Exploring the Relative Role of Vapor Pressure Deficit and Soil Moisture on Vegetation Productivity Using Data-Driven Machine Learning
Authors
Lingcheng Li1* (lingcheng.li@pnnl.gov), Yilin Fang1, Nate McDowell1,2, Ruby Leung1, Shiqin Xu3, Zhonghua Zheng4, Jeffrey Chambers5,6
Institutions
1Pacific Northwest National Laboratory, Richland, WA; 2School of Biological Sciences, Washington State University, Pullman, WA; 3Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia; 4Department of Earth and Environmental Sciences, The University of Manchester, Manchester, U.K.; 5Lawrence Berkeley National Laboratory, Berkeley, CA; 6Department of Geography, University of California–Berkeley, CA
URLs
Abstract
With increasing frequency and severity of droughts projected for the future climate with warming, the impact of drought on vegetation productivity is expected to intensify. Drought stress on ecosystem productivity is commonly characterized by low soil moisture (SM) and high atmospheric water demand (i.e., high vapor pressure deficit; VPD). However, the relative dominance of VPD versus SM on vegetation production is still being debated. In this study, the team presents an explainable machine-learning approach to disentangle the relative role of VPD and SM on vegetation greenness (i.e., normalized difference vegetation index) across global ecosystems with a particular focus on tropical regions such as the Amazon basin using multisource datasets. The project’s research shows that globally, SM typically has a more pronounced effect on vegetation greenness variation than VPD in most regions. However, in tropical forests, VPD is the more critical factor compared to SM. The relative importance of VPD and SM varies with climate and plant functional types. The study provides a large-scale benchmark for modeling the drought impacts on terrestrial ecosystems in Earth system models like DOE’s Energy Exascale Earth System Model with vital implications for understanding global water, carbon, and energy cycles in the face of climate change.