Abstract
Nuru is a deep learning object detection model for diagnosing plant diseases and pests developed as a public good by PlantVillage (Penn State University), FAO, IITA, CIMMYT, and others. It provides a simple, inexpensive and robust means of conducting in-field diagnosis without requiring an internet connection. Diagnostic tools that do not require the internet are critical for rural settings, especially in Africa where internet penetration is very low. An investigation was conducted in East Africa to evaluate the effectiveness of Nuru as a diagnostic tool by comparing the ability of Nuru, cassava experts (researchers trained on cassava pests and diseases), agricultural extension officers and farmers to correctly identify symptoms of cassava mosaic disease (CMD), cassava brown streak disease (CBSD) and the damage caused by cassava green mites (CGM). The diagnosis capability of Nuru and that of the assessed individuals was determined by inspecting cassava plants and by using the cassava symptom recognition assessment tool (CaSRAT) to score images of cassava leaves, based on the symptoms present. Nuru could diagnose symptoms of cassava diseases at a higher accuracy (65% in 2020) than the agricultural extension agents (40–58%) and farmers (18–31%). Nuru’s accuracy in diagnosing cassava disease and pest symptoms, in the field, was enhanced significantly by increasing the number of leaves assessed to six leaves per plant (74–88%). Two weeks of Nuru practical use provided a slight increase in the diagnostic skill of extension workers, suggesting that a longer duration of field experience with Nuru might result in significant improvements. Overall, these findings suggest that Nuru can be an effective tool for in-field diagnosis of cassava diseases and has the potential to be a quick and cost-effective means of disseminating knowledge from researchers to agricultural extension agents and farmers, particularly on the identification of disease symptoms and their management practices.
Highlights
The steady increase in the world population and changes in climate are adding pressure to agriculture as the need to produce more food intensifies, and pests and diseases exacerbate these threats to food production
The model was subsequently deployed as a mobile app (PlantVillage Nuru) in Android smartphones and tested in fields to account for environmental factors and determine the best conditions that will enable the model to perform with high accuracy (Ramcharan et al, 2019)
PlantVillage Nuru could identify asymptomatic leaves with an accuracy above 90%, which is higher than the accuracy for symptomatic leaves (21–59%); it could identify symptoms of cassava green mites (CGM)-damage (40–56%) and cassava mosaic disease (CMD) (52–59%) better than cassava brown streak disease (CBSD) (21% accuracy) (Table 2)
Summary
The steady increase in the world population and changes in climate are adding pressure to agriculture as the need to produce more food intensifies, and pests and diseases exacerbate these threats to food production. Information and Communication Technology (ICT) platforms in the form of the internet, call-centers and SMS have been adopted to disseminate agricultural information to farmers in several regions including Latin America, Asia, and Africa (Qiang et al, 2012; Tsan et al, 2019). The image recognition system developed by Tuhaise et al (2014) is one of the first systems developed for cassava It estimates disease severity by evaluating the percentage of root necrosis attributed to cassava brown streak disease (CBSD). Even though this method is effective and might be useful for research purposes it is not practical for farmers as it requires plants to be uprooted
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
