Data-Mining-Oriented Discovery of Spatio-Temporal Patterns in Volunteered Phenological Observations

The world is experiencing climate change and this raises several pressing questions. An important one is “How does climate change affect the yearly timing of periodic life cycle events of animals and plants?”. Phenology, the science of the timing of seasonal plant and animal activities, provides relevant spatio-temporal information to answer this question. Phenological observations contain the location and time of species life cycle events (e.g. first flowering). These observations are often collected by volunteers. Hence, spatial and temporal uncertainties in actual locations and times are an inseparable part of these observations. This makes spatio-temporal analysis of phenological observations a challenging task.

This research aims to develop workflows to study climate change and its impact on phenology by using volunteered phenological observations. First of all, a consistency checking workflow was developed to ensure the quality of volunteered phenological observations on plants. Next, a data-driven approach is used to model spatio-temporal variation in plant phenology so that we can move from point observations to continuous products. After that, long term gridded time series of phenological data relevant to agriculture will be generated and spatio-temporal data mining methods will be applied to extract trends and changes.

The outputs of the workflows will help decision-makers to understand the impacts of climate change on plants. Further, from a spatial point of view, this research will develop methods to analyze and model volunteered geographic information and to mine gridded time series of relevant heterogeneous geoinformation sources.