Date of Award
January 2025
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Atmospheric Sciences
First Advisor
Jared Marquis
Abstract
As the world’s population continues to grow, the importance of food security willonly continue to increase, with some estimates requiring a global increase in food production between 59 and 98% by 2050. The agriculture industry is also a crucial economic driver, with the industry supporting 20% of the state of North Dakota’s workforce, and with a total valuation of $41.3 billion. The economic importance of this industry and the challenges of future growth prompt a need for data driven decision making into the future, particularly with predictive crop breeding. This is the method by which crops are developed that are more resilient to biotic and abiotic stresses. If we can identify the key variables that are affecting the health of crops, we can use crop breeding as a tool to mitigate negative impacts on our crops due to climate change.
Using the North American Regional Reanalysis as well as data from the National Agricultural Statistics Survey, we determine what atmospheric variables are important for predicting yields for a variety of crops across the state of North Dakota. Non-linear relationships between atmospheric variables and crop yield encourage the use of machine learning to diagnose the importance of each variable. We utilize a random forest ensemble learning algorithm to determine the importance of each atmospheric variable, then determine the ideal range for that variable to produce the highest yield. Finally, we quantify how these important features are changing in the future decades by utilizing the Community Earth System Model Large Ensemble Project. This allows us to deliver a probabilistic forecast to crop breeders on the likelihood of the climate changing from ideal growing conditions. Results indicate that summer temperatures across most of North Dakota have already exceeded the optimal range for both barley and durum wheat, and projections suggest this trend will continue in the coming decades.
Recommended Citation
Newell, Levi, "Using Machine Learning To Investigate Weather Impacts On Crop Yield For Probabilistic, Climate-Informed Predictive Crop Breeding" (2025). Theses and Dissertations. 7533.
https://commons.und.edu/theses/7533