The Linux Foundation’s AgStack project to build the world’s first global dataset of agricultural field boundaries
AgStack, a project of the Linux Foundation.
The Linux Foundationa global nonprofit organization that enables innovation through open source, today announced that its agstack project will house a new open source codebase, along with a fully automated continuous computing engine, to create, maintain and host a global agricultural field boundary “record” dataset to assist in things like food traceability, carbon monitoring, crop production. and other analyzes at the field level.
AgStack will use machine learning and artificial intelligence to manage global field boundary data for public use.
The contributed code is based on research by Dr. Sherrie Wang, Dr. Francois Waldner, and Professor David Lobell of Stanford University’s Center for Food Safety and the Environment, and is funded by organizations such as the NASA Harvest Consortium.
AgStack’s asset record dataset, the first of its kind in the world, is continuously built and updated using satellite data and real field records containing boundary information, not ownership, which will then train machine learning models to determine more limits.
Precise knowledge of field boundaries can help farmers, agribusinesses and the public sector to control and manage crop production, study management practices (crop rotation, cover crops, tillage, irrigation), determinants of productivity, spread of pests and diseases and diversity of species. . By sharing reusable agricultural data, new insights can also be gained for global food security research and innovation.
Crop field boundaries are the fundamental unit for addressing such datasets in agriculture worldwide, but they are rarely available as public datasets, especially in smallholder regions. According to the FAO, there are more than 1.5 billion hectares of arable land in the world (approximately 12% of the world’s land area). With the average field size of more than 80% of farms being less than one hectare, this equates to more than 1.2 billion active field boundaries, constantly changing throughout the growing seasons.
Leveraging computing and artificial intelligence, members will create, curate and maintain global field boundaries as an open source digital public good available for anyone to use. The project has the potential to unlock the next revolution of digital agricultural services in the public and private sectors, especially for small farmers.
“Creating and maintaining a global, inclusive, neutral, and business-independent data set has been challenging for a number of reasons,” said Dr. Wang, who will continue to contribute to research as an incoming assistant professor in the Department of Mechanical Engineering from MIT. and the Institute for Data, Systems and Society. “Now is the time to do this. We rely on deep learning and satellite images to efficiently delineate crop fields on a planetary scale. The next steps are to scale the algorithm, release the dataset as a public good, and maintain and improve it over time.”
The research seeks to enable all kinds of agricultural data analytics and services by uniting computing and AI research expertise with a global network of partners in an open source software ecosystem, which is what the Linux Foundation was created to do.
“We believe that a public field boundary dataset can help empower many smart individuals and companies focused on improving agriculture and food security around the world,” said Lobell, who hosted the original research as Director. by Gloria and Richard Kushel of the Center for Food Security and the Environment at Stanford University and the Benjamin Page Professor of Earth System Sciences. “We are excited to help bring this dataset to life.”
All code will be contributed under an open source license and will be governed by the AgStack community within the Linux Foundation, using permissively licensed and open source tools and processes.
“We are thrilled to host this groundbreaking research and work with the university community to create machine learning models and approaches that can enable this powerful global dataset,” said Sumer Johal, executive director of the AgStack Project at the Linux Foundation. “The contribution of this code will launch an ecosystem-wide invitation to public and private sector stakeholders to ensure the availability of this data as a neutral, trustworthy and secure public good. Together we can help remove roadblocks related to working with field boundary data in a community-driven way.”
About The Linux Foundation and AgStack: The Linux Foundation is the world’s largest nonprofit organization connecting global technical experts and providing them with a neutral and trusted platform to develop open source projects. Founded in 2000 as the home of the Linux kernel, the Linux Foundation has grown to house hundreds of open source projects, with a community that includes more than 2,950 members, more than 540,000 contributing developers, and more than 19,000 contributing companies. AgStack is an open source digital infrastructure project for the global agricultural ecosystem, under the umbrella of the Linux Foundation.
Media Contact:
Noah Lehman
nlehman@linuxfoundation.org
The Linux Foundation