Tables index

From

Modelling Plant Growth Based on Gompertz, Logistic Curve, Extreme Gradient Boosting and Light Gradient Boosting Models Using High Dimensional Image Derived Maize (Zea mays L.) Phenomic Data

Peter Gachoki, Moses Muraya, Gladys Njoroge

American Journal of Applied Mathematics and Statistics. 2022, 10(2), 52-64 doi:10.12691/ajams-10-2-3
  • Table 1. Features used in fitting the statistical models
  • Table 2. Linear Models fitted using the plant volume, side area and side height image derived phenotypic features
  • Table 3. Gradient Boosting Models for plant phenotypic Features derived using Feature Importance
  • Table 4. Light Gradient Boosting Model for plant phenotypic features selected using Feature Importance
  • Table 5. Fitted Gompertz Model using volume plant phenotypic feature
  • Table 6. Perfomance metric for the Gompertz model using volume plant phenotypic feature
  • Table 7. Fitted Gompertz Model using the Feature using side area plant phenotypic feature
  • Table 8. Performance Metrics for the Gompertz model using side area plant phenotypic feature
  • Table 9. Fitted logistic growth curve using volume plant phenotypic feature
  • Table 10. Perfomance metrics for the logistic growth curve using volume plant phenotypic feature
  • Table 11. Fitted logistic growth curve using side area plant phenotypic feature
  • Table 12. Performance metrics for the logistic growth curve fitted using side area plant phenotypic feature
  • Table 13. Comparison of Statistical Power for Machine Learning Models for modelling plant growth
  • Table 14. Models Comparison for the Gompertz and Logistic Curve Models
  • Table 15. Models Comparison for XGBoost with 31 features and XGBoost with 1 feature