NASA Harvest’s AI Lead Hannah Kerner to Co-Edit New Research Topic
In areas where it is common, smallholder agriculture is vital to the local economy and food security. These farms are often in rural zones and not easily connected to extensive infrastructure, complicating efforts of authorities to monitor production and yields. Additionally, many small-scale farmers, particularly in Africa and Southeast Asia, are lower income and are vulnerable to financial setbacks when natural disasters occur and agricultural production suffers. As smallholder farms are projected to continue to rise in number, it will only become more imperative to develop the ability to accurately monitor them—both for local food security as well as the financial wellbeing of the farmers.
EO-based agricultural monitoring requires data of a high temporal and spatial resolution and methods that are scalable and accurate. Given the typical size and composition of smallholder farms however, traditional analysis can be insufficient. Advances in artificial intelligence are helping overcome these difficulties. New techniques in machine learning combined with new data platforms have allowed for improved monitoring of crops at very high temporal and spatial resolutions. In particular the launch of new “small sat” satellite constellations and increased access to mobile devices for recording field observations have enabled the study of small-scale fields at unprecedented levels.
Harvest’s AI Lead, Hannah Kerner, is curating these new advancements in the journal AI in Food, Agriculture, and Water. Dr. Kerner, alongside her co-editors Dr. Lyndon Estes and Dr. Ernest Mwebaze, is currently leading a special issue on the topic “Advances in AI Applications for Small-scale Agricultural Systems”. They are accepting submissions that “demonstrate how AI can be combined with new data collection technologies to improve the ability to monitor, measure, and/or manage small-scale farms.” They are particularly interested in methods that have only become possible in the previous 3-5 years either through the development of new techniques or the creation of new data.
Some examples of desired topics are:
Large area mapping of small-scale croplands using satellites and deep learning models
Application of AI to satellite time series to map land use and land cover change in small-scale systems, including crop types and field dynamics
AI-assisted upscaling of on-farm sensor observations through drones to satellites
Multi-sensor data fusion approaches to enhance AI-based agricultural mapping and monitoring
AI-based combination of multi-source, variable quality field observations to detect agricultural signals (e.g. pest events, management activities)
Combining AI and process-based models to improve estimation of smallholder yields
The submission deadline for abstracts is March 1, 2021 and for manuscripts is June 30, 2021. Those interested in submitting a manuscript can find more information here. Those who would face difficulty in publishing due to lack of financial support may request fee support here.