EarthCube Building Blocks: A Cognitive Computer Infrastructure for Geoscience

University Of Wisconsin-Madison, Madison WI

Investigators

Abstract

This is an era when access to information and data is often less of a problem than the ability to efficiently process and use it. In some cases, these problems are caused by massive, monolithic datasets that are difficult to store, transfer, and/or analyze. In other cases, the first-order problem is discovering and then aggregating relevant data that are widely disseminated in many different locations and formats, such as in the tables, text, and figures of published papers, government agency reports, spreadsheets, and websites. Geosciences currently lacks a cyberinfrastructure that can efficiently, cheaply, and with high precision and accuracy find, extract, and organize many different types of data that are critical to advancing science and leveraging current and past investments in data acquisition. Instead, there are dozens of isolated, sometimes redundant, geosciences data mining efforts that use humans as the primary mechanism for finding data and then keystroking them into structured databases. This mode of operation is not only costly and slow, but it is also an inefficient use of human resources and scientific expertise. This project develops a geoscience-oriented trained computing system that can serve as a cross-disciplinary tool for rapidly finding, extracting, and organizing geosciences data. Unlike traditional data processing systems, trained systems use statistical, or machine learning, techniques to provide rich answers to complex queries of data that are much less structured. The longer-term vision is to establish an EarthCube trained computing system that can aid in finding, extracting, and aggregating data, as well as in processing, summarizing, and synthesizing them in a way that helps geoscientists to tackle new problems and better understand and model Earth systems. This project brings together a unique interdisciplinary team that is committed to building, testing, and operating an EarthCube Building Block that will bring the power of trained computing systems technologies to the broader geoscience community. Trained computing systems offer an entirely new breed of tools for data processing.