Rainfall Prediction: A Deep Learning Approach

Emilcy Hernandez; Victor Sanchez-Anguix; Vicente Julian; Javier Palanca; Nestor Duque

doi:10.1007/978-3-319-32034-2_13

Rainfall Prediction: A Deep Learning Approach

Emilcy Hernandez, Victor Sanchez-Anguix, Vicente Julian, Javier Palanca, Nestor Duque

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

75 Citations (Scopus)

Abstract

Previous work has shown that the prediction of meteorological conditions through methods based on artificial intelligence can get satisfactory results. Forecasts of meteorological time series can help decision-making processes carried out by organizations responsible of disaster prevention. We introduce an architecture based on Deep Learning for the prediction of the accumulated daily precipitation for the next day. More specifically, it includes an autoencoder for reducing and capturing non-linear relationships between attributes, and a multilayer perceptron for the prediction task. This architecture is compared with other previous proposals and it demonstrates an improvement on the ability to predict the accumulated daily precipitation for the next day.

Original language	English
Title of host publication	International Conference on Hybrid Artificial Intelligence Systems
Editors	Francisco Martínez-Álvarez, Alicia Troncoso, Héctor Quintián, Emilio Corchado
Place of Publication	Switzerland
Publisher	Springer Verlag
Pages	151-162
Number of pages	12
ISBN (Electronic)	978-3-319-32034-2
ISBN (Print)	978-3-319-32033-5
DOIs	https://doi.org/10.1007/978-3-319-32034-2_13
Publication status	Published - 14 Apr 2016
Event	International Conference on Hybrid Artificial Intelligence Systems - Saville, Spain Duration: 18 Apr 2016 → 20 Apr 2016 Conference number: 11 http://hais2016.upo.es/

Conference

Conference	International Conference on Hybrid Artificial Intelligence Systems
Abbreviated title	HAIS 2016
Country/Territory	Spain
City	Saville
Period	18/04/16 → 20/04/16
Internet address	http://hais2016.upo.es/

Keywords

Artificial neural networks
Deep learning
Meteorological data
Rainfall prediction

Access to Document

10.1007/978-3-319-32034-2_13

Cite this

Rainfall Prediction: A Deep Learning Approach. / Hernandez, Emilcy; Sanchez-Anguix, Victor; Julian, Vicente; Palanca, Javier; Duque, Nestor.

International Conference on Hybrid Artificial Intelligence Systems. ed. / Francisco Martínez-Álvarez; Alicia Troncoso; Héctor Quintián; Emilio Corchado. Switzerland : Springer Verlag, 2016. p. 151-162.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Hernandez, E, Sanchez-Anguix, V, Julian, V, Palanca, J & Duque, N 2016, Rainfall Prediction: A Deep Learning Approach. in F Martínez-Álvarez, A Troncoso, H Quintián & E Corchado (eds), International Conference on Hybrid Artificial Intelligence Systems. Springer Verlag, Switzerland, pp. 151-162, International Conference on Hybrid Artificial Intelligence Systems, Saville, Spain, 18/04/16. https://doi.org/10.1007/978-3-319-32034-2_13

@inproceedings{b8ed45cc8c8a4602b3b2a75f60f8727f,

title = "Rainfall Prediction: A Deep Learning Approach",

abstract = "Previous work has shown that the prediction of meteorological conditions through methods based on artificial intelligence can get satisfactory results. Forecasts of meteorological time series can help decision-making processes carried out by organizations responsible of disaster prevention. We introduce an architecture based on Deep Learning for the prediction of the accumulated daily precipitation for the next day. More specifically, it includes an autoencoder for reducing and capturing non-linear relationships between attributes, and a multilayer perceptron for the prediction task. This architecture is compared with other previous proposals and it demonstrates an improvement on the ability to predict the accumulated daily precipitation for the next day.",

keywords = "Artificial neural networks, Deep learning, Meteorological data, Rainfall prediction",

author = "Emilcy Hernandez and Victor Sanchez-Anguix and Vicente Julian and Javier Palanca and Nestor Duque",

year = "2016",

month = apr,

day = "14",

doi = "10.1007/978-3-319-32034-2_13",

language = "English",

isbn = "978-3-319-32033-5",

pages = "151--162",

editor = "Francisco Mart{\'i}nez-{\'A}lvarez and Alicia Troncoso and H{\'e}ctor Quinti{\'a}n and Emilio Corchado",

booktitle = "International Conference on Hybrid Artificial Intelligence Systems",

publisher = "Springer Verlag",

address = "Austria",

note = "International Conference on Hybrid Artificial Intelligence Systems, HAIS 2016 ; Conference date: 18-04-2016 Through 20-04-2016",

url = "http://hais2016.upo.es/",

}

TY - GEN

T1 - Rainfall Prediction: A Deep Learning Approach

AU - Hernandez, Emilcy

AU - Sanchez-Anguix, Victor

AU - Julian, Vicente

AU - Palanca, Javier

AU - Duque, Nestor

N1 - Conference code: 11

PY - 2016/4/14

Y1 - 2016/4/14

N2 - Previous work has shown that the prediction of meteorological conditions through methods based on artificial intelligence can get satisfactory results. Forecasts of meteorological time series can help decision-making processes carried out by organizations responsible of disaster prevention. We introduce an architecture based on Deep Learning for the prediction of the accumulated daily precipitation for the next day. More specifically, it includes an autoencoder for reducing and capturing non-linear relationships between attributes, and a multilayer perceptron for the prediction task. This architecture is compared with other previous proposals and it demonstrates an improvement on the ability to predict the accumulated daily precipitation for the next day.

AB - Previous work has shown that the prediction of meteorological conditions through methods based on artificial intelligence can get satisfactory results. Forecasts of meteorological time series can help decision-making processes carried out by organizations responsible of disaster prevention. We introduce an architecture based on Deep Learning for the prediction of the accumulated daily precipitation for the next day. More specifically, it includes an autoencoder for reducing and capturing non-linear relationships between attributes, and a multilayer perceptron for the prediction task. This architecture is compared with other previous proposals and it demonstrates an improvement on the ability to predict the accumulated daily precipitation for the next day.

KW - Artificial neural networks

KW - Deep learning

KW - Meteorological data

KW - Rainfall prediction

U2 - 10.1007/978-3-319-32034-2_13

DO - 10.1007/978-3-319-32034-2_13

M3 - Conference proceeding

SN - 978-3-319-32033-5

SP - 151

EP - 162

BT - International Conference on Hybrid Artificial Intelligence Systems

A2 - Martínez-Álvarez, Francisco

A2 - Troncoso, Alicia

A2 - Quintián, Héctor

A2 - Corchado, Emilio

PB - Springer Verlag

CY - Switzerland

T2 - International Conference on Hybrid Artificial Intelligence Systems

Y2 - 18 April 2016 through 20 April 2016

ER -

Rainfall Prediction: A Deep Learning Approach

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this