Skip to main content

Using Machine-Learning Models for Field-Scale Crop Yield and Condition Modeling in Argentina

What We Do

NASA Harvest and SIMA, a private sector digital agtech platform provider, have partnered to use Earth observations and remote sensing technology to accurately determine crop yields at field-scale. NASA Harvest has developed a novel tool that has been integrated into SIMA’s platform which became operational in late 2020. The tool is targeted towards supporting farmers in improving their profits through better predictability of crop yields on their farms.



Latin America

How Satellites Make This Work

Accurately determining crop growth progress and crop yields at field-scale can help farmers estimate their net profit and enable insurance companies to ascertain payouts, ultimately bolstering food security. At field scales, the trifecta of management practices, soil health and weather conditions combine to impact crop growth progress, and this progress can be monitored in-season using satellite data. Here, we use satellite derived metrics from both optical and radar satellites as well as machine learning models to model field-scale crop yields for over 3,000 soybean and wheat farms in Argentina. When we compare several machine learning models, our results show the promise of combining mixed effect models with non-parametric models in improving yield modeling capabilities. We also demonstrate the utility of specific satellite derived metrics and extracted features in improving model performance. Overall, our approach can explain greater than 80% of the variation in yields while remaining generalizable across crops and agro-ecological zones.


In order to address the issue of cloud cover limiting satellite data acquisition, we also use double-bounce parameters derived from Sentinel-1 integrated with Difference Vegetation Indices (DVI) derived from Landsat-8 for prediction of soybean yield at the field level over central Argentina. The Artificial Neural Network (ANN) model was trained using time series of Synthetic Aperture Radar (SAR) and optical features during the growing season. For comparison of SAR versus optical versus their integration for soybean yield prediction, the ANN model was trained and tested for three scenarios of SAR-only, optical-only and SAR-optical integration. Accuracies of yield prediction including correlation of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) are 0.80, 0.589 t/ha, 0.445 t/ha for SAR-only; 0.65, 0.800 t/ha, 0.546 t/ha for optical-only; and 0.85, 0.554 t/ha, 0.389 t/ha for SAR-optical integration scenarios, respectively. These accuracies demonstrate high potential of SAR and SAR-optical integration for soybean yield prediction at field level.

Estefania Puricelli, University of Maryland
Mehdi Hosseini, University of Maryland
Ritvik Sahajpal, University of Maryland
Team Members
Inbal Becker-Reshef, University of Maryland

Guillermo Leale, Universidad Tecnológica Nacional, Argentina and SIMA

Mauricio Varela, SIMA

Pedro Lafluf, SIMA

Lucas Fontana, SIMA

Learn More

SIMA is a young and growing Argentinean company, who have developed a communication and management tool in the form of a mobile app to track field activities and a web app for data visualization and management. It is designed for agricultural production and scouting companies, engineers and advisors that collect data on crop status, pest infestation, spraying and other activities. Input data is guaranteed to be anonymized and standardized so that it can be easily shared and compared among team members and supervisors. SIMA currently manages more than a million hectares in Argentina. 

The private-public partnership between NASA Harvest and SIMA provides a unique synergy where remote sensing experts are able to develop new tools with the ground truth data of thousands of SIMA clients and the expertise of their partners.

Visit for additional details on SIMA’s operations and learn more about the new SIMA Harvest tool here.