Home »
Academic Articles »
C »
Generating Daily High-Resolution Regional XCO<sub>2</sub> by Deep Neural Network and Multi-Source Data
Generating Daily High-Resolution Regional XCO<sub>2</sub> by Deep Neural Network and Multi-Source Data
Wenjie Tian
(Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572029, China)
Lili Zhang
(Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572029, China)
Tao Yu
(Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572029, China)
Dong Yao
(QiLu Aerospace Information Research Institute, Jinan 250010, China)
Wenhao Zhang
(North China Institute of Aerospace Engineering, Langfang 065000, China)
Chunmei Wang
(Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China)
Journal: Atmosphere
•
• MDPI AG
• ISSN: 2073-4433
Abstract
CO<sub>2</sub> is one of the primary greenhouse gases impacting global climate change, making it crucial to understand the spatiotemporal variations of CO<sub>2</sub>. Currently, commonly used satellites serve as the primary means of CO<sub>2</sub> observation, but they often suffer from striping issues and fail to achieve complete coverage. This paper proposes a method for constructing a comprehensive high-spatiotemporal-resolution XCO<sub>2</sub> dataset based on multiple auxiliary data sources and satellite observations, utilizing multiple simple deep neural network (DNN) models. Global validation results against ground-based TCCON data demonstrate the excellent accuracy of the constructed XCO<sub>2</sub> dataset (R is 0.94, RMSE is 0.98 ppm). Using this method, we analyze the spatiotemporal variations of CO<sub>2</sub> in China and its surroundings (region: 0°–60° N, 70°–140° E) from 2019 to 2020. The gapless and fine-scale CO<sub>2</sub> generation method enhances people’s understanding of CO<sub>2</sub> spatiotemporal variations, supporting carbon-related research.
Wenjie Tian, Lili Zhang, Tao Yu, et al. (2024). "Generating Daily High-Resolution Regional XCO<sub>2</sub> by Deep Neural Network and Multi-Source Data". Atmosphere. https://doi.org/10.3390/atmos15080985