Skip to Main content Skip to Navigation
Journal articles

A Graph Neural Network with Spatio-temporal Attention for Multi-sources Time Series Data: An application to Frost Forecast

Abstract : Frost forecast is an important issue in climate research because of its economic impact on several industries. In this study, we propose GRAST-Frost, a graph neural network (GNN) with spatio-temporal architecture, which is used to predict minimum temperatures and the incidence of frost. We developed an IoT platform capable of acquiring weather data from an experimental site, in addition data was collected from 10 weather stations in close proximity to the aforementioned site. The model considers spatial and temporal relations while processing multiple time series simultaneously. Performing predictions of 6, 12, 24 and 48 hours in advance, this model outperforms classical time series forecasting methods including, linear and non-linear machine learning methods, simple deep learning architectures and non-graph deep learning models. In addition, we show that our model significantly improves on the current state of the art of frost forecasting methods.
Complete list of metadata

https://hal.inria.fr/hal-03541565
Contributor : Luis Martí Connect in order to contact the contributor
Submitted on : Tuesday, February 15, 2022 - 8:39:18 PM
Last modification on : Friday, February 18, 2022 - 3:03:56 AM

File

sensors-22-01486.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

Hernan Lira, Luis Martí, Nayat Sanchez-Pi. A Graph Neural Network with Spatio-temporal Attention for Multi-sources Time Series Data: An application to Frost Forecast. Sensors, MDPI, 2022, 22 (4), pp.1486. ⟨10.3390/s22041486⟩. ⟨hal-03541565v2⟩

Share

Metrics

Record views

145

Files downloads

159