The effects of climate extremes on global agricultural yields

Abstract

Climate extremes, such as droughts or heat waves, can lead to harvest failures and threaten the livelihoods of agricultural producers and the food security of communities worldwide. Improving our understanding of their impacts on crop yields is crucial to enhance the resilience of the global food system. This study analyses, to our knowledge for the first time, the impacts of climate extremes on yield anomalies of maize, soybeans, rice and spring wheat at the global scale using sub-national yield data and applying a machine-learning algorithm. We find that growing season climate factorsincluding mean climate as well as climate extremes-explain 20%-49% of the variance of yield anomalies (the range describes the differences between crop types), with 18%-43% of the explained variance attributable to climate extremes, depending on crop type. Temperature-related extremes show a stronger association with yield anomalies than precipitation-related factors, while irrigation partly mitigates negative effects of high temperature extremes. We developed a composite indicator to identify hotspot regions that are critical for global production and particularly susceptible to the effects of climate extremes. These regions include North America for maize, spring wheat and soy production, Asia in the case of maize and rice production as well as Europe for spring wheat production. Our study highlights the importance of considering climate extremes for agricultural predictions and adaptation planning and provides an overview of critical regions that are most susceptible to variations in growing season climate and climate extremes.

The Impact of Climate Change on Risk and Return in Indian Agriculture

“…37 Specifically, this modestly increases the size of the projected decrease in mean revenue to 27.9%. 38 This result is in line with the findings of Vogel et al (2019), who conclude that extreme temperature has been more important than precipitation in driving yield anomalies worldwide.…”

Predicting spatial and temporal variability in crop yields: an inter-comparison of machine learning, regression and process-based models

“…Besides process-based crop models, we use ML and a traditional multiple linear regression model to simulate maize yield. Here, the Random Forest algorithm (Breiman 2001) which has been successfully used in previous studies (Hoffman et al 2018, Feng et al 2019, Vogel et al 2019 is adopted. The Random Forest algorithm is a non-parametric ML method and relies on an ensemble of decision trees through two randomization steps: (1) each decision tree is constructed based on a bootstrapped sub-sample dataset, with the decision rule depending on a random sub-set of candidate predictor variables; (2) These processes are repeated at every decision split to overcome the limitations of single decision tree, thus avoiding the potential overfitting issue (Breiman 2001).…”

“…Recently, machine-learning (ML) has emerged as a powerful tool for environmental analysis (Chlingaryan et al 2018), as well as climate impact assessment on crop yield (Jeong et al 2016, Johnson et al 2016, Feng et al 2018, Cai et al 2019, Vogel et al 2019. ML often shows better performance compared to conventional linear regression models (Feng et al 2018), as it can capture non-linear relationships, handle the interactions among predictors and do not assume a certain shape of response function (e.g.…”

Forecasting maize yield in the Republic of Serbia by using Box-Jenkins methodology

“…Agricultural production, primarily crop production, bears significant risks in terms of achieving production results. When it comes to yield and production assessments, main limiting components are soil and weather conditions (Tokatlidis, 2013;Vanuytrecht et al 2014; Bartlova et al, 2015;Döring, Reckling, 2015;Ogar et al, 2017;Biberdžić et al, 2018;Vogel et al, 2019). Therefore, the Box-Jenkins methodology was used for analyzing previous movements in maize yields in order to anticipate future ones.…”