Geographic information systems for niche modeling of infectious diseases using remotely sensed environmental factors and boosted regression trees

Infectious diseases have great impact on the mortality and morbidity of human populations. Use of GIS has become an effective tool for the professionals to identify the trend of disease transmission, epidemic surveillance, geographical distributions of disease prevalence etc. This analysed information can ultimately be used for effective control of diseases or mitigate its impacts. A few of such diseases can be identified as Influenza, Diarrhoeal disease, Cholera, Malaria, Meningococcal meningitis, Leishmaniasis, Dengue, Japanese encephalitis, Lime fever, Yellow fever etc.

According to the literature there are infectious diseases, where their spreads have correlation to climate variation and those can be identified. In this study main attention is paid to infectious diseases that are linked to climate and initial step is taken to study Dengue. By identifying the both geographical and seasonal distributions which are linked to Dengue will enable to forecast various aspects related to spread of disease.

Many factors contribute to the emergence of infectious diseases including Dengue. Geographical data for those factors can be obtained from remotely sensing. For this study remote sensing data from the National Aeronautics and Space Administration (NASA) data servers at various resolutions will be used of the study period.  After establishing the relationships epidemiological data can be used to validation of the model. The established relationship can be used to predict the geographically risk locations for next two weeks by using three week data. The accuracy will be depending on the resolution of data and the data analysis protocol that will be developed.

Objective of the study

  • Combine disease ecology and landscape ecology to understand the spatial aspects that can affect epidemiological processes across disease’s geographical range and the spatial interactions involved
  • Identify the environmental factors that have the highest relative influence in association with infectious diseases
  • Understand the spatial distribution of the risk of diseases based on these environmental factors