IN007
Combining randomized field experiments with observational satellite data to assess the benefits of crop rotations on yields

Session ID#: 161973

Session Description:
To assess the effectiveness of agricultural practices, researchers often turn to randomized field experiments, which are reliable for identifying causal effects but are often limited in scope and therefore lack external validity. Recently, researchers have also leveraged large observational datasets from satellites and other sources, which can lead to conclusions biased by confounding variables or systematic measurement errors. Because experimental and observational datasets have complementary strengths, we propose a method that uses a combination of experimental and observational data in the same analysis. As a case study, we focus on the causal effect of crop rotation on corn (maize) and soybean yields in the Midwestern United States. We find that, in terms of root mean squared error, our hybrid method performs 13% better than using experimental data alone and 26% better than using the observational data alone in the task of predicting the effect of rotation on corn yield at held-out experimental sites. Further, the causal estimates based on our method suggest that benefits of crop rotations on corn yield are lower in years and locations with high temperatures whereas the benefits of crop rotations on soybean yield are higher in years and locations with high temperatures.
Co-Sponsor(s):
  • ASA: American Society of Agronomy -
  • ASPRS: American Society for Photogrammetry and Remote Sensing -
  • CSSA: Crop Science Society of America -
Index Terms:

0402 Agricultural systems [BIOGEOSCIENCES]
0480 Remote sensing [BIOGEOSCIENCES]
1942 Machine learning [INFORMATICS]
1986 Statistical methods: Inferential [INFORMATICS]

Primary Convener:  Dan Kluger, Stanford, Statistics, Stanford, CA, United States
Convener:  Dan Kluger, Stanford, Statistics, Stanford, CA, United States
Student/Early Career Convener:  Dan Kluger, Stanford, Statistics, Stanford, CA, United States
 
Integration of Remote Sensing and Field Observations in Evaluating DSSAT Model in Estimating Soybean and Maize Growth and Yield in Maryland, USA (1166003)
Uvirkaa Akumaga, USDA ARS, Hydrology and Remote Sensing Laboratory, Beltsville, United States, Feng Gao, USDA-ARS, Hydrology and Remote Sensing Laboratory, Beltsville, United States, Martha Anderson, USDA ARS Hydrology and Remote Sensing Laboratory, Beltsville, MD, United States and Wayne Dulaney, USDA ARS, Beltsville, MD, United States
See more of: Earth and Space Science Informatics
<< Previous Session Proposal | Next Session Proposal >>