Field phenotyping data analysis from KAUST internship. Includes trait distribution, species comparison (t-test), and automated plot summarization in R.
Context: Research internship at KAUST (Jesse Poland Lab). Focus: Digital phenotyping and statistical evaluation of plant traits. Key Skill: Advanced R (Tidyverse), Hypothesis Testing, and Phenotypic Visualization (ggplot2).
This repository contains R scripts developed during my research internship at KAUST (King Abdullah University of Science and Technology) in the Jesse Poland Lab.
The project focuses on digital phenotyping—analyzing physical traits of plants (Sesame and Wheat) to support breeding programs.
- Field Data Cleaning: Processing raw datasets from the
Field Bookmobile application. - Trait Summarization: Custom R functions for calculating plot-level statistics (Mean, SD).
- Statistical Validation: Hypothesis testing (t-test) to compare growth performance between species.
- Predictive Modeling: Correlation analysis between plant height, leaf count, and biomass.
phenotyping_analysis.R: Main analysis script.Plant_Trait_Dataset.csv: Sample dataset containing phenotypic observations.images/: Visualization plots (Histograms, Boxplots).
Demonstrated proficiency in using Tidyverse for agricultural data science and applying statistical methods to real-world field trials.