Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain
Subdaily rainfall data, though essential for applications in many fields, is not as readily available as daily rainfall data. In this work, regression approaches that use atmospheric data and daily rainfall statistics as predictors are evaluated to downscale daily-to-subdaily rainfall statistics on...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Water |
Subjects: | |
Online Access: | http://www.mdpi.com/2073-4441/11/1/125 |
id |
doaj-297a31c464ee4001aa64a4fcca4b6aad |
---|---|
record_format |
Article |
spelling |
doaj-297a31c464ee4001aa64a4fcca4b6aad2020-11-25T01:40:34ZengMDPI AGWater2073-44412019-01-0111112510.3390/w11010125w11010125Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in SpainJavier Diez-Sierra0Manuel del Jesus1Environmental Hydraulics Institute, Universidad de Cantabria—Avda. Isabel Torres, 15, Parque Científico y Tecnológico de Cantabria, 39011 Santander, SpainEnvironmental Hydraulics Institute, Universidad de Cantabria—Avda. Isabel Torres, 15, Parque Científico y Tecnológico de Cantabria, 39011 Santander, SpainSubdaily rainfall data, though essential for applications in many fields, is not as readily available as daily rainfall data. In this work, regression approaches that use atmospheric data and daily rainfall statistics as predictors are evaluated to downscale daily-to-subdaily rainfall statistics on more than 700 hourly rain gauges in Spain. We propose a new approach based on machine learning techniques that improves the downscaling skill of previous methodologies. Results are grouped by climate types (following the Köppen–Geiger classification) to investigate possible missing explanatory variables in the analysis. The methodology is then used to improve the ability of Poisson cluster models to simulate hourly rainfall series that mimic the statistical behavior of the observed ones. This approach can be applied for the study of extreme events and for daily-to-subdaily precipitation disaggregation in any location of Spain where daily rainfall data are available.http://www.mdpi.com/2073-4441/11/1/125rainfall modelingtemporal downscalingmachine learningsynthetic simulationrainfall extremes |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Javier Diez-Sierra Manuel del Jesus |
spellingShingle |
Javier Diez-Sierra Manuel del Jesus Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain Water rainfall modeling temporal downscaling machine learning synthetic simulation rainfall extremes |
author_facet |
Javier Diez-Sierra Manuel del Jesus |
author_sort |
Javier Diez-Sierra |
title |
Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain |
title_short |
Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain |
title_full |
Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain |
title_fullStr |
Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain |
title_full_unstemmed |
Subdaily Rainfall Estimation through Daily Rainfall Downscaling Using Random Forests in Spain |
title_sort |
subdaily rainfall estimation through daily rainfall downscaling using random forests in spain |
publisher |
MDPI AG |
series |
Water |
issn |
2073-4441 |
publishDate |
2019-01-01 |
description |
Subdaily rainfall data, though essential for applications in many fields, is not as readily available as daily rainfall data. In this work, regression approaches that use atmospheric data and daily rainfall statistics as predictors are evaluated to downscale daily-to-subdaily rainfall statistics on more than 700 hourly rain gauges in Spain. We propose a new approach based on machine learning techniques that improves the downscaling skill of previous methodologies. Results are grouped by climate types (following the Köppen–Geiger classification) to investigate possible missing explanatory variables in the analysis. The methodology is then used to improve the ability of Poisson cluster models to simulate hourly rainfall series that mimic the statistical behavior of the observed ones. This approach can be applied for the study of extreme events and for daily-to-subdaily precipitation disaggregation in any location of Spain where daily rainfall data are available. |
topic |
rainfall modeling temporal downscaling machine learning synthetic simulation rainfall extremes |
url |
http://www.mdpi.com/2073-4441/11/1/125 |
work_keys_str_mv |
AT javierdiezsierra subdailyrainfallestimationthroughdailyrainfalldownscalingusingrandomforestsinspain AT manueldeljesus subdailyrainfallestimationthroughdailyrainfalldownscalingusingrandomforestsinspain |
_version_ |
1725045003841961984 |