IBM 5 in 5

IBM 5 in 5: Smart Sensors will detect environmental pollution at the speed of light

Share this post:

In the next five years, networks of sensors like this miniature silicon chip trace-gas spectrometer will help us "see" and manage environmental pollutants. This sensor design uses IBM's expertise in silicon photonics to detect methane with infrared light brought in via optical fibers. Thousands of sensors can be manufactured on each silicon wafer, allowing large-scale sensor networks at low cost.

In the next five years, networks of sensors like this miniature silicon chip trace-gas spectrometer will help us “see” and manage environmental pollutants.

Our team brings together a variety of disciplines including silicon photonics, spectroscopy, materials science and physical analytics to create new sensing technologies that can pinpoint and monitor the quality of our environment. Why? Because we believe that a multidisciplinary, collaborative approach is what’s necessary to help prevent pollution. And that’s also why we’re working with natural gas producers such as Southwestern Energy to explore the development of an intelligent methane monitoring system, as part of the ARPA-E Methane Observation Networks with Innovative Technology to Obtain Reductions (MONITOR) program.

Methane is the primary component of natural gas and considered a cleaner energy source than coal. But if methane leaks into the air, it absorbs the sun’s heat, warming the Earth’s atmosphere. In fact, methane is estimated to be the second largest contributor to global warming after carbon dioxide (CO2).

IBM 5 in 5

In the United States, emissions from oil and gas systems are the largest source of atmospheric methane.  The U.S. Environmental Protection Agency (EPA) estimates that more than nine million metric tons of methane leaked from natural gas systems in 2014 alone. Measured as CO2-equivalent over 100 years, that’s more greenhouse gases than were emitted by all U.S. iron and steel, cement, and aluminum manufacturing facilities combined. The impact is undeniable.

What is our prediction?

In five years, affordable sensing technologies deployed near natural gas extraction wells, around storage facilities and along distribution pipelines will pinpoint invisible leaks in real-time, and with the help of Artificial Intelligence, deep analysis and insight extraction will be possible from continuous sensor data.

Why will this change the world?

Sensor systems that can “see” will extend their detection capabilities beyond methane to other contaminants as well: Sensing oil residue in water, harmful pollutants from vehicle exhaust and other particulates in the air, helping us better protect the environment by illuminating it in new ways, in real time and with local relevance. Over time, this technique could help unlock the full potential of cleaner natural gas energy, as well as determine levels of all hazardous chemicals in the environment.

What are the underlying technologies?

Our work is based on silicon photonics, an evolving technology that transfers data by light.  A tiny silicon photonic chip spectrometer – arguably the world’s smallest – could be embedded in a network of sensors on the ground or within infrastructure, or even fly on autonomous drones; generating insights that, when combined with real-time wind data, satellite data, and other historical sources, can be used to build complex environmental models to detect the origin and quantity of pollutants as they occur.

Related Papers
Eric J. Zhang, Lionel Tombez, Jason Orcutt, Swetha Kamlapurkar, Gerard Wysocki, and William M. Green, “Silicon Photonic On-chip Trace-gas Spectroscopy of Methane” in Conference on Lasers and Electro-Optics, OSA Technical Digest (2016).

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



More stories

Text2Scene: Generating Compositional Scenes from Textual Descriptions

At CVPR 2019, IBM researchers introduce techniques to interpret visually descriptive language to generate compositional scene representations from textual descriptions.

Continue reading

Overcoming Challenges In Automated Image Captioning

At CVPR 2019, IBM researchers introduce an improved method to bridge the semantic gap between visual scenes and language to produce diverse, creative and human-like captions.

Continue reading

IBM Researchers Design Winning AI Algorithms for Drones

For the second year in a row, researchers at the IBM-Illinois Center for Cognitive Computing Systems Research(C3SR) won a competition challenging experts worldwide to design low-power embedded systems for Internet-of-Things (IoT) applications. The 2019 Design Automation Conference (DAC) System Design Contest’s objective: create algorithms that can accurately detect and locate objects from images taken by […]

Continue reading