About This Special Issue
Earth system models can be used on different types of studies on weather and climate scale. They in global and regional scale have a lot of challenges and open Challenges issues regarding modeling different physical and chemical process such Precipitation, transpiration, Dust storms, and water and energy budget in order to improve numerical model capabilities. Many innovative methods had been used in order to improve existing modeling system performance. One of these methods is data assimilation for the different types of ground and remote sensing observations. Different type of Algorithms from least square approach till the Kalman filters and their families had been developed but still not all of them are well presented and investigated on different temporal and spatial scales on the earth system.
Due to very huge amount and different types of the available ground and remote sensing observations, new innovative approaches had been initiated such applying artificial intelligence (AI) specially , deep learning algorithms to either build new data driven models or enhance the existing numerical models by modifying/replacing some internal implemented physical schemes with new one based on different AI approaches.
In this special issue, different types of work related to any type of earth modeling either numerical or data driven models are welcomed using any kind of ground/remote sensing observation in order to study different physics on weather or climate scale.
Aims and Scope:
- Earth system modeling
- Data Assimilation
- Observations and Remote Sensing
- Deep learning for Earth system modeling
- Weather and Climate temporal Scale
- Global and Regional Scale events