Journal
ATMOSPHERIC RESEARCH
Volume 279, Issue -, Pages -Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.atmosres.2022.106398
Keywords
Maximum surface air temperature; Eurasian continent; Histogram -based gradient boosting modeling
Categories
Funding
- Strategic Priority Research Program of the Chinese Academy of Sciences-A
- Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Land and Resources (No. KF-2016-02-026), the Natural Science Foundation of China (No. 42071425), N [XDA19030402]
- Ministry of Land and Resources
- Natural Science Foundation of China [KF-2016-02-026]
- Natural Science Foundation of Shandong [42071425]
- Taishan Scholar Project of Shandong Province [ZR2020QE281]
- [TSXZ201712]
Ask authors/readers for more resources
This study developed a high-resolution temperature dataset for the Eurasian continent to support climate change analysis. Machine learning methods were used to train temperature estimation models and the impact of different features on the models was tested. The results showed that the model had high estimation accuracy and competitive temperature products. This study provides a scheme for estimating parameters with missing feature values and lays a solid foundation for environmental and climate change studies.
The Eurasian continent is highly vulnerable to climate change. However, there is a lack of high spatiotemporal resolution temperature datasets to support climate change analysis in this region. In this study, an all-sky daily maximum air temperature (Tmax) product at 0.05 degrees spatial resolution across Eurasia for 2003-2018 was devel-oped. This product is generated using a satellite-derived model, including parameters such as daytime and nighttime land surface temperature (LST), downward shortwave radiation, net radiation, leaf area index, enhanced vegetation index, and albedo. The study area, Eurasia, was divided into seven regions using a data -driven method. Four machine learning methods, histogram-based gradient boosting (HGB), extremely ran-domized trees (ET), random forest (RF), and deep belief network (DBN) were employed to train Tmax estimation models using 4476 stations from GHCN, GSOD, and CMDC. HGB was finally selected since it exhibited the highest estimation accuracy, the determination coefficient (R2) and root-mean-square-error (RMSE) of the HGB model are 0.984 and 1.736 degrees C with non-missing values in datasets and 0.985 and 1.812 degrees C with missing values respectively. The impact of the different situations of LST features on HGB models was tested. LST features containing interpolated LST and GLDAS Ta are considered the best. The spatial and temporal accuracy of HGB models was then examined across different land cover types, latitudes, elevations, and months. The permutation test was employed to examine the contributions of different features. Finally, HGB models trained using the best LST features were used to generate the Tmax products. In comparison with existing temperature products, the R2 and RMSE values were reported as 0.980 and 2.177 degrees C, indicating strong competition among existing Tmax products. In summary, our study provides a scheme for estimating parameters with missing feature values in a consistent manner and provides a solid foundation for the environmental and climate changes studies.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available