GPRChinaTemp1km: a high-resolution monthly air temperature data set for China (1951–2020) based on machine learning

He, Qian; Wang, Ming; Liu, Kai; Li, Kaiwen; Jiang, Ziyu

doi:https://doi.org/10.5194/essd-14-3273-2022

Articles | Volume 14, issue 7

https://doi.org/10.5194/essd-14-3273-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-14-3273-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 7

Data description paper

|

15 Jul 2022

Data description paper |

| 15 Jul 2022

GPRChinaTemp1km: a high-resolution monthly air temperature data set for China (1951–2020) based on machine learning

Qian He, Ming Wang, Kai Liu, Kaiwen Li, and Ziyu Jiang

Supplement

https://doi.org/10.5194/essd-14-3273-2022-supplement

Data sets

GPRChinaTemp1km: 1 km monthly mean air temperature for China from January 1951 to December 2020 Qian He, Ming Wang, Kai Liu, Kaiwen Li, and Ziyu Jiang https://doi.org/10.5281/zenodo.5111989

GPRChinaTemp1km: 1 km monthly minimum air temperature for China from January 1951 to December 2020 Qian He, Ming Wang, Kai Liu, Kaiwen Li, and Ziyu Jiang https://doi.org/10.5281/zenodo.5112232

GPRChinaTemp1km: 1 km monthly maximum air temperature for China from January 1951 to December 2020 Qian He, Ming Wang, Kai Liu, Kaiwen Li, and Ziyu Jiang https://doi.org/10.5281/zenodo.5112122

Download

Article (18024 KB)
Full-text XML

Short summary

We used three machine learning models and determined that Gaussian process regression (GPR) is best suited to the interpolation of air temperature data for China. The GPR-derived results were compared with that of traditional interpolation techniques and existing data sets and it was found that the accuracy of the GPR-derived data was better. Finally, we generated a gridded monthly air temperature data set with 1 km resolution and high accuracy for China (1951–2020) using the GPR model.