16 May 2019

16 May 2019

Review status: a revised version of this preprint is currently under review for the journal HESS.

Using Deep Learning to Fill Spatio-Temporal Data Gaps in Hydrological Monitoring Networks

Huiying Ren1, Erol Cromwell2, Ben Kravitz3,4, and Xingyuan Chen4 Huiying Ren et al.
  • 1Earth Systems Science Division, Pacific Northwest National Laboratory, WA, USA
  • 2Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, WA, USA
  • 3Department of Earth and Atmospheric Sciences, Indiana University, Bloomington, IN, USA
  • 4Atmospheric Sciences and Global Change Division, Pacific Northwest National Laboratory, WA, USA

Abstract. Long-term spatio-temporal changes in subsurface hydrological flow are usually quantified through a network of wells; however, such observations often are spatially sparse and temporal gaps exist due to poor quality or instrument failure. In this study, we explore the ability of deep neural networks to fill in gaps in spatially distributed time-series data. We selected a location at the U.S. Department of Energy's Hanford site to demonstrate and evaluate the new method, using a 10-year spatio-temporal hydrological dataset of temperature, specific conductance, and groundwater table elevation from 42 wells that monitor the dynamic and heterogeneous hydrologic exchanges between the Columbia River and its adjacent groundwater aquifer. We employ a long short-term memory (LSTM)-based architecture, which is specially designed to address both spatial and temporal variations in the property fields. The performance of gap filling using an LSTM framework is evaluated using test datasets with synthetic data gaps created by assuming the observations were missing for a given time window (i.e., gap length), such that the mean absolute percentage error can be calculated against true observations. Such test datasets also allow us to examine how well the original nonlinear dynamics are captured in gap-filled time series beyond the error statistics. The performance of the LSTM-based gap-filling method is compared to that of a traditional, popular gap-filling method: autoregressive integrated moving average (ARIMA). Although ARIMA appears to perform slightly better than LSTM on average error statistics, LSTM is better able to capture nonlinear dynamics that are present in time series. Thus, LSTMs show promising potential to outperform ARIMA for gap filling in highly dynamic time-series observations characterized by multiple dominant modes of variability. Capturing such dynamics is essential to generate the most valuable observations to advance our understanding of dynamic complex systems.

Huiying Ren et al.

Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for authors/editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Huiying Ren et al.

Huiying Ren et al.


Total article views: 1,802 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,159 620 23 1,802 91 36 35
  • HTML: 1,159
  • PDF: 620
  • XML: 23
  • Total: 1,802
  • Supplement: 91
  • BibTeX: 36
  • EndNote: 35
Views and downloads (calculated since 16 May 2019)
Cumulative views and downloads (calculated since 16 May 2019)

Viewed (geographical distribution)

Total article views: 1,425 (including HTML, PDF, and XML) Thereof 1,405 with geography defined and 20 with unknown origin.
Country # Views %
  • 1


Latest update: 24 Jul 2021
Short summary
We used a deep learning method called Long Short-Term Memory (LSTM) to fill gaps in data collected by hydrologic monitoring networks. LSTM accounted for correlations in space and time and nonlinear trends in data. Compared to a traditional regression based time series method, LSTM performed comparably when filling gaps in data with smooth patterns, while it better captured highly dynamic patterns in data . Capturing such dynamics is critical for understanding dynamic complex system behaviors.