Abstract
Weather-based forecasting models play a major role in agricultural decision support systems but warnings are usually computed at regional level due to a limited amount of automatic weather stations. Farmers have to refer to the nearest AWS but recommendations are not always adapted to their situation. Agromet project aims to set up an operational web-platform designed for real-time agro-meteorological data dissemination at high spatial (1 km × 1 km grid) and temporal (hourly) resolution in Wallonia, southern part of Belgium. This paper focuses on the interpolation of hourly temperature and daily maximum temperature. Five learners are tested: multilinear regression, inverse distance weighted, one nearest neighbor, ordinary kriging and kriging with external drift. All interpolation methods except ordinary kriging perform better than taking the nearest station to predict air temperature. Multilinear regression is the best one. The size of the dataset is a limit to data interpolation. IoT is an opportunity to improve the quality of the interpolated data by increasing the size of our training dataset. Either by developing our own low price and robust sensors to measure air temperature and humidity or by exploiting data measured by non-meteorological devices monitoring temperature (e.g. tractors or cars).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zeuner, T., Kleinhenz, B.: Use of geographic information systems in warning services for late blight*. EPPO Bull. 37(2), 327–334 (2007). https://doi.org/10.1111/j.1365-2338.2007.01134.x
Racca, P., Kleinhenz, B., Zeuner, T., Keil, B., Tschöpe, B., Jung, J.: Decision support systems in agriculture: administration of meteorological data, use of geographic information systems (GIS) and validation methods in crop protection warning service (2011). https://doi.org/10.5772/20809
Perry, M., Hollis, D.: The generation of monthly gridded datasets for a range of climatic variables over the UK. Int. J. Climatol. 25, 1041–1054 (2005)
Dobesch, H., Dumolard, P., Dryas, I. (eds.): Spatial Interpolation for Climate Data: the Use of GIS in Climatology and Meteorology. Geographical Information Systems Series. ISTE Ltd., London (2007)
Appelhans, T., Mwangomo, E., Hardy, D.R., Hemp, A., Nauss, T.: Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro, Tanzania. Spat. Stat. 14, 91–113 (2015)
R Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2018). https://www.R-project.org/
Bischl, B., et al.: mlr: machine learning in R. J. Mach. Learn. Res. 17(170), 1–5 (2016). http://jmlr.org/papers/v17/15-066.html
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Rosillon, D., Huart, J.P., Goossens, T., Journée, M., Planchon, V. (2019). The Agromet Project: A Virtual Weather Station Network for Agricultural Decision Support Systems in Wallonia, South of Belgium. In: Palattella, M., Scanzio, S., Coleri Ergen, S. (eds) Ad-Hoc, Mobile, and Wireless Networks. ADHOC-NOW 2019. Lecture Notes in Computer Science(), vol 11803. Springer, Cham. https://doi.org/10.1007/978-3-030-31831-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-31831-4_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31830-7
Online ISBN: 978-3-030-31831-4
eBook Packages: Computer ScienceComputer Science (R0)