Reliable defect detection is critical for the safe operation of heavy-haul railways. However, ultrasonic inspection signals are often distorted by complex non-Gaussian noise in small-radius curve sections. A research team developed a physics-informed denoising framework that integrates multi-feature fusion within an ideal binary mask paradigm. The proposed method improves defect echo extraction accuracy and reduces the risk of missed detections.

In a new comprehensive review, researchers from Tsinghua University, Xiaomi EV, Beijing Institute of Technology, and University of Electronic Science and Technology of China examine how these two AI paradigms are being applied across the development, validation, and operation of autonomous driving systems, discuss their strengths and limitations, and further review their emerging synergy for more robust, interpretable, and trustworthy autonomous driving systems. 

Using demographic profiles from surveys in Sydney, Hong Kong, and Nanjing, the authors construct role-playing prompts to test three LLMs on lottery-choice tasks. Three findings emerge. First, GPT models are more risk-averse than human benchmarks, whereas Gemini is more risk-seeking. Second, prompt language affects simulated risk attitudes, with non-English prompts often inducing more conservative choices. Third, LLMs fail to reproduce empirical heterogeneity, producing distributions that are either overly concentrated or unrealistically dispersed.

Researchers at the University of Georgia conducted the first empirical study investigating how "one-pedal driving" (OPD) influences electric vehicle car-following behavior. The study reveals a striking contrast: while manual one-pedal driving increases speed oscillations and driver variability, integrating OPD with Adaptive Cruise Control (ACC) significantly enhances traffic stability and produces smoother, more conservative driving patterns compared to traditional two-pedal systems.

Selective activation of inert C-H bonds-the "Holy Grail" of organic synthesis-has long eluded chemists due to their high bond energy and weak polarity. Now, a comprehensive review published in Polyoxometalates highlights how metal-organic frameworks (MOFs) and polyoxometalate-based MOFs (POMOFs) are emerging as game-changing photocatalysts that harness sunlight to convert these stubborn bonds into high-value chemicals under mild conditions, offering a greener path for the pharmaceutical, agrochemical, and fine chemical industries.

Researchers from UCL, the University of Southampton and the University of Nottingham have developed a reinforcement learning-based control scheme that helps wave energy converters harvest more power from the ocean without relying on a precise mathematical model of the device. By combining a proximal policy optimization (PPO) algorithm with short-term wave forecasts, the controller continuously adapts itself and generated up to 13.9% more energy than a conventional controller when tested on real sea-wave data collected off the coast of Cornwall, UK.

A research team has developed a new type of battery component that results in safer and higher-capacity batteries. It can improve lithium metal batteries’ safety, reliability, and electrochemical performance. Their work provides a feasible molecular engineering strategy for developing safe, high-performance lithium metal batteries.

Wind-assisted propulsion systems (WAPS) can convert naturally available wind energy directly into additional thrust, reducing ships’ dependence on conventional fuels. A new techno-economic review examines four major systems: rotor sails, boundary-layer control sails, wing sails and kite sails, and evaluates their aerodynamic principles, industrial readiness, design requirements, operational risks and lifecycle impacts. The authors also identify nine research priorities for turning promising performance estimates into safe, measurable and commercially viable emissions reductions.

A research team has developed an efficient, low-cost material designed to produce clean hydrogen gas from water. This research offers news perspectives and valuable insights into the development of efficient, stable, and economical noble metal-free electrocatalysts for green hydrogen production.