Exploiting the full potential of Bayesian networks in predictive ecology

Abstract

1. Although ecological models used to make predictions from underlying covariates have a record of success, they also suffer from limitations. They are typically unable to make predictions when the value of one or more covariates is missing during the testing. Missing values can be estimated but methods are often unreliable and can result in poor accuracy. Similarly, missing values during the training can hinder parameter estimation of many ecological models. Bayesian networks can handle these and other limiting issues, such as having highly correlated covariates.However, they are rarely used to their full potential.2. Indeed, Bayesian networks are commonly used to evaluate the knowledge of experts by constructing the network manually and often (incorrectly) interpreting the resulting network causally. We provide an approach to learn a Bayesian network fully from observed data, without relying on experts and show how to appropriately interpret the resulting network, both to identify how the variables (covariates and target) are interrelated and to answer probabilistic queries.3. We apply this method to the case study of a mountain pine beetle infestation and find that the trained Bayesian network has a predictive accuracy of 0.88 AUC. We classify the covariates as primary and secondary in terms of contributing to the prediction and show that the predictive accuracy does not deteriorate when the secondary covariates are missing and degrades to only 0.76 when one of the primary covariates is missing. As a complement to the previous work on constructing Bayesian networks byhand, we show that if instead, both the structure and parameters are learned only from data, we can achieve more accurate predictions as well as generate new insights about the underlying processes. K E Y W O R D Sautomatic learning, Bayesian network, invasive species, machine-learning, mountain pine beetle, pest, risk modelling, structure learning | INTRODUC TI ONPredictions are essential in aquatic and terrestrial ecology, whether the focus lies in changes in ecosystem composition, structure and richness to preserve the biodiversity and ecosystem function, or in the spatial distribution of individuals and species to inform conservation and invasive species policies. The field of predictive ecology focuses on how to make such predictions, particularly in the This is an open access article under the terms of the Creat ive Commo ns Attri bution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Accurate long-range forecasting of COVID-19 mortality in the USA

“…Then, a feature selection algorithm would have to implicitly consider all 2 55 combinations. To reduce the chance of overfitting and to save computational time, LaFoPaFo instead considers a systematically-constructed fixed subset of covariates, where all of the historical values of the selected covariates are included, counting from the current times 12 .…”

A hypothesis-free bridging of disease dynamics and non-pharmaceutical policies

“…Non-pharmaceutical preventive policies are often a priori known and available for making predictions. In situations where the data is unavailable regularly or contains missing values, Bayesian networks can be used instead of GBM [RKLGL21a].…”

Predicting insect outbreaks using machine learning: A mountain pine beetle case study

“…All covariates except for minimum temperature and outbreak phase are taken from (Ramazi et al., 2021 ). Each covariate is associated with a pixel and/or a time .…”

“…We address these three issues with the case study of a mountain pine beetle (MPB) outbreak in the Cypress Hills area in Canada. We have recently investigated the impact of, and relations between, some potential covariates of the MPB infestation using Bayesian networks (Ramazi et al., 2021 ). Predicting future MPB infestation, however, requires different tools and analysis, which is what we investigate here.…”