Assessing machine learning techniques in forecasting lumpy skin disease occurrence based on meteorological and geospatial features
- 14 January 2022
- journal article
- research article
- Published by Springer Nature in Tropical Animal Health and Production
- Vol. 54 (1) , 1-11
Abstract
Lumpy skin disease virus (LSDV) causes an infectious disease in cattle. Due to its direct relationship with the survival of arthropod vectors, geospatial and climatic features play a vital role in the epidemiology of the disease. The objective of this study was to assess the ability of some machine learning algorithms to forecast the occurrence of LSDV infection based on meteorological and geological attributes. Initially, ExtraTreesClassifier algorithm was used to select the important predictive features in forecasting the disease occurrence in unseen (test) data among meteorological, animal population density, dominant land cover, and elevation attributes. Some machine learning techniques revealed high accuracy in predicting the LSDV occurrence in test data (up to 97%). In terms of area under curve (AUC) and F1 performance metric scores, the artificial neural network (ANN) algorithm outperformed other machine learning methods in predicting the occurrence of LSDV infection in unseen data with the corresponding values of 0.97 and 0.94, respectively. Using this algorithm, the model consisted of all predictive features and the one which only included meteorological attributes as important features showed similar predictive performance. According to the findings of this research, ANN can be used to forecast the occurrence of LSDV infection with high precision using geospatial and meteorological parameters. Applying the forecasting power of these methods could be a great help in conducting screening and awareness programs, as well as taking preventive measures like vaccination in areas where the occurrence of LSDV infection is a high risk.Keywords
This publication has 43 references indexed in Scilit:
- Risk assessments of lumpy skin diseases in Borena bull market chain and its implication for livelihoods and international tradeTropical Animal Health and Production, 2012
- Development of an optimized multi-biomarker panel for the detection of lung cancer based on principal component analysis and artificial neural network modelingExpert Systems with Applications, 2012
- Review: Lumpy Skin Disease: An Emerging Threat to Europe, the Middle East and AsiaTransboundary and Emerging Diseases, 2011
- Risk factors associated with observed clinical lumpy skin disease in EthiopiaEpidemiology and Infection, 2010
- Feature subset selection in large dimensionality domainsPattern Recognition, 2010
- SlimPLS: A Method for Feature Selection in Gene Expression-Based Disease ClassificationPLOS ONE, 2009
- A system to diagnose atherosclerosis via wavelet transforms, principal component analysis and artificial neural networksExpert Systems with Applications, 2007
- Extremely randomized treesMachine Learning, 2006
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- A survey of decision tree classifier methodologyIEEE Transactions on Systems, Man, and Cybernetics, 1991