Scholarlink

Purpose <p>Scientists and producers have pursued precision agriculture to increase yields and limit environmental impacts. Applying precision agriculture concepts has not been straightforward, however, because complex interactions between soil and weather govern crop growth. We hypothesize that evapotranspiration (ET) is a single metric that captures interactions between plant status, soil, topography, and weather and can be used to predict spatial patterns in crop yield.</p> Methods <p>We used remotely sensed estimates of ET to calculate a normalized ET metric describing the ratio of actual to reference ET (f<sub>RET</sub>) at a research farm located in the U.S. Corn Belt. Using the resulting 30-m resolution maps of f<sub>RET</sub>, we estimated the within-field variability in crop water stress and used machine learning techniques to relate f<sub>RET</sub>, soil, and topographic properties to crop yield.</p> Results <p>We show that total growing season ET is not a strong predictor of yield spatial variability (<i>r</i> &lt; 0.3), but when used to train a random forest model, f<sub>RET</sub> estimates are stronger predictors (mean R<sup>2</sup> = 0.6). In fact, f<sub>RET</sub> alone is better at predicting yield than any other combination of soil, topographic, and hydrologic data tested with machine learning methods. We also show that end of season yield can be predicted with just 9 weeks of f<sub>RET</sub> data which provides the opportunity to use remotely sensed ET to guide in-season site-specific management decisions.</p> Conclusion <p>This novel combination of earth observations and machine learning algorithms can guide sustainable intensification of agricultural systems within the context of increasing water stress.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Monitoring evapotranspiration to link agricultural water use with crop yield at sub-field scales

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月8日

查看全文
  • Adam P. Schreiner-McGraw,
  • Martha C. Anderson,
  • Kenneth A. Sudduth,
  • Curtis J. Ransom,
  • Jisung G. Chang,
  • Feng Gao

摘要

Purpose

Scientists and producers have pursued precision agriculture to increase yields and limit environmental impacts. Applying precision agriculture concepts has not been straightforward, however, because complex interactions between soil and weather govern crop growth. We hypothesize that evapotranspiration (ET) is a single metric that captures interactions between plant status, soil, topography, and weather and can be used to predict spatial patterns in crop yield.

Methods

We used remotely sensed estimates of ET to calculate a normalized ET metric describing the ratio of actual to reference ET (fRET) at a research farm located in the U.S. Corn Belt. Using the resulting 30-m resolution maps of fRET, we estimated the within-field variability in crop water stress and used machine learning techniques to relate fRET, soil, and topographic properties to crop yield.

Results

We show that total growing season ET is not a strong predictor of yield spatial variability (r < 0.3), but when used to train a random forest model, fRET estimates are stronger predictors (mean R2 = 0.6). In fact, fRET alone is better at predicting yield than any other combination of soil, topographic, and hydrologic data tested with machine learning methods. We also show that end of season yield can be predicted with just 9 weeks of fRET data which provides the opportunity to use remotely sensed ET to guide in-season site-specific management decisions.

Conclusion

This novel combination of earth observations and machine learning algorithms can guide sustainable intensification of agricultural systems within the context of increasing water stress.