Called IBM PAIRS (Physical Analytics Integrated Data Repository & Services) Geoscope, the service is aimed at “accelerating the discovery of new insights” by extracting value from geospatial-temporal big data – so named because of its inherent link to place and time. Such data, which is vast in scope and growing exponentially, is being fueled by increasingly sophisticated and affordable electronics in applications such as the Internet of Things (IoT).
Extracting insights from geospatial-temporal big data – which includes satellite and aerial imagery, global-scale data and models (weather, climate, oceans, etc.), geo-referenced IoT/sensor networks, and big-event data captured on platforms like Twitter and GDELT – poses a significant challenge. While often freely available, its massive size and the complexities associated with its preparation for use make it difficult to exploit and scale, says the company, especially for large areas and time-critical applications.
For example, geospatial-temporal datasets are often too large to transfer for analysis in a reasonable time. And according to some projections, data generation rates from just IoT alone could reach 600 zettabytes (ZB) per year by 2020, .
Another challenge hindering rapid analysis is the “daunting array” of complex formats of various geospatial-temporal datasets. Understanding and curating this diversity can present significant and sometimes insurmountable bottlenecks when attempting to bring the data to the analytics.
“PAIRS Geoscope addresses this problem by reversing the situation – that is, by offering a service that allows clients to bring their analytics to the data.” says Hendrik Hamann, Senior Manager, Physical Analytics, IBM Research. “It frees clients from the cumbersome processes that dominate conventional geospatial-temporal data acquisition and preparation and provides search-friendly, ready access to a rich, diverse, and growing catalog of historical and continuously updated geospatiotemporal information.”
PAIRS Geoscope is built on a highly scalable, cloud-based repository – currently growing by terabytes per day – especially crafted for the complexities of geospatial-temporal information, says the company. The repository can automatically ingest, curate, and seamlessly integrate all forms of geospatial-temporal data. Large, heterogeneous, and complex datasets are converted into an aligned and indexed structure designed for efficient retrieval and query.
“Clients can now use PAIRS Geoscope at different levels to tap a vast and valuable source of previously underutilized data,” says Hamann. “As an information service, PAIRS Geoscope can quickly provide a variety of contextual information about a particular place and time. Used as a discovery service, it can identify a set of regions that share a similar set of client-defined characteristics. As an advanced analytics service, it can leverage machine learning and artificial intelligence techniques to make predictions based on a complex mix of parameters, models, and historical data.”
IBM PAIRS Geoscope originated from a project where IBM and a winery collaborated on an effort to conserve water while improving crop uniformity and yield, which resulted in a precision irrigation system incorporating a cloud-based communication network, hundreds of sensors and actuators, and satellite imagery to measure the uniformity and health of the greenery. In addition it used a complex model for estimating water loss from greenery and soil that required numerous meteorological and atmospheric parameters from a variety of sources, and a localized weather model to estimate future irrigation needs.
According to the company, ongoing development of PAIRS Geoscope remains intentionally tethered to its real-world origins. It is currently in trial deployments with clients in the areas of agriculture, finance, energy, and meteorology.
New magnetic tape storage record aims at cloud, big data
Breakthrough HDD storage tech for big data ‘ready for prime time’
Making sense of big data with graph technology, machine learning
IBM, Maersk blockchain platform to digitize global trade
Cisco to acquire streaming data analytics startup