January 18, 2023

By Lynda Kiernan-Stone, Global AgInvesting Media

After being in development for five years at Alphabet’s moonshot lab – X, Google’s parent company has officially debuted its newest portfolio company, Mineral (ML). 

With a mission to scale sustainable agriculture, Mineral is designed to gather, organize, and uncover the deepest understanding yet of the plant ecosystem with the goal of making it actionable and beneficial for farmers and food supply chains.

To achieve this, the company is focusing on three key areas: developing sensor technology to generate deep data sets on plants; organizing data from diverse sources for machine learning and develop powerful software algorithms; and conducting meaningful research to advance our understanding of the plant world. 

Mineral CEO Elliott Grant expressed how agriculture is both a cause and a victim of climate change, making it critical that we gain a better understanding of plant genetics, the environment, and new approaches to farm management. 

“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,” wrote Grant in a Mineral blog post.

“We are confident the foundational technology (such as generative artificial intelligence, machine learning and edge compute power) has matured to the point where we can solve problems at the scale needed for production agriculture and with the accuracy and speed demanded by farmers.”

The technology is there, but the data needed to fully leverage these capabilities is lacking, according to Grant who said, “We found that most companies are not collecting the quantity, diversity, or quality of data needed to take full advantage of machine learning.”

Acknowledging that there is not a single form of data collection that would benefit every crop or task, Mineral approached the challenge by developing hardware, software, advanced perceptions technology and data science tools to gather, curate, clean, and augment multimodal datasets, and that would enrich the contributions of human experts, not replace them. 

The company analyzes huge volumes of multimodal, unstructured sets of agricultural data sourced from satellite images, farm equipment, public databases, and Mineral’s own proprietary data streams.

It also has developed and deployed an advanced camera-equipped roving robot nicknamed Don Roverto that has been used by the Alliance of Bioversity International and CIAT, navigating test fields of bean plants using machine learning to identify and track granular traits including leaf count, leaf area, leaf color, flower count, plant count, and pod dimensions for each plant in the field.

To-date, the ML team has analyzed more than 10 percent of the world’s total farmland, modeled more than 200 plant traits, phenotyped 17 crop varieties, and developed more than 80 high-performance ML models. Partners can combine this data with their private data to attain greater insight into yields, genomics, or agronomic discovery, according to the company.

Indeed, farmers, researchers, and breeders on five continents are already being helped to predict crop output, increase production, target pests and weeds, reduce waste, and reduce the negative impacts of agricultural production. 

“Software can help overcome the technology accessibility barriers that have historically held back farmers worldwide,” noted Grant. “While high performing seeds, fertilizer, and equipment can be hard for farmers to find – data, advice, and the power of ML will reach anyone with access to a smartphone.”

~ Lynda Kiernan-Stone is editor in chief with GAI Media, and is managing editor and daily contributor for Global AgInvesting’s AgInvesting Weekly News and  Agtech Intel News, as well as HighQuest Group’s Unconventional Ag. She can be reached at lkiernan-stone@globalaginvesting.com.

*The content put forth by Global AgInvesting News and its parent company HighQuest Partners is intended to be used and must be used for informational purposes only. All information or other material herein is not to be construed as legal, tax, investment, financial, or other advice. Global AgInvesting and HighQuest Partners are not a fiduciary in any manner, and the reader assumes the sole responsibility of evaluating the merits and risks associated with the use of any information or other content on this site.