Abstract
The proliferation of geospatial data from diverse sources, such as Earth observation satellites, social media, and unmanned aerial vehicles (UAVs), has created a pressing demand for cross-platform data integration, interoperation, and intelligent data analysis. To address this big data challenge, this paper reports our research in developing a rule-based, semantic-enabled service chain model to support intelligent question answering for leveraging the abundant data and processing resources available online. Four key techniques were developed to achieve this goal: (1) A spatial and temporal reasoner resolves the spatial and temporal information in a given scientific question and enables place-name disambiguation based on support from a gazetteer; (2) a spatial operation ontology categorizes important spatial analysis operations, data types, and data themes, which will be used in automated chain generation; (3) a language-independent chaining rule defines the template for input, spatial operation, and output as well as rules for embedding multiple spatial operations for solving a complex problem; and (4) a recursive algorithm facilitates the generation of executive workflow metadata according to the chaining rules. We implement this service chain model in a cyberinfrastructure for online and reproducible spatial analysis and question answering. Moving the problem-solving environment from a desktop-based environment onto a geospatial cyberinfrastructure (GeoCI) offers better support to collaborative spatial decision-making and ensures science replicability. We expect this work to contribute significantly to the advancement of a reproducible spatial data science and to building the next-generation open knowledge network.
Highlights
To accelerate the knowledge discovery process and foster interdisciplinary research, it is important to move today’s science paradigm toward becoming more open, collaborative, and reproducible
This paper introduces the development of a domain ontology and rule-based service chain model to automatically generate an executable workflow for tackling complex spatial and temporal questions
We built this workflow based on a service-oriented architecture, in which data resources and analytical components are all encapsulated into web services compliant with Open Geospatial Consortium (OGC) standards
Summary
To accelerate the knowledge discovery process and foster interdisciplinary research, it is important to move today’s science paradigm toward becoming more open, collaborative, and reproducible. It becomes utterly important to develop a new mechanism to integrate spatial analytics and link a dataset to a spatial analytical function and/or link between spatial analytical functions for the dynamic generation of scientific workflows towards intelligent analysis and question answering [10] Another challenge for current cyberinfrastructure portals, or the majority of available Geographic Information Systems (GIS), is the very weak capability for tracking the flow of data—what data is used, which spatial analytical function it is fed in, how the output result is presented, and so on [11]. This limitation has significantly hindered the ability to reproduce and validate one’s own or others’ work [12].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
