A new study reported by the journal Remote Sensing of Environment, with researchers affiliated with the Brazilian Agricultural Research Corporation (EMBRAPA) and the State University of Campinas (UNICAMP), a new AI-powered method of identifying Crop-livestock integration areas by analyzing satellite images.
What makes these systems special is that they improve soil fertility, raise yields, and help to rehabilitate degraded areas. They do all this while reducing the use of pesticides, mitigating the risk of erosion and the seasonality of production, and lowering operating costs.
CLIs combine the growing of crops in rotation or consortium, especially grain crops such as soybeans, corn, and sorghum, and forage plants used to feed cattle and pigs, with the raising of livestock. The crops provide most of the cash income, while the livestock has food available during the dry season and facilitates seed management.
Overall, this makes farming more sustainable with crops benefiting livestock and vice-versa; the environmental impact of agricultural activity falls; and the carbon footprint is reduced. This is a big deal as the impact of agriculture on the environment has been a growing concern.
Inácio Thomaz Bueno, the first author of the article said, “The main aim of the project, which was an international collaboration to address issues relating to sustainable agriculture, was to promote the integration of remote sensing data with satellite images using AI, precision agriculture and biogeochemical models to understand and create models of the dynamics of this type of system,”.
A forest engineer, Bueno conducted postdoctoral research on the monitoring of CLI systems using remote sensing data and satellite imagery with high spatiotemporal resolution. He went on to say, “We also aimed to increase knowledge of CLI, given the many questions still open and the lack of effective methods for monitoring and development of its potential,…”
Continuing, “as well as the need to identify areas in which it’s being practiced, in line with the UN’s Sustainable Development Goals [SDGs] relating to agriculture, the environment, and economic and social development,“.
According to the report, the team used deep learning techniques to process satellite imagery time series and extract patterns pointing to areas where CLI was being practiced. The study sites were in the states of São Paulo and Mato Grosso.
Object-based image analysis was performed at intervals of 10 and 15 days in four steps. First CLI data acquisition via Planetscope, a constellation of satellites that capture high-resolution images of Earth’s surface.
Then by showing changes in the areas over time, the training of algorithms recognize patterns associated with CLI, which map CLI areas. Finally, there is an assessment of the model’s accuracy by comparing automatic results with previous knowledge.
For Bueno, the promising results obtained by this method have many positive outcomes, “Precise identification of CLI areas permits more efficient resource management to optimize land allocation and use. In addition, diversification of activities offers farmers an additional source of income.”