Forecasting Invasive Mosquito Abundance in the Basque Country, Spain Using Machine Learning Techniques

Overview

Journal Parasit Vectors

Publisher Biomed Central

Specialties Parasitology
Tropical Medicine

Date 2025 Mar 16

PMID 40089776

Authors

Vanessa Steindorf

Hamna Mariyam K B

Nico Stollenwerk

Aitor Cevidanes

Jesus F Barandika

Patricia Vazquez

Ana L Garcia-Perez

Maira Aguiar

Affiliations

Soon will be listed here.

Abstract

Background: Mosquito-borne diseases cause millions of deaths each year and are increasingly spreading from tropical and subtropical regions into temperate zones, posing significant public health risks. In the Basque Country region of Spain, changing climatic conditions have driven the spread of invasive mosquitoes, increasing the potential for local transmission of diseases such as dengue, Zika, and chikungunya. The establishment of mosquito species in new areas, coupled with rising mosquito populations and viremic imported cases, presents challenges for public health systems in non-endemic regions.

Methods: This study uses models that capture the complexities of the mosquito life cycle, driven by interactions with weather variables, including temperature, precipitation, and humidity. Leveraging machine learning techniques, we aimed to forecast Aedes invasive mosquito abundance in the provinces of the Basque Country, using egg count as a proxy and weather features as key independent variables. A Spearman correlation was used to assess relationships between climate variables and mosquito egg counts, as well as their lagged time series versions. Forecasting models, including random forest (RF) and seasonal autoregressive integrated moving average (SARIMAX), were evaluated using root mean squared error (RMSE) and mean absolute error (MAE) metrics.

Results: Statistical analysis revealed significant impacts of temperature, precipitation, and humidity on mosquito egg abundance. The random forest (RF) model demonstrated the highest forecasting accuracy, followed by the SARIMAX model. Incorporating lagged climate variables and ovitrap egg counts into the models improved predictions, enabling more accurate forecasts of Aedes invasive mosquito abundance.

Conclusions: The findings emphasize the importance of integrating climate-driven forecasting tools to predict the abundance of mosquitoes where data are available. Furthermore, this study highlights the critical need for ongoing entomological surveillance to enhance mosquito spread forecasting and contribute to the development and assessment of effective vector control strategies in regions of mosquito expansion.

References

Goiri F, Gonzalez M, Cevidanes A, Barandika J, Garcia-Perez A . Mosquitoes in urban green spaces and cemeteries in northern Spain. Parasit Vectors. 2024; 17(1):168. PMC: 10986117. DOI: 10.1186/s13071-024-06263-z. View

Cochet A, Calba C, Jourdain F, Grard G, Durand G, Guinard A . Autochthonous dengue in mainland France, 2022: geographical extension and incidence increase. Euro Surveill. 2022; 27(44). PMC: 9635021. DOI: 10.2807/1560-7917.ES.2022.27.44.2200818. View

Cevidanes A, Goiri F, Barandika J, Vazquez P, Goikolea J, Zuazo A . Invasive Aedes mosquitoes in an urban-peri-urban gradient in northern Spain: evidence of the wide distribution of Aedes japonicus. Parasit Vectors. 2023; 16(1):234. PMC: 10349466. DOI: 10.1186/s13071-023-05862-6. View

Diniz D, Romao T, Helvecio E, de Carvalho-Leandro D, Xavier M, Peixoto C . A comparative analysis of and subjected to diapause-inducing conditions reveals conserved and divergent aspects associated with diapause, as well as novel genes associated with its onset. Curr Res Insect Sci. 2023; 2:100047. PMC: 9846470. DOI: 10.1016/j.cris.2022.100047. View

Prasad A, Sreedharan S, Bakthavachalu B, Laxman S . Eggs of the mosquito Aedes aegypti survive desiccation by rewiring their polyamine and lipid metabolism. PLoS Biol. 2023; 21(10):e3002342. PMC: 10597479. DOI: 10.1371/journal.pbio.3002342. View

Juliano S, OMeara G, Morrill J, Cutwa M . Desiccation and thermal tolerance of eggs and the coexistence of competing mosquitoes. Oecologia. 2011; 130(3):458-469. PMC: 2944657. DOI: 10.1007/s004420100811. View

Ezeakacha N, Yee D . The role of temperature in affecting carry-over effects and larval competition in the globally invasive mosquito Aedes albopictus. Parasit Vectors. 2019; 12(1):123. PMC: 6423813. DOI: 10.1186/s13071-019-3391-1. View

Alto B, Juliano S . Precipitation and temperature effects on populations of Aedes albopictus (Diptera: Culicidae): implications for range expansion. J Med Entomol. 2001; 38(5):646-56. PMC: 2579929. DOI: 10.1603/0022-2585-38.5.646. View

Betanzos-Reyes A, Rodriguez M, Romero-Martinez M, Sesma-Medrano E, Rangel-Flores H, Santos-Luna R . Association of dengue fever with Aedes spp. abundance and climatological effects. Salud Publica Mex. 2018; 60(1):12-20. DOI: 10.21149/8141. View

10.

Carvajal T, Viacrusis K, Hernandez L, Ho H, Amalin D, Watanabe K . Machine learning methods reveal the temporal pattern of dengue incidence using meteorological factors in metropolitan Manila, Philippines. BMC Infect Dis. 2018; 18(1):183. PMC: 5905126. DOI: 10.1186/s12879-018-3066-0. View

11.

Chaves L, Valerin Cordero J, Delgado G, Aguilar-Avendano C, Maynes E, Gutierrez Alvarado J . Modeling the association between ovitrap egg counts, multi-scale remotely sensed environmental data and arboviral cases at Puntarenas, Costa Rica (2017-2018). Curr Res Parasitol Vector Borne Dis. 2022; 1:100014. PMC: 8906134. DOI: 10.1016/j.crpvbd.2021.100014. View

12.

Andreza da Cruz Ferreira D, Degener C, Marques-Toledo C, Bendati M, Fetzer L, Teixeira C . Meteorological variables and mosquito monitoring are good predictors for infestation trends of Aedes aegypti, the vector of dengue, chikungunya and Zika. Parasit Vectors. 2017; 10(1):78. PMC: 5307865. DOI: 10.1186/s13071-017-2025-8. View

13.

Leung X, Islam R, Adhami M, Ilic D, McDonald L, Palawaththa S . A systematic review of dengue outbreak prediction models: Current scenario and future directions. PLoS Negl Trop Dis. 2023; 17(2):e0010631. PMC: 9956653. DOI: 10.1371/journal.pntd.0010631. View

14.

de Jesus C, Dias F, Villela D, Maciel-de-Freitas R . Ovitraps Provide a Reliable Estimate of Frequency during MelBr Strain Deployment in a Geographically Isolated Population. Insects. 2020; 11(2). PMC: 7074419. DOI: 10.3390/insects11020092. View

15.

Kinney A, Current S, Lega J . Aedes-AI: Neural network models of mosquito abundance. PLoS Comput Biol. 2021; 17(11):e1009467. PMC: 8641871. DOI: 10.1371/journal.pcbi.1009467. View

16.

Tran A, LAmbert G, Lacour G, Benoit R, Demarchi M, Cros M . A rainfall- and temperature-driven abundance model for Aedes albopictus populations. Int J Environ Res Public Health. 2013; 10(5):1698-719. PMC: 3709343. DOI: 10.3390/ijerph10051698. View

17.

Goiri F, Gonzalez M, Goikolea J, Oribe M, de Castro V, Delacour S . Progressive Invasion of in Northern Spain in The Period 2013-2018 and A Possible Association with the Increase in Insect Bites. Int J Environ Res Public Health. 2020; 17(5). PMC: 7084620. DOI: 10.3390/ijerph17051678. View

18.

Sarker I . Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021; 2(3):160. PMC: 7983091. DOI: 10.1007/s42979-021-00592-x. View

19.

Akram M, Cerin E, Lamb K, White S . Modelling count, bounded and skewed continuous outcomes in physical activity research: beyond linear regression models. Int J Behav Nutr Phys Act. 2023; 20(1):57. PMC: 10163772. DOI: 10.1186/s12966-023-01460-y. View

20.

Schaffer A, Dobbins T, Pearson S . Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions. BMC Med Res Methodol. 2021; 21(1):58. PMC: 7986567. DOI: 10.1186/s12874-021-01235-8. View