EurekAlert!

Integrating physics and AI: Novel graph neural network models enhance precipitation forecasting

In the AI era, pure data-driven meteorological and climate models are gradually catching up with, and even surpassing, traditional numerical models. However, significant challenges persist in current ...
GlobalData on MSN

Redefining load forecasting and management: how AI is making smart grids smarter

Legacy load forecasting models are struggling with ever-more-common, unpredictable events; power-hungry AI offers a solution.
pv magazine International

Ultra-short-term PV forecasting based on convolutional neural network, long short-term memory

Scientists have created a novel probabilistic model for 5-minutes ahead PV power forecasting. The method combines a convolutional neural network with bidirectional long short-term memory, attention ...
Semiconductor Engineering

Physics Simulation With Graph Neural Networks Targeting Mobile

The demand for immersive, realistic graphics in mobile gaming and AR or VR is pushing the limits of mobile hardware. Achieving lifelike simulations of fluids, cloth, and other materials historically ...
pv magazine International

PV energy forecasting based on genetic algorithms, dynamic neural network

Scientists in Spain have used genetic algorithms to optimize a feedforward artificial neural network for the prediction of energy generation of PV systems. Genetic algorithms use “parents” and ...
EurekAlert!

Real-time, large-scale graph neural network inference through BingoCGN

BingoCGN employs cross-partition message quantization to summarize inter-partition message flow, which eliminates the need for irregular off-chip memory access and utilizes a fine-grained structured ...