Menopausal Mother Nature

News about Climate Change and our Planet

machine learning


Some Amazon rainforest regions more resistant to climate change than previously thought

(Columbia University School of Engineering and Applied Science) Is the Amazon rainforest as sensitive to water stress as what the current models have been showing? Columbia Engineering researchers found that the models have been largely over-estimating water stress in tropical forests. While models show that increases in air dryness greatly diminish photosynthesis rates in certain regions of the Amazon rainforest, observational data results show the opposite: in certain very wet regions, the forests instead even increase photosynthesis rates in response to drier air.

Does air pollution increase women’s risk of dementia?

Older women who live in locations with higher levels of air pollution may have more brain shrinkage, the kind seen in Alzheimer’s disease, than women who live in locations with lower levels, according to a new study.

Predicting urban water needs

New Stanford research uses Zillow and census data combined with machine learning to identify residential water consumption based on housing characteristics. The approach could help cities better understand water use and design water-efficient communities.

New method brings physics to deep learning to better simulate turbulence

(University of Illinois Grainger College of Engineering) Deep learning, also called machine learning, reproduces data to model problem scenarios and offer solutions. However, some problems in physics are unknown or cannot be represented in detail mathematically on a computer. Researchers at the University of Illinois Urbana-Champaign developed a new method that brings physics into the machine learning process to make better predictions. The researchers used turbulence to test their method.

Terminator salvation? New machine learning program to accelerate clean energy generation

(ARC Centre of Excellence in Exciton Science) A new type of machine learning model will predict the efficiency of materials that can be used in next-generation organic solar panels, including ‘virtual’ compounds that don’t exist yet. The program is free and easy to use for scientists and engineers creating prototype devices.