Satellite Earth Observation Data in Epidemiological Modeling of Malaria, Dengue and West Nile Virus: A Scoping Review

Landscape and meteorological determinants of malaria vectors' presence and abundance in the rural health district of Korhogo, Côte d'Ivoire, 2016-2018, and comparison with the less anthropized area of Diébougou, Burkina Faso

BACKGROUND

Understanding how weather and landscape shape the fine-scale distribution and diversity of malaria vectors is crucial for efficient and locally tailored vector control. This study examines the meteorological and landscape determinants of (i) the spatiotemporal distribution (presence and abundance) of the major malaria vectors in the rural region of Korhogo (northern Côte d'Ivoire) and (ii) the differences in vector probability of presence, abundance, and diversity observed between that area and another rural West African region located 300 km away in Diébougou, Burkina Faso.

METHODS

We monitored Anopheles human-biting activity in 28 villages of the Korhogo health district for 18 months (2016 to 2018), and extracted fine-scale environmental variables (meteorological and landscape) from high-resolution satellite imagery. We used a state-of-the-art statistical modeling framework to associate these data and identify environmental determinants of the presence and abundance of malaria vectors in the area. We then compared the results of this analysis with those of a similar, previously published study conducted in the Diébougou area.

RESULTS

The spatiotemporal distribution of malaria vectors in the Korhogo area was highly heterogeneous and appeared to be strongly determined and constrained by meteorological conditions. Rice paddies, temporary sites filled by rainfall, rivers and riparian forests appeared to be the larval habitats of Anopheles mosquitoes. As in Diébougou, meteorological conditions (temperatures, rainfall) appeared to significantly affect all developmental stages of the mosquitoes. Additionally, ligneous savannas were associated with lower abundance of malaria vectors. Anopheles species diversity was lower in Korhogo compared to Diébougou, while biting rates were much higher. Our results suggest that these differences may be due to the more anthropized nature of the Korhogo region in comparison to Diébougou (less forested areas, more agricultural land), supporting the hypothesis of higher malaria vector densities and lower mosquito diversity in more anthropized landscapes in rural West Africa.

CONCLUSION

This study offers valuable insights into the landscape and meteorological determinants of the spatiotemporal distribution of malaria vectors in the Korhogo region and, more broadly, in rural west-Africa. The results emphasize the adverse effects of the ongoing landscape anthropization process in the sub-region, including deforestation and agricultural development, on malaria vector control.

Spotting Culex pipiens from satellite: modeling habitat suitability in central Italy using Sentinel-2 and deep learning techniques

Culex pipiens, an important vector of many vector borne diseases, is a species capable to feeding on a wide variety of hosts and adapting to different environments. To predict the potential distribution of Cx. pipiens in central Italy, this study integrated presence/absence data from a four-year entomological survey (2019-2022) carried out in the Abruzzo and Molise regions, with a datacube of spectral bands acquired by Sentinel-2 satellites, as patches of 224 × 224 pixels of 20 meters spatial resolution around each site and for each satellite revisit time. We investigated three scenarios: the baseline model, which considers the environmental conditions at the time of collection; the multitemporal model, focusing on conditions in the 2 months preceding the collection; and the MultiAdjacency Graph Attention Network (MAGAT) model, which accounts for similarities in temperature and nearby sites using a graph architecture. For the baseline scenario, a deep convolutional neural network (DCNN) analyzed a single multi-band Sentinel-2 image. The DCNN in the multitemporal model extracted temporal patterns from a sequence of 10 multispectral images; the MAGAT model incorporated spatial and climatic relationships among sites through a graph neural network aggregation method. For all models, we also evaluated temporal lags between the multi-band Earth Observation datacube date of acquisition and the mosquito collection, from 0 to 50 days. The study encompassed a total of 2,555 entomological collections, and 108,064 images (patches) at 20 meters spatial resolution. The baseline model achieved an F1 score higher than 75.8% for any temporal lag, which increased up to 81.4% with the multitemporal model. The MAGAT model recorded the highest F1 score of 80.9%. The study confirms the widespread presence of Cx. pipiens throughout the majority of the surveyed area. Utilizing only Sentinel-2 spectral bands, the models effectively capture early in advance the temporal patterns of the mosquito population, offering valuable insights for directing surveillance activities during the vector season. The methodology developed in this study can be scaled up to the national territory and extended to other vectors, in order to support the Ministry of Health in the surveillance and control strategies for the vectors and the diseases they transmit.

"Urban-Satellite" estimates in the ABCD Study: Linking Neuroimaging and Mental Health to Satellite Imagery Measurements of Macro Environmental Factors

While numerous studies over the last decade have highlighted the important influence of environmental factors on mental health, globally applicable data on physical surroundings are still limited. Access to such data and the possibility to link them to epidemiological studies is critical to unlocking the relationship of environment, brain and behaviour and promoting positive future mental health outcomes. The Adolescent Brain Cognitive Development (ABCD) Study is the largest ongoing longitudinal and observational study exploring brain development and child health among children from 21 sites across the United States. Here we describe the linking of the ABCD study data with satellite-based "Urban-Satellite" (UrbanSat) variables consisting of 11 satellite-data derived environmental indicators associated with each subject's residential address at their baseline visit, including land cover and land use, nighttime lights, and population characteristics. We present these UrbanSat variables and provide a review of the current literature that links environmental indicators with mental health, as well as key aspects that must be considered when using satellite data for mental health research. We also highlight and discuss significant links of the satellite data variables to the default mode network clustering coefficient and cognition. This comprehensive dataset provides the foundation for large-scale environmental epidemiology research.

Predicting the distribution of Ixodes ricinus and Dermacentor reticulatus in Europe: a comparison of climate niche modelling approaches

BACKGROUND

The ticks Ixodes ricinus and Dermacentor reticulatus are two of the most important vectors in Europe. Climate niche modelling has been used in many studies to attempt to explain their distribution and to predict changes under a range of climate change scenarios. The aim of this study was to assess the ability of different climate niche modelling approaches to explain the known distribution of I. ricinus and D. reticulatus in Europe.

METHODS

A series of climate niche models, using different combinations of input data, were constructed and assessed. Species occurrence records obtained from systematic literature searches and Global Biodiversity Information Facility data were thinned to different degrees to remove sampling spatial bias. Four sources of climate data were used: bioclimatic variables, WorldClim, TerraClimate and MODIS satellite-derived data. Eight different model training extents were examined and three modelling frameworks were used: maximum entropy, generalised additive models and random forest models. The results were validated through internal cross-validation, comparison with an external independent dataset and expert opinion.

RESULTS

The performance metrics and predictive ability of the different modelling approaches varied significantly within and between each species. Different combinations were better able to define the distribution of each of the two species. However, no single approach was considered fully able to capture the known distribution of the species. When considering the mean of the performance metrics of internal and external validation, 24 models for I. ricinus and 11 models for D. reticulatus of the 96 constructed were considered adequate according to the following criteria: area under the receiver-operating characteristic curve > 0.7; true skill statistic > 0.4; Miller's calibration slope 0.25 above or below 1; Boyce index > 0.9; omission rate < 0.15.

CONCLUSIONS

This comprehensive analysis suggests that there is no single 'best practice' climate modelling approach to account for the distribution of these tick species. This has important implications for attempts to predict climate-mediated impacts on future tick distribution. It is suggested here that climate variables alone are not sufficient; habitat type, host availability and anthropogenic impacts, not included in current modelling approaches, could contribute to determining tick presence or absence at the local or regional scale.

Modelling the spread and mitigation of an emerging vector-borne pathogen: Citrus greening in the U.S

Predictive models, based upon epidemiological principles and fitted to surveillance data, play an increasingly important role in shaping regulatory and operational policies for emerging outbreaks. Data for parameterising these strategically important models are often scarce when rapid actions are required to change the course of an epidemic invading a new region. We introduce and test a flexible epidemiological framework for landscape-scale disease management of an emerging vector-borne pathogen for use with endemic and invading vector populations. We use the framework to analyse and predict the spread of Huanglongbing disease or citrus greening in the U.S. We estimate epidemiological parameters using survey data from one region (Texas) and show how to transfer and test parameters to construct predictive spatio-temporal models for another region (California). The models are used to screen effective coordinated and reactive management strategies for different regions.

The use of drones for mosquito surveillance and control

In recent years, global health security has been threatened by the geographical expansion of vector-borne infectious diseases such as malaria, dengue, yellow fever, Zika and chikungunya. For a range of these vector-borne diseases, an increase in residual (exophagic) transmission together with ecological heterogeneity in everything from weather to local human migration and housing to mosquito species' behaviours presents many challenges to effective mosquito control. The novel use of drones (or uncrewed aerial vehicles) may play a major role in the success of mosquito surveillance and control programmes in the coming decades since the global landscape of mosquito-borne diseases and disease dynamics fluctuates frequently and there could be serious public health consequences if the issues of insecticide resistance and outdoor transmission are not adequately addressed. For controlling both aquatic and adult stages, for several years now remote sensing data have been used together with predictive modelling for risk, incidence and detection of transmission hot spots and landscape profiles in relation to mosquito-borne pathogens. The field of drone-based remote sensing is under continuous change due to new technology development, operation regulations and innovative applications. In this review we outline the opportunities and challenges for integrating drones into vector surveillance (i.e. identification of breeding sites or mapping micro-environmental composition) and control strategies (i.e. applying larval source management activities or deploying genetically modified agents) across the mosquito life-cycle. We present a five-step systematic environmental mapping strategy that we recommend be undertaken in locations where a drone is expected to be used, outline the key considerations for incorporating drone or other Earth Observation data into vector surveillance and provide two case studies of the advantages of using drones equipped with multispectral cameras. In conclusion, recent developments mean that drones can be effective for accurately conducting surveillance, assessing habitat suitability for larval and/or adult mosquitoes and implementing interventions. In addition, we briefly discuss the need to consider permissions, costs, safety/privacy perceptions and community acceptance for deploying drone activities.

An epidemiological model for mosquito host selection and temperature-dependent transmission of West Nile virus

We extend a previously developed epidemiological model for West Nile virus (WNV) infection in humans in Greece, employing laboratory-confirmed WNV cases and mosquito-specific characteristics of transmission, such as host selection and temperature-dependent transmission of the virus. Host selection was defined by bird host selection and human host selection, the latter accounting only for the fraction of humans that develop symptoms after the virus is acquired. To model the role of temperature on virus transmission, we considered five temperature intervals (≤ 19.25 °C; > 19.25 and < 21.75 °C; ≥ 21.75 and < 24.25 °C; ≥ 24.25 and < 26.75 °C; and > 26.75 °C). The capacity of the new model to fit human cases and the week of first case occurrence was compared with the original model and showed improved performance. The model was also used to infer further quantities of interest, such as the force of infection for different temperatures as well as mosquito and bird abundances. Our results indicate that the inclusion of mosquito-specific characteristics in epidemiological models of mosquito-borne diseases leads to improved modelling capacity.

Effects of mosquito resting site temperatures on the estimation of pathogen development rates in near-natural habitats in Germany

BACKGROUND

Environmental temperature is a key driver for the transmission risk of mosquito-borne pathogens. Epidemiological models usually relate to temperature data from standardized weather stations, but these data may not capture the relevant scale where mosquitoes experience environmental temperatures. As mosquitoes are assumed to spend most of their lifetime in resting sites, we analysed mosquito resting site patterns and the associated temperatures in dependence on the resting site type, resting site height and the surrounding land use.

METHODS

The study was conducted in 20 areas in near-natural habitats in Germany. Ten areas were studied in 2017, and another 10 in 2018. Each study area consisted of three sampling sites, where we collected mosquitoes and microclimatic data in artificial (= garden pop-up bags) and natural resting sites at three height levels between 0 and 6 m. Land use of the study sites was characterized as forest and meadows based on reclassified information of the CORINE (Coordination of Information on the Environment) Land Cover categories. The hourly resting site temperatures and the data from the nearest weather station of the German meteorological service were used to model the duration of the extrinsic incubation period (EIP) of mosquito-borne pathogens.

RESULTS

Anopheles, Culex and Culiseta preferred artificial resting sites, while Aedes were predominantly collect in natural resting sites. Around 90% of the mosquitoes were collected from resting sites below 2 m. The mosquito species composition did not differ significantly between forest and meadow sites. Mean resting site temperatures near the ground were approximately 0.8 °C lower than at a height of 4-6 m, which changed the predicted mean EIP up to 5 days at meadow and 2 days at forest sites. Compared with temperature data from standardized weather stations, the resting site temperatures near the ground would prolong the mean estimated EIP 4 days at forest sites and 2 days at meadow sites.

CONCLUSIONS

The microclimate of mosquito resting sites differs from standardized meteorological data, which can influence the transmission of mosquito-borne pathogens. In a near-natural environment, colder temperatures at mosquitoes' preferred resting sites near the ground would prolong the EIP of mosquito-borne pathogens relative to data from weather stations.

Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers

Background

In Europe, the frequency, intensity, and geographic range of West Nile virus (WNV)-outbreaks have increased over the past decade, with a 7.2-fold increase in 2018 compared to 2017, and a markedly expanded geographic area compared to 2010. The reasons for this increase and range expansion remain largely unknown due to the complexity of the transmission pathways and underlying disease drivers. In a first, we use advanced artificial intelligence to disentangle the contribution of eco-climatic drivers to WNV-outbreaks across Europe using decade-long (2010-2019) data at high spatial resolution.

Methods

We use a high-performance machine learning classifier, XGBoost (eXtreme gradient boosting) combined with state-of-the-art XAI (eXplainable artificial intelligence) methodology to describe the predictive ability and contribution of different drivers of the emergence and transmission of WNV-outbreaks in Europe, respectively.

Findings

Our model, trained on 2010-2017 data achieved an AUC (area under the receiver operating characteristic curve) score of 0.97 and 0.93 when tested with 2018 and 2019 data, respectively, showing a high discriminatory power to classify a WNV-endemic area. Overall, positive summer/spring temperatures anomalies, lower water availability index (NDWI), and drier winter conditions were found to be the main determinants of WNV-outbreaks across Europe. The climate trends of the preceding year in combination with eco-climatic predictors of the first half of the year provided a robust predictive ability of the entire transmission season ahead of time. For the extraordinary 2018 outbreak year, relatively higher spring temperatures and the abundance of Culex mosquitoes were the strongest predictors, in addition to past climatic trends.

Interpretation

Our AI-based framework can be deployed to trigger rapid and timely alerts for active surveillance and vector control measures in order to intercept an imminent WNV-outbreak in Europe.

Funding

The work was partially funded by the Swedish Research Council FORMAS for the project ARBOPREVENT (grant agreement 2018-05973).

An Overview of the Applications of Earth Observation Satellite Data: Impacts and Future Trends

As satellite observation technology develops and the number of Earth observation (EO) satellites increases, satellite observations have become essential to developments in the understanding of the Earth and its environment. However, the current impacts to the remote sensing community of different EO satellite data and possible future trends of EO satellite data applications have not been systematically examined. In this paper, we review the impacts of and future trends in the use of EO satellite data based on an analysis of data from 15 EO satellites whose data are widely used. Articles that reference EO satellite missions included in the Web of Science core collection for 2020 were analyzed using scientometric analysis and meta-analysis. We found the following: (1) the number of publications and citations referencing EO satellites is increasing exponentially; however, the number of articles referencing AVHRR, SPOT, and TerraSAR is tending to decrease; (2) papers related to EO satellites are concentrated in a small number of journals: 43.79% of the articles that were reviewed were published in only 13 journals; and (3) remote sensing impact factor (RSIF), a new impact index, was constructed to measure the impacts of EO satellites and to predict future trends in applications of their data. Landsat, Sentinel, MODIS, Gaofen, and WorldView were found to be the most significant current EO satellite missions and MODIS data to have the widest range of applications. Over the next five years (2021–2025), it is expected that Sentinel will become the satellite mission with the greatest influence.

Estimating Next Day’s Forest Fire Risk via a Complete Machine Learning Methodology

Next day wildfire prediction is an open research problem with significant environmental, social, and economic impact since it can produce methods and tools directly exploitable by fire services, assisting, thus, in the prevention of fire occurrences or the mitigation of their effects. It consists in accurately predicting which areas of a territory are at higher risk of fire occurrence each next day, exploiting solely information obtained up until the previous day. The task’s requirements in spatial granularity and scale of predictions, as well as the extreme imbalance of the data distribution render it a rather demanding and difficult to accurately solve the problem. This is reflected in the current literature, where most existing works handle a simplified or limited version of the problem. Taking into account the above problem specificities, in this paper, we present a machine learning methodology that effectively (sensitivity > 90%, specificity > 65%) and efficiently performs next day fire prediction, in rather high spatial granularity and in the scale of a country. The key points of the proposed approach are summarized in: (a) the utilization of an extended set of fire driving factors (features), including topography-related, meteorology-related and Earth Observation (EO)-related features, as well as historical information of areas’ proneness to fire occurrence; (b) the deployment of a set of state-of-the-art classification algorithms that are properly tuned/optimized on the setting; (c) two alternative cross-validation schemes along with custom validation measures that allow the optimal and sound training of classification models, as well as the selection of different models, in relation to the desired trade-off between sensitivity (ratio of correctly identified fire areas) and specificity (ratio of correctly identified non-fire areas). In parallel, we discuss pitfalls, intuitions, best practices, and directions for further investigation derived from our analysis and experimental evaluation.

Temporal Monitoring and Predicting of the Abundance of Malaria Vectors Using Time Series Analysis of Remote Sensing Data through Google Earth Engine

In many studies regarding the field of malaria, environmental factors have been acquired in single-time, multi-time or a short-time series using remote sensing and meteorological data. Selecting the best periods of the year to monitor the habitats of Anopheles larvae can be effective in better and faster control of malaria outbreaks. In this article, high-risk times for three regions in Iran, including Qaleh-Ganj, Sarbaz and Bashagard counties with a history of malaria prevalence were estimated. For this purpose, a series of environmental factors affecting the growth and survival of Anopheles were used over a seven-year period through the Google Earth Engine. The results of this study indicated two high-risk times for Qaleh-Ganj and Bashagard counties and three high-risk times for Sarbaz county over the course of a year observing an increase in the abundance of Anopheles mosquitoes. Further evaluation of the results against the entomological data available in previous studies showed that the high-risk times predicted in this study were consistent with an increase in the abundance of Anopheles mosquitoes in the study areas. The proposed method is extremely useful for temporal prediction of the increase in abundance of Anopheles mosquitoes in addition to the use of optimal data aimed at monitoring the exact location of Anopheles habitats.

Ovipositional Reproduction of the Dengue Vector for Identifying High-Risk Urban Areas

Identification and classification of high-risk areas for the presence of Aedes aegypti is not an easy task. To develop suitable methods to identify this areas is an essential task that will increase the efficiency and effectiveness of control measures and to optimize the use of resources. The objectives of this study were to identify high- risk areas for the presence of Ae. aegypti using mosquito traps and household visits to identify breeding sites; to identify and validate aspects of the remote sensing images that could characterize these areas; to evaluate the relationship between this spatial risk classification and the occurrence of Ae. aegypti; and provide a methodology to the health and control vector services and prioritize these areas for development of control measure. Information about the geographical coordinates of these traps will enable us to apply the kriging spatial analysis tool to generate maps with the predicted numbers of Ae. aegypti. Satellite images were used to identify the characteristic features the four areas, so that other areas could also be classified using only the sensing remote images. The developed methodology enables the identification of high-risk areas for Ae. aegypti and for the occurrence of Dengue, as well as Zika fever and Chikungunya fever using only sensing remote images. These results allow health and vector control services to prioritize these areas for developing surveillance and control measures. The use of the available resources can be optimized and potentially promote a decrease in the expected incidences of these diseases, particularly Dengue.

Oviposition dynamics of Aedes aegypti in Central Argentina

Aedes (Stegomyia) aegypti (L.) (Diptera: Culicidae) is the vector of multiple arboviruses. To evaluate the association between environmental factors and the oviposition activity of Ae. aegypti in Argentina, data on the presence and abundance of eggs were collected using ovitraps, between September of 2018 and May of 2019, in the cities of Villa María, Río Cuarto and Salsipuedes (Córdoba province, Argentina). We analysed the relationships between oviposition and five environmental factors: Temperature, precipitation, vegetation cover, human population density and distance to sites with a potential high density of larval habitats, like cemeteries and trash dumps. Environmental factors' data were collected using satellite image products. The oviposition activity was randomly distributed in three cities. Using generalized linear mixed models, we show that the house where each ovitrap was placed was a source of variability in oviposition, suggesting the relevance of microsite factors and the importance of domestic control actions. Ae. aegypti oviposition was positively correlated with night-time temperature of the previous 3 weeks, and in a context-dependent manner, it was positively correlated with human population density, vegetation cover and precipitation. The consistency and magnitude of these relationships varied between cities, indicating that oviposition is related to a complex system of environmental variables.

Spatial patterns of West Nile virus distribution in the Volgograd region of Russia, a territory with long-existing foci

Southern Russia remains affected by West Nile virus (WNV). In the current study, we identified the spatial determinants of WNV distribution in an area with endemic virus transmission, with special reference to the urban settings, by mapping probable points of human infection acquisition and points of virus detection in mosquitoes, ticks, birds, and mammals during 1999-2016. The suitability of thermal conditions for extrinsic virus replication was assessed based on the approach of degree-day summation and their changes were estimated by linear trend analysis. A generalized linear model was used to analyze the year-to-year variation of human cases versus thermal conditions. Environmental suitability was determined by ecological niche modelling using MaxEnt software. Human population density was used as an offset to correct for possible bias. Spatial analysis of virus detection in the environment showed significant contributions from surface temperature, altitude, and distance from water bodies. When indicators of location and mobility of the human population were included, the relative impact of factors changed, with roads becoming most important. When the points of probable human case infection were added, the percentage of leading factors changed only slightly. The urban environment significantly increased the epidemic potential of the territory and created quite favorable conditions for virus circulation. The private building sector with low-storey houses and garden plots located in the suburbs provided a connection between urban and rural transmission cycles.

A climate-dependent spatial epidemiological model for the transmission risk of West Nile virus at local scale

In this study, initial elements of a modelling framework aimed to become a spatial forecasting model for the transmission risk of West Nile virus (WNV) are presented. The model describes the dynamics of a WNV epidemic in population health states of mosquitoes, birds and humans and was applied to the case of Greece for the period 2010–2019. Calibration was performed with the available epidemiological data from the Hellenic Centre for Disease Control and Prevention and the environmental data from the European Union's earth observation program, Copernicus. Numerical results of the model for each municipality were evaluated against observations. Specifically, the occurrence of WNV, the number of infected humans and the week of incidence predicted from the model were compared to the corresponding numbers from observations. The results suggest that dynamic downscaling of a climate-dependent epidemiological model is feasible down-to roughly 80km². This below nomenclature of territorial units for statistics (NUTS) 3 level represents the municipalities being the lowest level of administrative units, able to cope with WNV and take actions. The average detection probability in hindcast mode was 72%, improving strongly as the number of infected humans increased. Using the developed model, we were also able to show the fundamental importance of the May temperatures in shaping the WNV dynamics. The modeling framework couples epidemiological and environmental dynamical variables with surveillance data producing risk maps downscaled at a local level. The approach can be expanded to provide targeted early warning probabilistic forecasts that can be used to inform public health policy decision making.

•

Downscaling of a climate-dependent epidemiological model feasible to roughly 80 km².

•

The model demonstrates competence in reproducing WNV event occurrence spatially at the municipality scale.

•

The average detection probability is 72%, improving with increasing human infections.

•

The hardest to model WNV events occurred at municipalities and years with only one human infection annually.

•

Temperatures in May are found most critical in shaping the WNV dynamics.

Habitat and microclimate affect the resting site selection of mosquitoes

Mosquitoes (Diptera: Culicidae) use certain resting sites during their inactive phase. The microclimatic conditions of these resting sites might affect their physiology and vectorial capacity. In this study, we combined a field and a laboratory study to investigate the natural resting site and temperature preferences of mosquitoes. The field study was conducted at a forest close to Oldenburg (Lower Saxony, Germany) from May to October 2018. Mosquitoes were collected in five different natural habitats with seven replicates each. Temperature was recorded hourly at each site. Significantly more mosquitoes were collected in deadwood (predominantly Culiseta morsitans/fumipennis) and shaded herb layer (predominantly Aedes species) compared to unshaded herb layer or broadleaf and coniferous trees. GLMMs revealed resting site habitats as the best predictor to explain the observed preference patterns, but microclimatic conditions are also involved in mosquito resting site selection. Most mosquitoes were collected at resting sites with relatively colder and more stable temperatures. In concert, laboratory choice experiments with a thermal gradient ring demonstrated that Cs. morsitans/fumipennis avoid temperatures over 30 °C. Understanding the small-scaled resting site preferences and the related microclimatic conditions can improve mosquito collection techniques and refine the prediction of mosquito-borne pathogen transmission.

Data-driven and interpretable machine-learning modeling to explore the fine-scale environmental determinants of malaria vectors biting rates in rural Burkina Faso

Background

Improving the knowledge and understanding of the environmental determinants of malaria vector abundance at fine spatiotemporal scales is essential to design locally tailored vector control intervention. This work is aimed at exploring the environmental tenets of human-biting activity in the main malaria vectors (Anopheles gambiae s.s., Anopheles coluzzii and Anopheles funestus) in the health district of Diébougou, rural Burkina Faso.

Methods

Anopheles human-biting activity was monitored in 27 villages during 15 months (in 2017–2018), and environmental variables (meteorological and landscape) were extracted from high-resolution satellite imagery. A two-step data-driven modeling study was then carried out. Correlation coefficients between the biting rates of each vector species and the environmental variables taken at various temporal lags and spatial distances from the biting events were first calculated. Then, multivariate machine-learning models were generated and interpreted to (i) pinpoint primary and secondary environmental drivers of variation in the biting rates of each species and (ii) identify complex associations between the environmental conditions and the biting rates.

Results

Meteorological and landscape variables were often significantly correlated with the vectors’ biting rates. Many nonlinear associations and thresholds were unveiled by the multivariate models, for both meteorological and landscape variables. From these results, several aspects of the bio-ecology of the main malaria vectors were identified or hypothesized for the Diébougou area, including breeding site typologies, development and survival rates in relation to weather, flight ranges from breeding sites and dispersal related to landscape openness.

Conclusions

Using high-resolution data in an interpretable machine-learning modeling framework proved to be an efficient way to enhance the knowledge of the complex links between the environment and the malaria vectors at a local scale. More broadly, the emerging field of interpretable machine learning has significant potential to help improve our understanding of the complex processes leading to malaria transmission, and to aid in developing operational tools to support the fight against the disease (e.g. vector control intervention plans, seasonal maps of predicted biting rates, early warning systems).

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1186/s13071-021-04851-x.

Remote sensing of environmental risk factors for malaria in different geographic contexts

BACKGROUND

Despite global intervention efforts, malaria remains a major public health concern in many parts of the world. Understanding geographic variation in malaria patterns and their environmental determinants can support targeting of malaria control and development of elimination strategies.

METHODS

We used remotely sensed environmental data to analyze the influences of environmental risk factors on malaria cases caused by Plasmodium falciparum and Plasmodium vivax from 2014 to 2017 in two geographic settings in Ethiopia. Geospatial datasets were derived from multiple sources and characterized climate, vegetation, land use, topography, and surface water. All data were summarized annually at the sub-district (kebele) level for each of the two study areas. We analyzed the associations between environmental data and malaria cases with Boosted Regression Tree (BRT) models.

RESULTS

We found considerable spatial variation in malaria occurrence. Spectral indices related to land cover greenness (NDVI) and moisture (NDWI) showed negative associations with malaria, as the highest malaria rates were found in landscapes with low vegetation cover and moisture during the months that follow the rainy season. Climatic factors, including precipitation and land surface temperature, had positive associations with malaria. Settlement structure also played an important role, with different effects in the two study areas. Variables related to surface water, such as irrigated agriculture, wetlands, seasonally flooded waterbodies, and height above nearest drainage did not have strong influences on malaria.

CONCLUSION

We found different relationships between malaria and environmental conditions in two geographically distinctive areas. These results emphasize that studies of malaria-environmental relationships and predictive models of malaria occurrence should be context specific to account for such differences.

Ecology, evolution, and epidemiology of zoonotic and vector-borne infectious diseases in French Guiana: Transdisciplinarity does matter to tackle new emerging threats

French Guiana is a European ultraperipheric region located on the northern Atlantic coast of South America. It constitutes an important forested region for biological conservation in the Neotropics. Although very sparsely populated, with its inhabitants mainly concentrated on the Atlantic coastal strip and along the two main rivers, it is marked by the presence and development of old and new epidemic disease outbreaks, both research and health priorities. In this review paper, we synthetize 15 years of multidisciplinary and integrative research at the interface between wildlife, ecosystem modification, human activities and sociodemographic development, and human health. This study reveals a complex epidemiological landscape marked by important transitional changes, facilitated by increased interconnections between wildlife, land-use change and human occupation and activity, human and trade transportation, demography with substantial immigration, and identified vector and parasite pharmacological resistance. Among other French Guianese characteristics, we demonstrate herein the existence of more complex multi-host disease life cycles than previously described for several disease systems in Central and South America, which clearly indicates that today the greater promiscuity between wildlife and humans due to demographic and economic pressures may offer novel settings for microbes and their hosts to circulate and spread. French Guiana is a microcosm that crystallizes all the current global environmental, demographic and socioeconomic change conditions, which may favor the development of ancient and future infectious diseases.

Performance Evaluation of Biozentech Malaria Scanner in Plasmodium knowlesi and P. falciparum as a New Diagnostic Tool

The computer vision diagnostic approach currently generates several malaria diagnostic tools. It enhances the accessible and straightforward diagnostics that necessary for clinics and health centers in malaria-endemic areas. A new computer malaria diagnostics tool called the malaria scanner was used to investigate living malaria parasites with easy sample preparation, fast and user-friendly. The cultured Plasmodium parasites were used to confirm the sensitivity of this technique then compared to fluorescence-activated cell sorting (FACS) analysis and light microscopic examination. The measured percentage of parasitemia by the malaria scanner revealed higher precision than microscopy and was similar to FACS. The coefficients of variation of this technique were 1.2–6.7% for Plasmodium knowlesi and 0.3–4.8% for P. falciparum. It allowed determining parasitemia levels of 0.1% or higher, with coefficient of variation smaller than 10%. In terms of the precision range of parasitemia, both high and low ranges showed similar precision results. Pearson’s correlation test was used to evaluate the correlation data coming from all methods. A strong correlation of measured parasitemia (r²=0.99, P<0.05) was observed between each method. The parasitemia analysis using this new diagnostic tool needs technical improvement, particularly in the differentiation of malaria species.

Can we use local climate zones for predicting malaria prevalence across sub-Saharan African cities?

Malaria burden is increasing in sub-Saharan cities because of rapid and uncontrolled urbanization. Yet very few studies have studied the interactions between urban environments and malaria. Additionally, no standardized urban land-use/land-cover has been defined for urban malaria studies. Here, we demonstrate the potential of local climate zones (LCZs) for modeling malaria prevalence rate (Pf PR_2-10) and studying malaria prevalence in urban settings across nine sub-Saharan African cities. Using a random forest classification algorithm over a set of 365 malaria surveys we: (i) identify a suitable set of covariates derived from open-source earth observations; and (ii) depict the best buffer size at which to aggregate them for modeling Pf PR_2-10. Our results demonstrate that geographical models can learn from LCZ over a set of cities and be transferred over a city of choice that has few or no malaria surveys. In particular, we find that urban areas systematically have lower Pf PR_2-10 (5%-30%) than rural areas (15%-40%). The Pf PR_2-10 urban-to-rural gradient is dependent on the climatic environment in which the city is located. Further, LCZs show that more open urban environments located close to wetlands have higher Pf PR_2-10. Informal settlements-represented by the LCZ 7 (lightweight lowrise)-have higher malaria prevalence than other densely built-up residential areas with a mean prevalence of 11.11%. Overall, we suggest the applicability of LCZs for more exploratory modeling in urban malaria studies.

Predicting WNV Circulation in Italy Using Earth Observation Data and Extreme Gradient Boosting Model

West Nile Disease (WND) is one of the most spread zoonosis in Italy and Europe caused by a vector-borne virus. Its transmission cycle is well understood, with birds acting as the primary hosts and mosquito vectors transmitting the virus to other birds, while humans and horses are occasional dead-end hosts. Identifying suitable environmental conditions across large areas containing multiple species of potential hosts and vectors can be difficult. The recent and massive availability of Earth Observation data and the continuous development of innovative Machine Learning methods can contribute to automatically identify patterns in big datasets and to make highly accurate identification of areas at risk. In this paper, we investigated the West Nile Virus (WNV) circulation in relation to Land Surface Temperature, Normalized Difference Vegetation Index and Surface Soil Moisture collected during the 160 days before the infection took place, with the aim of evaluating the predictive capacity of lagged remotely sensed variables in the identification of areas at risk for WNV circulation. WNV detection in mosquitoes, birds and horses in 2017, 2018 and 2019, has been collected from the National Information System for Animal Disease Notification. An Extreme Gradient Boosting model was trained with data from 2017 and 2018 and tested for the 2019 epidemic, predicting the spatio-temporal WNV circulation two weeks in advance with an overall accuracy of 0.84. This work lays the basis for a future early warning system that could alert public authorities when climatic and environmental conditions become favourable to the onset and spread of WNV.

Early warning climate indices for malaria and meningitis in tropical ecological zones

This study aims at assessing the impacts of climate indices on the spatiotemporal distribution of malaria and meningitis in Nigeria. The primary focus of the research is to develop an Early Warning System (EWS) for assessing climate variability implications on malaria and meningitis spread in the study area. Both climate and health data were used in the study to determine the relationship between climate variability and the occurrence of malaria and meningitis. The assessment was based on variations in different ecological zones in Nigeria. Two specific sample locations were randomly selected in each ecological zone for the analysis. The climatic data used in this study are dekadal precipitation, minimum and maximum temperature between 2000 and 2018, monthly aerosol optical depth between 2000 and 2018. The results show that temperature is relatively high throughout the year because the country is located in a tropical region. The significant findings of this study are that rainfall has much influence on the occurrence of malaria, while temperature and aerosol have more impact on meningitis. We found the degree of relationship between precipitation and malaria, there is a correlation coefficient R2 ≥ 70.0 in Rainforest, Freshwater, and Mangrove ecological zones. The relationship between temperature and meningitis is accompanied by R2 ≥ 72.0 in both Sahel and Sudan, while aerosol and meningitis harbour R2 = 77.33 in the Sahel. The assessment of this initial data seems to support the finding that the occurrences of meningitis are higher in the northern region, especially the Sahel and Sudan. In contrast, malaria occurrence is higher in the southern part of the study area. In all, the multiple linear regression results revealed that rainfall was directly associated with malaria with β = 0.64, p = 0.001 but aerosol was directly associated with meningitis with β = 0.59, p < 0.001. The study concludes that variability in climatic elements such as low precipitation, high temperature, and aerosol may be the major drivers of meningitis occurrence.

[Satellite data for recording health-relevant environmental conditions: examples and interdisciplinary potential]

Environmental conditions influence human health and interact with other factors such as DNA, lifestyle, or the social environment. Earth observations from space provide data on the most diverse manifestations of these environmental conditions and make it possible to quantify them spatially. Using two examples - the availability of open and recreational space and the spatial distribution of air pollution - this article presents the potential of Earth observations for health studies. In addition, possible applications for health-related issues are discussed. To this end, we try to outline key points for an interdisciplinary approach that meets the conceptual, data technology, and ethical challenges.

Malaria Risk Map Using Spatial Multi-Criteria Decision Analysis along Yunnan Border During the Pre-elimination Period

In moving toward malaria elimination, finer scale malaria risk maps are required to identify hotspots for implementing surveillance–response activities, allocating resources, and preparing health facilities based on the needs and necessities at each specific area. This study aimed to demonstrate the use of multi-criteria decision analysis (MCDA) in conjunction with geographic information systems (GISs) to create a spatial model and risk maps by integrating satellite remote-sensing and malaria surveillance data from 18 counties of Yunnan Province along the China–Myanmar border. The MCDA composite and annual models and risk maps were created from the consensus among the experts who have been working and know situations in the study areas. The experts identified and provided relative factor weights for nine socioeconomic and disease ecology factors as a weighted linear combination model of the following: ([Forest coverage × 0.041] + [Cropland × 0.086] + [Water body × 0.175] + [Elevation × 0.297] + [Human population density × 0.043] + [Imported case × 0.258] + [Distance to road × 0.030] + [Distance to health facility × 0.033] + [Urbanization × 0.036]). The expert-based model had a good prediction capacity with a high area under curve. The study has demonstrated the novel integrated use of spatial MCDA which combines multiple environmental factors in estimating disease risk by using decision rules derived from existing knowledge or hypothesized understanding of the risk factors via diverse quantitative and qualitative criteria using both data-driven and qualitative indicators from the experts. The model and fine MCDA risk map developed in this study could assist in focusing the elimination efforts in the specifically identified locations with high risks.

Semi-Supervised Text Classification Framework: An Overview of Dengue Landscape Factors and Satellite Earth Observation

In recent years there has been an increasing use of satellite Earth observation (EO) data in dengue research, in particular the identification of landscape factors affecting dengue transmission. Summarizing landscape factors and satellite EO data sources, and making the information public are helpful for guiding future research and improving health decision-making. In this case, a review of the literature would appear to be an appropriate tool. However, this is not an easy-to-use tool. The review process mainly includes defining the topic, searching, screening at both title/abstract and full-text levels and data extraction that needs consistent knowledge from experts and is time-consuming and labor intensive. In this context, this study integrates the review process, text scoring, active learning (AL) mechanism, and bidirectional long short-term memory (BiLSTM) networks, and proposes a semi-supervised text classification framework that enables the efficient and accurate selection of the relevant articles. Specifically, text scoring and BiLSTM-based active learning were used to replace the title/abstract screening and full-text screening, respectively, which greatly reduces the human workload. In this study, 101 relevant articles were selected from 4 bibliographic databases, and a catalogue of essential dengue landscape factors was identified and divided into four categories: land use (LU), land cover (LC), topography and continuous land surface features. Moreover, various satellite EO sensors and products used for identifying landscape factors were tabulated. Finally, possible future directions of applying satellite EO data in dengue research in terms of landscape patterns, satellite sensors and deep learning were proposed. The proposed semi-supervised text classification framework was successfully applied in research evidence synthesis that could be easily applied to other topics, particularly in an interdisciplinary context.

A Mapping Review on Urban Landscape Factors of Dengue Retrieved from Earth Observation Data, GIS Techniques, and Survey Questionnaires

To date, there is no effective treatment to cure dengue fever, a mosquito-borne disease which has a major impact on human populations in tropical and sub-tropical regions. Although the characteristics of dengue infection are well known, factors associated with landscape are highly scale dependent in time and space, and therefore difficult to monitor. We propose here a mapping review based on 78 articles that study the relationships between landscape factors and urban dengue cases considering household, neighborhood and administrative levels. Landscape factors were retrieved from survey questionnaires, Geographic Information Systems (GIS), and remote sensing (RS) techniques. We structured these into groups composed of land cover, land use, and housing type and characteristics, as well as subgroups referring to construction material, urban typology, and infrastructure level. We mapped the co-occurrence networks associated with these factors, and analyzed their relevance according to a three-valued interpretation (positive, negative, non significant). From a methodological perspective, coupling RS and GIS techniques with field surveys including entomological observations should be systematically considered, as none digital land use or land cover variables appears to be an univocal determinant of dengue occurrences. Remote sensing urban mapping is however of interest to provide a geographical frame to distribute human population and movement in relation to their activities in the city, and as spatialized input variables for epidemiological and entomological models.