Isam Al Jawarneh
Recent research is focusing extensively on building Cloud based open source solutions for big geospatial data analytics in the Cloud. Avalanches of georeferenced mobility and micro blogging data are being collected and processed daily. However, mobility data alone is not enough to unleash the opportunities for insightful analytics that may assist in mitigating the adverse effects of climate change. For example, answering complex queries such as follows 'what are the Top-3 neighbourhoods in Buenos Aires in Argentina in terms of vehicle mobility where the index of Particulate Matters PM10 is greater than 80. Similar queries are necessary for emergent health aware smart city policies. For example, they can provide insights to municipality administrators so that they foster the design of future city infrastructure plans that feature citizen health as a priority. For example, by restricting the number of vehicles accessing highly polluted areas of the city during peak hours. Also, such information can be used to build mobile interactive maps for daily dwellers so that to inform them which routes to avoid passing-through during specific hours of a day to avoid being subjected to high-levels of vehicle-caused air-borne pollutants such as PM10. However, answering such a query would require joining real-time mobility and meteorological data. Stock versions of the current Cloud-based open-source geospatial management systems do not include intrinsic solutions for such scenarios. Future research efforts should consider developing Cloud-based open-source geospatial solutions that foster a streamlined integration with other data sources. In this talk we will show case some of the few available Cloud-based big spatial data management frameworks and how they can be utilized as springboards for further development so that they become mature enough to support the decisions that aim to mitigate the mobility-caused climate change problems. We will walkthrough an example that shows how we could tweak an open-source geospatial framework for answering such multi-domain queries. We will conclude the talk with short discussion of open research frontiers in this direction. For example, since the data that need to be collected is massive and sometimes may exceed the processing and storage capacities, there would be a need for efficient spatial- and climatologically-aware approximate techniques for compressing and summarizing the data, probably before even reaching the Cloud-based deployment (by utilizing Fog and Edge computing).