Accuracy in the prediction of disease epidemics when ensembling simple but highly correlated models

Abstract

Ensembling combines the predictions made by individual component base models with the goal of achieving a predictive accuracy that is better than that of any one of the constituent member models. Diversity among the base models in terms of predictions is a crucial criterion in ensembling. However, there are practical instances when the available base models produce highly correlated predictions, because they may have been developed within the same research group or may have been built from the same underlying algorithm. We investigated, via a case study on Fusarium head blight (FHB) on wheat in the U.S., whether ensembles of simple yet highly correlated models for predicting the risk of FHB epidemics, all generated from logistic regression, provided any benefit to predictive performance, despite relatively low levels of base model diversity. Three ensembling methods were explored: soft voting, weighted averaging of smaller subsets of the base models, and penalized regression as a stacking algorithm. Soft voting and weighted model averages were generally better at classification than the base models, though not universally so. The performances of stacked regressions were superior to those of the other two ensembling methods we analyzed in this study. Ensembling simple yet correlated models is computationally feasible and is therefore worth pursuing for models of epidemic risk.

A Machine-Learning-Based System for Prediction of Cardiovascular and Chronic Respiratory Diseases

“…ese time frames have been chosen because average response times in critical situations of a patient are 60 seconds and 3 minutes [11,12]. e harnessed regression models include the following: (a) Linear regression: it fits a line to a dataset of observations and then analyzes it to predict the unobserved values [33]. e formal description of linear regression is presented in…”

Plant disease threats to food security in the Northern Great Plains of North America

“…Fusarium head blight is a devastating wheat disease that is promoted by high F I G U R E 1 A winter wheat field with severe Wheat streak mosaic disease in South Dakota. This field was eventually tilled under because the plants were too stunted to yield wheat worth combining relative humidity from shortly prior to heading and throughout the initial grain development stages (Shah et al, 2021). Fusarium head blight epidemics have been correlated with seasons of frequent rainfall, and this has led to increased use of fungicides, which increases costs of production for wheat.…”

“…In most cases, the environment is the most determining factor because the host is the planted crop and the inoculum is usually abundant in most environments. Temperature and rainfall are the most important environmental factors that influence disease development (Agrios, 2005; Anderson et al., 2004; Shah et al., 2021). These affect pathogen viability and survival as well as dispersal within and between plants and fields.…”

“…Frequent rainfall implies wet plant surfaces, which encourage fungal and bacterial infections. Fusarium head blight is a devastating wheat disease that is promoted by high relative humidity from shortly prior to heading and throughout the initial grain development stages (Shah et al., 2021). Fusarium head blight epidemics have been correlated with seasons of frequent rainfall, and this has led to increased use of fungicides, which increases costs of production for wheat.…”

“…This prediction system has saved growers from unnecessary fungicide application when the risk is low or has led to timely fungicide application when the risk is moderate to high. This system continues to be improved to be more accurate (Shah et al., 2021). Combined with precision technology (GPS‐guided sprayers and spot treatment equipment such as drones), for certain fungal diseases, specific parts of the field can be treated, therby reducing the amount of fungicides applied in the field.…”