Next Article in Journal
Tri-Clustering Based Exploration of Temporal Resolution Impacts on Spatio-Temporal Clusters in Geo-Referenced Time Series
Next Article in Special Issue
Semantic Segmentation of Remote-Sensing Imagery Using Heterogeneous Big Data: International Society for Photogrammetry and Remote Sensing Potsdam and Cityscape Datasets
Previous Article in Journal
An Analysis of Online Reputation Indicators by Means of Geostatistical Techniques—The Case of Rural Accommodation in Extremadura, Spain
Open AccessArticle

CostNet: A Concise Overpass Spatiotemporal Network for Predictive Learning

1
Future GIS Laboratory, SuperMap Software Co., Ltd., Beijing 100015, China
2
School of Software and Microelectronics, Peking University, Beijing 102600, China
3
Institute of Geographic Sciences and Natural Resources Research, China Academy of Science, Beijing 100101, China
4
360 Security Technology Inc., Beijing 100015, China
*
Author to whom correspondence should be addressed.
ISPRS Int. J. Geo-Inf. 2020, 9(4), 209; https://doi.org/10.3390/ijgi9040209
Received: 13 January 2020 / Revised: 29 February 2020 / Accepted: 7 March 2020 / Published: 30 March 2020
(This article belongs to the Special Issue Geospatial Big Data and Machine Learning Opportunities and Prospects)
Predicting the futures from previous spatiotemporal data remains a challenging topic. There have been many previous works on predictive learning. However, mainstream models suffer from huge memory usage or the gradient vanishing problem. Enlightened by the idea from the resnet, we propose CostNet, a novel recursive neural network (RNN)-based network, which has a horizontal and vertical cross-connection. The core of this network is a concise unit, named Horizon LSTM with a fast gradient transmission channel, which can extract spatial and temporal representations effectively to alleviate the gradient propagation difficulty. In the vertical direction outside of the unit, we add overpass connections from unit output to the bottom layer, which can capture the short-term dynamics to generate precise predictions. Our model achieves better prediction results on moving-mnist and radar datasets than the state-of-the-art models. View Full-Text
Keywords: spatiotemporal network; predictive learning; horizon LSTM; vertical structure; encoder-decoder architecture spatiotemporal network; predictive learning; horizon LSTM; vertical structure; encoder-decoder architecture
Show Figures

Figure 1

MDPI and ACS Style

Sun, F.; Li, S.; Wang, S.; Liu, Q.; Zhou, L. CostNet: A Concise Overpass Spatiotemporal Network for Predictive Learning. ISPRS Int. J. Geo-Inf. 2020, 9, 209.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop