Review of machine learning techniques for mosquito control in urban environments

Joshi, Ananya; Miller, Clayton

doi:10.1016/j.ecoinf.2021.101241

Cited by 56 publications

(26 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been signi cant advances in the use of available datasets and targeted data collection to predict mosquito populations, particularly in preventing the spread of mosquito-borne diseases. Joshi and Miller (2021) give a comprehensive overview of state-of-the-art. However, there is a lack of software solutions that would serve as auxiliary tools and a basis for decision-making for local authorities to optimize mosquito population control and change its nature from reactive to preventive.…”

Section: Discussionmentioning

confidence: 99%

Modelling can reduce contamination from mosquito population control

Djerdj

Hackenberger²,

Klanjšček³

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Environmental contamination due to pest control in general, and mosquito control in particular, is an important issue expected to increase with climate change. We use a validated model for population dynamics of mosquitoes and historical environmental data to explore performance of larvicidal, adulticidal, and combined treatments. Results show that depending on treatment timing, larvicidal treatments can induce very good results, or have negative outcomes that increase overall mosquito population. Combined larvicidal and adulticidal treatments, however, exhibit much lesser dependence on timing, and therefore give the greatest chance of positive outcomes if environmental conditions are not known. Based on the results, we argue for adaptive mosquito management, in which weather data and forecasts are used to drive a model that identi es best intervals for insecticide use. Such an approach can have considerably better results than static, calendar-driven management and, therefore, considerably reduce environmental contamination. Adaptive management could consider larvicidal treatment because it gives good results if the timing is correct. Static management should, however, combine larvicidal and adulticidal treatments for the greatest chance of success.

show abstract

Section: Discussionmentioning

confidence: 99%

Modelling can reduce contamination from mosquito population control

Djerdj

Hackenberger²,

Klanjšček³

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

show abstract

“…Mosquitoes have particularly short, truncated wings allowing them to flap their wings faster than any other insect of equivalent size -up to 1,000 beats per second [Simões et al, 2016, Bomphrey et al, 2017. This produces their distinctive flight tone and has led many researchers to try and use their sound to attract, trap or kill them [Perevozkin and Bondarchuk, 2015, Johnson and Ritchie, 2016, Jakhete et al, 2017, Joshi and Miller, 2021. Table 1 provides details of the few datasets released to the public to aid this research.…”

Section: Related Workmentioning

confidence: 99%

HumBugDB: A Large-scale Acoustic Mosquito Dataset

Kiskin¹,

Sinka²,

Cobb³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents the first large-scale multi-species dataset of acoustic recordings of mosquitoes tracked continuously in free flight. We present 20 hours of audio recordings that we have expertly labelled and tagged precisely in time. Significantly, 18 hours of recordings contain annotations from 36 different species. Mosquitoes are well-known carriers of diseases such as malaria, dengue and yellow fever. Collecting this dataset is motivated by the need to assist applications which utilise mosquito acoustics to conduct surveys to help predict outbreaks and inform intervention policy. The task of detecting mosquitoes from the sound of their wingbeats is challenging due to the difficulty in collecting recordings from realistic scenarios. To address this, as part of the HumBug project, we conducted global experiments to record mosquitoes ranging from those bred in culture cages to mosquitoes captured in the wild. Consequently, the audio recordings vary in signal-to-noise ratio and contain a broad range of indoor and outdoor background environments from Tanzania, Thailand, Kenya, the USA and the UK. In this paper we describe in detail how we collected, labelled and curated the data. The data is provided from a PostgreSQL database, which contains important metadata such as the capture method, age, feeding status and gender of the mosquitoes. Additionally, we provide code to extract features and train Bayesian convolutional neural networks for two key tasks: the identification of mosquitoes from their corresponding background environments, and the classification of detected mosquitoes into species. Our extensive dataset is both challenging to machine learning researchers focusing on acoustic identification, and critical to entomologists, geo-spatial modellers and other domain experts to understand mosquito behaviour, model their distribution, and manage the threat they pose to humans. Preprint. This paper has been accepted at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks.

show abstract

“…Artificial neural networks for the prediction of mosquito abundance and mosquito-borne disease incidence have also been previously described (Laureano-Rosario et al 2018;Lee et al 2016). Studies on mosquito control have also implemented maximum entropy modeling and artificial neural networks (Joshi and Miller 2021). Based on these studies, mosquito forecasting systems have been implemented as part of public health programs in various countries.…”

Section: Introductionmentioning

confidence: 99%

Interpretable machine learning approach to analyze the effects of landscape and meteorological factors on mosquito occurrences in Seoul, South Korea

Lee

Park

2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

Mosquitoes are the underlying cause of various public health and economic problems. In this study, patterns of mosquito occurrence were analyzed based on landscape and meteorological factors in the metropolitan city of Seoul. We evaluated the influence of environmental factors on mosquito occurrence through the interpretation of prediction models with a machine learning algorithm. Through hierarchical cluster analysis, the study areas were classified into waterside and non-waterside areas, according to the landscape patterns. The mosquito occurrence was higher in the waterside area, and mosquito abundance was negatively affected by rainfall at the waterside. The mosquito occurrence was predicted in each cluster area based on the landscape and cumulative meteorological variables using a random forest algorithm. Both models exhibited good performance (both accuracy and AUROC > 0.8) in predicting the level of mosquito occurrence. The embedded relationship between the mosquito occurrence and the environmental factors in the models was explained using the Shapley additive explanation method. According to the variable importance and the partial dependence plots for each model, the waterside area was more influenced by the meteorological and land cover variables than the non-waterside area. Therefore, mosquito control strategies should consider the effects of landscape and meteorological conditions, including the temperature, rainfall, and the landscape heterogeneity. The present findings can contribute to the development of mosquito forecasting systems in metropolitan cities for the promotion of public health.

show abstract

Review of machine learning techniques for mosquito control in urban environments

Cited by 56 publications

References 103 publications

Modelling can reduce contamination from mosquito population control

Modelling can reduce contamination from mosquito population control

HumBugDB: A Large-scale Acoustic Mosquito Dataset

Interpretable machine learning approach to analyze the effects of landscape and meteorological factors on mosquito occurrences in Seoul, South Korea

Contact Info

Product

Resources

About