Modeling dengue vector population with earth observation data and a generalized linear model

Abstract

Mosquitoes are vectors of many human diseases. In particular, Aedes aegypti (Linnaeus) is the main vector for Chikungunya, Dengue, and Zika viruses in Latin America and it represents a global threat. Public health policies that aim at combating this vector require dependable and timely information, which is usually expensive to obtain with field campaigns. For this reason, several efforts have been done to use remote sensing due to its reduced cost. The present work includes the temporal modeling of the oviposition activity (measured weekly on 50 ovitraps in a north Argentinean city) of Aedes aegypti (Linnaeus), based on time series of data extracted from operational earth observation satellite images. We use are NDVI, NDWI, LST night, LST day and TRMM-GPM rain from 2012 to 2016 as predictive variables. In contrast to previous works which use linear models, we employ Machine Learning techniques using completely accessible open source toolkits. These models have the advantages of being non-parametric and capable of describing nonlinear relationships between variables. Specifically, in addition to two linear approaches, we assess a support vector machine, an artificial neural networks, a K-nearest neighbors and a decision tree regressor. Considerations are made on parameter tuning and the validation and training approach. The results are compared to linear models used in previous works with similar data sets for generating temporal predictive models. These new tools perform better than linear approaches, in particular nearest neighbor regression (KNNR) performs the best. These results provide better alternatives to be implemented operatively on the Argentine geospatial risk system that is running since 2012.

Epidemiological characteristics of severe fever with thrombocytopenia syndrome and its relationship with meteorological factors in Liaoning Province, China

“…The GLM extends ordinary linear regression by establishing the relationship between the mathematical expectation of the response variable and the predictor variables through a linkage function. The GLM based on Poisson distribution can directly solve the problem of the nonlinear relationship between meteorological factors and infectious diseases [ 33 ]. As the correlation coefficients between the number of lagged SFTS cases and meteorological factors did not change significantly compared to the immediate SFTS cases, we analyzed only the regression relationship between the immediate SFTS cases and meteorological factors.…”

The Effects of Meteorological Factors on Dengue Cases in Malaysia

“…More recently, EO data derived from satellites has been used in several dengue-related studies [ 11 , 12 ]. However, as of yet, in Malaysia, no published studies exist that use EO meteorological data to examine the correlation between temperature, wind speed, and rainfall with dengue infections.…”

Common patterns between dengue cases, climate, and local environmental variables in Costa Rica: A Wavelet Approach

“…The complexity of dengue transmission has driven many studies to assess its correlation with meteorological and ecological variables [11,12,13,14,15,16,17]. Most of these works evaluated the effects and correlation between dengue cases and climate variables [18,19] and seasonal vegetation dynamics, which may also influence the biology of the vector populations at relatively local scales [20,21,22]. Barrera et al [23] suggested that dense vegetation can promote Ae.…”