Identifying meteorological drivers of extreme impacts: an application to simulated crop yields

Abstract

Abstract. Compound weather events may lead to extreme impacts that can affect many aspects of society including agriculture. Identifying the underlying mechanisms that cause extreme impacts, such as crop failure, is of crucial importance to improve understanding and forecasting. In this study we investigate whether key meteorological drivers of extreme impacts can be identified using Least Absolute Shrinkage and Selection Operator (Lasso) in a model environment, a method that allows for automated variable selection and is able to handle collinearity between variables. As an example of an extreme impact, we investigate crop failure using annual wheat yield as simulated by the APSIM crop model driven by 1600 years of daily weather data from a global climate model (EC-Earth) under present-day conditions for the Northern Hemisphere. We then apply the logistic Lasso regression to predict which weather conditions during the growing season lead to crop failure. We obtain good model performance in Central Europe and the eastern half of the United States, while crop failure years in regions in Asia and the western half of the United States are less accurately predicted. Model performance correlates strongly with annual mean and variability of crop yields, that is, model performance is highest in regions with relatively large annual crop yield mean and variability. Overall, for nearly all grid points the inclusion of temperature, precipitation and vapour pressure deficit is key to predict crop failure. In addition, meteorological predictors during all seasons are required for a good prediction. These results illustrate the omnipresence of compounding effects both between meteorological drivers and different periods of the growing season for creating crop failure events. Especially vapour pressure deficit and climate extreme indicators such as diurnal temperature range and the number of frost days are selected by the statistical model as relevant predictors for crop failure at most grid points, underlining their overarching relevance. We conclude that the Lasso regression model is a useful tool to automatically detect compound drivers of extreme impacts, and could be applied to other weather impacts such as wildfires or floods. As the detected relationships are of purely correlative nature, more detailed analyses are required to establish the causal structure between drivers and impacts.

Weather-induced crop failure events under climate change: a storyline approach

“…Temperature, precipitation and diurnal temperature range along July and August are deemed key climatic drivers in the region studied. The meteorological variables identified in this work are in agreement with the work of Vogel et al (2020), which also shows temperature, precipitation and DTR to be important meteorological variables for crop development, and with the work of Hamed et al (2021), that highlights the harmful combination of hot and dry conditions along summer for soybeans in the same region. This work considers only meteorological variables during the growing season of rainfed soybeans, so management practices, irrigation and sub-surface conditions are not considered.…”

“…The random forest model here developed is successful at predicting soybean failure seasons and shows an overall better performance than benchmark methods. It adds to the list of works that demonstrate the usefulness of impact-inspired approaches (Ben-Ari et al, 2018;Vogel et al, 2020;van der Wiel et al, 2020;Hamed et al, 2021;Zhu et al, 2021). The feature selection process used here combines machine learning with findings from the literature to identify compound drivers 350 of soybean failures in the US.…”

“…The reasons for using yields from crop models are the longer timeseries that allow for more years to be included in the training of the statistical model and uniformity of data quality for regions where there is low quality of observational data. Other works have also adopted simulated yields for climate-crop analysis (Vogel et al, 2020;Zhu et al, 2021). Details of the EPIC-IIASA model's performance can be seen in Müller et al (2017).…”

“…Some have included the possible impacts of global warming under different scenarios (Rosenzweig et al, 2014;Lobell and Tebaldi, 2014;Feng et al, 2019;Xie et al, 2018). Others aimed to represent the compound nature of crop failures (Ben-Ari et al, 2018;van der Wiel et al, 2020;Vogel et al, 2020;Hamed et al, 2021;Zhu et al, 2021). van der Wiel et al (2020) show the complexity between climate and crops by explicitly modelling the full distribution of climate impacts on crops with a physical crop model and large ensembles of climatic data.…”

“…They demonstrate that links between extreme weather and extreme impacts are non-linear and the need for modelling impacts. Vogel et al (2020) apply a statistical linear model to automatically identify the most relevant meteorological variables for simulated extreme impact events in large ensemble crop data. They conclude that compounding effects are ubiquitous across time and meteorological drivers for crop failures.…”