Date of Graduation
5-2013
Document Type
Thesis
Degree Name
Master of Arts in Geography (MA)
Degree Level
Graduate
Department
Geosciences
Advisor/Mentor
Tullis, Jason A.
Committee Member
Cothren, Jackson D.
Second Committee Member
Hammig, Bart J.
Keywords
Biological sciences; Health and environmetal sciences; Earth sciences; Landscape epidemiology; Machine learning; Medical geography; Remote sensing; West nile virus
Abstract
The complex interactions between human health and the physical landscape and environment have been recognized, if not fully understood, since the ancient Greeks. Landscape epidemiology, sometimes called spatial epidemiology, is a sub-discipline of medical geography that uses environmental conditions as explanatory variables in the study of disease or other health phenomena. This theory suggests that pathogenic organisms (whether germs or larger vector and host species) are subject to environmental conditions that can be observed on the landscape, and by identifying where such organisms are likely to exist, areas at greatest risk of the disease can be derived. Machine learning is a sub-discipline of artificial intelligence that can be used to create predictive models from large and complex datasets. West Nile virus (WNV) is a relatively new infectious disease in the United States, and has a fairly well-understood transmission cycle that is believed to be highly dependent on environmental conditions. This study takes a geospatial approach to the study of WNV risk, using both landscape epidemiology and machine learning techniques. A combination of remotely sensed and in situ variables are used to predict WNV incidence with a correlation coefficient as high as 0.86. A novel method of mitigating the small numbers problem is also tested and ultimately discarded. Finally a consistent spatial pattern of model errors is identified, indicating the chosen variables are capable of predicting WNV disease risk across most of the United States, but are inadequate in the northern Great Plains region of the US.
Citation
Young, S. G. (2013). Landscape Epidemiology and Machine Learning: A Geospatial Approach to Modeling West Nile Virus Risk in the United States. Graduate Theses and Dissertations Retrieved from https://scholarworks.uark.edu/etd/683
