Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms
The interplay of biotic and abiotic factors driving Ixodes ricinus abundance trends are not fully understood. Machine learning (ML) approaches are being increasingly used to explore this and predict future abundance patterns of this species, however, the studies focusing on this to date have had lim...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ticks and Tick-Borne Diseases |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1877959X25000019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540409422675968 |
|---|---|
| author | Samantha Lansdell Abin Zorto Misaki Seto Edessa Negera Saeed Sharif Sally Cutler |
| author_facet | Samantha Lansdell Abin Zorto Misaki Seto Edessa Negera Saeed Sharif Sally Cutler |
| author_sort | Samantha Lansdell |
| collection | DOAJ |
| description | The interplay of biotic and abiotic factors driving Ixodes ricinus abundance trends are not fully understood. Machine learning (ML) approaches are being increasingly used to explore this and predict future abundance patterns of this species, however, the studies focusing on this to date have had limitations (including short study duration, limited sample size, narrow geographical range and use of a single ML model). This study was undertaken to address these limitations by applying 11 predictive ML models (across three data clustering techniques) to a large I. ricinus occurrence dataset (27,150 records) containing geographical and temporal data from a 20-year period across 30 European countries, coupled with data covering a range of climatic and habitat features (temperature, rainfall, Normalised Difference Vegetation Index (NDVI), percentage of discontinuous urban fabric and land use category). To assess which ML model was most suited to prediction of I. ricinus abundance, four performance metric values were calculated per model: Normalised Root Mean Square Error (NRMSE), Scatter Index (SI), Mean Absolute Percentage Error (MAPE) and R2, all of which describe the statistical relationship between predicted and actual I. ricinus abundance values. Furthermore, using a Random Forest (RF) model across three clustering methods, we determined which features most significantly impacted upon I. ricinus abundance. The study demonstrated that Agglomerative Hierarchical Clustering (AC) methods and Linear Regression (LR) modelling performed best with this dataset. Our findings revealed that land use and rainfall were the primary contributors to I. ricinus abundance, with temperature playing a lesser role. This was measured according to the extent of prediction error increase following exclusion of that factor from the analysis. We provide a summary of the factors most strongly linked to I. ricinus abundance, which can be used to guide interventions to aid the control of ticks and tick-borne disease across Europe. |
| format | Article |
| id | doaj-art-9cafed1ae5c0435f8108b736f56643e0 |
| institution | Kabale University |
| issn | 1877-9603 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ticks and Tick-Borne Diseases |
| spelling | doaj-art-9cafed1ae5c0435f8108b736f56643e02025-02-05T04:31:33ZengElsevierTicks and Tick-Borne Diseases1877-96032025-01-01161102437Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithmsSamantha Lansdell0Abin Zorto1Misaki Seto2Edessa Negera3Saeed Sharif4Sally Cutler5Department of Health, Sport and Bioscience. University of East London, Water Lane, Stratford E15 4LZ, United KingdomDepartment of Architecture, Computing and Engineering. University of East London, University Way, London E16 2RD, United KingdomDepartment of Health, Sport and Bioscience. University of East London, Water Lane, Stratford E15 4LZ, United KingdomDepartment of Health, Sport and Bioscience. University of East London, Water Lane, Stratford E15 4LZ, United KingdomDepartment of Architecture, Computing and Engineering. University of East London, University Way, London E16 2RD, United KingdomDepartment of Health, Sport and Bioscience. University of East London, Water Lane, Stratford E15 4LZ, United Kingdom; Corresponding author.The interplay of biotic and abiotic factors driving Ixodes ricinus abundance trends are not fully understood. Machine learning (ML) approaches are being increasingly used to explore this and predict future abundance patterns of this species, however, the studies focusing on this to date have had limitations (including short study duration, limited sample size, narrow geographical range and use of a single ML model). This study was undertaken to address these limitations by applying 11 predictive ML models (across three data clustering techniques) to a large I. ricinus occurrence dataset (27,150 records) containing geographical and temporal data from a 20-year period across 30 European countries, coupled with data covering a range of climatic and habitat features (temperature, rainfall, Normalised Difference Vegetation Index (NDVI), percentage of discontinuous urban fabric and land use category). To assess which ML model was most suited to prediction of I. ricinus abundance, four performance metric values were calculated per model: Normalised Root Mean Square Error (NRMSE), Scatter Index (SI), Mean Absolute Percentage Error (MAPE) and R2, all of which describe the statistical relationship between predicted and actual I. ricinus abundance values. Furthermore, using a Random Forest (RF) model across three clustering methods, we determined which features most significantly impacted upon I. ricinus abundance. The study demonstrated that Agglomerative Hierarchical Clustering (AC) methods and Linear Regression (LR) modelling performed best with this dataset. Our findings revealed that land use and rainfall were the primary contributors to I. ricinus abundance, with temperature playing a lesser role. This was measured according to the extent of prediction error increase following exclusion of that factor from the analysis. We provide a summary of the factors most strongly linked to I. ricinus abundance, which can be used to guide interventions to aid the control of ticks and tick-borne disease across Europe.http://www.sciencedirect.com/science/article/pii/S1877959X25000019TickIxodes ricinusMachine learningModelEuropeTemperature |
| spellingShingle | Samantha Lansdell Abin Zorto Misaki Seto Edessa Negera Saeed Sharif Sally Cutler Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms Ticks and Tick-Borne Diseases Tick Ixodes ricinus Machine learning Model Europe Temperature |
| title | Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms |
| title_full | Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms |
| title_fullStr | Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms |
| title_full_unstemmed | Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms |
| title_short | Insights into the contribution of multiple factors on Ixodes ricinus abundance across Europe spanning 20 years using different machine learning algorithms |
| title_sort | insights into the contribution of multiple factors on ixodes ricinus abundance across europe spanning 20 years using different machine learning algorithms |
| topic | Tick Ixodes ricinus Machine learning Model Europe Temperature |
| url | http://www.sciencedirect.com/science/article/pii/S1877959X25000019 |
| work_keys_str_mv | AT samanthalansdell insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms AT abinzorto insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms AT misakiseto insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms AT edessanegera insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms AT saeedsharif insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms AT sallycutler insightsintothecontributionofmultiplefactorsonixodesricinusabundanceacrosseuropespanning20yearsusingdifferentmachinelearningalgorithms |