Connect with us

Published

on

The India Meteorological Department (IMD) is testing artificial intelligence (AI) to build climate models to improve weather forecasting as torrential rains, floods and droughts proliferate across the vast country, a top weather official said.

Global warming has triggered more intense clashes of weather systems in India in recent years, increasing extreme weather events, which the independent Centre for Science and Environment estimates have killed nearly 3,000 people this year.

Weather agencies around the world are focussing on AI, which can bring down cost and improve speed, and which Britain’s Met Office says could “revolutionise” weather forecasting, with a recent Google-funded model found to have outperformed conventional methods.

Accurate weather forecasting is particularly crucial in India, a country of 1.4 billion people, many impoverished, and the world’s second-largest producer of rice, wheat and sugar.

The IMD provides forecasts based on mathematical models using supercomputers. Using AI with an expanded observation network could help generate higher-quality forecast data at lower cost.

The department expects the AI-based climate models and advisories it is developing to help improve forecasts, K.S. Hosalikar, head of climate research and services at IMD, told Reuters.

The weather office has used AI to generate public alerts regarding heatwaves and such diseases as malaria, Hosalikar said. It plans to increase weather observatories, providing data down to village level, potentially offering higher-resolution data for forecasts, he said.

The government said on Thursday it wants to generate weather and climate forecasts by incorporating AI into traditional models, and has set up a centre to test the idea through workshops and conferences.

“An AI model doesn’t require the high cost involved in running a supercomputer – you can even run it out of a good quality desktop,” said Saurabh Rathore, an assistant professor at Indian Institute of Technology-Delhi.

Better data is also needed to make the most out of AI, experts say.

“Without having high-resolution data in space and time, no AI model for location-specific magnification of existing model forecasts is feasible,” said Parthasarathi Mukhopadhyay, a climate scientist at the Indian Institute of Tropical Meteorology.

© Thomson Reuters 2023


Affiliate links may be automatically generated – see our ethics statement for details.

Continue Reading

Science

Aeneas AI Model Helps Decode and Restore Ancient Roman Inscriptions

Published

on

By

Aeneas AI Model Helps Decode and Restore Ancient Roman Inscriptions

Ancient Roman Inscriptions help us understand laws, traditions, economy, and even the emotional perspective of ancient people. Their lives and histories, however, have been rendered difficult to understand because, over time, the inscriptions have been damaged. Every year, there are 1500 Roman inscriptions discovered, albeit many of them are incomplete. Fortunately, advancements in technology like the new Aeneas tool, is helping in the future understanding of the Roman inscriptions. It serves as a large language model specializing in reading, interpreting, and giving context to Roman inscriptions.

Decode Ancient Roman Inscriptions

As Per Report,Drawing its name from a hero in Roman history, Aeneas, the model has been trained on nearly 200,000 latian inscriptions, which span from the 7th century to the 8th century covering regions from Portugal to Iraq.Aneas has the capability to analyze images of damaged inscriptions and predict or even fill in missing letters or words. In addition to that, it is able to determine a time frame and location for the inscription, as well as cross-reference it with other inscriptions containing similar phrases or purposes.

Making History Clearer Through Technology

Since Aeneas is trained exclusively on Latin inscriptions, specialists believe that he is less prone to random or false errors when compared to general AI approaches. University of Sydney historian Anne Rogerson remarked that Aeneas’s proposals, as informed guesses, still involve real historical data as opposed to baseless conjectures.

Despite the model’s open availability,Made public alongside the model’s code and data, Aeneas’s creator, Google DeepMind, offered the model without restrictions.

Most impressively, Aeneas can be accessed for free, enabling students and researchers to shift through and reinterpret previously concealed fragments of Roman history to understand them on a deeper level.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who’sThat360 on Instagram and YouTube.


Robot Drummer: Humanoid Robot Learns to Play Drums with Human-Like Precision

Continue Reading

Science

Robot Drummer: Humanoid Robot Learns to Play Drums with Human-Like Precision

Published

on

By

Robot Drummer: Humanoid Robot Learns to Play Drums with Human-Like Precision

Human-like designed robots have so far been tested for the assistive and manual tasks such as carrying objects, assisting in physical therapy and supporting elderly individuals. Their potential in expressive and creative fields, such as arts and music performance have introduced Robot Drummer which is a humanoid robot capable of drum playing both expressively and precisely. This project’s objective is to explore that robots could perform in rhythm and artistic roles.

Exploring Creativity in Humanoid Robotics

As per Tech Explore, the concept started from the casual coffee break gathering between the first author and the co-author, Asad AIi and Los Roveda respectively. They saw that humanoid robots are great at practical tasks and drumming was observed as a challenge, with combining rhythm, physical skill and coordination.

To get this, the team made a system which represents music as the rhythmic contact chain, which is a sequence of the events which signals which drum to strike and when. With the help of these cues, the robot has been trained in a simulated milieu, learning to perform the realistic techniques including switching sticks, adapting movements for efficiency and crossing arm.

Robot Drummer’s Skills and Future Potential

Tests were conducted on the simulated G1 Unitree humanoid robot, playing full drum tracks of songs from jazz to rock and metal. These included “Take Five” by Dave Brubeck, Living on a Prayer” by Bon Jovi, and “In the End” by Linkin Park. The robot achieved over 90% rhythmic accuracy, demonstrating the ability to master complex patterns.

The robot has been designed to use the ability of human drummers, such as anticipating upcoming dynamically adjusting hand positions and beats. These behaviors emerged naturally from the training process, guided by rhythmic performance rewards. The researchers believe this opens doors for robotic performers in live entertainment and other precision-based tasks.

The team’s next goal is to transfer these learned skills from simulation to a physical robot. They also aim to enable improvisation, allowing the robot to adjust its style in real time based on musical cues. This could give future robotic drummers the ability to respond to music with a level of expression closer to human musicians.

Continue Reading

Science

Twisted Jet Confirms Most Extreme Binary Black Hole System in the Universe

Published

on

By

Twisted Jet Confirms Most Extreme Binary Black Hole System in the Universe

Astronomers using a global radio telescope array have captured a record-sharp image of the blazar OJ 287, showing its particle jet is sharply bent. This twisted jet provides compelling evidence that OJ 287’s core contains not one but two supermassive black holes in a tight orbit. For decades, OJ 287’s ~12-year cycle of flares hinted at a secondary black hole, and the new image confirms that model. In fact, this appears to be the most extreme binary black hole system ever observed. Researchers say the finding makes OJ 287 “an ideal candidate for further research into merging black holes and the associated gravitational waves”.

Twisted Jet Reveals a Cosmic Duo

According to the study, using an Earth-space radio interferometer, astronomers produced an ultra-sharp image of OJ 287’s center. The image shows the jet bends sharply three times within ~0.3 light-year and swings by about 30° over a few years. Such dramatic twists so close in are naturally explained by a second black hole tugging on the jet’s base. This fits the picture of OJ 287’s 12-year flare cycle: a ~150-million-solar-mass companion plunges through the primary’s accretion disk roughly every 12 years, triggering bright outbursts and bending the jet. The observations even caught a shock wave forming in the jet, unleashing a burst of gamma rays seen by NASA’s Fermi and Swift satellites. Astronomers say this twisted, ribbon-like jet is the clearest evidence yet of two supermassive black holes locked in a gravitational tug-of-war.

Implications for Black Hole Evolution

OJ 287’s black holes will eventually merge, but that won’t happen for a very long time. In the meantime, their orbit sends out ultra-long-wavelength gravitational waves that current detectors cannot pick up. Scientists expect pulsar-timing arrays – which monitor the ticking of distant neutron stars – may detect this faint gravitational-wave signal. Looking farther ahead, future space missions like ESA/NASA’s planned LISA observatory (2030s) could catch the final merger of such supermassive pairs.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who’sThat360 on Instagram and YouTube.


Hubble Delivers Best View Yet of Rare Interstellar Comet 3I/ATLAS Racing Through Solar System

Related Stories

Continue Reading

Trending