Frequently Asked Questions

CIBO, a science-based software company, was founded by Flagship Pioneering in 2015 to apply science and technology to the scaling of environmentally and economically sustainable agriculture. By using big data, computer vision, remote sensing, and science-based modeling, CIBO delivers unique field-level insights at a national scale to empower users with the knowledge needed to take action.

Dr. Bruno Basso, an internationally renowned professor of earth and environmental sciences at Michigan State University, whose research into plant growth led the academic industry in that field, helped develop the platform. Dr. Basso founded CIBO in 2015 along with founder investor Flagship Pioneering. CIBO Impact™ is based on an exclusively licensed technology developed over 30 years from Michigan State University that simulates the way plants grow daily in varied environments. CIBO engineers scaled that core technology and augmented it with critical elements, including proprietary data science algorithms and artificial intelligence (AI) modeling applied to satellite imagery.
Both the technology and the approach are continually enriched with farmers’ collaboration around the country to validate data models and obtain feedback on insights and offerings.

Farmers are intimately knowledgeable about their parcels of land—we have no intention of replacing that. CIBO fills the information gap for any stakeholder who needs to make better-informed, objective decisions about land parcels with which he or she are not personally familiar. For example, when an individual purchases or leases a new piece of land or when a bank is considering approving a loan for a farmer.

Most agriculture applications focus on farm management, not the objective land evaluation that CIBO provides. Second, other offerings rely upon farmers or users to input local data about their land—CIBO uses a science-based approach that removes that data input burden from farmers’ shoulders.
Last, while other offerings might address farmland information elements, none deliver to individual users the same depth and scale of land information—at the parcel level and national scale—as what’s made available by CIBO. For instance:

• Only CIBO combines public data with proprietary insights driven by ecosystem simulation, computer vision, and data science to deliver comprehensive, science-based, and objective information about land parcels.
• Only CIBO delivers rich, accurate insights about land parcels via a single technology platform.

Our goal at CIBO is to create a new, common “language” that will help inform and drive any land stakeholder’s decisions, even those who aren’t personally familiar with a particular parcel.

CIBO has been independently verified by farmers. Affiliations:

• Farmer Advisory Network https://www.cibotechnologies.com/cibo-farmer-advisory-network/
• Field To Market https://www.cibotechnologies.com/blog/cibo-joins-field-to-market-the-alliance-for-sustainable-agriculture/

Some of the best minds in the industry back the proprietary data and insights provided by CIBO.
CIBO derives our unique data and insights by combining:

• an objective, scientific approach built upon more than 30 years of proven academic research across the U.S.;
• technology that simulates the way plants grow daily basis, in varied environments, which we exclusively license from Michigan State University; and
• powerful, breakthrough technologies like artificial intelligence (AI) and machine learning.

But we don’t rely upon science and technology alone. Our CIBO Farmers Advisory Network (CFAN) members and other farmers around the country helped us create and continually update the extensive, farm-level dataset used to test and validate the results of all of the models, simulations, algorithms, and insights that go into the CIBO platform. These farmer partners ensure all of CIBO’s science, products, and proprietary metrics are in keeping with reality.

Simply put, we replace the local land information, historically input by farmers with science.
The CIBO technology relies upon proven, scientific modeling that helps us understand “how a plant grows,” for instance. We generate rich insights from that kind of raw data by applying proprietary data science algorithms, computer vision, and AI modeling to remotely sensed data (such as satellite images). Then we combine those insights with easy access to publicly available data for a unified set of rich land details about each parcel.
Since we value—but don’t rely upon—local data input by farmers, we unburden farmers from inputting data details about their land and enabling our insights to scale infinitely.

Regarding Field Management: Remote sensing is a significant source of verification data because it scales well. We would use remote-sensed methodologies for crop rotation, cover cropping, and tillage for verification. If that fails, we will use other verification methods, depending on specific circumstances. For example, suppose we cannot verify a crop rotation using remote sensing. In that case, we might ask the grower for electronic planting records from a combine as evidence that the specified crop rotation occurred. Remote-sensed methods will work in the vast majority of cases; we will deal with the exceptions on a case-by-case basis.  
Regarding Nitrogen Application: One exception to this rule is nitrogen application. Growers upload electronic records of nitrogen application. These files are called “As Applied” files and are produced by a combine as a real-time record of nitrogen fertilizer application amounts. These files are tagged to a specific geographical location and have a timestamp, so they are good evidence of how much nitrogen fertilizer was applied to a field in a given year. 
Regarding Tillage and Remote Sensing: Different tillage types leave different amounts of residue on the field. These differing amounts of residue result in different near-IR “signatures”; using infrared and near-infrared wavebands, we apply residue indices. This sensing tillage method is similar to the process used to develop NDVI and other spectral indices. 

CIBO’s proprietary algorithms update continuously based upon real-time data—such as weather information and satellite imagery—to reflect the latest market and on-the-ground developments. CIBO data and insights that feature different types of in-season forecasts—such as yield forecast, planting acres, and harvest status—also continually update during the growing season.