Posted in: IBM 5 in 5, Internet of Things, Publications

IBM 5 in 5: Macroscopes will help us understand Earth’s complexity in infinite detail

Group photo of IBM Research team building the world’s first platform for collecting, curating and searching global data by space and time. From left to right: Rong Chang, Hendrik Hamman, Xiaoyan Shao, Marcus Freitag, Ildar Khabibrakhmanov, Siyuan Lu

The IBM Research team building the world’s first platform for collecting, curating and searching global data by space and time. From left to right: Rong Chang, Hendrik Hamman, Xiaoyan Shao, Marcus Freitag, Ildar Khabibrakhmanov, Siyuan Lu

I am part of a team of scientists in IBM Research that study and explore the intersection of big data with physics; a field that is known as physical analytics. My team’s expertise in physical models, machine-learning, sensors, data curation and big data technologies has been put to use in applications dealing with renewable energy, precision agriculture and energy management. We are now leading the company’s research in the quickly developing area of the Internet of Things (IoT), an extension of the classical internet of computers to any physical object.

As a scientist, I am always open to new ideas and suggestions regardless of where they come from. Only the scientific merit matters. That is why I like to bridge different disciplines in many aspects of my work. For example, I’ve worked on the development of a near-field optical microscope to study single molecules at high spatial resolution; and also helped IBM win a Vintage Report Innovation Award from the wine industry by co-developing a prototype irrigation system based on IoT technology that cut water use at Gallo Wines by 25 percent and improved crop yields by 26 percent.

IBM 5 in 5

Our latest work is focused on what we can learn about the physical world as it becomes increasingly instrumented and whether we can better understand complex systems such as weather, climate, ground water hydrology or the electric grid — or to at least describe these systems such that we can better predict them.

The physical world before our eyes only gives us a small view into what’s an infinitely more interconnected and complex ecosystem. The time has come for us to truly see more of the world thanks to being able to digitize and collect new sources of data from millions of connected objects — from household objects like toasters and medical devices like sphygmomanometers, to remote sensors such as drones and satellites.

Following the advent of the internet, where everything is digital — which was, in turn, followed by the digitization of business and then social interactions — digitizing the physical world is the next logical step. Everything in the physical world can be linked in time and space, giving us the ability to search and analyze vast troves of complex geospatial information to reveal new insights about some of the most fundamental problems we face, such as the availability of food, water and energy. Beyond our own planet, new capabilities could handle, for example, the complicated indexing and correlation of various layers and volumes of data collected by telescopes to predict asteroid collisions with one another and even learn more about their composition.

This effort is a workstream within the IBM Research Frontiers Institute, a consortium built on open and collaborative research in which member companies from diverse industries collaborate with IBM’s research talent and cutting-edge infrastructure to spur world-changing innovations with global impact.

What is our prediction?

In five years, new macroscope technology will allow us to observe the complex environments of our physical world by organizing and indexing geospatial information, making it searchable and bringing it within the range of our vision and understanding — much like how the invention of the microscope made very small regions of the physical world visible and how the telescope opened our eyes to the cosmos.

Why will this change the world?

If you consider that the world’s population will exceed nine billion by 2050, it’s clear the world’s social and economic leaders must grapple with how we continue to grow more food and how we ensure the sustainability of crop production. Most of the population growth is expected in the developing world where adoption of modern agricultural practices lags. To address this need of ever-increasing food production, global solutions are needed that promote yield increases without aggravating soil erosion, water pollution or further expansion of land use for agricultural purposes.

A solution built with macroscope technology will help. By aggregating and analyzing data on climate, soil conditions, water levels, irrigation practices — even data on the social and political climate of a country — farmers, seed companies, food manufacturers and others will be able to tap into insights that help them determine the right crop choices, where to plant them and how they’re growing to delicately balance optimal yield with the right amount of water and fertilizer.

What are the underlying technologies?

The biggest hurdle today is getting data that is clean, indexed and formatted. Data scientists can spend approximately 80-90 percent of their time on this task alone, as today, data from various systems is unorganized and undiscoverable. At the heart of our vision and development of a platform for collecting, curating and searching global data by space and time, is a set of technologies that include new indexing schemes for data from the physical world, smart cognitive data curation, parallel processing, and both large scale and physics-inspired machine-learning.

Related Papers
Siyuan Lu*, Xiaoyan Shao, Marcus Freitag, Levente J. Klein, Jason Renwick, Fernando J. Marianno, Conrad Albrecht, Hendrik F. Hamann, “IBM PAIRS Curated Big Data Service for Accelerated Geospatial Data Analytics and Discovery2016 IEEE International Conference on Big Data (Big Data).

G. Badr, L. J. Klein, M. Freitag, C. M. Albrecht, F. J. Marianno, S. Lu, X. Shao, N. Hinds, G. Hoogenboom, H. F. Hamann, “Toward large-scale crop production forecasts for global food securityIBM Journal of Research and Development.

L.J. Klein, F.J. Marianno, C.M Albrecht, M. Freitag, H.F. Hamann, “PAIRS: A scalable geo-spatial data analytics platform2015 IEEE Conference on Big Data (Big Data).

Read all of IBM’s 2016 technology predictions at IBM 5 in 5.

Save

Save

Save

Comments

Add Comment

Your email address will not be published. Required fields are marked *

Hendrik Hamann, Research Manager for Physical Analytics, IBM Research

Hendrik Hamann

Research Manager for Physical Analytics, IBM Research