In the lush, undulating landscapes where coffee plants stretch towards the sky, a silent revolution is taking place. High above the verdant fields, unmanned aircraft are capturing data that could redefine how we approach precision agriculture, particularly in the coffee sector. This isn’t science fiction; it’s the cutting-edge work of Nicole Lopes Bento, a researcher from the Department of Agricultural Engineering at the Federal University of Lavras in Brazil.
Bento and her team have been exploring the use of Remotely Piloted Aircraft Systems (RPAS) and machine learning to detect the application of chitosan, a biostimulant, on coffee plants. Chitosan, derived from chitin, is known for its ability to enhance plant resilience to water stress, acting as a natural antitranspirant. By leveraging spectral data from RPAS-acquired images and advanced machine learning techniques, the researchers aim to differentiate between plants treated with chitosan and those that are not.
The study, published in the European Journal of Remote Sensing (translated from the original Italian name, Rivista Europea di Telerilevamento), focuses on two coffee cultivars, Catucaí Amarelo 2SL and Catuaí Vermelho IAC 99, over a two-year period. The images were captured using a 3DR SOLO aircraft equipped with a Parrot Sequoia sensor, processed with PIX4D Mapper software, and analyzed using QGIS and RStudio. The results are promising, with the random forest (RF) classifier showing high accuracy in distinguishing between treated and untreated plants.
“This method not only helps in identifying the presence of chitosan but also supports precision agriculture practices,” Bento explains. “By understanding how chitosan affects plant physiology under water stress, we can optimize irrigation and fertilizer use, leading to more sustainable and efficient farming practices.”
The implications for the coffee industry are significant. Precision agriculture, driven by data and technology, can lead to more efficient use of resources, reduced environmental impact, and potentially higher yields. For coffee growers, this means better management of water and nutrients, which are critical in regions prone to drought and water scarcity.
But the impact doesn’t stop at the farm gate. The energy sector, which often relies on agricultural by-products for biofuels, stands to benefit as well. More efficient farming practices can lead to a more reliable supply of biomass, reducing the need for fossil fuels and contributing to a more sustainable energy mix.
As Bento’s research continues to evolve, the potential for scaling up these technologies becomes increasingly apparent. “The future of agriculture lies in the integration of technology and data,” Bento says. “By harnessing the power of RPAS and machine learning, we can create smarter, more resilient agricultural systems that benefit both farmers and the environment.”
The work of Bento and her team is a testament to the transformative power of technology in agriculture. As we look to the future, the skies above our fields may hold the key to more sustainable, efficient, and profitable farming practices. The integration of RPAS and machine learning is not just a technological advancement; it’s a step towards a more resilient and sustainable future for agriculture and the energy sector.
