Prediction of response to input drivers by unmonitored entities has been recognized as one of the most important problems in many scientific problems. This problem is challenging due to the non-stationary processes that underlie the dynamics of data observations over space and time. Hence, directly transferring models from well-observed data entities to unmonitored target entity often lead to sub-optimal performance due to the shift in data distribution. This paper proposes a new meta-transfer learning framework that automatically estimates the similarity amongst entities to transfer knowledge from well-observed entities to unmonitored entities. A sequence autoencoder embeds temporal behaviors of time series data and simulations generated by traditional physics-based models. This embedding model is trained in a meta-transfer learning framework under the guidance of source-to-source transferring experiences. We tested this method in streamflow prediction for multiple river segments in the Delaware River Basin, an ecologically diverse region along the eastern coast of the United States. The experimental results demonstrate the superiority of the proposed method in predicting streamflow for unmonitored stream segments compared to a diverse set of baselines. Our method also creates meaningful similarity estimates amongst segments to guide the transfer learning process.
|Original language||English (US)|
|Title of host publication||Proceedings - 22nd IEEE International Conference on Data Mining, ICDM 2022|
|Editors||Xingquan Zhu, Sanjay Ranka, My T. Thai, Takashi Washio, Xindong Wu|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||10|
|State||Published - 2022|
|Event||22nd IEEE International Conference on Data Mining, ICDM 2022 - Orlando, United States|
Duration: Nov 28 2022 → Dec 1 2022
|Name||Proceedings - IEEE International Conference on Data Mining, ICDM|
|Conference||22nd IEEE International Conference on Data Mining, ICDM 2022|
|Period||11/28/22 → 12/1/22|
Bibliographical noteFunding Information:
This work was supported by the National Science Foundation (NSF) Awards 1934721 and 2147195, USGS Awards G200011317, G21AC10207 and G21AC10564, and NASA program grant 80NSSC22K1164. Access to computing facilities was provided by the Minnesota Supercomputing Institute and the University of Pittsburgh Center for Research Computing.
© 2022 IEEE.
- Meta-transfer learning
- Metric learning
- Representation learning
- Streamflow prediction