Unlock stock picks and a broker-level newsfeed that powers Wall Street. Upgrade Now
Google's X spins out Heritable Agriculture, a startup using AI to improve crop yield

In This Article:

Google’s X "moonshot factory" this week announced its latest graduate. Heritable Agriculture is a data- and machine learning-driven startup aiming to improve how crops are grown.

As the firm noted in an announcement post published Tuesday, plants are incredibly efficient and impressive systems. “Plants are solar powered, carbon negative, self-assembling machines that feed on sunlight and water,” Heritable wrote.

Yet agriculture puts a massive strain on the planet and its resources, accounting for around 25% of anthropogenic greenhouse emissions. It’s the planet’s largest consumer of groundwater and can lead to soil erosion and water pollution via pesticides, fertilizers, and other chemicals.

The newly independent startup is approaching these global issues by doing what Google does best: analyzing massive datasets through artificial intelligence and machine learning. Data collection is the easy part, relatively speaking. The hard part is transforming all that data into actionable instructions for growers to help bring the 12,000-year-old industry into the 21st century.

Heritable Architecture’s seeds were planted by founder and CEO, Brad Zamft. The physics PhD served as a program officer and fellow at the Bill & Melinda Gates Foundation before spending a year as the chief scientific officer at a venture-backed startup called TL Biolabs. Eight months later, in late 2018, Zamft joined Google X, quickly becoming the project lead of what would become Heritable.

<span class="wp-block-image__credits"><strong>Image Credits:</strong>Heritable Agriculture</span>
Image Credits:Heritable Agriculture

“I was given broad purview to work on whatever I wanted, as long as it could scale to a Google-size business,” Zamft tells TechCrunch. “That was the mandate. The idea of how do we get better at optimizing plants stuck with me and it gained traction with the leadership. We did a very good job moving through the gauntlet that is Google X.”

Using machine learning, Heritable analyzes plant genomes to determine combinations that could improve crop production. By way of example, Zamft writes, "By understanding those genomes, the crops can then be bred with climate-friendly traits for increased yields, lower water requirements, and higher carbon storage capacity in roots and soil."

The models the company built were tested on thousands of plants, grown to those specifications within a "specialized growth chamber” at X’s Bay Area headquarters. The researchers also conducted field work at sites in California, Nebraska, and Wisconsin.

Zamft explains that CRISPR-fueled gene editing will eventually play a role in making plants “programmable.” For now, however, Heritable is focused on more conventional methods.


Waiting for permission
Allow microphone access to enable voice search

Try again.