<div>Over 50% of the world population is at risk of mosquito-borne diseases. Female Ae. aegypti mosquito species transmit Zika, Dengue, and Chikungunya. The spread of these diseases correlate positively with the vector population, and this population depends on biotic and abiotic environmental factors including temperature, vegetation condition, humidity and precipitation. To combat virus outbreaks, information about vector population is required. To this aim, Earth observation (EO) data provide fast, efficient and economically viable means to estimate environmental features of interest. In this work, we present a temporal distribution model for adult female Ae. aegypti mosquitoes based on the joint use of the Normalized Difference Vegetation Index, the Normalized Difference Water Index, the Land Surface Temperature (both at day and night time), along with the precipitation information, extracted from EO data. The model was applied separately to data obtained during three different vector control and field data collection condition regimes, and used to explain the differences in environmental variable contributions across these regimes. To this aim, a random forest (RF) regression technique and its nonlinear features importance ranking based on mean decrease impurity (MDI) were implemented. To prove the robustness of the proposed model, other machine learning techniques, including support vector regression, decision trees and k-nearest neighbor regression, as well as artificial neural networks, and statistical models such as the linear regression model and generalized linear model were also considered. Our results show that machine learning techniques perform better than linear statistical models for the task at hand, and RF performs best. By ranking the importance of all features based on MDI in RF and selecting the subset comprising the most</div>

Over 50% of the world population is at risk of mosquito-borne diseases. Female Ae. aegypti mosquito species transmit Zika, Dengue, and Chikungunya. The spread of these diseases correlate positively with the vector population, and this population depends on biotic and abiotic environmental factors including temperature, vegetation condition, humidity and precipitation. To combat virus outbreaks, information about vector population is required. To this aim, Earth observation (EO) data provide fast, efficient and economically viable means to estimate environmental features of interest. In this work, we present a temporal distribution model for adult female Ae. aegypti mosquitoes based on the joint use of the Normalized Difference Vegetation Index, the Normalized Difference Water Index, the Land Surface Temperature (both at day and night time), along with the precipitation information, extracted from EO data. The model was applied separately to data obtained during three different vector control and field data collection condition regimes, and used to explain the differences in environmental variable contributions across these regimes. To this aim, a random forest (RF) regression technique and its nonlinear features importance ranking based on mean decrease impurity (MDI) were implemented. To prove the robustness of the proposed model, other machine learning techniques, including support vector regression, decision trees and k-nearest neighbor regression, as well as artificial neural networks, and statistical models such as the linear regression model and generalized linear model were also considered. Our results show that machine learning techniques perform better than linear statistical models for the task at hand, and RF performs best. By ranking the importance of all features based on MDI in RF and selecting the subset comprising the most informative ones, a more parsimonious but equally effective and explainable model can be obtained. Moreover, the results can be empirically interpreted for use in vector control activities. INDEX TERMS Ae. aegypti, machine learning, random forest, remote sensing.

This paper introduces a technique for using Recurrent Neural Networks to forecast Ae. aegypti mosquito (Dengue transmission vector) counts at neighbourhood-level, using Earth Observation data inputs as proxies to environmental variables. The model is validated using in situ data in two Brazilian cities, and compared with state-of-the-art multi-output Random Forest and k-Nearest Neighbor models. The approach exploits a clustering step performed before the model definition, which simplifies the task by aggregating mosquito count sequences with similar temporal patterns.

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.

Mosquitoes propagate many human diseases, some widespread and with no vaccines. The Ae. aegypti mosquito vector transmits Zika, Chikungunya, and Dengue viruses. Effective public health interventions to control the spread of these diseases and protect the population require models that explain the core environmental drivers of the vector population. Field campaigns are expensive, and data from meteorological sites that feed models with the required environmental data often lack detail. As a consequence, we explore temporal modeling of the population of Ae. aegypti mosquito vector species and environmental conditions- temperature, moisture, precipitation, and vegetation- have been shown to have significant effects. We use earth observation (EO) data as our source for estimating these biotic and abiotic environmental variables based on proxy features, namely: Normalized difference vegetation index, Normalized difference water index, Precipitation, and Land surface temperature. We obtained our response variable from field-collected mosquito population measured weekly using 791 mosquito traps in Vila Velha city, Brazil, for 36 weeks in 2017, and 40 weeks in 2018. Recent similar studies have used machine learning (ML) techniques for this task. However, these techniques are neither intuitive nor explainable from an operational point of view. As a result, we use a Generalized Linear Model (GLM) to model this relationship due to its fitness for count response variable modeling, its interpretability, and the ability to visualize the confidence intervals for all inferences. Also, to improve our model, we use the Akaike Information Criterion to select the most informative environmental features. Finally, we show how to improve the quality of the model by weighting our GLM. Our resulting weighted GLM compares well in quality with ML techniques: Random Forest and Support Vector Machines. These results provide an advancement with regards to qualitative and explainable epidemiological risk modeling in urban environments.