Dear All, We are currently hosting a thematic issue regarding the application of "Big Data in Environmental Science". We are specifically looking for new contributions of Big Data in Ecology, Climate, Land Use, Hydrology or any other environmental dimensions that deal with Geospatial and temporal data as well as Geospatial and temporal models.
Please visit below link for more information. http://www.iemss.org/society/index.php/special-issues/290-advances-in-theories-data-management-data-mining-and-data-visualization Below is full description of call: Title: “Advances in Theories, Data Management, Data Mining and Data Visualization to Support Big Data in the Environmental Sciences” Theme: Big data in environmental sciences (e.g., climate, land use, hydrology, geography, ecology) has become increasingly common due to rapid advancements in data collection technologies. It is known that around 2.5 exabytes of data have been created every day since 2011 and new data produced during the last five years are equal in amount to all the data created in human history. A large proportion of big data has spatial and temporal dimensions that can have direct applications in the environmental sciences. As environmental scientists usually deal with different types of spatial and temporal data, they often cannot use exactly the same approaches to handle their spatial and temporal big data. Big data includes cutting-edge and innovative approaches, particularly regarding new tools, software or demonstrations of efficient techniques in practical cases to deal with specific types of big data in environmental sciences that cannot be addressed using conventional techniques. This call is seeking papers to report on: 1) advances in theories; 2) data management; 3) data mining; and 4) data visualization that provide cutting-edge and innovative approaches for using GIScience, remote sensing and technology to support big data in the environmental sciences. Despite the recent interest in big data by the environmental sciences, there is a lack of a common definition of big data that is accepted by environmental scientists across disciplines. Since environmental scientists deal with various types of spatial and temporal data, the term big data has different meanings for each discipline. Firstly, this special issue is seeking papers that can offer new definitions and examples of big data in various disciplines as well as ideas that contribute to a coherent definition of big data in environmental sciences. Big data in the environmental sciences are usually socio-economic or social media data (e.g., census, Twitter, Facebook, YouTube) and imagery data (e.g., data from airborne, satellite and underwater sensors). Big data also vary in terms of volume (e.g., social media and sensor), velocity (e.g., sensors delivering real time data) and variability (e.g., structured numeric data to unstructured data such as text, video, and audio). Heterogeneous big data must be assimilated into environmental models which is a critical challenge in term of access, storage, management and data processing. This is due to the fact that big data can exceed the processing capacity of conventional databases. Bigger data require using new modelling software that can handle concurrent processing and parallel I/O on high performance computing systems. Secondly, this special issue is seeking papers on new advances in database design and software engineering for environmental modelling that can handle petabyte scale data and are efficient in terms of price and resources (e.g., Google Earth Engine). With the birth of big data, extracting useful information from proliferating data streams is a new and major challenge in environmental sciences. The availability of big data can limit options for constructing predictive models. To gain value from big data in the environmental sciences, we must choose alternative approaches to detecting relevant patterns more effectively. Advanced tools provide information from big data and translate it into scientific solutions to better understand environmental issues. Thirdly, this special issue is seeking papers to show how the development of new data mining, statistical models, process-based models, scenario analysis tools, and data intensive approaches can benefit from using geocomputation (e.g., Hadoop) to simulate and analyze environmental phenomena over large geographic domains and at high spatial and temporal resolutions. Data visualization is important component in the age of big data. This special issue also aims to summarize the challenges to visualization methods for big data in the environmental sciences and offer novel solutions for issues related to the current state of big data visualization. We are seeking papers that provide unique innovations in visualization to foster a better understanding of big data. Finally, this call is also interested in papers that can summarize new challenges of big data that are required to be addressed in the future by the environmental sciences. Full papers will be selected based on how strongly the work to the big data themes outlined above. Let me know if you have any question. Regards Amin - Amin Tayyebi, PhD Geospatial Data Scientist, Monsanto, Saint Louis, MO
