• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer
  • Skip to navigation
Close Ad

The Spoon

Daily news and analysis about the food tech revolution

  • Home
  • Podcasts
  • Events
  • Newsletter
  • Connect
    • Custom Events
    • Slack
    • RSS
    • Send us a Tip
  • Advertise
  • Consulting
  • About
The Spoon
  • Home
  • Podcasts
  • Newsletter
  • Events
  • Advertise
  • About

Alphabet

January 13, 2023

Google’s Farm Tech Moonshot Mineral Becomes Alphabet Company

Google parent company Alphabet has added a new company to its portfolio this week in Mineral, a farm tech startup that spent the last five years incubating within Google’s X.

The news of Mineral’s graduation to full-fledged Alphabet company came in the form a blog post by Mineral CEO Elliott Grant (previously of Shopwell, a shopping startup sold to Innit). According to Grant, the mission behind Mineral is to “help scale sustainable agriculture”, which they are doing by “developing a platform and tools that help gather, organize, and understand never-before known or understood information about the plant world – and make it useful and actionable.”

According to Mineral, they have analyzed over 10% of the total farmland on Earth, modeled more than 200 plant traits, phenotyped 17 crop varieties, and developed more than 80 high-performance ML models. Mineral’s ag-optimized analysis tools will be used to process large unstructured sets of the world’s agricultural data, sourced from satellite images, farm equipment, public databases, and Mineral’s own proprietary data streams. The company will make this data available to partners to combine this data with their private data to derive insights into yield, genomic understanding, and agronomic discovery.

One such partner is Driscoll’s. The large berry company has been working with Mineral to explore ways to improve data collection in its breeding operations and work on better yield forecasting. The two also worked together to enhance berry inspection using Mineral’s perception tools and, according to Driscoll’s, was able to build a system that many believe performed similarly to human experts.

Another Mineral project Mineral was the creation of a special crop-roving robot named Don Roverto. Don Roverto was used by Mineral to assist the Alliance for Biodiversity and CIAT to accelerate their work to understand and uncover hidden crop traits within the world’s largest bean collection. Using Don Roverto, the Alliance, after thirty years of searching, found a “magic” bean with intrinsic drought-resistant characteristics.

Google has often used X to incubate mission-based startups, and Mineral is no different. According to Grant, they chose ag as a vertical because it is “increasingly believed to be a major contributor to the climate crisis — but it is also a victim of a changing climate. There is no time to waste to find more climate-resilient crop varieties, to transition to less chemical- and fossil fuel-intensive practices, to improve soil health, and to restore biodiversity.”

March 8, 2022

Meet Don Roverto, X’s Robotic Rover on the Hunt for The Next Magic Bean to Feed a Hungry Planet

When you spend thirty years looking for a magic bean, you’re open to a helping hand when trying to find the next one. For the Alliance of Bioversity International and CIAT, that help has arrived in the form of a crop-roving robot nicknamed Don Roverto.

The farmbot is part of Project Mineral, an endeavor from X – Google’s famous R&D subsidiary that researches challenging problems and searches for moonshots – to scale sustainable agriculture. In a blog post published today, project head Elliott Grant describes how Mineral has been assisting the Alliance for Biodiversity and CIAT to accelerate their work to understand and uncover hidden crop traits within the world’s largest bean collection.

From the post:

The Alliance’s team has been using Mineral’s technologies at their newly opened Future Seeds genebank in Colombia, which contains over 36,000 varieties of beans. The hope is that what the Alliance discovers with Mineral’s tools can be used to grow better beans for the world, faster.

According to Andy Jarvis, the Associate Director-General with the Alliance, the organization has spent decades building and analyzing its bean collection. Finally, after thirty years of searching, they found a “magic” bean with intrinsic drought-resistant characteristics. With tools like Don Roverto, the organization can process its discoveries at lightning speed and find the next game-changing bean faster than ever before.

Don Roverto’s machine vision scanning crop traits

The rover is currently roving around the test field outside of the Alliance’s Future Seeds facility in Columbia to capture imagery of bean plants. It uses machine learning to identify characteristics such as leaf count, leaf area, leaf color, flower count, plant count and pod dimensions. Don Roverto does this for every plant in the field, so it can report how the plant has changed when it comes back the next week.

Alliance researchers say the rover is already enabling them to measure crop traits with far greater speed, frequency, and accuracy than has been possible before. For example, they can now see how a bean plant is flowering — which can help them better understand how it will cope and continue to reproduce in response to different environmental stressors, like hotter temperatures and droughts. Previously, it was nearly impossible for researchers to track this because the different components of flowering are so subtle. Now researchers can capture flowering, as it’s happening.

X’s Mineral team is continuing their work with the Alliance to better understand and map the various crops across the organization’s seed banks, but is also looking to expand their efforts with others who are interested.

You can learn more about the Mineral project and see Don Roverto roving and scanning in the video below.

Uncovering the hidden magic of beans with X's Project Mineral

December 8, 2020

Google Takes on Food Waste With Food Tech Innovations Built by X

X, the “moonshot factory” of Google parent company Alphabet, announced today that two prototypes developed as part of a project called Project Delta have graduated and are now being transferred to Google for scaling and commercialization.

Project Delta, which has been incubating within X for the past two and a half years, was led by Emily Ma, who announced the transition to Google today in a blog post.

From the post:

Our team’s mission was to create a smarter food system — one that knows where the food is, what state it’s in, and where best to direct it to ensure it doesn’t end up in a landfill and instead goes to the people who need it most. After two and a half years of prototyping and testing a range of technologies to help reduce food waste and food insecurity, I’m pleased to share that some of our prototypes and team are moving to Google so we can scale up our work.

In her post, Ma highlights two prototypes developed as part of Project Delta. The first is an “intelligent food distribution network” nicknamed “dana-bot.” To build dana-bot, the X team took a dataset donated by the Southwest Produce Cooperative, categorized and standardized each entry, and then used it to match food in food banks and pantries based on “real-time needs in the Feeding America network.” Grocery chain Kroger also leveraged dana-bot to manage excess deli products, which allowed it to open up “millions more meals to communities that need it.”

Above: Project Delta’s prototype food identification and categorization system uses machine learning to automatically identify different types of food.

The second prototype utilized computer vision and machine learning to capture images of food thrown out in Alphabet kitchens. After running it in 20 different units across Alphabet cafes over a period of six months, the system was “able to automatically collect two times as much information about the kitchen’s food waste as the manual system.”

And now these two systems are graduating to Google proper, where Ma says her team hopes to “start tackling food waste and food insecurity on a larger scale.” The team plans to roll out its computer vision system to more Alphabet kitchens and utilize Google’s resources to expand the food distribution network and eventually offer it to other organizations.

As more and more venture funding pours into the future of food, it looks like big tech is starting to also wake up to the possibilities of applying their technology innovation to creating a new food system. Google is no exception. This news is just the latest development from Google and its parent company Alphabet that could have larger-scale implications on the broader food system.

Last week Alphabet announced that its DeepMind group had used AI to help solve a grand challenge around protein structure prediction that the scientific community had been working on for half a century. In August, Google Lookout added food label reading to help the visually impaired, and back in 2017 the company unveiled that its Lens visual discovery technology could serve up recipe suggestions based on images of food.

Primary Sidebar

Footer

  • About
  • Sponsor the Spoon
  • The Spoon Events
  • Spoon Plus

© 2016–2025 The Spoon. All rights reserved.

  • Facebook
  • Instagram
  • LinkedIn
  • RSS
  • Twitter
  • YouTube
 

Loading Comments...