Building explainable predictive analytics for location-dependent time-series data

There are increasing numbers of online sources of real-time and historical location-dependent time-series data describing various types of environmental phenomena, e.g., traffic conditions and air quality levels. When coupled with the information that characterizes the natural and built environments, these location-dependent time-series data can help better understand interactions between and within human social systems and the ecosystem. Nevertheless, these data are still limited by their spatial and temporal resolution for downstream use (e.g., generating residential-level environmental exposures for human health studies). In this paper, we present a vision of a general machine learning framework for explainable predictive analytics for location-dependent time-series data. The framework will effectively deal with data-and model-related challenges for general scientific predictive analytics on spatiotemporal environmental phenomena. The challenges include how to identify the main features driving the phenomena, how to handle complex spatiotemporal variations in the phenomena, and how to utilize sparse ground truth measurements for training and validation. The resulting framework will enable fine spatial and temporal scale environmental exposure assessment and allow researchers to carry out unprecedented inquiries, such as understanding relationships between health outcomes and long-term air pollution exposures.