As one of the major cleaning mechanisms in the atmosphere, wet scavenging can help to remove the ambient pollutants efficiently from the air. However, chemical components of the particulate matter can be dissolved into the rainwater and exert adverse impacts on the ecological systems. Therefore, it is of great significance for us to understand the pattern of wet deposition globally and evaluate how the chemical species in the rainwater influence our natural systems. In this project, the students are expected to help to collect the wet deposition observation data in the northern hemisphere and implement a deep-learning technique (e.g., CNN) to estimate the wet deposition spatial patterns. The applicants are expected to implement the machine-learning techniques before and be familiar with one of the programming languages, such as Matlab, Python, and R. Depending on their performance, the students will be included when the academic paper is published, which is highly important for the future graduate school