Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction

no code implementations • 10 Dec 2021 • Yijun Lin, Yao-Yi Chiang, Meredith Franklin, Sandrah P. Eckel, José Luis Ambite

In addition to a feature selection module and a spatiotemporal learning module, DeepLATTE contains an autocorrelation-guided semi-supervised learning strategy to enforce both local autocorrelation patterns and global autocorrelation trends of the predictions in the learned spatiotemporal embedding space to be consistent with the observed data, overcoming the limitation of sparse and unevenly distributed observations.

feature selection Time Series +1