English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present an approach that uses a deep learning model, in particular, aMultiLayer Perceptron (MLP), for estimating the missing values of a variable inmultivariate time series data. We focus on filling a long continuous gap (e.g.,multiple months of missing daily observations) rather than on individualrandomly missing observations. Our proposed gap filling algorithm uses anautomated method for determining the optimal MLP model architecture, thusallowing for optimal prediction performance for the given time series. Wetested our approach by filling gaps of various lengths (three months to threeyears) in three environmental datasets with different time seriescharacteristics, namely daily groundwater levels, daily soil moisture, andhourly Net Ecosystem Exchange. We compared the accuracy of the gap-filledvalues obtained with our approach to the widely-used R-based time series gapfilling methods ImputeTS and mtsdi. The results indicate that using an MLP forfilling a large gap leads to better results, especially when the data behavenonlinearly. Thus, our approach enables the use of datasets that have a largegap in one variable, which is common in many long-term environmental monitoringobservations.

Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks