Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets

Insecticide-treated nets (ITNs) remain a critical intervention in controlling malaria transmission, yet the behavioural adaptations of mosquitoes in response to these interventions are not fully understood. This study examined the flight behaviour of insecticide-resistant (IR) and insecticide-suscep...

Full description

Saved in:
Bibliographic Details
Main Authors: Yasser M. Qureshi, Vitaly Voloshin, Amy Guy, Hilary Ranson, Philip J. McCall, James A. Covington, Catherine E. Towers, David P. Towers
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Current Research in Parasitology and Vector-Borne Diseases
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667114X25000330
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218862980628480
author Yasser M. Qureshi
Vitaly Voloshin
Amy Guy
Hilary Ranson
Philip J. McCall
James A. Covington
Catherine E. Towers
David P. Towers
author_facet Yasser M. Qureshi
Vitaly Voloshin
Amy Guy
Hilary Ranson
Philip J. McCall
James A. Covington
Catherine E. Towers
David P. Towers
author_sort Yasser M. Qureshi
collection DOAJ
description Insecticide-treated nets (ITNs) remain a critical intervention in controlling malaria transmission, yet the behavioural adaptations of mosquitoes in response to these interventions are not fully understood. This study examined the flight behaviour of insecticide-resistant (IR) and insecticide-susceptible (IS) Anopheles gambiae strains around an Olyset net (OL), a permethrin-impregnated ITN, versus an untreated net (UT). Using machine learning (ML) models, we classified mosquito flight trajectories with high balanced accuracy (0.838) and ROC AUC (0.925). Contrary to assumptions that behavioural changes at OL would intensify over time, our findings show an immediate onset of convoluted, erratic flight paths for both IR and IS mosquitoes around the treated net. SHAP analysis identified three key predictive features of OL exposure: frequency of zero-crossings in flight angle change; first quartile of flight angle change; and zero-crossings in horizontal velocity. These suggest disruptive flight patterns, indicating insecticidal irritancy. While IS mosquitoes displayed rapid, disordered trajectories and mostly died within 30 min, IR mosquitoes persisted throughout the 2-h experiments but exhibited similarly disturbed behaviour, suggesting resistance does not fully mitigate disruption. Our findings challenge literature suggesting permethrin’s repellency in solution form, instead supporting an irritant or contact-driven effect when incorporated into net fibres. This study highlights the value of ML-based trajectory analysis for understanding mosquito behaviour, refining ITN configurations and evaluating novel active ingredients aimed at disrupting mosquito flight behaviour. Future work should extend these methods to other ITNs to further illuminate the complex interplay between mosquito behaviour and insecticidal intervention.
format Article
id doaj-art-ee5abcbafa9c43bd8539efefa4d61394
institution OA Journals
issn 2667-114X
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Current Research in Parasitology and Vector-Borne Diseases
spelling doaj-art-ee5abcbafa9c43bd8539efefa4d613942025-08-20T02:07:34ZengElsevierCurrent Research in Parasitology and Vector-Borne Diseases2667-114X2025-01-01710027310.1016/j.crpvbd.2025.100273Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset netsYasser M. Qureshi0Vitaly Voloshin1Amy Guy2Hilary Ranson3Philip J. McCall4James A. Covington5Catherine E. Towers6David P. Towers7School of Engineering, University of Warwick, Coventry, CV4 7AL, UK; Corresponding author.School of Engineering, University of Warwick, Coventry, CV4 7AL, UK; School of Biological and Behavioural Sciences, Queen Mary University of London, E1 4NS, UKVector Biology Department, Liverpool School of Tropical Medicine, Pembroke Place, Liverpool, L3 5QA, UKVector Biology Department, Liverpool School of Tropical Medicine, Pembroke Place, Liverpool, L3 5QA, UKVector Biology Department, Liverpool School of Tropical Medicine, Pembroke Place, Liverpool, L3 5QA, UKSchool of Engineering, University of Warwick, Coventry, CV4 7AL, UKSchool of Engineering, University of Warwick, Coventry, CV4 7AL, UKSchool of Engineering, University of Warwick, Coventry, CV4 7AL, UKInsecticide-treated nets (ITNs) remain a critical intervention in controlling malaria transmission, yet the behavioural adaptations of mosquitoes in response to these interventions are not fully understood. This study examined the flight behaviour of insecticide-resistant (IR) and insecticide-susceptible (IS) Anopheles gambiae strains around an Olyset net (OL), a permethrin-impregnated ITN, versus an untreated net (UT). Using machine learning (ML) models, we classified mosquito flight trajectories with high balanced accuracy (0.838) and ROC AUC (0.925). Contrary to assumptions that behavioural changes at OL would intensify over time, our findings show an immediate onset of convoluted, erratic flight paths for both IR and IS mosquitoes around the treated net. SHAP analysis identified three key predictive features of OL exposure: frequency of zero-crossings in flight angle change; first quartile of flight angle change; and zero-crossings in horizontal velocity. These suggest disruptive flight patterns, indicating insecticidal irritancy. While IS mosquitoes displayed rapid, disordered trajectories and mostly died within 30 min, IR mosquitoes persisted throughout the 2-h experiments but exhibited similarly disturbed behaviour, suggesting resistance does not fully mitigate disruption. Our findings challenge literature suggesting permethrin’s repellency in solution form, instead supporting an irritant or contact-driven effect when incorporated into net fibres. This study highlights the value of ML-based trajectory analysis for understanding mosquito behaviour, refining ITN configurations and evaluating novel active ingredients aimed at disrupting mosquito flight behaviour. Future work should extend these methods to other ITNs to further illuminate the complex interplay between mosquito behaviour and insecticidal intervention.http://www.sciencedirect.com/science/article/pii/S2667114X25000330Insecticide-treated netsInsecticide resistanceMosquito behaviourMachine learningTrajectoriesMalaria control
spellingShingle Yasser M. Qureshi
Vitaly Voloshin
Amy Guy
Hilary Ranson
Philip J. McCall
James A. Covington
Catherine E. Towers
David P. Towers
Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
Current Research in Parasitology and Vector-Borne Diseases
Insecticide-treated nets
Insecticide resistance
Mosquito behaviour
Machine learning
Trajectories
Malaria control
title Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
title_full Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
title_fullStr Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
title_full_unstemmed Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
title_short Machine learning reveals immediate disruption in mosquito flight when exposed to Olyset nets
title_sort machine learning reveals immediate disruption in mosquito flight when exposed to olyset nets
topic Insecticide-treated nets
Insecticide resistance
Mosquito behaviour
Machine learning
Trajectories
Malaria control
url http://www.sciencedirect.com/science/article/pii/S2667114X25000330
work_keys_str_mv AT yassermqureshi machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT vitalyvoloshin machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT amyguy machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT hilaryranson machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT philipjmccall machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT jamesacovington machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT catherineetowers machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets
AT davidptowers machinelearningrevealsimmediatedisruptioninmosquitoflightwhenexposedtoolysetnets