Recently, Farian Severine Ishengoma, a Sokoine University of Agriculture staff member studying at the University of Rwanda in collaboration with colleagues from the State University of Zanzibar and the University of Rwanda published two papers on the prestigious journals of Computers and Electronics in Agriculture and Ecological Informatics.
The first paper titled “Identification of maize leaves infected by fall armyworms using UAV-based imagery and convolutional neural networks.” The goal of this study was to use artificial intelligence-based automatic recognition algorithm models (Convolution Neural Network) to precisely detect maize leaves infected with fall armyworms (faw). During scouting, an unmanned aerial vehicle (UAV) using remote sensing technologies captured images, allowing the team to cover a large area in a short period of time. This process of automatic detection of healthy crops from images helps farmers increase yield and profit while reducing input costs and time. For more details, visit https://doi.org/10.1016/j.compag.2021.106124
In the second paper, titled "Hybrid convolution neural network model for a quicker detection of infested maize plants with fall armyworms using UAV-based images," they expanded their work by including an automatic notification system that notifies farmers via short messages (SMS) and electronic mails about the percentage of infected leaves, healthy leaves, and weeds in the field. For more details, visit https://doi.org/10.1016/j.ecoinf.2021.101502
Their future work will be to develop an algorithm that will pinpoint the location of all infected leaves, allowing farmers to spray only the areas that are affected by the disease.
Share this page
