Lars Dyrud is the CEO of EarthOptics, and he wants to make the soil healthier.
Carbon sequestration in soil is a critical piece of the climate change mitigation puzzle. Almost 45 percent of the world’s soil is used for agriculture, and soil can store about 2.3 times the amount of carbon compared to carbon in atmospheric CO2 and 3.5 times more than in living plants.
According to Global X, their Charting Disruption 2022 report found that by 2050, cumulative investment in clean technology is expected to reach between $ 94 million and $ 131 million, depending on the decarbonization scenario.
EarthOptics’ new Soil Carbon Project labeling initiative is designed to help producers and the food industry quantitatively demonstrate to consumers that the climate-smart products they have purchased have contributed to global carbon neutrality goals.
“Consumers will know that every time they buy food from the grocery store with the carbon weight attached, they will know that the labeled amount of carbon was added to the soil in the year the food was grown, where it has been cultivated, ”Dyrud added.
The critical value is to create a long-term incentive structure linking consumer choices to the activities of producers and farms that drive more carbon into the soil every year, ”adds Dyrud.
Use AI and ML
To make this work, EarthOptics uses machine learning (ML) and teaches its artificial intelligence (AI) to read every attribute in the ground from the ground penetrating radar and electromagnetic induction scanning of attributes in the ground.
Dyrud says their approach is carbon focused. “Soil carbon is only a small percentage of soil mass, and small changes are hard to measure. A change in one tonne of soil carbon (the standard carbon credit amount) on an acre of soil weighing 2,000 tonnes is difficult to measure.
“The attributes surrounding compaction and low carbon are closely related, so EarthOptics scours fields scanning and identifying compaction, knowing carbon conductivity, and taking soil samples for validation with machine learning,” we’re teaching AI to read attributes in soil at an accurate rate, ”Dyrud added.
Dyrud says the sample and pixel rate is currently measured with an accuracy of less than one sample per acre, with the standard rate being one sample per five acres. “The current method of soil sampling is labor intensive fieldwork with a level of imprecision due to the skill of sampling, and it has not changed for 80 years. Dyrud said.
“Traditionally, you would take a sample, package it, send it to the lab, and the lab does a test,” Dyrud said. “But using AI and ML, precision is simplified to plot a model in the field, visualized from the GPR data with digitized information uploaded to the AI, then published to the cloud and available to the farmer. . ”
Dyrud says AI improves with every field uploaded to the cloud, and ML helps unravel the complexity by interpreting data from sensors in the field to isolate only the influencing factor of interest as long as there is enough soil samples to form the ML model.
Climate-smart packaging awareness
“Consumer packaging companies partnering with EarthOptics will be able to accurately measure and display on climate-friendly product packaging the amount of carbon removed from the atmosphere and stored in the ground where the ingredients are crops were harvested, ”Dyrud said.
Dyrud says the Soil Labeling Project is designed to educate consumers and people in the food industry and food production about their role in removing carbon from the atmosphere.
“For example, all factories are built from atmospheric carbon. Less than half a dollar more for a box of ‘carbon cornflakes’ could generate hundreds of dollars per acre for food producers and a significant incentive to stimulate both producer practices and innovations in food production. way to get more carbon in the soil, ”Dyrud said. “It can all be driven by consumer choice. “
EarthOptics has raised $ 10.3 million, led by Bayer’s venture capital arm, to expand adoption of its AI / ML soil carbon monitoring tools in farmland.