Electric load forecasting (ELF) is vitally beneficial for electrical power planning and economical running in smart grid. However, the medium-term load forecasting has been rarely studied. In addition, existing ELF models mainly consider the impact of limited external factors, which are usually difficult to forecast accurately. In this paper, the characteristics of the electric loads are analyzed and used as a guideline for the design of the proposed methods. To fully exploit the quasi-periodicity with different time ranges, i.e., year, quarter, month, and week, two deep learning methods, time-dependency convolutional neural network (TD-CNN), and cycle-based long short-term memory (C-LSTM) network are proposed to improve the forecasting performance of short-term load forecasting and MTLF with a little payload of computational complexity. Both of them only utilize the historical electric load and can mine the underlying load patterns by extracting the long-term global integrated features and short-term local similar features. By representing the loads as pixels and rearranging them into a 2-D photograph, TD-CNN transforms the temporal correlation of load series into the spatial correlation and keeps the long-term memory. Specifically, the convolutional kernel with special size targeted to load data is designed to extract the local pattern with similar characteristic, while the pooling layer is removed in order to keep the finer features. Moreover, in order to extract the temporal correlation between the long-term sequences with lower complexity, the proposed C-LSTM method generates a new short series from the original long load series without information loss. The LSTM is then applied to model the dynamical relationship of the load series with shorter time steps. The experimental results show that the proposed methods outperform the existing method with greatly reduced computation complexity, whose training time is about two-to-five times shorter than the existing method.

Short-term traffic prediction (STTP) is one of the most critical capabilities in Intelligent Transportation Systems (ITS), which can be used to support driving decisions, alleviate traffic congestion and improve transportation efficiency. However, STTP of large-scale road networks remains challenging due to the difficulties of effectively modeling the diverse traffic patterns by high-dimensional time series. Therefore, this paper proposes a framework that involves a deep clustering method for STTP in large-scale road networks. The deep clustering method is employed to supervise the representation learning in a visualized way from the large unlabeled dataset. More specifically, to fully exploit the traffic periodicity, the raw series is first divided into a number of sub-series for triplet generation. The convolutional neural networks (CNNs) with triplet loss are utilized to extract the features of shape by transforming the series into visual images. The shape-based representations are then used to cluster road segments into groups. Thereafter, a model sharing strategy is further proposed to build recurrent NNs-based predictions through group-based models (GBMs). GBM is built for a type of traffic patterns, instead of one road segment exclusively or all road segments uniformly. Our framework can not only significantly reduce the number of prediction models, but also improve their generalization by virtue of being trained on more diverse examples. Furthermore, the proposed framework over a selected road network in Beijing is evaluated. Experiment results show that the deep clustering method can effectively cluster the road segments and GBM can achieve comparable prediction accuracy against the IBM with less number of prediction models.

The geological characteristics of old landslides can provide crucial information for the task of landslide protection. However, detecting old landslides from high-resolution remote sensing images (HRSIs) is of great challenges due to their partially or strongly transformed morphology over a long time and thus the limited difference with their surroundings. Additionally, small-sized datasets can restrict in-depth learning. To address these challenges, this paper proposes a new iterative classification and semantic segmentation network (ICSSN), which can significantly improve both object-level and pixel-level classification performance by iteratively upgrading the feature extraction module shared by the object classification and semantic segmentation networks. To improve the detection performance on small-sized datasets, object-level contrastive learning is employed in the object classification network featuring a siamese network to realize global features extraction, and a sub-object-level contrastive learning method is designed in the semantic segmentation network to efficiently extract salient features from boundaries of landslides. An iterative training strategy is also proposed to fuse features in the semantic space, further improving both the object-level and pixel-level classification performances. The proposed ICSSN is evaluated on a real-world landslide dataset, and experimental results show that it greatly improves both the classification and segmentation accuracy of old landslides. For the semantic segmentation task, compared to the baseline, the F1 score increases from 0.5054 to 0.5448, the mIoU improves from 0.6405 to 0.6610, the landslide IoU grows from 0.3381 to 0.3743, the PA is improved from 0.945 to 0.949, and the object-level detection accuracy of old landslides surges from 0.55 to 0.90. For the object classification task, the F1 score increases from 0.8846 to 0.9230, and the accuracy score is up from 0.8375 to 0.8875.

Big data analytics has been rapidly integrated into Intelligent Transportation System (ITS), empowering diverse applications such as real-time traffic prediction and management. However, incomplete traffic time-series data during the data analysis are nearly inevitable due to the constraints of data collection or packet loss in the communication process. Existing tensor-based completion methods fail to perform well in consecutively missing (CM) cases where a sub-series of the traffic time series is completely missing. Moreover, their high computational complexity prevents the road network-level implementation. Therefore, to tackle these problems, a batch-oriented traffic data completion method for large-scale road networks is proposed in this paper. In order to preserve multi-way natures of traffic data, we first model the traffic data by tensors so that traffic data completion becomes a tensor completion problem. Several types of tensor structures are adopted in order to analyze their impacts on traffic data completion. Thereafter, a Content-Aware traffic data completion method is further developed based on the Generative Adversarial Net (CA-GAN). More specifically, the formulated traffic tensors are interpreted as samples from a high-dimensional traffic distribution and a GAN is then proposed to learn this distribution. By considering effects of traffic data from different days and links, a weighted loss function is employed to search for the raw traffic tensor in the obtained traffic distribution. Afterwards, the estimated raw traffic tensor is used to complete the missing data. Visualization results demonstrate that our GANs can produce verisimilar traffic patterns with different time spans. Finally, our experiments on real traffic datasets show that the proposed CA-GAN method can effectively batch incomplete traffic tensors in CM cases with fast recovery process.

The rapid and accurate extraction of wide-area coseismic landslide locations is critical in earthquake emergencies. At present, the extraction of coseismic landslides is mainly based on post-earthquake site investigation or the interpretation of human–computer interactions based on remote sensing images. However, the identification efficiency is low, which seriously delays the earthquake emergency response. On the basis of the available multisource and multiscale remote sensing data, numerous studies have been carried out on the methods of coseismic landslide extraction, such as pixel analysis, object-oriented analysis, change detection, and machine learning. However, the effectiveness of coseismic landslide extraction was low in wide areas with complex topographic and geomorphic backgrounds. Therefore, this paper offers a comprehensive study of the factors influencing coseismic landslides and researches rapid and accurate wide-area coseismic landslide extraction methods with multisource remote sensing and geoscience technology. These techniques include digital elevation modeling (DEM) and its derived slopes and aspects. An embedded multichannel spectral–topographic feature fusion model for coseismic landslide extraction based on DeepLab V3+ is proposed, and a knowledge-enhanced deep learning information extraction method integrating geological knowledge is formed. Using the Jiuzhaigou Ms7.0 earthquake (seismic intensity VIII) in Sichuan Province, China, a comparison of landslide extraction models and strategies is carried out. The results show that the model proposed in this paper achieves the best balance in the accuracy and efficiency of wide-area extractions. Using multiple feature data of coseismic landslides, the problem of mixed pixels is solved. The rate of the misidentification of landslides as clouds, snow, buildings, and roads is significantly lower than in other methods. The identified landslide boundaries are smoother and more accurate, and the connectivity is better. Compared with other methods, ours can more accurately eliminate landslides not triggered by the Jiuzhaigou earthquake. While using the image block strategy to ensure extraction efficiency, it also improves the extraction accuracy of wide-area coseismic landslides in complex backgrounds.

Accurate analysis of traffic flow (TF) data is crucial for the vehicular applications. Conventional deep learning models require task-specific training and are susceptible to high-frequency disturbances, degrading the feature representation capability. To overcome these limitations, this paper proposes a Token-based Self-Supervised Network (TSSN) that can learn TF features in both tokenization and task-agnostic manners. It provides a properly bootstrapped pre-training model for various downstream tasks. In support of the edge computing and vehicular cloud computing, the pooled computational resources facilitate real-time inferences of downstream models. In TSSN, TF data are segmented into tokens. A pretext task, named as Masked Token Prediction (MTP), is then developed to allow TSSN to understand the underlying correlations of TF by predicting randomly masked tokens. By utilizing MTP, TSSN is able to extract the high-level intrinsic semantics of TF, and provide general-purpose token embeddings, leading to improved overall performance and enhanced ability to adapt to different tasks. By substituting the last fully-connected layers with a group of untrained new layers and fine-tuning using small-scale task-specific data, TSSN can be utilized for a variety of downstream tasks in vehicular applications. Simulation results indicate that the TSSN enhances overall performance in comparison to state-of-the-art models.