Sign in Subscribe
Agricultural industry

Sustainable Agriculture Research Highlights Precision Farming Potential

Strategic Insights

— 1 min read

Precision agriculture and sustainable farming require accurate crop yield prediction and mapping, but research in Prince Edward Island (PEI), Canada, has highlighted a literature gap in potato yield prediction data. A study conducted by the University of Guelph, with support from the Natural Sciences and Engineering Research Council of Canada (NSERC), has demonstrated the potential of high-resolution satellite imagery and machine learning (ML) for potato yield prediction.

Key Takeaways:

  • The study focused on four plots in PEI during the 2021 and 2022 growing seasons, collecting potato crop yield data using a combined harvester and manual digging.
  • High-resolution multispectral imagery and ML were used to predict potato yields, with satisfactory results from three ML algorithms: random forest regression (RFR), classification and regression trees (CART), and gradient tree boosting (GTB).
  • The GTB model with Sentinel-2A and harvester data produced slightly higher estimation accuracy, with R2 values of 0.71-0.78, RMSE values of 2.82-5.96 t/ha, and MAE values of 2.33-4.2 t/ha.
  • The research concluded that the approach used in the study provides real-time seasonal yield prediction maps on a field scale, helping farmers identify targeted areas for variable rate application and promoting resource efficiency and sustainability.
  • The study highlights the need for improved data-driven precision agriculture in PEI and the potential of high-resolution satellite imagery and ML for potato yield prediction.

Statistics:

  • The study analyzed potato crop yield data from four plots in PEI during the 2021 and 2022 growing seasons.
  • The GTB model produced R2 values of 0.71-0.78, RMSE values of 2.82-5.96 t/ha, and MAE values of 2.33-4.2 t/ha.
  • The study used Sentinel-2A and PlanetScope imagery, as well as harvester and manual digging data, to train and evaluate the ML models.

Sources:

  • "Optimizing Potato Yield Mapping and Prediction: Integrating Satellite-based Remote Sensing and Machine Learning for Sustainable Agriculture" (Computers and Electronics In Agriculture, 2025; 237).
  • Gurjit S. Randhawa, University of Guelph, School of Computer Science (author).
  • Natural Sciences and Engineering Research Council of Canada (NSERC) (supporting organization).
  • Gurjit S. Randhawa, et al. "Optimizing Potato Yield Mapping and Prediction: Integrating Satellite-based Remote Sensing and Machine Learning for Sustainable Agriculture" Computers and Electronics In Agriculture, 2025;237.

Read more