摘要：The United States is the largest producer of maize in the world, a crop for which demand continues to rise rapidly. Past studies have projected that climate change will negatively impact mean maize yields in this region, while at the same time increasing yield variability. However, some have questioned the accuracy of these projections because they are often based on indirect measures of soil moisture, have failed to explicitly capture the potential interactions between temperature and soil moisture availability, and often omit the beneficial effects of elevated carbon dioxide (CO2) on transpiration efficiency. Here we use a new detailed dataset on field-level yields in Iowa, Indiana, and Illinois, along with fine-resolution daily weather data and moisture reconstructions, to evaluate the combined effects of moisture and heat on maize yields in the region. Projected climate change scenarios over this region from a suite of CMIP5 models are then used to assess future impacts and the differences between two contrasting emissions scenarios (RCP 4.5 and RCP 8.5). We show that (i) statistical models which explicitly account for interactions between heat and moisture, which have not been represented in previous empirical models, lead to significant model improvement and significantly higher projected yield variability under warming and drying trends than when accounting for each factor independently; (ii) inclusion of the benefits of elevated CO2 significantly reduces impacts, particularly for yield variability; and (iii) net damages from climate change and CO2 become larger for the higher emission scenario in the latter half of the 21st century, and significantly so by the end of century.
