Incremental Dual-memory LSTM in Land Cover Prediction

ABSTRACT

Land cover prediction is essential for monitoring global environmental change. Unfortunately, traditional classification models are plagued by temporal variation and emergence of novel/unseen land cover classes in the prediction process. In this paper, we propose an LSTM-based spatio-temporal learning framework with a dual-memory structure. The dual-memory structure captures both long-term and short-term temporal variation patterns, and is updated incrementally to adapt the model to the ever-changing environment. Moreover, we integrate zero-shot learning to identify unseen classes even without labelled samples. Experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed framework over multiple baselines in land cover prediction.

References

1. Kimberly M Carlson, Lisa M Curran, Gregory P Asner, Alice McDonald Pittman, Simon N Trigg, and J Marion Adeney 2013. Carbon emissions from forest conversion by Kalimantan oil palm plantations. Nature Climate Change (2013).
2. Yanwei Fu, Timothy M Hospedales, Tao Xiang, Zhenyong Fu, and Shaogang Gong 2014. Transductive multi-view embedding for zero-shot recognition and annotation European Conference on Computer Vision. Springer.
3. Jacob Goldberger, Geoffrey E Hinton, Sam T Roweis, and Ruslan Salakhutdinov 2004. Neighbourhood components analysis. In NIPS.
4. A Graves, M Liwicki, S Fernández, R Bertolami, H Bunke, and J Schmidhuber. 2009. A novel connectionist system for unconstrained handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2009).
5. Nancy B Grimm, Stanley H Faeth, Nancy E Golubiewski, Charles L Redman, Jianguo Wu, Xuemei Bai, and John M Briggs 2008. Global change and the ecology of cities. science (2008).
6. P. Gunarso, M. E. Hartoyo, F. Agus, Killeen, T. J., and J. Goon. 2013. RSPO, Kuala Lumpur, Malaysia. Reports from the technical panels of the 2nd greenhouse gas working group of the Roundtable on sustainable palm oil (2013).
7. Collin Homer, Chengquan Huang, Limin Yang, Bruce Wylie, and Michael Coan 2004. Development of a 2001 national land-cover database for the United States. Photogrammetric Engineering and Remote Sensing (2004).
8. Xiaowei Jia, Ankush Khandelwal, James Gerber, Kimberly Carlson, Paul West, and Vipin Kumar. 2016. Learning large-scale plantation mapping from imperfect annotators Big Data (Big Data), 2016 IEEE International Conference on. IEEE.
9. Xiaowei Jia, Ankush Khandelwal, Guruprasad Nayak, James Gerber, Kimberly Carlson, Paul West, and Vipin Kumar 2017. Predict Land Covers with Transition. Modeling and Incremental Learning Proceedings of the 2017 SIAM International Conference on Data Mining. SIAM.
10. Ian Jolliffe. 2002. Principal component analysis. Wiley Online Library.
11. Anuj Karpatne, Zhe Jiang, Ranga Raju Vatsavai, Shashi Shekhar, and Vipin Kumar 2016. Monitoring Land-Cover Changes: A Machine-Learning Perspective. IEEE Geoscience and Remote Sensing Magazine (2016).
12. Eric F Lambin, Bi L Turner, Helmut J Geist, Samuel B Agbola, Arild Angelsen, John W Bruce, Oliver T Coomes, Rodolfo Dirzo, Günther Fischer, Carl Folke, and others 2001. The causes of land-use and land-cover change: moving beyond the myths. Global environmental change (2001).
13. Xiaoyi Li, Xiaowei Jia, Hui Li, Houping Xiao, Jing Gao, and Aidong Zhang. 2015. DRN: Bringing Greedy Layer-Wise Training into Time Dimension Data Mining (ICDM), 2015 IEEE International Conference on. IEEE.
14. Viktor Losing, Barbara Hammer, and Heiko Wersing. 2016. KNN Classifier with Self Adjusting Memory for Heterogeneous Concept Drift ICDM.
15. Haobo Lyu, Hui Lu, and Lichao Mou 2016. Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection. Remote Sensing (2016).
16. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013).
17. Guruprasad Nayak, Varun Mithal, and Vipin Kumar. 2016. Multiple Instance Learning for burned area mapping using multi -temporal reflectance data. (2016).
18. Mohammad Norouzi, Mani Ranjbar, and Greg Mori. 2009. Stacks of convolutional restricted boltzmann machines for shift-invariant feature learning CVPR.
19. Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, and Tom M Mitchell 2009. Zero-shot learning with semantic output codes. In Advances in neural information processing systems.
20. RACHAEL Petersen, ED Goldman, N Harris, S Sargent, D Aksenov, A Manisha, and others 2016. Mapping tree plantations with multispectral imagery: preliminary results for seven tropical countries. WRI (2016).
21. Roger A Pielke. 2005. Land use and climate change. In Science.
22. Tobias Sauter, Björn Weitzenkamp, and Christoph Schneider. 2010. Spatio-temporal prediction of snow cover in the Black Forest mountain range using remote sensing and a recurrent neural network. International Journal of Climatology (2010).
23. Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng 2013. Zero-shot learning through cross-modal transfer. Advances in neural information processing systems.
24. Martin Sundermeyer, Ralf Schlüter, and Hermann Ney. 2012. LSTM Neural Networks for Language Modeling.. In Interspeech.
25. Qiong Wu, Hong-qing Li, Ru-song Wang, Juergen Paulussen, Yong He, Min Wang, Bi-hui Wang, and Zhen Wang. 2006. Monitoring and predicting land use change in Beijing using remote sensing and GIS. Landscape and urban planning (2006).
26. Guangxu Xun, Xiaowei Jia, Vishrawas Gopalakrishnan, and Aidong Zhang 2016. A Survey on Context Learning. IEEE Transactions on Knowledge and Data Engineering (2016).
27. Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, and George Toderici 2015. Beyond short snippets: Deep networks for video classification IEEE CVPR.

Index Terms

• Information systems

  • Information systems applications

    • Data mining