Posted on

AI Being Applied in Agriculture to Help Grow Food, Support New Methods


AI is being applied to many areas of agriculture, including vertical farming, where crops are grown vertically-stacked in a controlled environment. (GETTY IMAGES)

By John P. Desmond, AI Trends Editor

AI continues to have an impact in agriculture, with efforts underway to help grow food, combat disease and pests, employ drones and other robots with computer vision, and use machine learning to monitor soil nutrient levels.

In Leones, Argentina, a drone with a special camera flies low over 150 acres of wheat checking each stock, one-by-one, looking for the beginnings of a fungal infection that could threaten this year’s crop.

The flying robot is powered by a computer vision system incorporating AI supplied by Taranis, a company founded in 2015 in Tel Aviv, Israel by a team of agronomists and AI experts. The company is focused on bringing precision and control to the agriculture industry through a system it refers to as an “agriculture intelligence platform.”

The platform relies on sophisticated computer vision, data science and deep learning algorithms to generate insights aimed at preventing crop yield loss from diseases, insects, weeds and nutrient deficiencies. The Taranis system is monitoring millions of farm acres across the US, Argentina, Brazil, Russia, Ukraine and Australia, the company states. The company has raised some $30 million from investors.

“Today, to increase yields in our lots, it’s essential to have a technology that allows us to make decisions immediately,” Ernesto Agüero, the producer on San Francisco Farm in Argentina, stated in an account in Business Insider.

Elsewhere, a fruit-picking robot named Virgo is using computer vision to decide which tomatoes are ripe and how to pick them gently, so that just the ripe tomatoes are harvested and the rest keep growing. Boston-based startup Root AI developed the robot to assist indoor farmers.

“Indoor growing powered by artificial intelligence is the future,” stated Josh Lessing, co-founder and CEO of Root AI. This year the company is currently installing systems in commercial greenhouses in Canada.

More indoor farming is happening, with AI heavily engaged. 80 Acres Farms of Cincinnati opened a fully-automated indoor growing facility last year, and currently has seven sites in the US. AI is used to monitor every step of the growing process.

“We can tell when a leaf is developing and if there are any nutrient deficiencies, necrosis, whatever might be happening to the leaf,” stated Mike Zelkind, CEO of 80 Acres. “We can identify pest issues and a variety of other things with vision systems today.” The crops grow faster indoors and have the potential to be more nutrient-dense, he suggests.

A subset of indoor farming is “vertical farming,” the practice of growing crops in vertically-stacked layers, often incorporating a controlled environment which aims to optimize plant growth. It may also use an approach without soil, such as hydroponics, aquaponics and aeroponics.

Austrian Researchers Studying AI in Vertical Farming

Researchers at the University of Applied Sciences Burgenland in Austria are involved in a research project to leverage AI to help make the vertical farming industry viable, according to an account in Hortidaily.

The team has built a small experimental factory, a 2.5 x 3 x 2.5-meter cube, double-walled with light-proof insulation. No sun is needed inside the cube. Light and temperature are controlled. Cultivation is based on aeroponics, with roots suspended in the air and nutrients delivered via a fine mist, using a fraction of the amount of water required for conventional cultivation. The fine mist is mixed with nutrients, causing the plants to grow faster than when in soil.

The program, called Agri-Tec 4.0, is run by Markus Tauber, head of the Cloud Computing Engineering program at the university. His team contributes expertise in sensors and sensor networking, and plans to develop algorithms to ensure optimal plant growth.

Markus Tauber, head of the Cloud Computing Engineering program, University of Applied Sciences Burgenland, Austria

The software architecture bases actions based on five points: monitoring, analysis, planning, execution and existing knowledge. In addition to coordinating light, temperature, nutrients and irrigation, the wind must also be continuously coordinated, even though the plants grow inside a dark cube.

“In the case of wind control, we monitor the development of the plant using the sensor and our knowledge. We use image data for this. We derive the information from the thickness and inclination of the stem. From a certain thickness and inclination, more wind is needed again,” Tauber stated.

The system uses an irrigation robot supplied by PhytonIQ Technology of Austria. Co-founder Martin Parapatits cited the worldwide trend to combine vertical farming and AI. “Big players are investing but there is no ready-made solution yet,” he stated.

He seconded the importance of wind control. “Under the influence of wind ventilation or different wavelengths of light, plants can be kept small and bushy or grown tall and slender,” Parapatits stated. “At the same time, the air movement dries out the plants’ surroundings. This reduces the risk of mold and encourages the plant to breathe.”

San Francisco Startup Trace Genomics Studies Soil

Soil is still important for startup Trace Genomics of San Francisco, founded in 2015 to provide soil analysis services using machine learning to assess soil strengths and weaknesses. The goal is to prevent defective crops and optimize the potential to produce healthy crops.

Services are provided in packages which include a pathogen screening based on bacteria and  fungi, and a comprehensive pathogen evaluation, according to an account in emerj.

Co-founders Diane Wu and Poornima Parameswaran met in a laboratory at Stanford University in 2009, following their passions for pathology and genetics. The company has raised over $35 million in funding so far, according to its website.

Trace Genomics was recently named a World Economic Forum Technology Partner, in recognition of its use of deep science and technology to tackle the challenge of soil degradation.

Poornima Parameswaran, Co-founder and Senior Executive, Trace Genomics

“This planet can easily feed 10 billion people, but we need to collaborate across the food and agriculture system to get there,” stated Parameswaran in a press release. “Every stakeholder in food and agriculture – farmers, input manufacturers, retail enterprises, consumer packaged goods companies – needs science-backed soil intelligence to unlock the full potential of the last biological frontier, our living soil. Together, we can discover and implement new and improved agricultural practices and solutions that serve the dual purpose of feeding the planet while preserving our natural resources and positioning agriculture as a solution for climate change.”

Read the source articles in Business Insider, Hortidaily and emerj.

Read More

Posted on

AI Innovation in Manufacturing, Robotics, New Apps on Display at CES


AI was at the center of much innovation on display at the recent CES trade show, with highlights in the manufacturing industry and in robotics. (GETTY IMAGES)

By AI Trends Staff

AI was showcased in many areas at the recent CES trade show in Las Vegas, attended by over 4,400 exhibitors and 170,000 attendees.

In manufacturing, the majors were showing off their AI prowess.

A new washing machine from LG Electronics uses AI to precisely clean clothes. Internal sensors in the AI DD washer detect the load volume and weight as well as the clothing fabric, according to an account in the WSJ Pro. The washing machine’s AI models then compare those details against 20,000 data points to determine the optimal cycle settings for the laundry. A load of T-shirts and pants needs a certain type of wash, temperature and wash time for best results; the AI figures it out and sets it.

John Deere & Co. showed off its See & Spray machine pulled behind a tractor, using vision and machine learning to detect weeds and determine plant health. See & Spray came with Deere’s acquisition of Blue River Technology in 2017 for $305 million. The technology is said to help reduce agrochemical use. The company is suggesting farmers can save up to $30 per acre by using See & Spray. “We’ve got AI in production, on machines, today and there is more coming,” stated John Stone, senior vice president for the Intelligent Solutions Group at Deere.

Mercedes-Benz is developing an AI system for its Sprinter vans to assist workers in loading packages in an optimal way. Expected to be available within a year, Coros—“cargo recognition and organization system”—is intended to help with “last-mile” logistics. Cameras in the van cargo section read package barcodes, then refer to a model that assesses the package size and where it best belongs. A blue light comes on in the shelf section where the package should be placed. The system identifies the package when it is being picked up for delivery as well. If a package does not belong in a vehicle, red lights come on. The hope is to optimize package loading and reduce training costs.

Innovations Exploiting the Power of AI

Innovations were on display among the many exhibitors at CES. An account in Forbes highlighted a selection, including:

Whisk, a smart food platform acquired by Samsung’s innovation-focused subsidiary Samsung Next earlier this year, is now capable of scanning the contents of your refrigerator and suggesting dishes to cook. The AI model refers to research from over 100 nutritionists, food scientists, engineers, and retailers. The company suggests the technology will also help to reduce food waste.

Wiser from Schneider Electric is a small device that monitors energy use by each home appliance in real-time. It installs in the home circuit breaker box; its machine learning models are aimed at optimizing savings, including for solar systems.

A vital signs monitoring app from Binah.ai analyzes a person’s face to detect medical insights. The app detects oxygen saturation, respiration rate, heart rate variability and mental stress. Plans are to add monitoring for hemoglobin levels and blood pressure.

Robots Extending into Homes, Humanoid Forms

Interesting robots incorporating AI was the focus of an account from CES from TechRepublic; including the following examples.

Samsung’s Ballie, still a research project, is a tennis ball-sized life companion, reported ZDNet. Ballie is a small, round, rolling robot designed to support, understand, and react to the needs of its owner, specifically in households. Ballie’s AI capabilities use sensors and data within the home to attempt an immersive experience. The device will be designed to be able to connect with and control other smart devices in the home.

Graphics chipmaker NVIDIA showed its reach in robotics at CES, with its GPU chips used in a number of innovative robots. For example, Toyota’s new humanoid robot T-HR3, along with its Jetson AGX Xavier computer. The T-HR3 uses advanced synchronization and master maneuvering to move smoothly and control the force of its body. The system is controlled by a human operator wearing a virtual reality (VR) headset. T-HR3 receives the data through augmented video and perception data via a NVIDIA’s Jetson AGX Xavier computer within the robot, according to a NVIDIA blog post.

Other NVIDIA-powered robots at CES, cited in an account in ZDNet, included an autonomous wheelchair from WHILL powered by a Jetson TX2, a home security drone from Sunflower Labs, a delivery robot from PostMates and an inspection snake robot from Sarcos.

Read the source articles in WSJ Pro, Forbes and   TechRepublic.

Source: AI Trends

Posted on

The Environmental Impacts of AI and IoT In Agriculture


The promise of AI in agriculture is to increase crop yields and lead to more environmentally friendly farming practices. (GETTY IMAGES)

By Caleb Danziger, Science Writer

As the world’s citizenry continues to grow, with estimates putting 2100’s population at 11.2 billion, the agriculture industry will need to compensate for increased demand. Within the next 80 years, an additional 3.6 billion people will need food; production needs to improve beyond what’s possible today. At the same time, land dedicated to agricultural projects may become limited, calling for enhanced efficiency and viability.

IoT and AI solutions can vastly improve crop yields and may be the only way to achieve a better system, according to some experts. The technology can also pave the way for environmentally friendly processes.

AI and IoT for Agricultural Applications

If AI and IoT are the answer, at least in some small form, what will they do? How can the technology integrate into existing operations, and how will it present new opportunities?

  • Precision Farming Through Micro-Sensors: Most farming operations require a keen eye, as farmers scan their crops for signs of disease and contamination. At a macro-level, the process is easy, but the eyes can’t spot everything. With the help of modern IoT solutions, as well as AI and mobile computing, farmers can offset the entire process, relying on technology to do the review. Farmers can monitor Individual plants for potential sickness and disease with the help of micro-sensors. Plus, the technology can display stats remotely via a smartphone or similar device, allowing farmers to see instant alerts about what’s happening in their fields, whether it has to do with pests, disease or something else. Many sensors are already in use in the current market, from mechanical sensors that measure soil compaction and erosion to real-time devices that detect pest populations.
  • Drone Operations and Crop Monitoring: Alongside IoT monitoring—or perhaps in place of it—aerial drones can analyze and monitor crops. Using cameras and sensors embedded inside, the drones gather information about plants down to a single leaf. When fed into a neural network or machine learning solution, all the collected data can provide a detailed image of a farmer’s stock.
  • Smart Collars for Livestock: Cattle and livestock management is no small feat. Not only do farmers have to monitor each animal’s whereabouts accurately, but they also have to stay informed about their health. To alleviate some of the responsibility, farmers have begun equipping their cows with Fitbit-like IoT wearables that monitor data in real-time. Wearable applications can be used on any animals on a farm, including horses, cattle and poultry.
  • AI-Powered Pesticide Applicators: By combining AI control solutions and IoT sensors, farmers can better protect crops from pests. Spot treatment allows farmers to treat plants individually and keep away potential insects. At the same time, fewer chemicals enter the surrounding environment, including the soil underneath.

Smarter Operations Through Data Sharing

AI and neural network solutions can be trained through data ingestion. As a result, technology controlled by AI could see an increase in efficiency over time as the system becomes smarter, contextualized and more aware.

Collectively, experts can use that gathered information to generate predictive models and compare performance statistics to find insights. In the farming world, the data-sharing of thousands of setups and relevant statistics can make for more effective operations across the board.

With data sharing, agricultural experts can share and consume a vast amount of knowledge, everything from soil and seed tests to yield-improving maintenance tips.

The Downside to Modern Technology

AI and IoT will undoubtedly make a significant impact in agriculture. These tech innovations, however, come with potential setbacks, both for farmers and the environment.

  • Increased Cybersecurity Risk: As technology continues to rely on the internet — and more operation-specific data is collected — vulnerabilities and access points will appear. Thieves can steal more than sensitive information. If IoT solutions are in place, remote hackers can seize control of applications. If a hacker were to gain control of a pesticide dispersal system, for example, it could prove disastrous. Theoretically, they could spray more chemicals than needed, poisoning or killing crops. As a preventive, farmers must implement cybersecurity foundationally to prevent potential attacks.
  • High Adoption Costs: IoT-enabled devices and sensors, while not incredibly expensive, can prove pricey when bought in bulk. Along with the hardware, a suitable local network must be put in place to facilitate and support the massive influx of data. Plus, there’s the matter of proper data storage, either locally or cloud-based. AI and big data solutions must also be implemented on the backend to analyze, organize, and extract usable insights from digital content. These requirements can lead to incredibly high adoption costs at even the smallest of agricultural facilities.
  • Environmental Risks: To make matters worse, all new technology requires power to run. A system that supports a large-scale agricultural operation will require massive amounts of energy. Furthermore, many advanced robots and solutions still need fossil fuels to operate, polluting the environment. Without more sustainable energy—or even renewable solutions—IoT and similar modern technologies are not a proper fix for environmental issues. Instead, adoption may cause more problems in the short term.

AI and IoT In Agriculture — The Way Forward

As a society, we have a long way to go when it comes to improving the impact of our actions on the environment. The agricultural field is no exception. Experts won’t see a change tomorrow or in the coming weeks. However, what’s important is that we’re continuously working toward that goal.

Farmers and manufacturers already use IoT and AI technology to increase operational efficiency and reduce waste output. From drone and sensor monitoring to Fitbit-like wearables, the innovations seem endless. As smart devices complete routine tasks, farmers can spend more time on critical matters, such as reducing emissions and their environmental impact.

Technology has been a boon for the agricultural industry, yet it’s also seen some drawbacks. Increasing efficiency often comes with a steep price tag, a cost many small-scale farmers can’t afford. Plus, devices that run on fossil fuels further contribute to climate change. Only time will tell what roles AI and IoT play in the future.

Caleb Danziger is a tech blogger and freelance writer. He co-owns thebytebeat.com.

Source: AI Trends