Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Filling Gaps in Micro-Meteorological Data

Abstract : Filling large data-gaps in Micro-Meteorological data has mostly been done using interpolation techniques based on a marginal distribution sampling. Those methods work well but need a large horizon of the previous events to achieve good results since they do not model the system but only rely on previously encountered iterations. In this paper, we propose to use multi-head deep attention networks to fill gaps in Micro-Meteorological Data. This methodology couples large-scale information extraction with modeling capabilities that cannot be achieved by interpolation-like techniques. Unlike Bidirectional RNNs, our architecture is not recurrent, it is simple to tune and our data efficiency is higher. We apply our architecture to real-life data and clearly show its applicability in agriculture, furthermore, we show that it could be used to solve related problems such as filling gaps in cyclic-multivariate-time-series.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03091151
Contributor : Cedric Pradalier Connect in order to contact the contributor
Submitted on : Wednesday, December 30, 2020 - 4:40:46 PM
Last modification on : Wednesday, November 3, 2021 - 8:36:09 AM
Long-term archiving on: : Wednesday, March 31, 2021 - 6:47:53 PM

File

ECML_PKDD_ADS_2020.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03091151, version 1

Citation

Antoine Richard, Lior Fine, Offer Rozenstein, Joseph Tanny, Matthieu Geist, et al.. Filling Gaps in Micro-Meteorological Data. 2020. ⟨hal-03091151⟩

Share

Metrics

Record views

67

Files downloads

319