Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Incremental Dual-memory LSTM in Land Cover Prediction

Incremental Dual-memory LSTM in Land Cover Prediction KDD 2017 Research Paper KDD ™17, August 13 “17, 2017, Halifax, NS, Canada Incremental Dual-memory LSTM in Land Cover Prediction Xiaowei Jia1 , Ankush Khandelwal1 , Guruprasad Nayak1 , James Gerber2 , Kimberly Carlson3 , Paul West2 , Vipin Kumar1 Department of Computer Science and Engineering, University of Minnesota Institute on the Environment, University of Minnesota Department of Natural Resources and Environmental Management, University of Hawai ™i M¯noa a jiaxx221@umn.edu, {ankush,nayak,kumar}@cs.umn.edu, 2 {jsgerber,pcwest}@umn.edu, kimberly.carlson@hawaii.edu ABSTRACT importantly, the required substantial human resources make it infeasible for large regions or for a long period. Therefore, high-quality land cover mapping products created by manual labeling are only available in speci c years in history and usually cannot cover recent years due to the time expense of visual interpretation. In contrast, we focus on automated land cover monitoring and develop a classi cation model to map land covers in recent years. In this way, we allow the scienti c domain researcher to analyze the latest land cover conditions and land cover changes. Speci cally, assume we have the manually created ground-truth in history (e.g. before 2010), we aim to train a classi cation model to learn the land cover patterns from ground-truth http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Incremental Dual-memory LSTM in Land Cover Prediction

Association for Computing Machinery — Aug 13, 2017

Loading next page...
/lp/association-for-computing-machinery/incremental-dual-memory-lstm-in-land-cover-prediction-8cvVKc5iFG

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Datasource
Association for Computing Machinery
Copyright
Copyright © 2017 by ACM Inc.
ISBN
978-1-4503-4887-4
doi
10.1145/3097983.3098112
Publisher site
See Article on Publisher Site

Abstract

KDD 2017 Research Paper KDD ™17, August 13 “17, 2017, Halifax, NS, Canada Incremental Dual-memory LSTM in Land Cover Prediction Xiaowei Jia1 , Ankush Khandelwal1 , Guruprasad Nayak1 , James Gerber2 , Kimberly Carlson3 , Paul West2 , Vipin Kumar1 Department of Computer Science and Engineering, University of Minnesota Institute on the Environment, University of Minnesota Department of Natural Resources and Environmental Management, University of Hawai ™i M¯noa a jiaxx221@umn.edu, {ankush,nayak,kumar}@cs.umn.edu, 2 {jsgerber,pcwest}@umn.edu, kimberly.carlson@hawaii.edu ABSTRACT importantly, the required substantial human resources make it infeasible for large regions or for a long period. Therefore, high-quality land cover mapping products created by manual labeling are only available in speci c years in history and usually cannot cover recent years due to the time expense of visual interpretation. In contrast, we focus on automated land cover monitoring and develop a classi cation model to map land covers in recent years. In this way, we allow the scienti c domain researcher to analyze the latest land cover conditions and land cover changes. Speci cally, assume we have the manually created ground-truth in history (e.g. before 2010), we aim to train a classi cation model to learn the land cover patterns from ground-truth

There are no references for this article.