Spatiotemporal analysis of atmospheric methane concentrations and key influencing factors using machine learning in the Middle East (2010–2021)

Abstract

Methane (CH4) is a potent greenhouse gas that significantly impacts climate change due to its rising atmospheric concentrations. Hence, it is crucial to comprehend the spatial and temporal fluctuations in atmospheric CH4 concentration (XCH4) at both national and international levels. This study investigates the correlation between atmospheric XCH4 concentrations (XCH4) and key influencing factors to identify the primary sources and sinks of CH4 across the Middle East (ME). Initially, XCH4 data from the GOSAT satellite, covering the period from 2010 to 2021, were employed to generate spatiotemporal distribution maps of XCH4 across the ME region. Subsequently, the study investigated the single and simultaneous relationship between XCH4 and relevant environmental factors, such as vegetation, temperature, precipitation, and others, across different months using correlation analysis and the Permutation Feature Importance (PFI) method to identify the key factors influencing XCH4 variations. The results reveal significant spatial and temporal variations in XCH4 concentrations, with higher levels detected in the central and southern regions of the ME during the summer months. The results also highlight the presence of both peak positive and negative correlations with temperature and moisture during winter months. Additionally, both precipitation and vegetation demonstrated negative correlations with XCH4, especially during the winter and plant-growing seasons. According to the PFI results, temperature emerged as the most significant factor, accounting for over 40% of the variance in XCH4 concentrations during summer. At the same time, anthropogenic activities exerted minimal influence on these patterns. This comprehensive spatiotemporal analysis provides crucial insights into the variation of CH4 and its primary drivers in this climatically vulnerable region. Identifying emission patterns can support the development of targeted mitigation policies to curb the future rise of CH4.