smart agriculture

Part 2 of 2-part series on MSEC 2019 highlights. Read Part 1. Neural Networks on ChipTo be sure, low power is king when bringing machine learning to the sensor edge. Battery-powered, always-on sensing devices require it since frequent recharging is the death knell of any electronic product. That’s why semiconductor companies are offering new ways to conserve power.“MEMS sensor suppliers have made significant strides in the power, size and performance of their devices,” said Aspinity CEO Tom Doyle. “Yet these gains deliver only incremental power improvements to the system.”Doyle advocates a new architectural model that uses an analog neuromorphic processor to analyze all sensor data at the start of the signal chain instead of sending it downstream so power-hungry chips such as DSPs can digitize it before analysis.“The technology industry wants to take advantage of the many benefits of always-on sensing applications,” said Doyle. “Before we can reach mass proliferation, however, we need to resolve the power issues that are deal-breakers for some applications. We believe the answer to this challenge is architectural. All the data gathered by always-on sensing systems is analog in nature, yet as soon as it’s captured, it’s digitized immediately for analysis. Determining which data is important up front eliminates the digitization and processing of irrelevant data so that voice-first devices such as smart speakers and wearables/hearables can run for long periods of time without requiring battery recharge.”Syntiant CTO Jeremy Holleman agreed that on-device intelligence is the future.“Did you just fall? Is your heartrate a bit off? Deep learning provides a toolset that yields vastly superior decisions,” said Holleman. “The problem is that deep learning is computationally intensive. The answer is a neural network that performs on-device edge inferencing.”Holleman added that Syntiant’s neural decision processor was recently certified as Amazon Voice Service (AVS)-compliant for wake-word detection, making it easier to design voice control in battery-powered devices such as earbuds and wearables.MSEC Technology Showcase WinnerWith the groundswell of interest in intelligence at the edge, it was no surprise that Cartesiam won top honors among all competitors in the MSEC Technology Showcase for its NanoEdge AI, software that brings AI to the edge of the signal chain, making it easier for designers to create intelligent objects that can learn and understand.“Unlike other AI algorithmic technologies for sensing devices, NanoEdge enables both learning and inference at the edge, providing accurate and adaptive intelligence,” said Cartesiam Managing Director and Co-founder Marc Dupaquier, who accepted the award. “It’s also the only tool of its kind that does not require data scientists on board for implementation, which saves a tremendous amount of money. Our clients can build a machine learning library and embed it into their own code within weeks to realize the same caliber of unsupervised neural network that was once the exclusive domain of AI cloud vendors.”MSIG 2019 Hall of FameAt this year’s conference, MSIG Director Carmelo Sansone recognized two longtime contributors to the commercialization of MEMS and sensors: Peter G. Hartwell, Ph.D., chief technology officer at InvenSense, a TDK group company; and Thomas Kenny, professor and senior associate dean of engineering at Stanford University.Hartwell leads technology strategy and the InvenSense advanced technology research group. He has more than 25 years’ experience commercializing silicon MEMS products, including advanced sensors and actuators, and developing MEMS testing techniques.Kenny’s academic accomplishments include authoring or co-authoring more than 250 scientific papers and holding 50 issued patents. He has also advised more than 50 graduated Ph.D. students from Stanford.MSEC 2020Mark your calendar for next year’s MSEC, October 12-14, at Coronado Island Marriott Resort Spa in Coronado, Calif. Get updates from MSIG on MSEC and other upcoming events including MSTC 2020.Stay in Touch with MSIGMEMS Sensors Industry Group (MSIG), a SEMI Strategic Association Partner, is the industry association representing the global MEMS and sensors supply chain. To learn how MSIG enables professionals in the MEMS and sensors industry to innovate, address common challenges and accelerate business results, visit us today.Connect with MSIG on Twitter and LinkedIn. Subscribe to SEMI Blog: Technology and Trends.Maria Vetrano is a public relations consultant at SEMI.

Part of 1 of 2-part series on MSEC 2019 highlights. Read Part 2. MEMS and sensors are proliferating across consumer, automotive, biomedical/healthcare, robotics, industrial and agriculture applications to harvest sensory data in a hyper-connected world and meet demand from consumers and organizations alike as they clamor for more intelligence in electronics.Take the ubiquitous iPhone. Shipped in 2007, Apple’s first iPhone sported five sensors. By contrast, the most feature-packed smartphones will embed up to 20 sensors by 2021, according to Yole Développement’s Jérôme Azémar. He estimates that the devices will feature four MEMS microphones, four CMOS image sensors (CIS), a RGB color sensor, a laser rangefinder, an infrared sensor, a gas sensor, a heart rate monitor and a fingerprint sensor, not to mention the MEMS inertial sensors that device users have come to know and trust.The MEMS market is expected to reach $18.5 billion in 2024 [1], up a whopping 60 percent from $11.6 billion in 2018, according to Azémar, who presented at MEMS Sensors Industry Group’s 15th annual MEMS Sensors Executive Congress (MSEC) in late October in Coronado, Calif. Add other types of sensors to the mix – CIS, environmental sensors, LiDARs, radars, ultrasonics, and fingerprint sensors – and the market will mushroom to $93 billion by 2024, said Azémar.Since MEMS Sensors Industry Group (MSIG) joined SEMI as a Strategic Association Partner three years ago, SEMI has expanded its MEMS and sensors programs to Europe and Asia while continuing to grow its U.S. conferences. “SEMI is continually investing in MEMS and sensors innovation across the supply chain,” said Dave Anderson, president of SEMI Americas and host of MSEC. “For example, MSIG is contributing to the development of the Heterogeneous Integration Roadmap, an initiative designed to drive heterogeneous integration technology development and accelerate electronics innovation. The roadmap spans device design, test and fabrication, ecosystem development, R D, equipment and materials. “At MSEC, executives and other speakers explored how AI and blockchain are remaking the food supply chain, air transportation and other sectors as MEMS and sensors improve the quality of our lives,” said Anderson.Sensing at the EdgeThe concept of artificial intelligence (AI), that a machine can harness intelligence that rivals or outperforms humans – and act without human intervention – has been a feature of the human imagination since at least the 1968 film 2001: A Space Odyssey. MEMS and sensors facilitate intelligence in a wide range of electronics such as smartphones, healthcare wearables, robots, industrial predictive maintenance systems, and cars. AI is sure to augment that functionality.MEMS and sensors are now in their third wave of evolution, a focus on edge AI, Bosch Sensortec CEO and General Manager Stefan Finkbeiner told MSEC attendees. For its part, Bosch is working to add AI to MEMS devices. The first wave integrated software with MEMS sensors, and the second, sensor fusion, enabled designers to allocate performance and power strategically to tune MEMS for resource-constrained devices. The third wave is “an active-learning phase in which MEMS facilitates real-time learning at the edge to promote greater personalization, environmental feedback, privacy of user data and improved battery life,” said Finkbeiner.Small sensor nodes with edge AI exemplify third-wave applications. Integrating low-power environmental sensors (e.g., gas, temperature, pressure, humidity and air-flow sensors), the nodes could be deployed in fire-prone forests to assess fire risk and support early detection. Access to this real-time environmental information could prove invaluable to residents and public-safety personnel alike.Google takes another tack, applying machine learning to resource-constrained devices, said Nick Kreeger, a senior software engineer at the Internet giant. The company’s Google Brain creates machine learning models that can run on inexpensive, low-power microcontrollers using Google’s TensorFlow Lite, an open-source machine learning tool that’s been deployed on a multitude of mobile devices. Inferencing is done at the device’s edge, rather than transmitted to the cloud.Meeting the power constraints of battery-powered sensing devices is another matter that starts with minimizing energy and data waste. “Deep learning is compute-bound and runs well on existing microcontrollers,” Kreeger said. “Because it’s all arithmetic, it’s low-power compared to storage access.”Already Google has worked with Plant Village, a research unit at Penn State University, and the International Institute of Tropical Agriculture (IITA) to help farmers improve food production by using machine learning and cheap sensors to spot and manage planet diseases in developing countries. And that production chain is in dire need of a boost, according to Rajendra Rao, general manager of IBM Food Trust, an enterprise-class blockchain solution.“We are on the cusp of complete failure of the food system,” Rao said. “One out of 10 people gets sick each year from foodborne illness, 420,000 die from this annually, 80 percent of companies in the food supply chain have not digitized, one-third of all fresh food in the US is thrown away, and one in five seafood samples worldwide is mislabeled.”IBM Food Trust’s work with Sucafina, which manages a global green coffee supply chain, shows how sensors can trace food from the farm to the processing plant to the consumer. With the IBM Food Trust platform, Sucafina can track the origin of the beans used in a cup of coffee – a competitive differentiator to coffee drinkers eager to support fair-trade coffee roasters.ripe.io, one of Forbes’ 25 most innovative AgTech startups, is also tackling the challenges and complexities of the food supply chain.“Our secure blockchain platform creates a digital twin of food items, transparently aggregating foods’ journey in real-time, to provide a harmonized trustworthy platform for multiple stakeholders,” said Rachel Gabato, the company’s COO. The ripe.io blockchain-based platform collects data from various sensors – temperature, pressure, light, humidity and inertial MEMS sensors. Growers, distributors and end customers including sweetgreen – a U.S. restaurant chain that depends on fresh produce – use the information to trace the origin and quality of food.MSEC 2020Mark your calendar for next year’s MSEC, October 12-14, at Coronado Island Marriott Resort Spa in Coronado, Calif. Get updates from MSIG on MSEC and other upcoming events including MSTC 2020.Stay in Touch with MSIGMEMS Sensors Industry Group (MSIG), a SEMI Strategic Association Partner, is the industry association representing the global MEMS and sensors supply chain. To learn how MSIG enables professionals in the MEMS and sensors industry to innovate, address common challenges and accelerate business results, visit us today.Connect with MSIG on Twitter and LinkedIn. Subscribe to SEMI Blog: Technology and Trends.[1] Source: Status of the MEMS Industry report, Yole Développement, 2019Maria Vetrano is a public relations consultant at SEMI.

At the SEMI FLEX 2019 and MEMS Sensors Technical Congress (MSTC) (MSTC) February 18-21 in Monterey, California, I had the pleasure of meeting many old friends and colleagues as well as making some great new acquaintances. With MEMS and sensors still a relatively young industry, I am delighted that our community is thriving. We continue to see double-digit growth rates, there is plenty of innovation, and the technology generates massive amounts of data that gets everyone excited about artificial intelligence, deep and machine learning, and blockchain. Those are all the buzzwords that any tech startup needs for funding these days.While it is hard to single out any one presentation at conferences, I was particularly struck by Nadia Shakoor’s keynote address, “Driving Advances in Crop Breeding and Smart Farm Management.” From Nadia I learned that the world’s largest agriculture sensing platform was a mere 45 minutes south of where I live in Phoenix, Arizona. This is a major embarrassment to admit as I have lived here for almost 30 years, have been involved in MEMS and sensors for a decade, and have a particular passion for the use of sensors in agriculture and food to improve crop yields and food quality, and to reduce food waste. This humongous sensor was hiding in plain sight right under my nose!After Nadia’s keynote, I just had to speak to her at the break. Nadia is the senior research scientist and project director for TERRA-REF at the Danforth Plant Science Center based in St. Louis, Missouri. Nadia’s work employs field-level crop phenomics, the biological study of the set of physical and biochemical traits belonging to a given organism (phenomes). Phenomes are fascinating because they change in response to genetic mutation and environmental influences. The Danforth Plant Science Center and its partners are involved in many phenotyping projects using autonomous vehicles, drones, field scanners, satellite imaging and more.After the FLEX MSTC event, I emailed Nadia to ask if I could visit the field scanner and her partner team at the University of Arizona in Maricopa, Arizona. She kindly introduced me to Maria Newcomb, a plant research scientist at the site, who gave me a good look at this mother of all field scanners: the Transportation Energy Resources from Renewable Agriculture Phenotyping Reference Platform (TERRA-REF). TERRA-REF aims to transform plant breeding by using remote sensing to quantify plant traits such as plant architecture, carbon uptake, tissue chemistry, water use and other features to predict the yield potential and stress resistance of 400+ diverse sorghum lines. The TERRA-REF Field Scanner at the University of Arizona Maricopa Agricultural Center. It’s the largest field crop analytics robot in the world, one that’s critical to the crop research underway at the Donald Danforth Plant Science Center in St. Louis, Missouri. Source: Steve Whalley TERRA-REF’s Lemnatec Field Scanalyzer is the largest field crop analytics robot in the world. This high-throughput phenotyping field-scanning robot has a 30-ton steel gantry that autonomously moves along two 200-meter steel rails that have recently been extended another 170 meters. It continuously images the crops growing below it by using a diverse array of cameras and sensors to observe the field at a dense-collection frequency with high resolution. These sensors include RGB stereo; thermal, chlorophyll fluorescence imaging system; hyperspectral cameras; a 3D laser scanner; and environmental monitors.Plant breeding is currently limited by the speed at which phenotypes can be measured, and the information that can be extracted from these measurements. Current instruments used to quantify plant traits do not scale to the thousands or tens of thousands of individual plants that need to be evaluated in a breeding program. The TERRA-REF field scanner system, on the other hand, uses sensors to scan over one acre of plants, collecting thousands of daily measurements throughout the growing season, and these are used to determine plant phenotypes and inform breeding decisions. TERRA-REF’s advanced sensor technologies include: Hyperspectral (250nm-2500nm) Thermal Infrared 2D and Stereo RGB PSII chlorophyll fluorescence 3D laser Environmental sensors The TERRA-REF field scanner platform features a massive sensor-rich scanner head. Source: Steve Whalley The humongous TERRA-REF field-scanner was certainly a sight to behold, looming like a cargo-ship container crane in the vast flat plains of the Arizona desert landscape. I’ve only scratched the surface of what this enormous sensor platform can accomplish so if you are a MEMS/sensor company interested in agriculture and food production, I encourage you to get more information at terraref.org and pay a visit next time you are in the area.Steve Whalley, CEO, Strategic World Ventures, is a strategic consultant to SEMI-MEMS Sensors Industry Group (MSIG). He also consults with established and emerging semiconductor, MEMS and sensors companies.

Jason Jelinek, a software technical manager at John Deere Electronics Solutions, has parlayed his more than two decades of embedded software engineering experience into commercializing controls and sensing technologies for rugged/harsh environments, including agriculture/off-road and aerospace. During his keynote at the upcoming FLEX and MEMS Sensors Technical Congress 2019, February 18-21 in Monterey, Calif., Jelinek will address the driving need for advanced sensing technologies that will fuel the continued growth of autonomy in agriculture.SEMI’s Maria Vetrano asked Jelinek to help FLEX/MSTC attendees understand his vision of autonomy in agriculture, which heavily leverages advanced sensing technologies to help farmers master equipment logistics, handle vehicle- and fleet-level operational efficiency, and manage the entire lifecycle of crops.SEMI: Did autonomy in agriculture start with autonomous equipment, such as tractors and combines?JELINEK: Automation, the first step on the road to autonomy, has been occurring in agriculture for a long time. Over the past 100 years, automation has dramatically reduced manual effort and simplified jobs in farming, allowing operators to focus more on administrative and other aspects of their work.The evolution of the combine is a good example of automation in agriculture. Long ago farmers would use a scythe to cut down the crop before bundling or stacking it up. Later they would manually thresh and winnow the crop to get the grain. Over time, we developed windrowers to cut the grain, threshing machines to separate the grain from the chaff, and winnowing machines to get only the grain. Combines now “combine” all those steps to go from grain on the stalk in the field to grain in the hopper. One person in a combine can do the work that once required many people and animals — all in a much shorter timeframe. We are now looking at automating harvesting to maximize yield and reduce fuel consumption. The AUTOTRAC feature on John Deere machines is a recent example. AUTOTRAC divides a field into rows based upon the parameters of the machine in operation, supporting hands-free driving with very high accuracy. It allows consistent, accurate rows for tilling, planting, crop treatment and harvesting, saving considerable time, improving overall quality and freeing the operator to do other work while in the vehicle.The Exact Emerge and Section Control features (which also use AUTOTRAC) will spur greater future autonomy. Control over both the seed spacing (Exact Emerge) and when the machine drops seeds (Section Control) prevents overseeding and provides the right seed-spacing for optimal crop production.As we look to the future, sustained growth in automation of jobs will enable the development of fully autonomous equipment. Currently, however, skilled operators are still closely involved in job management and execution. To realize greater autonomy, we will need machines that make the decisions once made by people.SEMI: How will autonomy in agriculture change the ways that we grow and harvest food — and even affect when we sell it?JELINEK: Autonomy will lead to more efficient production, reducing fuel, fertilizer, herbicide and water requirements. It will also enable fewer people to do more of the work.Let’s start with conditions that are hard, even impossible, to control: weather and staffing.While farming is still tied to the weather — and will remain so for some time — more efficient operations will allow tilling, planting, spraying and harvesting of fields to occur in shorter time windows that more easily match conducive weather conditions.There is also a human-resource issue: The agricultural industry must compensate for population decline in the rural areas where farmers operate. Doing more with less is essential for agriculture to continue to meet the rising food and clothing demands of the world’s population.SEMI: To what degree will we see artificial intelligence in autonomous agricultural systems?JELINEK: While autonomous systems had their start at the vehicle level, they will one day move to the entire fleet, providing suggestions on when the owner should execute operations. Autonomous systems may also help owners to decide when to store or sell crops, based on market conditions, operating costs and desired margin levels. That’s the initial level of artificial intelligence that I foresee.SEMI: How can sensing improve autonomy in agriculture?JELINEK: The challenges we face in agriculture are many, but technology will help us meet them. We must transfer responsibility for operations and decision-making from the skilled operator to the intelligent machine. Through increased use of sensing, we can gather large amounts of data, which autonomous agricultural systems will process, communicate and interpret to streamline jobs and boost agricultural production.SEMI: What would you like FLEX/MSTC attendees to take away from your presentation?JELINEK: I would like FLEX/MSTC attendees to understand the environment in which agricultural sensors need to operate. We need sensing solutions that will survive and thrive in rugged, outdoor variable environments to support the automation that will fuel autonomy.I would also like to engage suppliers in the application of current technology to meet our sensing needs.Jason Jelinek will present Autonomy in Agriculture at FLEX/MSTC on Tuesday, February 19 at 9:00 am.Register today to connect with him at the event. To learn more, click here.MSTC Flex 2019 is organized by the MEMS Sensors Industry Group (MSIG) and FlexTech. Maria Vetrano is a public relations consultant at SEMI.