Spatio-temporal data mining in ecological and veterinary epidemiology

Abstract

Understanding the spread of any disease is a highly complex and interdisciplinary exercise as biological, social, geographic, economic, and medical factors may shape the way a disease moves through a population and options for its eventual control or eradication. Disease spread poses a serious threat in animal and plant health and has implications for ecosystem functioning and species extinctions as well as implications in society through food security and potential disease spread in humans. Spacetime epidemiology is based on the concept that various characteristics of the pathogenic agents and the environment interact in order to alter the probability of disease occurrence and form temporal or spatial patterns. Epidemiology aims to identify these patterns and factors, to assess the relevant uncertainty sources, and to describe disease in the population. Thus disease spread at the population level differs from the approach traditionally taken by veterinary practitioners that are principally concerned with the health status of the individual. Patterns of disease occurrence provide insights into which factors may be affecting the health of the population, through investigating which individuals are affected, where are these individuals located and when did they become infected. With the rapid development of smart sensors, social networks, as well as digital maps and remotely-sensed imagery spatio-temporal data are more ubiquitous and richer than ever before. The availability of such large datasets (big data) poses great challenges in data analysis. In addition, increased availability of computing power facilitates the use of computationally-intensive methods for the analysis of such data. Thus new methods as well as case studies are needed to understand veterinary and ecological epidemiology. A special issue aimed to address this topic.

A Space-Time Study of Hemorrhagic Fever with Renal Syndrome (HFRS) and Its Climatic Associations in Heilongjiang Province, China

“…; [63]). Hence, the observation series may contain a large amount of direct and indirect information.…”

Spatial Downscaling of Alien Species Presences Using Machine Learning

“…While data on alien species presences may be scarce, environmental data may be readily available. Recent advances in remote sensing, social networks, and digital technology resulted in the availability of large spatially and temporally explicit datasets (Moustakas, 2017). Ecology, epidemiology, and biogeography need to employ novel methods for big data analytics combing statistics and computer science, as the analysis of such datasets requires advanced methods for compiling the data, their visualization, and their analyses (Moustakas, 2017;Moustakas and Evans, 2017).…”

Handling Big Data of Alien Species in Europe: The European Alien Species Information Network Geodatabase

“…This is because bigger data sets could result in higher bias and bring up spurious correlations (Silver, 2012;Donoho and Jin, 2015) with possible implications to outcomes crucial to biological invasions research and to related policies. To this end, careful selection of data and appropriate statistical design should be ensured in order to limit correlated errors when handling big data sets (see also Moustakas, 2017 and references therein).…”