Understanding and modeling climate impacts on ecosystem dynamics with FLUXNET data and artificial intelligence

2019 9th International Conference on Future Environment and Energy

生态环境科学;能源学

Zhu, N.Y.^1 ; Yu, X.L.^2 ; Zhang, S.R.^3 ; Liu, Z.S.^4 ; Tong, Y.W.^5

Graduate Study of Art and Science, Columbia University, New York City, United States^1

School of Science, Beijing University of Posts and Telecommunications, Beijing, China^2

School of Biological Science and Medical Engineering, Southeast University, Nanjing, Jiangsu, China^3

College of Agriculture, Shandong Agricultural University, Taian, Shandong, China^4

School of Economics and Management, Nanchang University, Nanchang, China^5

关键词: Anthropogenic activity;    Controlling factors;    Fossil fuel burning;    Global temperatures;    Predictive modeling;    Radiative energy balance;    Temporal evolution;    Vapor pressure deficit;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/257/1/012005/pdf
DOI  :  10.1088/1755-1315/257/1/012005

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Since preindustrial era, the radiative energy balance of the earth system has been largely perturbed by anthropogenic activities such as CO2 emissions from fossil fuel burning. As a net effect, global temperature increasingly warms up and will further increase in the future if CO2 concentration in the atmosphere keeps going up. Plants sequestrate a large amount of atmospheric CO2 via photosynthesis, thus greatly mediate the global warming. In this study, we aim to model the temporal dynamics of photosynthesis for various different vegetation types and further understand controlling factors of photosynthesis machinery. Our results showed that the photosynthesis and its interactions with climate drivers, such as temperature, precipitatin, radiation, and vapor pressure deficit, has an internal system memory about 14 days. Thus, the predictive model could be best trained with historical data of the past two weeks and could best predict future temporal evolution of photosynthesis in the following two weeks. Our leave-one-out experiment also showed that temperature and solar radiation dramatically control grassland and forest photosynthesis activity.