Machine learning procedures for daily interpolation of rainfall in Navarre (Spain)

Militino, Ana F.; Ugarte Martínez, María Dolores; Pérez Goya, Unai

Publication:
Machine learning procedures for daily interpolation of rainfall in Navarre (Spain)

dc.contributor.author	Militino, Ana F.
dc.contributor.author	Ugarte Martínez, María Dolores
dc.contributor.author	Pérez Goya, Unai
dc.contributor.department	Estadística, Informática y Matemáticas	es_ES
dc.contributor.department	Estatistika, Informatika eta Matematika	eu
dc.contributor.department	Institute for Advanced Materials and Mathematics - INAMAT2	en
dc.date.accessioned	2024-01-18T11:17:19Z
dc.date.issued	2023
dc.date.updated	2024-01-18T11:11:58Z
dc.description.abstract	Kriging is by far the most well known and widely used statistical method for interpolating data in spatial random fields. The main reason is that it provides the best linear unbiased predictor and it is an exact interpolator when normality is assumed. The robustness of this method allows small departures from normality, however, many meteorological, pollutant and environmental variables have extremely asymmetrical distributions and Kriging cannot be used. Machine learning techniques such as neural networks, random forest, and k-nearest neighbor can be used instead, because they do not require specific distributional assumptions. The drawback is that they do not take account of the spatial dependence, and for an optimal performance in spatial random fields more complex machine learning techniques could be considered. These techniques also require a relatively large amount of training data and they are computationally challenging to implement. For a reduced number of observations, we illustrate the performance of the aforementioned procedures using daily rainfall data of manual meteorological gauge stations in Navarre, where the only auxiliary variables available are the spatial coordinates and the altitude. The quality of the predictions is carefully checked through three versions of the relative root mean squared error (RRMSE). The conclusion is that when we cannot use Kriging, random forest and neural networks outperform k-nearest neighbor technique, and provide reliable predictions of rainfall daily data with scarce auxiliary information.	en
dc.description.sponsorship	This research was supported by the Spanish Research Agency (PID2020-113125RB-I00/MCIN/AEI/10.13039/501100011033 project). It has also received funding from la Caixa Foundation (ID1000010434), Caja Navarra Foundation, and UNED Pamplona, under agreement LCF/PR/PR15/51100007.	en
dc.embargo.lift	2024-06-28
dc.embargo.terms	2024-06-28
dc.format.mimetype	application/pdf	en
dc.identifier.citation	Militino, A. F., Ugarte, M. D., & Pérez-Goya, U. (2023). Machine learning procedures for daily interpolation of rainfall in navarre(Spain). En N. Balakrishnan, M. Á. Gil, N. Martín, D. Morales, & M. D. C. Pardo (Eds.), Trends in Mathematical, Information and Data Sciences (Vol. 445, pp. 399-413). Springer International Publishing. https://doi.org/10.1007/978-3-031-04137-2_34	en
dc.identifier.doi	10.1007/978-3-031-04137-2_34
dc.identifier.isbn	978-3-031-04137-2
dc.identifier.uri	https://academica-e.unavarra.es/handle/2454/47088
dc.language.iso	eng	en
dc.publisher	Springer	en
dc.relation.ispartof	Balakrishnan, N.; Gil, M. Á.; Martín, N.; Morales, D.; Pardo, M. C. (Eds.). Trends in mathematical, information and data sciences: a tribute to Leandro Pardo. Springer; 2023. p. 399-413 978-3-031-04137-2	en
dc.relation.projectID	info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-113125RB-I00/ES/	en
dc.relation.publisherversion	https://doi.org/10.1007/978-3-031-04137-2_34
dc.rights	© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023	en
dc.rights.accessRights	Acceso abierto / Sarbide irekia	es
dc.rights.accessRights	info:eu-repo/semantics/openAccess	en
dc.subject	Kriging	en
dc.subject	Machine learning techniques	en
dc.subject	Spatial random fields	en
dc.subject	Rainfall data	en
dc.title	Machine learning procedures for daily interpolation of rainfall in Navarre (Spain)	en
dc.type	Capítulo de libro / Liburuen kapitulua	es
dc.type	info:eu-repo/semantics/bookPart	en
dc.type.version	Versión aceptada / Onetsi den bertsioa	es
dc.type.version	info:eu-repo/semantics/acceptedVersion	en
dspace.entity.type	Publication
relation.isAuthorOfPublication	d3c066e9-6b6f-40b0-ac34-4bb96a71bb82
relation.isAuthorOfPublication	e87ff19e-9d36-4286-989b-cafd391dff9d
relation.isAuthorOfPublication	003960f8-aa6d-47ec-bec1-6bc59c3c8edb
relation.isAuthorOfPublication.latestForDiscovery	d3c066e9-6b6f-40b0-ac34-4bb96a71bb82