摘要：Global crop demand is expected to increase by 60-110% by 2050. Climate change has already affected crop yields in some countries, and these effects are expected to continue. Identification of weather-related yield-limiting conditions and development of strategies for agricultural adaptation to climate change is essential to mitigate food security concerns. Here we used machine learning on US soybean yield data, collected from cultivar trials conducted in 27 states from 2007 to 2016, to examine crop sensitivity to varying in-season weather conditions. We identified the month-specific negative effect of drought via increased water vapor pressure deficit. Excluding Texas and Mississippi, where later sowing increased yield, sowing 12 days earlier than what was practiced during this decade across the US would have resulted in 10% greater total yield and a cumulative monetary gain of ca. US$9 billion. Our data show the substantial nation- and region-specific yield and monetary effects of adjusting sowing timing and highlight the importance of continuously quantifying and adapting to climate change. The magnitude of impact estimated in our study suggest that policy makers (e.g., federal crop insurance) and laggards (farmers that are slow to adopt) that fail to acknowledge and adapt to climate change will impact the national food security and economy of the US.
