Microsoft is unleashing AI on environmental issues facing the planet.
The company is specifically looking at using data to solve problems in the fields of agriculture, biodiversity, climate change and water access.
The initiative, called AI for Earth, is described as a program to “empower people and organizations” to solve challenges in the environment and climate. Microsoft thinks that making AI more accessible could enable breakthroughs in sustainability that help to protect the Earth.
Microsoft has committed $2 million in the next fiscal year to facilitate this work. It will partner with individuals and organizations who have ideas for the future, offering AI tools to accelerate their projects.
Microsoft’s not going to be directly investing in companies or taking equity stakes. Instead, it wants to provide tangible resources in the form of artificial intelligence. It’s part of a wider endeavour within the company to position itself as a leading member of the AI industry. Solving sustainability challenges using AI will give Microsoft and the technology a place to demonstrate its benefits from.
Organisations involved with AI for Earth will be offered grants that enable them to access Microsoft’s Azure cloud and AI computing tools. The company will also provide education on artificial intelligence, informing project leaders of what’s available and how it works.
“Our goal is to empower others in new and more impactful ways to help create a more sustainable future,” said Microsoft. “This program expands our commitments to democratizing AI and advancing sustainability around the globe. And it builds upon our experience in accelerating the pace of innovation bringing together philanthropic work, connectivity advances and more accessible technology around the world.”
There are currently three “lighthouse” projects in AI for Earth.
- FarmBeats is a data-driven approach to farming that helps farmers improve their yield and lower costs.
- Project Premonition is tracking mosquitoes to monitor the spread of diseases.
- Land Cover Mapping is a fast land mapping system being used by an NGO to help conserve the Chesaspeake watershed.
Applications are currently open for groups looking to enrol in the program.
Big data analytics provides first world vegetation maps
Artificial intelligence and big data analytics have been applied to produce the first global map of the world’s regions where vegetation can and cannot be grown.
The Valencia University study assesses the global abundance of the phosphorus and nitrogen content in vegetation. Also assessed is the efficiency in water use. The scientists’ aim is to show where the best places are for agriculture and where environmental conditions are changing in response to climate change. The application of artificial intelligence and big data methodologies also enables an assessment to be made of our planet’s biodiversity.
Together with carbon, hydrogen, oxygen and sulfur, nitrogen and phosphorus are the principal chemical elements incorporated into living systems. They are strong signals of the suitability of different parts of the Earth for agriculture. Both nitrogen and phosphorus are needed by plants in large amounts (although excessive quantities can also cause environmental damage). In soil, nitrogen and phosphorus are typically found in the form of nitrates and phosphates.
The new global maps produced by the researchers gathered information from Google mass satellite observation data and then used a specially developed artificial intelligence program to assess the data and produce the color-coded maps. The satellites gathered temporal and spatial observations, and this produced a series of maps characterizing different biophysical parameters. To develop the maps required numerous observation-measurement pairings to be number crunched.
Speaking with Phys.org, lead researcher Álvaro Moreno explained why the maps were significant: “Until now, it was impossible to produce these maps because the required conditions weren’t available. We didn’t have powerful and accurate machine learning statistical tools, nor did we have access to great bodies of data or cloud computing.”
The new maps and the process behind them are published in the journal Remote Sensing, in a paper titled “Regional Crop Gross Primary Productivity and Yield Estimation Using Fused Landsat-MODIS Data” and an companion article in Remote Sensing of Environment titled “A methodology to derive global maps of leaf traits using remote sensing and climate data.”
The next steps are to use the technology to further assess the impact of climate change and to assess other important societal and ecological questions like the pressure on food production to meet population growth and the development of new technologies, like biofuel production.
Growing more with less – Using AI and robotics to grow crops
Startup Iron Ox has created a fully autonomous farm in San Carlos, California. The hydroponic indoor farm relies on two robots to plant, care for and harvest produce, and by doing so, they grow 30 times more produce than traditional farms.
San Carlos, California-based Iron Ox is a startup company founded in 2015 by Brandon Alexander and Jon Binney. The two founders decided to get into robotic farms after working at a number of other robotics companies. But as Alexander notes, in his stint at Google X, it was more about building cool technologies, rather than how robots could be used. As he told Tech Crunch, “We’d seen lots of novelty robotics stuff and wanted to avoid that.”
The two would-be urban farmers also realized that farming is very hard work. The U.S. alone has more than two million farms with 925,000 people to perform tasks like planting, seeding and inspection, contributing to total production expenses of $350 billion in 2017.
Then, there is the knowledge that agricultural productivity will need to increase by 60 percent in order to feed the world population by 2050. These factors inspired the young company to tap into a database of agricultural and horticultural knowledge, along with robotics, to design an indoor farm of the future.
Today, most of the leafy greens grown in the U.S. are produced in California and Colorado, particularly in the winter months when it’s colder in the rest of the country. So fresh leafy greens are actually two or three days old by the time they reach the supermarket. “That’s why we switched to indoors,” Alexander said. “We can decentralize the farm.”
The ‘robotics-first’ approach
“At Iron Ox, we’ve designed our entire grow process with a robotics-first approach,” Alexander said. “That means not just adding a robot to an existing process, but engineering everything … around our robots.”
In the company’s first 1,000-square-foot farm, which is already in full production, there is a 1,000-pound robot named Angus that can lift and move the large hydroponic boxes in which the produce is growing, and Iron Ox ’s robotic arm for all the fine manipulation tasks, like seeding and transplanting.
With this current setup, Alexander says they can produce about 26,000 plants per year — equivalent to the output of a one-acre outdoor farm. With this system, the farm grows leafy greens such as romaine, butterhead and kale, and herbs like basil, cilantro and chives — using sensors and collision avoidance systems “similar to that of a self-driving car.”
Alexander claimed that Iron Ox is able to do the equivalent of 30 acres of outdoor farming in just a single acre on its robotic farm. The company wants to build more small farms near urban centers so produce is fresher upon arrival. “Right now fresh produce really isn’t all that fresh. It’s traveling on average 2,000 miles from farm to grocery store, which means a lot of people are eating week-old lettuce or strawberries,” Alexander explained
5 Cargill digital initiatives making food production more sustainable
How the agriculture giant is using the cloud, AI and facial recognition tech to transform the agriculture industry
Agricultural production needs to increase by 70 percent globally by 2050 in order to keep pace with population growth and shifting diets, according to the UN.
Agriculture giant Cargill is turning to digital technology to tackle this challenge.
Whether through creating predictive software to give shrimp farmers real-time insights into their operations, or applying smart weather sensor technology to row crop irrigation to help farmers cut back on water usage, Cargill is creating IoT technologies to help farmers make their processes more sustainable.
“We are trying to bring digital transformation to the industry,” Neil Wendover, an executive from the Cargill Digital Insights department, told Bloomberg.
1. Mobile Shrimp Monitoring:
Cargill’s iQuatic software is a cloud-based digital platform specifically for aquaculture that syncs with a farm operations dashboard so farmers can monitor what’s going on in their farms using data collected in real-time.
iQuatic powers Cargill’s iQShrimp app, which receives data about shrimp size, water quality, feeding patterns, and health and weather conditions from shrimp ponds by way of sensors and automatic feeders.
This data is then sent to the app that uses predictive technology to give farmers insights and recommendations on feed management strategies for the shrimp, and the best dates for harvest.
2. Connected Crop Irrigation:
Cargill is also looking to help farmers on land by using smart weather sensors and IoT technology on sprinklers connected to smartphone apps to help Nebraska beef farmers cut back on water usage in crop irrigation.
“By using smart weather sensor technology in row crop irrigation, this program could help save 2.4 billion gallons of irrigation water over three years, which is equivalent to roughly 7,200 households over that time period,” said Hannah Birge, water and agriculture program manager at The Nature Conservancy about the partnership. “The reduction of pumping also means less energy used and less labor expense for farmers.”
3.Animal Facial Recognition:
Facial recognition is big these days — even on farms.
Earlier this year, Cargill invested in Cainthus, an Irish startup that has developed facial recognition for cows. Cainthus uses artificial intelligence and imaging software to identify and monitor individual animals on a farm. The cows are monitored for what they eat and how much milk they produce in an effort to help farmers manage their herd.
The images are collected from drones, satellites, CCTV, and smart devices.
Cargill also entered a partnership with Cainthus to bring its technology to dairy farms globally.
4. Cocoa in the Cloud:
Tracking and tracing cocoa shipments has largely gone untouched by technology. To change that, big companies like Cargill started utilizing mobile applications to get a better picture of where their cocoa comes from.
Traders from the companies, local traders and partner organizations started to collect GPS coordinates of each farm and details about the farmer themselves, like if the farm is within a protected forest area.
The system keeps a record of cocoa transactions, acting as a digital ledger. All this information is stored on a cloud-based database.
Cargill also has a target to commit to sourcing “fully traceable farm-to-factory cocoa” by 2030.
5. Techstars Farm to Fork Accelerator:
Last year Cargill partnered with tech startups Techstars and Ecolab to create the Techstars Farm to Fork Accelerator, a “mentorship-driven” program with a goal of safer, more secure and sustainable food supply.
Participants in the accelerator are expected to be tackling problems like supply chain management, food safety, waste reduction, and traceability.
“This Accelerator allows us to invest our time and resources in technology shaping the future of agriculture, and to address some of the greatest challenges facing the food system,” said Cargill’s CIO Justin Kershaw in a Cargill press release.
The accelerator is expected to continued for three years and it recently announced the inaugural class of startups who will spend 13 weeks building their businesses.
DX Journal covers the impact of digital transformation (DX) initiatives worldwide across multiple industries.