Harvest Insights: Interpretable Machine Learning to Understand Environmental Drivers of U.S. Corn and Soybean Yields

Machine Learning


  • USDAERS. Agriculture and Farm Income: Cash Income in the U.S. Agricultural Sector (2023). https://www.ers.usda.gov/data-products/farm-income-and-wealth-statistics.

  • USDA NASS. Crop Production Annual Summary, 2023 (2024). https://usda.library.cornell.edu/concern/publications/k3569432s.

  • USDA FAS. Global Agricultural Trade System (GATS) (2024). https://apps.fas.usda.gov/gats.

  • Godfrey, HCJ et al. Food security: The challenge of feeding 9 billion people. science 327812–818 (2010).

    Article ADS CAS PubMed Google Scholar

  • Tilman, D., Balzer, C., Hill, J. & Befort, BL Global food demand and the intensification of sustainable agriculture. PNAS 10820260–20264 (2011).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Persson, UM The impact of biofuel demand on agricultural commodity prices: a systematic review. in Advances in bioenergy 465–482 (John Wiley & Sons, Ltd, 2016).

  • Lauer, JG et al. 21st Century Scientific Grand Challenges for the Crop Science Society of America. crop science. 521003–1010 (2012).

    Article Google Scholar

  • Reddy, BVS, Reddy, S., Bidinger, P., Blümmel, M. & F. & Crop management factors influencing crop residue yield and quality. Field Crops Research Institute 8457–77 (2003).

    Article Google Scholar

  • Peng, B. et al. Towards a multiscale crop modeling framework for climate change adaptation assessment. nut. plant. 6338–348 (2020).

    Article PubMed Google Scholar

  • Andorff, C. et al. Technological advances in corn breeding: past, present, and future. theory. Applied Genet. 132817–849 (2019).

    Article CAS PubMed Google Scholar

  • Boehm, JD Jr. et al. Genetic improvement of U.S. soybeans in maturity groups V, VI, and VII. crop science. 591838–1852 (2019).

    Article CAS Google Scholar

  • Prasanna, BM World maize germplasm diversity: characterization and utilization. J. Biosci. 37843–855 (2012).

    Article CAS PubMed Google Scholar

  • Xavier, A., Thapa, R., Muir, WM & Rainey, KM Population and quantitative genomic characterization of the USDA soybean germplasm collection. plant. Genet. resource. 16513–523 (2018).

    Article CAS Google Scholar

  • Heineman, JA et al. Sustainability and innovation in staple crop production in the Midwest and the US. internal. J. Agric. last. 1271–88 (2014).

    Article Google Scholar

  • Egli, DB U.S. corn and soybean yield comparisons: past trends and future prospects. Agron. J. 10079–88 (2008).

    Article Google Scholar

  • Yost, MA et al. Long-term precision farming systems keep crops profitable. Plessis Agri. 201177–1198 (2019).

    Article Google Scholar

  • Gage, JL et al. Effects of artificial selection on phenotypic plasticity in maize. nut. common. 81348 (2017).

    Article ADS PubMed PubMed Central Google Scholar

  • Kang, Y. & Özdoğan, M. Field-level crop yield mapping with Landsat using a hierarchical data assimilation approach. Remote sensory environment. 228144–163 (2019).

    Article ADS Google Scholar

  • Lobell, DB & Burke, MB On the use of statistical models to predict crop yield responses to climate change. Agriculture. meteorol. 1501443–1452 (2010).

    Article Google Scholar

  • Khaki, S. & Wang, L. Crop yield prediction using deep neural networks. front. plant. Science. 10621 (2019).

    Article PubMed PubMed Central Google Scholar

  • Shahhosseini, M., Hu, G. & Archontoulis, SV Predicting maize yield using machine learning ensembles. front. plant. Science. 111120 (2020).

    Article PubMed PubMed Central Google Scholar

  • Molnar, C. Interpretable Machine Learning: A Guide to Making Black Box Models Explainable (2025).

  • Kasper, T.C. et al. Relationship between maize yield and topographic characteristics over 6 years. Plessis Agri. 487–101 (2003).

    Article Google Scholar

  • Jagadamma, S., Lal, R., Hoeft, RG, Nafziger, ED & Adee, EA Nitrogen fertilization and cropping systems influence the relationship between soil properties and crop yield in the central corn belt of the United States. soil. Tillage resistance 98120–129 (2008).

    Article Google Scholar

  • Ericsson, N. et al. AutoGluon-tabular: Robust and accurate automl for structured data. preprint in https://doi.org/10.48550/arXiv.2003.06505 (2020).

    Article Google Scholar

  • Geurts, P., Ernst, D. & Wehenkel, L. Highly randomized trees. Mach. learn. 633–42 (2006).

    Article Google Scholar

  • Ke, G. et al. LightGBM: A highly efficient gradient boosting decision tree. in Evolving neural information. process. system Vol. 30 (2017).

  • Dhillon, R., Takoo, G., Sharma, V., Nagle, M. Utilizing a machine learning framework to assess the impact of climate change on corn and soybean yields. Calculate. electronic. Agriculture. 221108982 (2024).

    Article Google Scholar

  • Chang, Y., Latham, J., Licht, M., Wang, L. Data-driven crop models for corn yield prediction. common. Biol. 61–9 (2023).

    Article Google Scholar

  • Cheney, NW et al. POLARIS soil properties: 30-meter probability map of soil properties in the continental United States. Water resources. resolution 552916–2938 (2019).

    Article ADS Google Scholar

  • Lv, X et al. Heat stress and sexual reproduction in maize: uncovering the most important factors and greatest opportunities. J.Exp.Bot. 754219–4243 (2024).

    Article CAS PubMed Google Scholar

  • Hoffman, L., Kemanian, AR, Forest, E. & A. & Machine learning reveals corn, sorghum, and soybean yield responses to growing season climate. environment. resolution let. 15094013 (2020).

    Article ADS Google Scholar

  • Ray, DK, Gerber, JS, MacDonald, GK & West, PC Climate change explains one-third of global crop yield variation. nut. common. 65989 (2015).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Ashworth, AJ, Allen, FL, Saxton, AM Using partial least squares and regression to interpret the effects of temperature and precipitation on genetic variance expression in corn and soybean. Agriculture 132752 (2023).

    Article CAS Google Scholar

  • Bhattarai, B., Leasor, Z. & Reis, Incorporating AFDB soil moisture data into a machine learning framework improves U.S. corn yield prediction accuracy Agriculture. Water management. 319109762 (2025).

    Article Google Scholar

  • Kravchenko, AN & Bullock, DG Correlation of corn and soybean grain yield with topography and soil properties. Agron. J. 9275–83 (2000).

    Article Google Scholar

  • Cairns, J. E. et al. Identification of drought, heat, and combined drought and heat tolerance donors in maize. crop science. 531335–1346 (2013).

    Article Google Scholar

  • Valliyodan, B. et al. Genetic diversity and genomic strategies to improve drought and waterlogging tolerance in soybean. J.Exp.Bot. 681835–1849 (2017).

    CAS PubMed Google Scholar

  • Safi, AR, Karimi, P., Mul, M., Chukalla, A. & de Fraiture, C. Translating open-source remote sensing data into crop water productivity enhancement activities. Agriculture. Water management. 261107373 (2022).

    Article Google Scholar

  • Jin, Z. et al. National small-scale corn area and yield mapping using Google Earth engine. Remote sensory environment. 228115–128 (2019).

    Article ADS Google Scholar

  • Celis, J., Xiao, X., Wagle, P., Adler, PR & White, P. A review of yield prediction techniques and their impact on sustainable agriculture. in Transforming to a circular food system: sustainable, smart and resilient citrus supply chains in the Mediterranean region 139–168 (Springer Nature, 2024).

  • Block, DS et al. Data-intensive farm management projects: Transforming agricultural research through precision on-farm experiments. Agron. J. 1112736–2746 (2019).

    Article Google Scholar

  • Vega, A., Córdaba, M., Castro-Franco, M. & Balzarini, M. A protocol for automating error removal from yield maps. Plessis Agri. 201030–1044 (2019).

    Article Google Scholar

  • Thornton, MM, Shrestha, R., Wei, Y., Thornton, PE & Kao, SC Daymet: Daily surface weather data on a 1 km grid for North America, version 4 R1 (ORNL Distributed Active Archive Center, 2022). https://doi.org/10.3334/ORNLDAAC/2129.

  • U.S. Geological Survey. 3D Elevation Program 1 meter resolution digital elevation model (2019). https://www.usgs.gov/the-national-map-data-delivery

  • Safanelli, JL et al. Terrain analysis using the Google Earth engine: A method adapted for high-performance global analysis. ISPRS International J.Geo-Inf. 9400 (2020).

    Article Google Scholar

  • Lehner, B., Verdin, K. & Jarvis, A. A new global hydrographic map derived from spaceflight elevation data. iostrans. morning. Geophysics. union. 8993–94 (2008).

    Article ADS Google Scholar

  • Gorelick, N. et al. Google Earth Engine: Planetary-scale geospatial analysis available to everyone. Remote sensory environment. 20218–27 (2017).

    Article ADS Google Scholar

  • Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. learn. resolution 122825–2830 (2011).

    MathSciNet Google Scholar

  • Lundberg, SM & Lee, SI A unified approach to interpreting model predictions. in Evolving neural information. process. system Vol. 30 (2017).

  • Mosca, E., Szigeti, F., Tragianni, S., Gallagher, D. & Groh, G. SHAP-based explanation methods: A review of NLP interpretability. in Proceedings of the 29th International Conference on Computational Linguistics 4593–4603 (2022).

  • Ying, X. An overview of overfitting and its solutions. J. Phys. conference sir. 1168022022 (2019).

    Article Google Scholar



  • Source link