woman looking at a plant

Plant Village

PlantVillage (https://plantvillage.psu.edu/) is a research and development unit of Penn State that empowers smallholder farmers and seeks to lift them out of poverty using cheap, affordable technology to reduce yield losses to plant diseases and pests

PlantVillage (https://plantvillage.psu.edu/) is a research and development unit of Penn State that empowers smallholder farmers and seeks to lift them out of poverty using cheap, affordable technology to reduce yield losses to plant diseases and pests

There are almost 500 million smallholder farmers around the world who have 2 ha or less to raise enough produce for their family and to sell at the market. There are many stressors on these farms from poor soil to infectious diseases and insect pests. PlantVillage (https://plantvillage.psu.edu/) aims to mitigate the impact of these stressors by leveraging cutting edge technology and making it work for smallholder farmers. PlantVillage is a web platform developed at Penn State that also connects the international community of public funded scientists (i.e. UN FAO, CGIAR, US Land Grants, GODAN) to farmers around the world and assist helps country level extension workers to help farmers.

Working with human experts on diseases we developed an Artificially Intelligent assistant, Nuru (Swahili for light).  We have developed her in very close collaboration with the International Institute for Tropical Agriculture (notably the group of Dr James Legg) and United Nations FAO.  Nuru has proven herself to be x2 as good as extension workers in Tanzania for cassava diseases.  A major technical accomplishment was having Nuru work offline. We have benefitted greatly from a long-term relationship with the TensorFlow team at Google.  Offline is important in rural settings, as well as reducing data charges for users. At PlantVillage we are also using precision Ag tools like satellites, drones and mobile spectrophotometry to determine how these can help smallholder farmers. We are also working with modelers who use past disease occurrence and forecasted weather patterns to predict infection risk. 

Discover Other Research Areas