Incremental Dual-memory LSTM in Land Cover Prediction
Xiaowei Jia (University of Minnesota);Ankush Khandelwal (University of Minnesota);Guruprasad Nayak (University of Minnesota);James Gerber (University of Minnesota);Kimberly Carlson (University of Hawaii Manoa);Paul West (University of Minnesota);Vipin Kumar (University of Minnesota)
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.
