A woman in Lagos, Nigeria, peels cassava to make flour. Diseases and pests can threaten the crop. Photo: Sunday Alamba / AP

Researchers at Penn State University and the International Institute for Tropical Agriculture in Tanzania have trained a neural network running on a smartphone to spot cassava disease with 93% accuracy.

Why it matters: Diseases and pests threaten cassava, a root vegetable that is critical for food security in sub-Saharan Africa, and can lead to losses of over a $1.2 billion each year.

The vision: "In the same way we have personalized medicine, I think we can have personalized agriculture on scale for hundreds of millions of people in real time," Penn State's David Hughes told Wired. He envisions farmers and gardeners using artificial intelligence to help them diagnose their crops.

How it works: Neural networks are typically trained with millions of images. Instead of starting from scratch, the researchers took advantage of something called transfer learning in which an existing network is retrained with new data. In this case, they used 2,756 images of cassava leaves with tell-tale signs of disease.

Go deeper

Updated 13 mins ago - Politics & Policy

Coronavirus dashboard

Illustration: Sarah Grillo/Axios

  1. Global: Total confirmed cases as of 6:15 p.m. ET: 30,611,684 — Total deaths: 953,820— Total recoveries: 20,836,867Map.
  2. U.S.: Total confirmed cases as of 6:15 p.m. ET: 6,756,781 — Total deaths: 199,090 — Total recoveries: 2,556,465 — Total tests: 93,150,052Map.
  3. Politics: In reversal, CDC again recommends coronavirus testing for asymptomatic people.
  4. Health: The dwindling chances of eliminating COVID-19.
  5. World: Guatemalan president tests positive for COVID-19 — The countries painting their pandemic recoveries green.

Trump says he expects to announce a Supreme Court nominee "next week"

President Trump speaking prior to his departure from the White House on Sept. 19. Photo: Sarah Silbiger/Getty Images

President Trump said Saturday he expects to announce a nominee for Justice Ruth Bader Ginsburg's vacant Supreme Court seat “next week” and that the person will “most likely" be a woman.

What he's saying: "If somebody were to ask me now, I would say that a woman would be in first place, yes. The choice of a woman, I would say, would certainly be appropriate," the president told pool reporters.

Susan Collins says Senate should postpone Supreme Court vote

Sen. Susan Collins. Photo: Tom Williams/Getty Images

Sen. Susan Collins (R-Maine) said in a statement Saturday she believes whoever is elected in the 2020 presidential race should pick the nominee to fill Justice Ruth Bader Ginsburg's Supreme Court seat.

Why it matters: Collins will be key in how the nomination process plays out. As one of the most centrist Senate Republicans, whether or not the Senate confirms Trump's SCOTUS nominee could hinge on her vote.