Reviewed by Lexie CornerDec 2 2024
Researchers from Brazil and Spain are using sensors installed in drones and agricultural equipment, along with satellite imagery, to forecast the best time to harvest, reduce CO2 emissions, and manage water use in plantations. They presented their work at FAPESP Week Spain.
Image Credit: Nikolai Tsvetkov/Shutterstock.com
Peanut (Arachis hypogaea L.), potato (Solanum tuberosum), and sweet potato (Lpomoce batatas) growers face challenges in predicting the optimal harvest time, as well as assessing crop quality and yield. These crops are subterranean, meaning the fruit grows underground and is not visible until harvest.
To harvest peanuts, 70 % of the pods must be ripe, and to check this, you have to pull the plants out of the ground and make a visual assessment. This operation, called uprooting, also ends up mobilizing the land and, consequently, emitting CO2 [carbon dioxide].
Rouverson Pereira da Silva, Professor, São Paulo State University
By using artificial intelligence tools, sensors in agricultural machinery, and remote sensing technologies like satellite or drone imagery, the researchers have developed computer models that help growers assess the maturity and yield of crops such as peanuts by remotely examining the plant’s leaves. This method can reduce CO2 emissions from heavy tillage and improve productivity.
Silva presented some of the findings from this FAPESP-supported project during a panel discussion on soil health within the context of digital agriculture at FAPESP Week Spain, held on November 27th and 28th, 2024, at the Complutense University of Madrid (UCM) Faculty of Medicine.
Santos added, “The models we have developed can estimate the maturity of peanuts, for example, with more than 90 % accuracy, eliminating the need for uprooting. In the case of sweet potatoes, we were even able to estimate the size of the crop.”
“Through the estimates made by these computer models, it is possible to work with more appropriate regulations to improve the efficiency of the harvesting process and, at the same time, reduce losses, because by estimating the productivity of crops, it is possible to regulate agricultural machinery to harvest more appropriately,” added the researcher.
The researchers used images captured by cameras on drones or satellites to measure the reflectance of the plant—the amount of solar energy reflected in both visible (green, yellow, and blue) and invisible (infrared, near-infrared, and red edge) bands—to accurately estimate crop maturity. Maturity indices can be calculated based on this reflectance data.
Da Silva noted, “Reflectance reveals the health of the plant. Diseased leaves have different colors and reflect the sun’s energy differently. And the healthier the plant is, the more it will produce.”
According to da Silva, the initiative is currently in the process of transferring the technology to producers, which is a time-consuming and challenging task.
“This phase is time-consuming because to carry out a project of this magnitude, we have to go out into the field and uproot thousands of plants over the years to get the data we need. In addition, there are different varieties of peanuts, for example. That is why we have not transferred the technology yet, because growers change the varieties they plant over the years, and we need to have a robust model that can make predictions under different conditions,” he explained.
Saving Water
Researchers from Brazil's State University of Campinas School of Agricultural Engineering (FEAGRI-UNICAMP) have developed soil moisture maps for sugarcane plantations using a miniature radar system installed in drones.
In collaboration with IBM Brazil, the scientists have created technology through a project funded by FAPESP, which enables the estimation of water availability in different areas of a crop. This technology is based on the interaction of frequency waves emitted by the radar system in three different bands, which not only touch but also penetrate the soil.
This research resulted in the establishment of Radaz, a business supported by the Innovative Research in Small Businesses Program (PIPE).
The accuracy of the system in estimating the relative humidity of a monitored soil plot is greater than 90 %.
Barbara Janet Teruel Medeiros, Professor and Project Member, Faculdade de Engenharia Agrícola
Tests on sugarcane fields in the state of São Paulo, along with validation using conventional techniques and field trials, were integral to the development of the system.
“We were able to predict the productivity of this crop well in advance, in terms of the amount of biomass that would be produced when it reached maturity, as well as the best date for harvesting,” stated Medeiros.
They emphasized that factors like water runoff, porosity, and soil moisture levels can vary across a field. By assessing the soil moisture of a plantation, variable-rate irrigation systems can be implemented, allowing for more efficient water use.
“In this way, it would no longer be necessary to open the irrigation system to release an unnecessary amount of water. It would be possible to adjust it to release the optimum amount for a given patch of soil, avoiding saturating certain areas or leaving shortages in others where levels are below what is needed for the crop to grow,” she explained.
Researchers from the Institute of Agricultural Sciences of the Spanish National Research Council (ICA-CSIC) have also been involved in two recent European projects with similar objectives.
The first project, known as the DATI project, involves researchers from Spain, Italy, Morocco, Portugal, and France. It aims to promote the development of new technological solutions in digital agriculture by utilizing drones, satellite imagery, and agro-meteorological stations to reduce water consumption by 15 % to 20 % compared to conventional irrigation systems.
The CSIC is leading the Earth Observation for Water Use Efficiency project, which seeks to develop Earth observation-based tools for managing and evaluating the productivity of cereal crops and pastures in the Mediterranean region, with a focus on improving water use efficiency.
We need to provide precision farming solutions because we know that soil is not homogeneous and plants do not develop in the same way across the entire surface. That is why we cannot manage an entire area in the same way. The idea is to divide it into zones so that we can really do site-specific treatment or management.
Irene Borra, Researcher, ICA
Using measurements based on evapotranspiration (the loss of water from the soil by evaporation and from the plant by respiration) and images captured by unmanned aerial vehicles, the Spanish researchers hope to improve the precision of identifying water stress (lack of water) in grapevines.
“We are drawing up maps that show us areas where everything is really good in terms of water and others that we need to take care of because they show water stress,” added Borra.