“In February, the European Centre for Medium-Range Weather Forecasts (ECMWF) — a world leader in forecasting global weather conditions up to a few weeks out — quietly went live with the planet’s first fully operational weather forecast system powered by artificial intelligence. 

The new A.I. forecasts are, by leaps and bounds, easier, faster, and cheaper to produce than the non-A.I. variety, using 1,000 times less computational energy. And, in most cases, these A.I. forecasts, powered by machine learning, are more accurate, too. ‘Right now the machine learning model is producing better scores,’ says Peter Dueben, a model developer at ECMWF in Bonn, who helped to develop the center’s Artificial Intelligence Forecasting System (AIFS). The improvement is hard to quantify, but the ECMWF says that for some weather phenomena, the AIFS is 20 percent better than its state-of-the-art physics-based models.

Andrew Charlton-Perez, a meteorologist at the University of Reading who also heads up that institution’s school of computational sciences, expects plenty more operational A.I. forecasts to follow — from both national weather agencies and companies like Google.”

From Yale Environment 360.

“In our work on natural disasters, we visualize data from EM-DAT, the most comprehensive international disaster database. Make a chart of the number of recorded disaster events over time — like the one above — and it looks like the number of disasters rose alarmingly from the 1970s to the millennium. This has led to many media outlets and organizations claiming that the number of disasters has quadrupled over the last 50 years.

However, as EM-DAT itself makes clear, most of this is due to improvements in recording. The Centre for Research on the Epidemiology of Disasters, which builds this database, was not established until 1973, and didn’t start publishing EM-DAT until 1988.

The number of recorded disasters increased due to more focused efforts to obtain globally comprehensive data and improvements in communication technologies, which allowed more events to be included, even in the planet’s most remote areas.”

From Our World in Data.

“One of the nation’s largest homebuilders have created a community of entirely wildfire-resilient homes to help reduce homebuyers’ risks of loss if another Palisades or Dixie fire comes roaring by.

With nothing flammable on the exterior or the roofs and curated desert foliage around the gardens and lawns, the homes aren’t necessarily fireproof, but the design of the entire community was informed by identifying and eliminating the most common causes of homes catching fire.

Available now, and with some already off the market, KB Homes estimates their price at around $1 million, a price consistent with disaster-proof housing around the country.”

From Good News Network.

“Using an innovative planting technique, Javier Munoz has been trialling the ‘Jaspe’ strain created by experts at the Agricultural Research Institute’s (INIA) Rice Breeding Program.

It is one of several research efforts worldwide to come up with less resource-hungry crops at a time of increased water scarcity in parts of the world due to global warming.

Using Jaspe in combination with a growing method that requires only intermittent watering cut the Munoz family’s water consumption in half in a country that has for generations cultivated rice in flooded fields, or paddies.

At the same time, yield rocketed, with each seed yielding about thirty plants — nearly ten times more than a conventional rice field.”

From FRANCE 24.