Abstract
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.
Highlights
The United States is a major soybean producing country that supplies 34% of global annual soybean production[1]
The conditional inference tree analyses revealed that Vapor pressure deficit (Vpd) during 61 to 90 days after sowing (DAS) was the most important predictor of soybean yield (Fig. 2), which was consistent with a finding in a previous study that focused on just three Midwestern states[12]
The lowest trial yields were observed in state-years in which Vpd was greater than 2.44 kPa from 61 to 90 DAS, and Vpd from −30 to 0 days before sowing (DBS) was greater than 1.79 kPa
Summary
The United States is a major soybean producing country that supplies 34% of global annual soybean production[1]. Drought-tolerant traits, introduced through conventional breeding, resulted in soybean transpiration rates that plateaued at Vpd levels above 1.4–2.1 kPa5–7. Crop management strategies, such as earlier-than-typical sowing, has been proposed as a strategy to increase yields in regional studies[8,9]. Soybean exhibits different sensitivities to weather during varied developmental stages[10], and the sensitivity of a crop to climate adaptation strategies and their effectiveness in mitigating drought-induced yield reduction remains unclear. The trial sowing date data (Fig. S1) bracketed the 50% sowing date progress reported by USDA-NASS for each state and year (Fig. S2) These 27 states accounted for ~99% of total US soybean cultivated area (2007 to 2016 average)[11]. State-wide average yield and weather conditions were calculated resulting in 186 state-year soybean yield and weather condition data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
