Life Inspirations: Ladies and Gentlemen!  |  Technology Inceptions: New Device Detects Decline in RBC Volume Causing Blurred Vision in Alcoholics  |  National Edu News: GATI, CURIE, WISTEMM, Vigyan Jyoti for attracting Women to Science & Tech  |  Rajagiri Round Table: Roadmap to Excellence in Research and Innovation  |  Policy Indications: Should Climate Change Communications be Emotional?  |  Science Innovations: Scientists Understand the Logistics of Protein Movement in a Cell  |  Health Monitor: Eating Disorders Linked to Psychiatric Disorders and Risk of Obesity  |  Science Innovations: The Mystery of the Flying Volcanic Ash Particles Revealed  |  Policy Indications: UK Graduate route to open to international students on 1 July 2021  |  Leadership Instincts: VP appeals to students to connect their knowledge with social relevance  |  Leadership Instincts: Catherine Dulac receives Nomis Distinguished Scientist and Scholar Award  |  Leadership Instincts: Online school reviews reflect school demographics more than effectiveness  |  Leadership Instincts: Researchers virtually open and read sealed historic letters  |  Cover Story: At Vantage Point  |  Management lessons: Why Aluminium Cans are Great for Packaging of Beverages?  |  
February 18, 2019 Monday 11:39:48 AM IST

AI Can Help Improve Understanding of Earth Science

Technology Inceptions

Artificial Intelligence (AI) can significantly improve our understanding of the climate and Earth science, says a study by German scientists.

AI can be applied to data related to extreme events such as fire spreads or hurricanes, which are very complex processes influenced by local conditions.

It can also be applied to atmospheric and ocean transport, soil movement and vegetation dynamics data - some of the classic topics of Earth system science.

"From a plethora of sensors, a deluge of Earth system data has become available, but so far we've been lagging behind in analysis and interpretation," said Markus Reichstein of the Max Planck Institute for Biogeochemistry in Jena, Germany.


"This is where deep learning techniques become a promising tool, beyond classical machine learning applications such as image recognition, natural language processing or AlphaGo," added co-author Joachim Denzler, from the Friedrich Schiller University in Jena (FSU).

However, deep learning approaches are difficult. All data-driven and statistical approaches do not guarantee physical consistency per se, are highly dependent on data quality, and may experience difficulties with extrapolations, according to the study published in the journal Nature.

Besides, the requirement for data processing and storage capacity is very high.


If both techniques are brought together, so-called hybrid models are created. They can, for example, be used for modelling the motion of ocean water to predict sea surface temperature. While the temperatures are modelled physically, the ocean water movement is represented by a machine learning approach.

"The idea is to combine the best of two worlds, the consistency of physical models with the versatility of machine learning, to obtain greatly improved models," Reichstein explained.

Comments