Predicting years with extremely low gross primary production from daily weather data using Convolutional Neural Networks

Details

Ressource 1Download: Marcolongo 2022.pdf (2664.03 [Ko])
State: Public
Version: Final published version
License: CC BY 4.0
Serval ID
serval:BIB_5DFA6967F996
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Predicting years with extremely low gross primary production from daily weather data using Convolutional Neural Networks
Journal
Environmental Data Science
Author(s)
Marcolongo Aris, Vladymyrov Mykhailo, Lienert Sebastian, Peleg Nadav, Haug Sigve, Zscheischler Jakob
ISSN
2634-4602
Publication state
Published
Issued date
2022
Peer-reviewed
Oui
Volume
1
Language
english
Abstract
Understanding the meteorological drivers of extreme impacts in social or environmental systems is important to better quantify current and project future climate risks. Impacts are typically an aggregated response to many different interacting drivers at various temporal scales, rendering such driver identification a challenging task. Machine learning–based approaches, such as deep neural networks, may be able to address this task but require large training datasets. Here, we explore the ability of Convolutional Neural Networks (CNNs) to predict years with extremely low gross primary production (GPP) from daily weather data in three different vegetation types. To circumvent data limitations in observations, we simulate 100,000 years of daily weather with a weather generator for three different geographical sites and subsequently simulate vegetation dynamics with a complex vegetation model. For each resulting vegetation distribution, we then train two different CNNs to classify daily weather data (temperature, precipitation, and radiation) into years with extremely low GPP and normal years. Overall, prediction accuracy is very good if the monthly or yearly GPP values are used as an intermediate training target (area under the precision-recall curve AUC 0.9). The best prediction accuracy is found in tropical forests, with temperate grasslands and boreal forests leading to comparable results. Prediction accuracy is strongly reduced when binary classification is used directly. Furthermore, using daily GPP during training does not improve the predictive power. We conclude that CNNs are able to predict extreme impacts from complex meteorological drivers if sufficient data are available.
Keywords
Carbon cycle, Convolutional Neural Networks, extreme events, extreme impacts
Open Access
Yes
Funding(s)
Swiss National Science Foundation / 179876
Swiss National Science Foundation / 189908
Create date
15/04/2022 7:40
Last modification date
21/11/2022 8:25
Usage data