CHANS-Net: The International Network of Research on Coupled Human and Natural Systems

Journal or Book Title: ENVIRONMENTAL DATA SCIENCE

DOI:10.1017/eds.2022.1

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.Impact StatementUnderstanding and predicting extreme climate-related impacts is crucial to constrain climate risk. This is a difficult task because of the typically multiple involved time scales and interactions between impact drivers. Here, we employ Convolutional Neural Networks (CNNs) and test their ability to predict years with extremely low carbon uptake (a proxy for vegetation mortality) from daily weather data. The employed CNNs can distinguish well between normal years and years with extremely low carbon uptake, with prediction power increasing from high to low latitudes. This highlights that deep learning can be used to learn very complex relationships between daily weather data and extreme impacts.

Type of Publication: Article