Biography:

Prof. El-Askary received his PhD in Computational Sciences and Informatics from George Mason University in 2004, along with his two MS degrees in Computational Sciences and Earth Systems Sciences. In 2015, he earned Chapman University's elite Senior Wang-Fradkin Professorship award. In 2018, he was named a ?Game Changer: Orange County Leaders Transforming the World? by the Orange County Business Council. Prof. El-Askary served as the regional coordinator on a $3 ME project under the Horizon 2020 framework. He currently serves as the Co-leader to the dissemination work package in the EU InDUST cost initiative.

In 2019, Prof. El-Askary contributed among 200 scientists worldwide to the IPCC report on the Desertification Chapter. He was also invited by the UN secretariat to the COP14 meeting in New Delhi to present on the sand and dust storms side event and to be part of the global Sand and Dust Storms Coalition.

Abstract:

Artificial Intelligence (AI) and Machine Learning (ML) are two very hot keywords and often seem to be used interchangeably. AI is the concept that machines can accomplish tasks in a way that we would consider "smart", whereas ML is the study of algorithms and statistical models (often built from known data) where machines rely on patterns and inference to independently carry out a specific task in an effective way, with no need for explicit instructions.

Owing to the complexities embedded in the field of earth systems science, it is dramatically benefiting from combining the rapidly increasing data sources and associated computational power. Moreover, the recent advances in AI allow us to expand our deep understanding and knowledge of the Earth's system driven from actual data and observations.

Not only that, but geo-scientific analysis is promised further advances with the booming new available tools from the fields of AI and ML, and yet to be further developed. Applying and developing ML methodologies to geoscience and remote-sensing problems made it a universal approach in geoscientific classification, as well as change- and anomaly-detection problems. Such advances also serve to address environmental challenges facing citizens, governments, natural resource managers and decision-makers. This leads to a better understanding on the utility of using extensive satellite earth observations on specific SDGs dealing with agriculture and food productivity, water resources, life underwater, air quality, clean energy, and climate action.