Machine-Learning Approach for Risk Estimation and Risk Prediction of the Effect of Climate on Bovine Respiratory Disease - read online

Aug 5, 2026

Upload by Finn

Bovine respiratory disease (BRD) is a major cause of illness and death in cattle, yet its global extent and distribution remain insufficiently defined. Climate change may drive BRD emergence and reemergence, making it critical to identify environmental determinants. The study applies machine-learning models with remotely sensed climate variables at fine spatial resolution to estimate BRD risk and forecast future geographical suitability, using 13,431 cases from 1,727 cities worldwide (2005–2021). Model performance is evaluated using AUC-ROC, positive predictive power, and Cohen’s Kappa, and uncertainty is assessed under multiple re-sampling schemes.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Study context and public health relevance

Climate change and livestock interventions

Methods

Machine-learning models and data sources

Uncertainty and model evaluation

mathematics Article Machine-Learning Approach for Risk Estimation and Risk Prediction of the Effect of Climate on Bovine Respiratory Disease Joseph K. Gwaka 1, Marcy A. Demafo 1, Joel-Pascal N. N'konzi 1, Anton Pak 2,3, Jamiu Olumoh 4, Faiz Elfaki 5,† and Oyelola A. Adegboye 2,6,7, *,† Citation: Gwaka, J.K.; Demafo, M.A.; N'konzi, J.-P.N.; Pak, A.; Olumoh, J.; Elfaki, F.; Adegboye, O.A. MachineLearning Approach for Risk Estimation and Risk Prediction of the Effect of Climate on Bovine Respiratory Disease. Mathematics 2023, 11, 1354. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/math11061354](10.3390/math11061354) Academic Editor: Mikhail Kolev Received: 30 December 2022 Revised: 21 February 2023 Accepted: 26 February 2023 Published: 10 March 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 African Institute for Mathematical Sciences, Kigali 20093, Rwanda 2 Australian Institute of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia 3 Centre for the Business and Economics of Health, The University of Queensland, Brisbane, QLD 4067, Australia 4 Department of Mathematics, American University of Nigeria, Yola 640001, Nigeria 5 Statistics Program, Department of Mathematics, Statistics and Physics, Qatar University, Doha P.O. Box 2713, Qatar 6 Public Health and Tropical Medicine, College of Public Health, Medical and Veterinary Sciences, James Cook University, Townsville, QLD 4811, Australia 7 World Health Organization Collaborating Center for Vector-Borne and Neglected Tropical Diseases, College of Public Health, Medical and Veterinary Sciences, James Cook University, Townsville, QLD 4811, Australia * Correspondence: [oyelola.adegboye@jcu.edu.au](oyelola.adegboye@jcu.edu.au); Tel.: +61-7-4781-5707 † Shared senior authors. Abstract: Bovine respiratory disease (BRD) is a major cause of illness and death in cattle; however, its global extent and distribution remain unclear. As climate change continues to impact the environment, it is important to understand the environmental factors contributing to BRD's emergence and reemergence. In this study, we used machine-learning models and remotely sensed climate data at 2.5 min (21 km2 ) resolution environmental layers to estimate the risk of BRD and predict its potential future distribution. We analysed 13,431 BRD cases from 1727 cities worldwide between 2005 and 2021 using two machine-learning models, maximum entropy (MaxEnt) and Boosted Regression Trees (BRT), to predict the risk and geographical distribution of the risk of BRD globally with varying model parameters. Different re-sampling regimes were used to visualise and measure various sources of uncertainty and prediction performance. The best-ﬁtting model was assessed based on the area under the receiver operator curve (AUC-ROC), positive predictive power and Cohen's Kappa. We found that BRT had better predictive power compared with MaxEnt. Our ﬁndings showed that favourable habitats for BRD occurrence were associated with the mean annual temperature, precipitation of the coldest quarter, mean diurnal range and minimum temperature of the coldest month. Similarly, we showed that the risk of BRD is not limited to the currently known suitable regions of Europe and west and central Africa but extends to other areas, such as Russia, China and Australia. This study highlights the need for global surveillance and early detection systems to prevent the spread of disease across borders. The ﬁndings also underscore the importance of bio-security surveillance and livestock sector interventions, such as policy-making and farmer education, to addr

FAQs

Why is BRD considered important for cattle health and broader well-being?

BRD can be fatal for feedlot cattle and affects both animal and human well-being. It is costly and often appears in young calves.

Which machine-learning methods were used to estimate BRD risk?

The study used two machine-learning models: maximum entropy (MaxEnt) and boosted regression trees (BRT).

What climate-related factors were linked to BRD habitat suitability?

Favorable habitats were associated with mean annual temperature, precipitation of the coldest quarter, mean diurnal range, and minimum temperature of the coldest month.

Aug 5, 2026

Upload by Finn