and the complexities of dynamic urban systems pose significant challenges for logistics distribution, especially since large-scale real-time dynamic traffic information is not always accessible. However, few studies have focused on optimizing logistics in the ever-changing traffic environments of megacities with multiple distribution centers. This study proposes two deep reinforcement learning models with Transformer architectures to optimize logistics distribution time costs across multiple depots in static and dynamic traffic scenarios, respectively. The first model (DTM-MDVRP) incorporates travel times between customers as edge information in the encoder to pre-plan delivery routes. The second model (DTM-DMDVRP) introduces a feature embedding module to extract real-time traffic information for dynamic route optimization. Wuhan city was selected for logistics optimization experiments. Results indicate that DTM-MDVRP surpasses heuristic methods and other deep reinforcement learning methods in optimization effectiveness and computation time. In dynamic urban traffic environments, DTM-DMDVRP further improves distribution efficiency. Compared to the traditional attention model, DTM-DMDVRP reduces time costs by 7.77, 3.51, and 3.58% across three problem scales and can optimize delivery routes for 100 customer points within 0.30 seconds. The proposed DTM-DMDVRP enables the real-time dynamic scheduling of logistics vehicles for logistics enterprises.

Actual land parcels vary significantly in size and complexity. Previous studies were limited by existing technical methods for fine-grained land use classification. The emergence of multimodal large language models offers new techniques for image classification, but their application in land use classification remains unexplored. This study presents LandGPT, a multimodal large language model trained on the CN-MSLU-100K dataset, covering fine-grained land use classification of irregular parcels. This study proposes a trans-level discrimination framework to improve LandGPT’s ability to classify fine-grained land use. Under this framework, LandGPT achieves a discrimination accuracy of 89.7% and a Kappa coefficient of 0.85 for fine-grained land use categories, outperforming state-of-the-art models with a 48.33% accuracy improvement. In some challenging categories, the improvement reaches nearly 1500%. This study finds that training with multi-source remote sensing image data improved LandGPT’s accuracy by 15.79% compared to single-image data. This study explores Prompt engineering based on LandGPT. The optimal prompt paradigm offers fine-grained categories and guides the model for accurate classification, reducing errors from LLM hallucinations. This study pioneeringly explores the application of large language models in the land use domain and offers a new solution for fine-grained land use classification.

Predicting PM2.5 concentrations at an hourly temporal resolution in urban areas can provide key information for public health protection. The spatiotemporal dependency among monitoring stations and the spatiotemporal correlations between PM2.5 and relevant factors (e.g. meteorology and emissions) are both essential for such predictions. This study proposes a multi-branch temporal graph convolutional neural network (MB-TGCN) for short-term predictions of PM2.5 concentrations at city monitoring stations. Composed of a set of graph convolutional networks (GCNs) for spatial dependency modeling, a set of gated recurrent units (GRUs) for temporal dependency modeling, and a multi-branch structure for integrating PM2.5 and relevant factors, MB-TGCN aims to accurately predict PM2.5 concentrations by capturing both spatial and temporal relationships through a graph modeling approach. Experiments with an air quality dataset from 35 stations in Beijing showed that MB-TGCN achieved higher accuracy than several deep learning models for various prediction durations ranging from 1 to 12 h. The method described in this study can help enhance the prediction capability of PM2.5 and provide decision support for environment-aware activity planning.

Fast urbanization brings great challenges to sustainable development goals, such as excessive exploitation and population explosion. Classical cellular automata (CA) have been widely used to independently simulate the change of spatial features, i.e. land use, population, economic production, etc. However, most CA models rely on historical data as static driving factors to simulate future scenarios while ignoring the inter-wined influences among multiple features in the development process. To address this issue, this study proposes a spatial cooperative simulation (SCS) approach to simulate the land use, population, and economy changes. The SCS approach starts with a separate CA model to obtain the initial scenes of each feature. Then, the simulation results of each other two features are used as dynamically updated driving factors, rather than the static historical data, to capture the inter-wined influence of multiple features during the development process. This step is iteratively performed until the changes of each feature converge and the final simulation results will be reported. The simulation experiment in Greater Bay Area demonstrates that the SCS approach can well capture the simultaneous development process and outperforms baseline approaches. The SCS approach is capable of forecasting future development scenarios and facilitates spatial planning and infrastructure synergies.

A high-quality land-use dataset is crucial for constructing a high-performance land-use classification model. Due to the complexity and spatial heterogeneity of land-use, the dataset construction process is inefficient and costly. This challenge affects the quality of datasets, consequently impacting the model’s performance. The emerging field of Data-Centric Artificial Intelligence (DCAI) is expected to deliver techniques for dataset optimization, offering a promising solution to the problem. Therefore, this study proposes a data-centric framework named DCAI-CLUD for the construction of land-use datasets. Based on this framework, the accuracy and rate of data labeling are improved by 5.93 and 28.97%. The Gini index of the dataset and the proportion of samples with non-mixed land-use categories are enhanced by 3.27 and 8.52%. The overall accuracy (OA) and Kappa of the land-use classification model improved significantly by 27.87 and 58.08%. This study is the first to introduce DCAI into the field of geographic information and remote sensing and verify its effectiveness. The proposed framework can effectively improve the construction efficiency and quality of the dataset and synchronously optimize the model performance. Based on the proposed framework, we constructed a multi-source land-use dataset of major cities in China named CN-MSLU-100K.

Urban logistics is vital to the development and operation of cities, and its optimization is highly beneficial to economic growth. The increasing customer needs and the complexity of urban systems are two challenges for current logistics optimization. However, little research considers both, failing to balance efficiency and cost. In this study, we propose a hybrid sparrow search algorithm (SA-SSA) by combining the sparrow search algorithm with fast computational speed and the simulated annealing algorithm with the ability to get the global optimum solution. Wuhan city was selected for logistics optimization experiments. The results show that the SA-SSA can optimize large-scale urban logistics with guaranteed efficiency and solution quality. Compared with simulated annealing, sparrow search, and genetic algorithm, the cost of SA-SSA was reduced by 17.12, 18.62, and 14.72%, respectively. Although the cost of SS-SSA was 11.50% higher than the ant colony algorithm, its computation time was reduced by 99.06%. In addition, the simulation experiments were conducted to explore the impact of spatial elements on the algorithm performance. The SA-SSA can provide high-quality solutions with high efficiency, considering the constraints of many customers and complex road networks. It can support realizing the scientific scheduling of distribution vehicles by logistics enterprises.

Rapid land-use change detection (LUCD) is pivotal for refined urban planning and management. In this paper, we investigate LUCD through learning embeddings of points of interest (POIs) from multiple temporalities. There are several prominent challenges: (1) the co-occurrence problem of multi-temporal POIs, (2) the heterogeneity of POI categorization, and (3) The lack of human-crafted labels. Therefore, multi-temporal POIs need to be aligned in the embedding space for effective LUCD. This study proposes a multi-temporal POI embedding (MT-POI2Vec) technique for LUCD in a fully unsupervised manner. In MT-POI2Vec, we first utilize random walks in POI networks to capture their single-period co-occurrence patterns; then, we leverage manifold learning to capture (1) single-period categorical semantics of POIs to enforce semantically similar POI embedding to be close and (2) cross-period categorical semantics to align multi-temporal POI embedding in a unified embedding space. We conducted experiments in Shenzhen, China, which demonstrates that the proposed method is effective. Compared with several baseline models, MT-POI2Vec can better align multi-temporal POIs and thus achieve higher performance in LUCD. In addition, our model can effectively identify areas with unchanged land use and land use changes in residential and industrial areas at a fine scale.

We present a novel approach for estimating the proportional distributions of function types (i.e. functional distributions) in an urban area through learning semantics preserved embeddings of points-of-interest (POIs). Specifically, we represent POIs as low-dimensional vectors to capture (1) the spatial co-occurrence patterns of POIs and (2) the semantics conveyed by the POI hierarchical categories (i.e. categorical semantics). The proposed approach utilizes spatially explicit random walks in a POI network to learn spatial co-occurrence patterns, and a manifold learning algorithm to capture categorical semantics. The learned POI vector embeddings are then aggregated to generate regional embeddings with long short-term memory (LSTM) and attention mechanisms, to take account of the different levels of importance among the POIs in a region. Finally, a multilayer perceptron (MLP) maps regional embeddings to functional distributions. A case study in Xiamen Island, China implements and evaluates the proposed approach. The results indicate that our approach outperforms several competitive baseline models in all evaluation measures, and yields a relatively high consistency between the estimation and ground truth. In addition, a comprehensive error analysis unveils several intrinsic limitations of POI data for this task, e.g. ambiguous linkage between POIs and functions.

Empirical data are limited to decipher where people live and work in large cities; however, neighborhood information, such as street view image, is rich and abundant. We construct a ResNet-50-based social detection model to explore the potential relationship between street view images and job-housing attributes. The method extracts street view images of a neighborhood in all eight directions to predict land parcels’ job-housing attributes and uses an entropy index to measure the degree of job-housing mixture in Shenzhen as an example. The social-detection model performs well with a low RMSE (0.1094) in identifying job-housing patterns. The eight-direction neighborhood method shows the best support for sufficient neighborhood information from street view images (RMSE = 0.1135) compared with other neighborhood methods. This study demonstrates the feasibility of using street-view images and deep learning to characterize job-housing attributes consistent with findings from urban studies with socioeconomic data; for example, the research finding concurs that Shenzhen has many high job-housing mixtures with very few areas designated for jobs or residences. The proposed method, when applied regularly, can help monitor spatial dynamics of urban job-housing patterns to inform city planning and development.

The formulation of mixed urban land uses is not only intended to find the ideal scenario of land use but also regarded as a way toward sustainable urban development. We propose a geo-semantic mining approach Traj2Vec to quantify the trajectories of residents as high-dimensional semantic vectors. Then, a random forest (RF) method is used to model the relationship between the semantic vectors and mixed urban land uses. The proposed Traj2Vec approach can obtain the highest accuracy (OA = 0.7733, kappa = 0.7245) in urban land-use classification and a high average proportion accuracy (64.0%) in capturing the proportions of urban land-use types. Diversity analysis indicates that Shenzhen has a high degree of mixed urban land use at the scale of a street block. By analyzing the mixing index and the travel distance, we find a weak but significant negative correlation between them (r=−0.107, p<0.001), which not only confirms the conclusion that an increase in the degree of mixing will reduce the travel distances of residents but also verifies the mixing index. This suggests that urban planning should focus on mixed urban land uses, which can reduce the travel distances of residents, reduce energy consumption, and make cities more compact.

Vector-based cellular automata (VCA) models have been applied in land use change simulations at fine scales. However, the neighborhood effects of the driving factors are rarely considered in the exploration of the transition suitability of cells, leading to lower simulation accuracy. This study proposes a convolutional neural network (CNN)-VCA model that adopts the CNN to extract the high-level features of the driving factors within a neighborhood of an irregularly shaped cell and discover the relationships between multiple land use changes and driving factors at the neighborhood level. The proposed model was applied to simulate urban land use changes in Shenzhen, China. Compared with several VCA models using other machine learning methods, the proposed CNN-VCA model obtained the highest simulation accuracy (figure-of-merit = 0.361). The results indicated that the CNN-VCA model can effectively uncover the neighborhood effects of multiple driving factors on the developmental potential of land parcels and obtain more details on the morphological characteristics of land parcels. Moreover, the land use patterns of 2020 and 2025 under an ecological control strategy were simulated to provide decision support for urban planning.

Though global-coverage urban perception datasets have been recently created using machine learning, their efficacy in accurately assessing local urban perceptions for other countries and regions remains a problem. Here we describe a human-machine adversarial scoring framework using a methodology that incorporates deep learning and iterative feedback with recommendation scores, which allows for the rapid and cost-effective assessment of the local urban perceptions for Chinese cities. Using the state-of-the-art Fully Convolutional Network (FCN) and Random Forest (RF) algorithms, the proposed method provides perception estimations with errors less than 10%. The driving factor analysis from both the visual and urban functional aspects demonstrated its feasibility in facilitating local urban perception derivations. With high-throughput and high-accuracy scorings, the proposed human-machine adversarial framework offers an affordable and rapid solution for urban planners and researchers to conduct local urban perception assessments.

An in-depth analysis of the urban road network structure plays an essential role in understanding the distribution of urban functional area. To concentrate topologically densely connected road segments, communities of urban roads provide a new perspective to study the structure of the network. In this study, based on OpenStreetMap (OSM) roads and points-of-interest (POI) data, we employ the Infomap community detection algorithm to identify the hierarchical community in city roads and explore the shaping role roads play in urban space and their relation with the distribution of urban functional areas. The results demonstrate that the distribution of communities at different levels in Guangzhou, China reflects the urban spatial relation between the suburbs and urban centers and within urban centers. Moreover, the study explored the functional area characteristics at the community scale and identified the distribution of various functional areas. Owing to the structure information contained in the identification process, the detected community can be used as a basic unit in other urban studies. In general, with the community-based network, this study proposes a novel method of combining city roads with urban space and functional zones, providing necessary data support and academic guidance for government and urban planners.

Intercity transportation infrastructures and services determine the depth and breadth of the spatial interactions among cities within an urban agglomeration, and have profound impacts on the spatial structure of the urban agglomeration. To evaluate whether the public intercity ground transportation infrastructures and services (i.e. passenger trains and long-distance buses) can support the integration and development of urban agglomerations, we propose a method for ‘transportation cluster’ detection (TCD), which has three unique features: (1) the K-shortest paths are used to quantify the proximity between cities, which is more in line with people’s travel behaviors; (2) a dendrogram is obtained through hierarchical clustering to reveal the structural hierarchies of transportation clusters; and (3) the integration of geo-modularity and hierarchical clustering assures high strength of division of transportation networks. The proposed TCD method was applied to the network of passenger trains, the network of long-distance buses, and the combined network of both in mainland China, respectively. By comparing the resultant transportation clusters with the urban agglomerations delineated by the Chinese government, cities that have weak transportation connections with other cities within an urban agglomeration were identified, and such findings could help devise transportation planning to better support the integrated development of urban agglomerations.

Along with the gradually accelerated urbanization process, simulating and predicting the future pattern of the city is of great importance to the prediction and prevention of some environmental, economic and urban issues. Previous studies have generally integrated traditional machine learning with cellular automaton (CA) models to simulate urban development. Nevertheless, difficulties still exist in the process of obtaining more accurate results with CA models; such difficulties are mainly due to the insufficient consideration of neighborhood effects during urban transition rule mining. In this paper, we used an effective deep learning method, named convolution neural network for united mining (UMCNN), to solve the problem. UMCNN has substantial potential to get neighborhood information from its receptive field. Thus, a novel CA model coupled with UMCNN and Markov chain was designed to improve the performance of simulating urban expansion processes. Choosing the Pearl River Delta of China as the study area, we excavate the driving factors and the transformational relations revealed by the urban land-use patterns in 2000, 2005 and 2010 and further simulate the urban expansion status in 2020 and 2030. Additionally, three traditional machine-learning-based CA models (LR, ANN and RFA) are built to attest the practicality of the proposed model. In the comparison, the proposed method reaches the highest simulation accuracy and landscape index similarity. The predicted urban expansion results reveal that the economy will continue to be the primary factor in the study area from 2010 to 2030. The proposed model can serve as guidance in urban planning and government decision-making.

Urban land use information plays an important role in urban management, government policy-making, and population activity monitoring. However, the accurate classification of urban functional zones is challenging due to the complexity of urban systems. Many studies have focused on urban land use classification by considering features that are extracted from either high spatial resolution (HSR) remote sensing images or social media data, but few studies consider both features due to the lack of available models. In our study, we propose a novel scene classification framework to identify dominant urban land use type at the level of traffic analysis zone by integrating probabilistic topic models and support vector machine. A land use word dictionary inside the framework was built by fusing natural–physical features from HSR images and socioeconomic semantic features from multisource social media data. In addition to comparing with manual interpretation data, we designed several experiments to test the land use classification accuracy of our proposed model with different combinations of previously acquired semantic features. The classification results (overall accuracy = 0.865, Kappa = 0.828) demonstrate the effectiveness of our strategy that blends features extracted from multisource geospatial data as semantic features to train the classification model. This method can be applied to help urban planners analyze fine urban structures and monitor urban land use changes, and additional data from multiple sources will be blended into this proposed framework in the future.

Cellular automata (CA) have been widely used to simulate complex urban development processes. Previous studies indicated that vector-based cellular automata (VCA) could be applied to simulate urban land-use changes at a realistic land parcel level. Because of the complexity of VCA, these studies were conducted at small scales or did not adequately consider the highly fragmented processes of urban development. This study aims to build an effective framework called dynamic land parcel subdivision (DLPS)-VCA to accurately simulate urban land-use change processes at the land parcel level. We introduce this model in urban land-use change simulations to reasonably divide land parcels and introduce a random forest algorithm (RFA) model to explore the transition rules of urban land-use changes. Finally, we simulate the land-use changes in Shenzhen between 2009 and 2014 via the proposed DLPS-VCA model. Compared to the advanced Patch-CA and RFA-VCA models, the DLPS-VCA model achieves the highest simulation accuracy (Figure-of-Merit = 0.232), which is 32.57% and 18.97% higher respectively, and is most similar to the actual land-use scenario (similarity = 94.73%) at the pattern level. These results indicate that the DLPS-VCA model can both accurately split the land during urban land-use changes and significantly simulate urban expansion and urban land-use changes at a fine scale. Furthermore, the land-use change rules that are based on DPLS-VCA mining and the simulation results of several future urban development scenarios can act as guides for future urban planning policy formulation.

Urban land use information plays an essential role in a wide variety of urban planning and environmental monitoring processes. During the past few decades, with the rapid technological development of remote sensing (RS), geographic information systems (GIS) and geospatial big data, numerous methods have been developed to identify urban land use at a fine scale. Points-of-interest (POIs) have been widely used to extract information pertaining to urban land use types and functional zones. However, it is difficult to quantify the relationship between spatial distributions of POIs and regional land use types due to a lack of reliable models. Previous methods may ignore abundant spatial features that can be extracted from POIs. In this study, we establish an innovative framework that detects urban land use distributions at the scale of traffic analysis zones (TAZs) by integrating Baidu POIs and a Word2Vec model. This framework was implemented using a Google open-source model of a deep-learning language in 2013. First, data for the Pearl River Delta (PRD) are transformed into a TAZ-POI corpus using a greedy algorithm by considering the spatial distributions of TAZs and inner POIs. Then, high-dimensional characteristic vectors of POIs and TAZs are extracted using the Word2Vec model. Finally, to validate the reliability of the POI/TAZ vectors, we implement a K-Means-based clustering model to analyze correlations between the POI/TAZ vectors and deploy TAZ vectors to identify urban land use types using a random forest algorithm (RFA) model. Compared with some state-of-the-art probabilistic topic models (PTMs), the proposed method can efficiently obtain the highest accuracy (OA = 0.8728, kappa = 0.8399). Moreover, the results can be used to help urban planners to monitor dynamic urban land use and evaluate the impact of urban planning schemes.

Fine-scale population distribution data at the building level play an essential role in numerous fields, for example urban planning and disaster prevention. The rapid technological development of remote sensing (RS) and geographical information system (GIS) in recent decades has benefited numerous population distribution mapping studies. However, most of these studies focused on global population and environmental changes; few considered fine-scale population mapping at the local scale, largely because of a lack of reliable data and models. As geospatial big data booms, Internet-collected volunteered geographic information (VGI) can now be used to solve this problem. This article establishes a novel framework to map urban population distributions at the building scale by integrating multisource geospatial big data, which is essential for the fine-scale mapping of population distributions. First, Baidu points-of-interest (POIs) and real-time Tencent user densities (RTUD) are analyzed by using a random forest algorithm to down-scale the street-level population distribution to the grid level. Then, we design an effective iterative building-population gravity model to map population distributions at the building level. Meanwhile, we introduce a densely inhabited index (DII), generated by the proposed gravity model, which can be used to estimate the degree of residential crowding. According to a comparison with official community-level census data and the results of previous population mapping methods, our method exhibits the best accuracy (Pearson R = .8615, RMSE = 663.3250, p < .0001). The produced fine-scale population map can offer a more thorough understanding of inner city population distributions, which can thus help policy makers optimize the allocation of resources.