Agriculture

MIT researchers have developed the Probabilistic Bias Correction (PBC) tool, which “uses machine learning to identify systematic bias in a model and make corrections” to improve weather forecasts, reports The Verge’s Justine Calma. “The researchers found that PBC improved the accuracy of a leading physics-based weather model by the European Centre for Medium-Range Weather Forecasts (ECMWF) for 98 percent of precipitation and 92 percent of temperature targets,” notes Calma. “The machine learning framework also doubled the accuracy of ECMWF’s new AI forecasting system in the study’s analysis.” 

Gizmodo’s Ellyn Lapointe spotlights the Probabilistic Bias Correction (PBC) tool developed by MIT researchers to “correct systemic errors in forecast models and improve the accuracy of their subseasonal outlooks.” “Extreme weather has the largest impact on our society and improved forecasts of these events can yield large societal benefits,” says Research Scientist Judah Cohen. “Interestingly, previous bias correction schemes actually made forecasts of extreme weather worse, and our model showed clear improvement of extreme weather forecasts.”  

MIT researchers have developed an AI system “that not only minimizes forecasting errors, but learns from its inevitable mistakes through a method called postprocessing,” writes reporter Andrew Paul for Popular Science. “Their AI postprocessing integration blew the existing forecasting models out of the water,” notes Paul. “Such massive improvements could soon help the farmers and energy providers who already rely on subseasonal forecasts, but the benefits may even save lives.” 

Hamid Doosthosseini PhD ‘25, an MIT postdoc, speaks to Tech Brief’s Andrew Corselli about his team’s work engineering bacteria to act as transistors on “living circuit boards.” “Simply, each cell works somewhat like a traffic light at an intersection, it determines whether traffic (here a chemical signal) should continue or stop based on traffic in the intersecting road,” says Doosthosseini. “Printing a network of cells can therefore combine, compute, or direct signals.” 

MIT researchers have engineered three strains of bacteria to function as living transistors, carrying signals across circuits, writes Gizmodo’s Gayoung Lee. “For instance, the circuit could sit near the roots of plants to detect different stresses or autonomously respond to the presence of pests or other environmental threats,” writes Lee.  

Prof. Sebastian Lourido speaks to Boston Globe reporter Lindsay Crudele about the safety of local produce amidst the current cyclospora outbreak. “There are many features of local agriculture that are less susceptible to the spread of these kinds of diseases,” says Lourido. 

New York Times reporter Melissa Kirsch spotlights a study by MIT scientists that explores how the “sound of rain causes some seeds to germinate faster.”

Prof. Kate Brown speaks with Zoe Matthews of GBH about growing interest in urban gardening. Matthews highlights Brown’s course about cooperative agriculture at MIT, during which “her students produced an accessible how-to guide on starting an urban farm.” 

It may sound fishy, but Prof. Benedetto Marelli and postdoc Giorgio Rizzo have developed a method to up-cycle seafood waste into a coating for seeds that could help plants better withstand drought, while also creating more nutritious and sustainable crops. “It all starts with the idea that we need to find new ways to grow food and, in particular, find new ways to decrease the amount of fertilizers we use,” says Marelli, during an appearance on GBH's Curiosity Desk. 

Researchers at MIT have found that plants can sense the sound of rain before the water reaches them.  “The sound of rain spurs rice seeds to sprout up to 40 percent faster than they would otherwise,” writes K.R. Callaway for Scientific American. “The results mark the first direct evidence that plants sense the sound of the world around them and respond to it.” 

A new study from MIT researchers shows that plants can ‘hear’ rain coming. “Plants have external sensing resulting from cellular structures called statoliths, which shift and settle at the bottom of plant cells, while assisting the organisms in detecting changes in stability and position,” reports Rob Taub for NewsNation.

Prof. Kate Brown, author of “Tiny Gardens Everywhere,” speaks with Forbes reporter Alan Ohnsman of Forbes about the benefits of home gardens. Brown notes that people can “put in some healthy soils that are rich with compost, which feeds microbes and worms and black soldier flies, all these creatures that are in the soil so the soil is alive. Then you put in plants, trees, berry bushes, lettuces, greens, whatever. And when it rains, those healthy soils soak up a lot more water… [which is] great for flooding. They sequester a lot of carbon, more than any of our aesthetic alternatives. And of course, they can feed people.”

Writing for The Boston Globe, Prof. Kate Brown and David Greenwood-Sanchez of the University of Iowa explore the growing popularity of transforming residential yards into home gardens. They emphasize: “With food prices up 27 percent since 2020, it is a good time for Massachusetts legislators to consider protecting gardeners from vegetation restrictions so that they can grow plants that, in contrast to turf grass, nurture birds, bees, and the occasional rabbit — and their own families and neighbors.”

Boon Uranukul PhD '19 co-founded Terra Oleo, a startup working to “develop microbes that can transform agricultural waste into a variety of oils,” reports Tim De Chant for TechCrunch. “The company selected three yeast species based on the microbes’ abilities to produce certain oils when fed with organic waste, including from agriculture and biodiesel production,” explains de Chant. “It then used genetic and metabolic engineering to boost and tune their ability to produce certain fats and triglycerides.” 

Tech Crunch reporter Tim De Chant spotlights Fieldstone Bio, an MIT startup that turns microbes into sensors to support agricultural and national security efforts. “Each strain is tailored to sense a particular compound, such as nitrogen on a farm field or TNT residue from a landmine,” explains De Chant. “After the microbes have some time to sense their environment — several hours to days, depending on the target — the company will have another drone snap photos of the area.”