Search

The profound impacts of severe air pollution on human health, ecological balance, and economic stability are undeniable. Precise air quality forecasting stands as a crucial necessity, enabling governmental bodies and vulnerable communities to proactively take essential measures to reduce exposure to detrimental pollutants. Previous research has primarily focused on predicting air quality using only time-series data. However, the importance of remote-sensing image data has received limited attention. This paper proposes a new multi-modal deep-learning model, Res-GCN, which integrates high spatial resolution remote-sensing images and time-series air quality data from multiple stations to forecast future air quality. Res-GCN employs two deep-learning networks, one utilizing the residual network to extract hidden visual information from remote-sensing images, and another using a dynamic spatio-temporal graph convolution network to capture spatio-temporal information from time-series data. By extracting features from two different modalities, improved predictive performance can be achieved. To demonstrate the effectiveness of the proposed model, experiments were conducted on two real-world datasets. The results show that the Res-GCN model effectively extracts multi-modal features, significantly enhancing the accuracy of multi-step predictions. Compared to the best-performing baseline model, the multi-step prediction's mean absolute error, root mean square error, and mean absolute percentage error increased by approximately 6%, 7%, and 7%, respectively. [ABSTRACT FROM AUTHOR]

Urban space architectural color is the first feature to be perceived in a complex vision beyond shape, texture and material, and plays an important role in the expression of urban territory, humanity and style. However, because of the difficulty of color measurement, the study of architectural color in street space has been difficult to achieve large-scale and fine development. The measurement of architectural color in urban space has received attention from many disciplines. With the development and promotion of information technology, the maturity of street view big data and deep learning technology has provided ideas for the research of street architectural color measurement. Based on this background, this study explores a highly efficient and large-scale method for determining architectural colors in urban space based on deep learning technology and street view big data, with street space architectural colors as the research object. We conducted empirical research in Jiefang North Road, Tianjin. We introduced the SegNet deep learning algorithm to semantically segment the street view images, extract the architectural elements and optimize the edges of the architecture. Based on K-Means clustering model, we identified the colors of the architectural elements in the street view. The accuracy of the building color measurement results was cross-sectionally verified by means of a questionnaire survey. The validation results show that the method is feasible for the study of architectural colors in street space. Finally, the overall coordination, sequence continuity, and primary and secondary hierarchy of architectural colors of Jiefang North Road in Tianjin were analyzed. The results show that the measurement model can realize the intuitive expression of architectural color information, and also can assist designers in the analysis of architectural color in street space with the guidance of color characteristics. The method helps managers, planners and even the general public to summarize the characteristics of color and dig out problems, and is of great significance in the assessment and transformation of the color quality of the street space environment. [ABSTRACT FROM AUTHOR]

In weather forecasting, numerical weather prediction (NWP) that is based on physical models requires proper post-processing before it can be applied to actual operations. Therefore, research on intelligent post-processing algorithms has always been an important topic in this field. This paper proposes a model output deep learning (MODL) method for post-processing, which can improve the forecast effect of numerical weather prediction. MODL is an end-to-end post-processing method based on deep convolutional neural network, which directly learns the mapping relationship between the forecast fields output by numerical model and the observation temperature field in order to obtain more accurate temperature forecasts. MODL modifies the existing deep convolution model according to the post-processing problem's characteristics, thereby improving the performance of the weather forecast. This paper uses The International Grand Global Ensemble (TIGGE) dataset from European Centre for Medium-Range Weather Forecasts (ECMWF) and the observed air temperature of 2 m obtained from Tianjin meteorological station in order to test the post-processing performance of MODL. The MODL method applied to temperature in post-processing is compared with the ECMWF forecast, Model Output Statistics (MOS) methods, and Model Output Machine Learning (MOML) methods. The Root Mean Square Error (RMSE) of the temperature field predicted by MODL and the observed temperature field is smaller than the other models and the accuracy of the temperature difference of 2 °C (Acc) is higher, especially where the prediction time is in the first three days. The lightweight nature of MODL also makes it suitable for most operations. [ABSTRACT FROM AUTHOR]

Under the Beijing-Tianjin regional comprehensive transportation system, the flow of air passengers between multiple airports in the region is more frequent. The fundamental reason for the flow of air passengers is that there are differences in the level of service quality provided by airports and airlines in the region. Passengers' choice intention is the consumption and purchase decision of passengers on aviation services. By constructing a Logit model, this paper analyzes the degree of influence on the travel choice intention of air passengers in the Beijing-Tianjin region from five aspects: individual passenger demographic characteristics, travel purpose, ground transportation characteristics, airport operation capacity, and airport soft power. Passengers can effectively predict the choice of air travel mode in the Beijing-Tianjin region. The results show that Beijing Capital Airport is favored by business travelers; Beijing Daxing International Airport is favored by travelers because of its fast security check-through speed; for Tianjin Binhai International Airport, the convenience of getting in and out of the airport by car and the speed of airport security check-through are two significant factors. Indicators do not affect the selection of airports; reasonable follow-up arrangements when airport flights are delayed are the only significant but negatively correlated factor; the research design results provide new ideas for the analysis of passenger travel mode selection behavior in multiple airport areas, enriching the data-driven research on transportation choices. [ABSTRACT FROM AUTHOR]

Understanding public perceptions of images of urban public spaces can guide efforts to improve urban vitality and spatial diversity. The rise of social media data and breakthroughs in deep learning frameworks for computer vision provide new opportunities for studying public perceptions in public spaces. While social media research methods already exist for extracting geo-information on public preferences and emotion analysis findings from geodata, this paper aims at deep learning analysis by building a VGG-16 image classification method that enhanced the research content of images without geo-information. In this study, 1940 Flickr images of the Haihe River in Tianjin were identified in multiple scenes with deep learning. The regularized VGG-16 architecture showed high accuracies of 81.75% for the TOP-1 and 96.75% for the TOP-5 and Grad-CAM visualization modules for the interpretation of classification results. The result of the present work indicate that images of the Haihe River are dominated by skyscrapers, bridges, promenades, and urban canals. After using kernel density to visualize the spatial distribution of Flickr images with geodata, it was found that there are three vitality areas in Haihe River. However, the kernel density result also shows that judging spatial visualization based solely on geodata is incomplete. The spatial distribution can be used as an assistant function in the case of the under-representation of geodata. Collectively, the field of how to apply computer vision to urban design research was explored and extended in this trial study. [ABSTRACT FROM AUTHOR]

Demand-side management (DSM) increases the complexity of forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from the data set. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to convert the continuity feature of input data into binomial distribution feature. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on the genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods. [ABSTRACT FROM AUTHOR]

The representational image of the city has attracted people's long-term attention. Nevertheless, the mechanism of interaction between the image and the built environment (BE) and image studies at the town scale have not been fully explored. In this study, we collected multi-source data from 26 characteristic towns in Tianjin, China. We explored a deep learning approach to recognize social media data, which led to the development of quantifiable town uniqueness image (UI) variables. We studied the influence of the BE on the town UI and the moderating effects of positive emotions on the relationship between the two. The results showed that positive emotions had significantly positive moderating effects on the water system ratio's effect on UI, but weakened sidewalk density and tourist attraction density. They also inhibited the negative effects of road connectivity but could strengthen the negative effects of the sky view factor and points of interest (POI) mix. The moderating effects on other variables are relatively mediocre. This study helps to reveal the inner mechanism of BE and town image. It is conducive to accurately coordinating the relationship between planning policies and design strategies, optimizing resource allocation, and promoting sustainable town development. [ABSTRACT FROM AUTHOR]

In the field of building information modeling (BIM), converting existing buildings into BIM by using orthophotos with digital surface models (DSMs) is a critical technical challenge. Currently, the BIM reconstruction process is hampered by the inadequate accuracy of building boundary extraction when carried out using existing technology, leading to insufficient correctness in the final BIM reconstruction. To address this issue, this study proposes a novel deep-learning- and postprocessing-based approach to automating reconstruction in BIM by using orthophotos with DSMs. This approach aims to improve the efficiency and correctness of the reconstruction of existing buildings in BIM. The experimental results in the publicly available Tianjin and Urban 3D reconstruction datasets showed that this method was able to extract accurate and regularized building boundaries, and the correctness of the reconstructed BIM was 85.61% and 82.93%, respectively. This study improved the technique of extracting regularized building boundaries from orthophotos and DSMs and achieved significant results in enhancing the correctness of BIM reconstruction. These improvements are helpful for the reconstruction of existing buildings in BIM, and this study provides a solid foundation for future improvements to the algorithm. [ABSTRACT FROM AUTHOR]

In this study, we propose a real-time ship anomaly detection method driven by Automatic Identification System (AIS) data. The method uses ship trajectory clustering classes as a normal model and a deep learning algorithm as an anomaly detection tool. The method is divided into three main steps: (1) quality maintenance of the original AIS data, (2) extraction of normal ship trajectory clusters using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), in which a segmented improved Dynamic Time Warping (DTW) algorithm is used to measure the degree of trajectory similarity, (3) the clustering results are used as a normative model to train a Bi-directional Gated Recurrent Unit (BiGRU) recurrent neural network, which is used as a trajectory predictor to achieve real-time ship anomaly detection. Experiments were conducted using real AIS data from the port of Tianjin, China. The experimental results are manifold. Firstly, the data pre-processing process effectively improves the quality of raw AIS data. Secondly, the ship trajectory clustering model can accurately classify the traffic flow of different modes in the sea area. Moreover, the trajectory prediction result of the BiGRU model has the smallest error with the actual ship trajectory and has a better trajectory prediction performance compared with the Long Short-Term Memory Network model (LSTM) and Gated Recurrent Unit (GRU). In the final anomaly detection experiment, the detection accuracy and timeliness of the BiGRU model are also higher than LSTM and GRU. Therefore, the proposed method can achieve effective and timely detection of ship anomalous behaviors in terms of position, heading and speed during ship navigation, which provides insight to enhance the intelligence of marine traffic supervision and improve the safety of marine navigation. [ABSTRACT FROM AUTHOR]

There is a collection of a large amount of automatic identification system (AIS) data that contains ship encounter information, but mining the collision avoidance knowledge from AIS big data and carrying out effective machine learning is a difficult problem in current maritime field. Herein, first the Douglas–Peucker (DP) algorithm was used to preprocess the AIS data. Then, based on the ship domain the risk of collision was identified. Finally, a double-gated recurrent unit neural network (GRU-RNN) was constructed to learn unmanned surface vehicle (USV) collision avoidance decision from the extracted data of successful encounters of ships. The double GRU-RNN was trained on the 2015 Tianjin Port AIS dataset to realize the effective learning of ship encounter data. The results indicated that the double GRU-RNN could effectively learn the collision avoidance pattern hidden in AIS big data, and generate corresponding ship collision-avoidance decisions for different maritime navigation states. This study contributes significantly to the increased efficiency and safety of sea operations. The proposed method could be potentially applied to USV technology and intelligence collision avoidance. [ABSTRACT FROM AUTHOR]

At present, deep-learning methods have been widely used in road extraction from remote-sensing images and have effectively improved the accuracy of road extraction. However, these methods are still affected by the loss of spatial features and the lack of global context information. To solve these problems, we propose a new network for road extraction, the coord-dense-global (CDG) model, built on three parts: a coordconv module by putting coordinate information into feature maps aimed at reducing the loss of spatial information and strengthening road boundaries, an improved dense convolutional network (DenseNet) that could make full use of multiple features through own dense blocks, and a global attention module designed to highlight high-level information and improve category classification by using pooling operation to introduce global information. When tested on a complex road dataset from Massachusetts, USA, CDG achieved clearly superior performance to contemporary networks such as DeepLabV3+, U-net, and D-LinkNet. For example, its mean IoU (intersection of the prediction and ground truth regions over their union) and mean F1 score (evaluation metric for the harmonic mean of the precision and recall metrics) were 61.90% and 76.10%, respectively, which were 1.19% and 0.95% higher than the results of D-LinkNet (the winner of a road-extraction contest). In addition, CDG was also superior to the other three models in solving the problem of tree occlusion. Finally, in universality research with the Gaofen-2 satellite dataset, the CDG model also performed well at extracting the road network in the test maps of Hefei and Tianjin, China. [ABSTRACT FROM AUTHOR]