With the goal of predicting the future rainfall intensity in a local region over a relatively short period time, precipitation nowcasting has been a long-time scientific challenge with great social and economic impact. The radar echo extrapolation approaches for precipitation nowcasting take radar echo images as input, aiming to generate future radar echo images by learning from the historical images. To effectively handle complex and high non-stationary evolution of radar echoes, we propose to decompose the movement into optical flow field motion and morphologic deformation. Following this idea, we introduce Flow-Deformation Network (FDNet), a neural network that models flow and deformation in two parallel cross pathways. The flow encoder captures the optical flow field motion between consecutive images and the deformation encoder distinguishes the change of shape from the translational motion of radar echoes. We evaluate the proposed network architecture on two real-world radar echo datasets. Our model achieves state-of-the-art prediction results compared with recent approaches. To the best of our knowledge, this is the first network architecture with flow and deformation separation to model the evolution of radar echoes for precipitation nowcasting. We believe that the general idea of this work could not only inspire much more effective approaches but also be applied to other similar spatiotemporal prediction tasks.
In wireless multimedia sensor networks (WMSNs), wirelessly interconnected devices are able to ubiquitously retrieve multimedia contents such as video and audio streams from the environment. However, since WMSN applications are large-scale, dynamic and highly concurrent, how to achieve both effective multimedia device resource management and collaborative task scheduling simultaneously becomes a serious problem. In this paper, using the hierarchical modeling technique, we first propose a device ability model including spatial information. In order to solve the problem of insufficient capacity of single devices, we then give a composite device ability model and relevant calculation formulae. Next, we introduce a novel device resource matching technique based on the proposed model. Compared with previous works, experimental results show that our technique achieves better recall and precision and meets WMSN application needs more effectively. Furthermore, our proposed approach greatly reduces the design complexity as well as the workload of application designers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.