Long-term series of daily snow depth dataset over the Northern Hemisphere based on machine learning (1980-2019)

Long-term series of daily snow depth dataset over the Northern Hemisphere based on machine learning (1980-2019)

With the support of the first topic "sharing and integration of three pole big data" (xda19070100) of the special space-time three pole environment project of the earth big data science project, Che Tao research group of Northwest Institute of ecological environment and resources, Chinese Academy of Sciences uses machine learning methods combined with multi-source snow depth product data The daily snow depth data set of long-time Series in the northern hemisphere is prepared.

Firstly, the applicability of artificial neural network, support vector machine and random forest method in snow depth fusion is compared. It is found that random forest method has strong advantages in snow depth data fusion. Secondly, using the random forest method, combined with remote sensing snow depth products such as AMSR-E, amsr2, NHsd and globsnow and reanalysis data such as era interim and merra2, the grid snow depth products and environmental factor variables are used as the input independent variables of the model, and the data of China Meteorological Station (945), Russia meteorological station (620) and Russia snow survey data (514) The snow depth data of 43340 ground observation stations such as the daily data of the global historical meteorological network (41261) are used as the reference truth to train and verify the model, and the daily grid snow depth data set of the snow hydrological year from 1980 to 2019 (September 1 of the previous year to May 31 of the current year) is prepared on the cloud platform provided by the special "earth big data science project". Using the global snow model comparison program and independent ground observation data for verification, the quality of the fusion data set has been improved as a whole. According to the comparison between the ground observation data and the snow depth products before fusion, the determination coefficient (R2) of the fusion data is increased from 0.23 (globsnow snow depth products) to 0.91, and the corresponding root mean square error (RMSE) and mean absolute error (MAE) are also reduced to 7.69 cm and 2.7 cm. The following is the header file content of each file. Adding it to the front of each file can display the data in ArcMap.

Ncols 1440 / / 1440 columns in the data matrix

Nrows 360 / / the data matrix has 360 rows in total

Xllcenter - 180 / / the corner coordinates of the grid at the lower left corner of the matrix in the X direction

Yllcenter 0 / / the corner coordinates of the grid at the lower left corner of the y-direction axis of the matrix

Cellsize 0.25 / / size of each grid

NODATA_ Value - 9999 / / default value

File naming and required software

The data is stored in a TXT file every day. Each file is composed of a header file (header file) and a 1440 * 360 snow depth matrix. Each snow depth value represents a 0.25 ° 0.25 ° grid. This data set is prepared according to the defined hydrological year (from September 1 of the previous year to May 31 of the current year) for the characteristics of snow depth over time. Taking the hydrological year of 1980 as an example, the data are 1980001 to 1980274, 1980001 represents September 1, 1979, 1980274 represents May 31, 1980, and so on. After adding the header file to the txt document, it can be displayed in ArcMap software.

Data Citations Data citation guideline What's data citation?
Cite as:

Che, T., Hu, Y., Dai, L., Xiao, L. (2021). Long-term series of daily snow depth dataset over the Northern Hemisphere based on machine learning (1980-2019). National Tibetan Plateau Data Center, DOI: 10.11888/Snow.tpdc.271701. CSTR: 18406.11.Snow.tpdc.271701. (Download the reference: RIS | Bibtex )

Related Literatures:

1. Hu,Y.X., Che, T., Dai, L.Y., & Xiao, L. (2021). Snow depth fusion based on machine learning methods for the Northern Hemisphere. Remote Sensing, 13,1250.( View Details | Bibtex)

Using this data, the data citation is required to be referenced and the related literatures are suggested to be cited.

Support Program

CASEarth:Big Earth Data for Three Poles(grant No. XDA19070000) (No:XDA19000000)

Copyright & License

To respect the intellectual property rights, protect the rights of data authors,expand servglacials of the data center, and evaluate the application potential of data, data users should clearly indicate the source of the data and the author of the data in the research results generated by using the data (including published papers, articles, data products, and unpublished research reports, data products and other results). For re-posting (second or multiple releases) data, the author must also indicate the source of the original data.

Example of acknowledgement statement is included below: The data set is provided by National Tibetan Plateau Data Center (http://data.tpdc.ac.cn).

License: This work is licensed under an Attribution 4.0 International (CC BY 4.0)

Related Resources

Current page automatically show English comments Show comments in all languages

Download Follow
Geographic coverage
East: 180.00 West: -180.00
South: 90.00 North: 0.00
  • Temporal resolution: Daily
  • Spatial resolution: 0.1º - 0.25º
  • File size: 3,245,520 MB
  • Views: 1,682
  • Downloads: 72
  • Access: Open Access
  • Temporal coverage: 1980-09-01 To 2019-05-31
  • Updated time: 2021-12-30
: CHE Tao   HU Yanxing   DAI Liyun   XIAO Lin  

Distributor: National Tibetan Plateau Data Center

Email: data@itpcas.ac.cn

Export metadata