Excellent | Farming | SDG13 | SDG15 | SDG2 | United States

Monitoring global soil carbon stocks in agricultural lands

Share this post

1. General

Category

SDG 2: Zero Hunger

SDG 13: Climate Action

SDG 15: Life on Land

Category

Farming

2. Project Details

Company or Institution

Cloud Agronomics

Project

Monitoring global soil carbon stocks in agricultural lands

General description of the AI solution

Farmland is one of the world’s largest untapped carbon sinks. As crops grow, carbon is pulled from the atmosphere into the soil where it regenerates and enriches soil health. So called regenerative agriculture includes on-farm practices such as no-till, cover cropping, and precision fertilizer applications.

Historically, to quantify soil carbon levels in agricultural soils, the industry has relied on expensive and laborious in-field sampling. Within a field, soil carbon can vary significantly, so a few samples are not representative of the field-average. One can imagine that this problem is exacerbated when scaling soil carbon monitoring to millions of acres globally.

Cloud Agronomics solves this problem by leveraging AI and remote sensing to remotely quantify soil carbon levels for millions of fields around the world. We then augment our models with physical samples to meet registry requirements to generate verified carbon credits.

Cloud Agronomics provides low-cost soil carbon quantification at scale which enables the scaling of farmland carbon credit programs and regenerative agriculture. We are continuously decreasing the number of physical samples required on each field, and we do not require farmers to share data about what practices they are performing on the field.

The industry no longer has to rely on physical samples and spreadsheets. Cloud Agronomics provides soil carbon measurements and data visualizations which show how soil carbon varies in a country, or zoomed in, the variation within an individual field.

Website

https://www.cloudagronomics.com/

Organisation

Cloud Agronomics

3. Aspects

Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.

Recent developments in remote sensing, machine learning and the statistics of carbon quantification from space can overcome the challenge of SOC quantification at scale. Numerous peer-reviewed studies over the last decade have demonstrated that remote sensing methods based on optical satellite data can quantify SOC stocks. We have developed measurement techniques that combine information from satellite remote sensing with on-the-ground physical samples at thousands of locations using a proprietary dataset of SOC measurements in North American farmland. Our analyses show that using these remote sensing measurements to quantify SOC stocks produces uncertainty in compliance with with global voluntary registry requirements. Our work builds on decades of research in remote sensing of carbon, including the work of national space agency scientists focused on aboveground carbon density in forests and the rigorous propagation of uncertainty in statistical models to achieve confidence in carbon quantification. The output of this work is the quantification of SOC stocks (mass of C per unit area) and stock changes to a depth of 30 cm at high spatial resolution in croplands, pasture lands, and rangelands worldwide.

The details of Cloud Agronomics’ methodology and soil organic carbon algorithms have not been released publicly and are fully owned by Cloud Agronomics Inc.

Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.

Leveraging AI enables Cloud to track carbon stocks at a low cost and in regions where it may be difficult or cost-prohibitive to collect, store, and process soil core samples. This technology directly enables the management and improvement of regenerative agriculture (SDG2), which directly sequesters and stores atmospheric carbon into farmland soils to help reverse the effects of climate change (SDG13), while also protecting and restoring farmland, improving water-holding capacity, and preventing further environmental degradation.

Our global analysis is only made possible through publicly available datasets from governments, NGOs, and research organizations such as the USDA NCRS and the World Bank.

In terms of potential for impact, this technology can help answer some of the industry’s burning questions around permanence, additionality, and the rate of carbon sequestration. This could be the largest soil health experiment ever performed in agricultural soils.

Today, we are commercially up and running in the United States and Australia, and we are quickly expanding to emerging markets.

Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.

We have produced soil carbon measurements at the scale of millions of acres. Until we completely the need to collect physical samples on every field (today the goal is to decrease the number that are required from approximately 40 to 0), then a few physical samples are required in the target geography.

Based on the core data layers that Cloud Agronomics provides, our partners will be able to track:

– net farmland emissions (CO2, N20, CH4)
– which regenerative practices are most optimal to sequester soil carbon
– the permanence of agricultural lands as a carbon sink
– how quickly can soil sequester carbon in different geographies

We are actively engaged with international organizations and governing bodies to help modernize standards to incorporate AI and remote sensing into verifiable standards. Today, we are partnered with some of the world’s largest agribusinesses including those in equipment manufacturing, fertilizer production, inputs, ag financing, and more.

Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.

The goal is to use AI to learn from a dataset of physical samples collected in advanced geographies to enable the application of these models to areas where traditionally technology has been slower to proliferate once the models don’t require the same number of physical samples.

Cloud Agronomics meets all the components of Trustworthiness of AI solutions, and we have the highest standards for ethical and scientific rigor.

This technology has the ability to generate premium returns by focusing specific programs on farmers or areas that have been previously underserved including BIPOC and indigenous farmers, as well as those in regions where farming practices differ due to environmental degradation.

CONTACT

International Research Centre in Artificial Intelligence
under the auspices of UNESCO (IRCAI)

Jožef Stefan Institute
Jamova cesta 39
SI-1000 Ljubljana

info@ircai.org

ircai.org

FOLLOW US

The designations employed and the presentation of material throughout this website do not imply the expression of any opinion whatsoever on the part of UNESCO concerning the legal status of any country, territory, city or area of its authorities, or concerning the delimitation of its frontiers or boundaries.

Design by Ana Fabjan