The dissertation showcases the effectiveness of explainable machine learning approaches in studying plant ecophysiology and agriculture. It demonstrates the identification and prioritization of ecologically relevant traits using such methods in the genus Helianthus (wild sunflowers). Phenotypic differentiation and interspecific diversification are explored, as well as intraspecific trait variations within Helianthus annuus across different ecological regions. Additionally, the dissertation applies similar methods to assess the impact of historical weather patterns on the agricultural yield of cultivated sunflower at national and regional scales. It also provides yield forecasts under future socioeconomic scenarios, considering the potential effects of climate change on sunflower cultivation. Overall, this work highlights the potential of machine learning coupled with interpretable methods, in analyzing nonlinear and multidimensional biological data, addressing important research questions in plant biology, ecology, and agriculture. The findings contribute to understanding evolutionary predictability, ecological strategies, and the impact of climate change on crop yields.
If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu
Doctor of Philosophy (Ph.D.)
College of Sciences
Integrative Conservation Biology; Integrative Biology
Length of Campus-only Access
Doctoral Dissertation (Campus-only Access)
Majumder, Sambadi, "Applications of Interpretable Machine Learning Methods in Plant Ecology and Crop Science" (2023). Electronic Theses and Dissertations, 2020-. 1802.
Restricted to the UCF community until August 2024; it will then be open access.