Spatial statistics of TRMM precipitation in the Tibetan Plateau using random forest algorithm

doi:10.6046/gtzyyg.2018.03.25

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(3828 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

So far, precipitation products with high spatial resolution have been crucial for the basin scale hydrology, meteorology and ecology. The climate in the Tibetan Plateau is of vital significance to global climate variation. So, the study of the distribution of precipitation with high spatial resolution is in the basic position of environmental science. Based on random-forest algorithm, the authors introduced environmental factors such as topography and vegetation, which was developed for downscaling the remote sensing precipitation products accurately and effectively. The non-linear spatial statistical downscaling model was demonstrated with the Tropical Rainfall Measuring Mission (TRMM) 3B43 dataset with the spatial resolution of 0.25°, the Normalized Difference Vegetation Index (NDVI) from NOAA-AVHRR with the spatial resolution of 8km, the Digital Elevation Model (DEM) from Shuttle Radar Topography Mission (SRTM) with the spatial resolution of 90 m and the information of slope, aspect, longitude and latitude. And the model based on time series and vegetation factor, which was demonstrated with TRMM3B43 annual data in order to forecast the precipitation, was introduced in this paper. The downscaling results were validated by applying the observations from the rain gauges in the Tibetan Plateau and the coefficient of determination R ² is 0.89. The analytical results showed that the downscaling results improved the spatial resolution and accuracy by applying the random-forest algorithm and introducing environmental factors. And the model, which was developed for forecasting the precipitation, captured the trends in inter-annual variability and the magnitude of annual precipitation with the R ² ranging from 0.81 to 0.87.

Keywords Tibetan Plateau precipitation downscale forecast Random-forest time series

TP79

Corresponding Authors: Yuanyuan WEI E-mail: weiyy@radi.ac.cn

Issue Date: 10 September 2018

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Binren XU
	Yuanyuan WEI

Cite this article:

Binren XU,Yuanyuan WEI. Spatial statistics of TRMM precipitation in the Tibetan Plateau using random forest algorithm[J]. Remote Sensing for Land & Resources, 2018, 30(3): 181-188.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2018.03.25 OR https://www.gtzyyg.com/EN/Y2018/V30/I3/181

Fig.1 Regression analysis of precipitation data from weather station and TRMM

Fig.2 Spatial distribution of TRMM precipitation in the Tibet Plateau in 2001

Fig.3 Spatial distribution of NDVI from NOAA-AVHRR in the Tibet Plateau in 2001

Tab.1 Random forest package main function name and function

Tab.2 Linear correlation between precipitation and other variables

Fig.4 Random forest model predictions and calibrated TRMM3B43 values

Fig.5 Multivariate linear model predictions and calibrated TRMM3B43 values

Fig.6 Spatial distribution of TRMM precipitation calibration value of Tibet Plateau in 2001

Fig.7 Spatial distribution of random forest output in the Tibet Plateau in 2001

Fig.8 8 km × 8 km spatial resolution error distribution

Fig.9 Downscaling results

Fig.10 TRMM calibration and downscaling results with site precipitation analysis

Fig.11 Interannual variation of observed and predicted values for five sites

Tab.3 Predicted results for 2006—2012 and TRMM precipitation fitting coefficient after calibration

[1]	吴国雄 . 我国青藏高原气候动力学研究的近期进展[J]. 第四季研究, 2004,24(1):1-9.
[1]	Wu G X . Recent progress in the study of the Qinghai-Xizang plateau climate dynamics in China[J]. Quaternary Sciences, 2004,24(1):1-9.
[2]	Immerzeel W W , Van Beek L P H,Bierkens M F P.Climate change will affect the Asian water towers[J]. Science, 2010,32(8):1382-1385.
[3]	程珂, 朱祯, 李铭 , 等. TRMM3B43降水产品在西藏地区的精度检验和应用[J]. 水利水电技术, 2014,45(1):44-46.
[3]	Cheng K, Zhu Z, Li M , et al. Application and accuracy testing of TRMM3B43 rainfall product in Tibetan Region[J]. Water Resources and Hydropower Engineering, 2014,45(1):44-46.
[4]	刘永和, 郭维栋, 冯锦明 , 等. 气象资料的统计降尺度方法综述[J]. 地球科学进展, 2011,26(8):837-847.
[4]	Liu Y H, Guo W D, Feng J M , et al. A summary of methods for statistical downscaling of meteorological data[J]. Advances in Earth Science, 2011,26(8):837-847.
[5]	Zorita E, Hughes J P, Lettemaier D P . Stochastic characterization of regional circulation patterns for climate model diagnosis and estimation of local precipitation[J]. Journal of Climate, 1995,8(5):1023-1042. doi: 10.1175/1520-0442(1995)008<1023:SCORCP>2.0.CO;2 url: http://journals.ametsoc.org/doi/abs/10.1175/1520-0442%281995%29008%3C1023%3ASCORCP%3E2.0.CO%3B2
[6]	Charles S P, Bates B C, Hughes J P . A spatiotemporal model for downscaling precipitation occurrence and amounts[J]. Journal of Geophysical Research: Atmospheres, 1999,104(D24):31657-31669. doi: 10.1029/1999JD900119 url: http://doi.wiley.com/10.1029/1999JD900119
[7]	Immerzeel W W, Rutten M M, Droogers P . Spatial downscaling of TRMM precipitation using vegetative response on the Iberian Peninsula[J]. Remote Sensing of Environment, 2009,113(2):362-370. doi: 10.1016/j.rse.2008.10.004 url: http://linkinghub.elsevier.com/retrieve/pii/S0034425708003155
[8]	Jia S F, Zhu W B, Lyu A F , et al. A statistical spatial downscaling algorithm of TRMM precipitation based on NDVI and DEM in the Qaidam Basin of China[J]. Remote Sensing of Environment, 2011,115(12):3069-3079. doi: 10.1016/j.rse.2011.06.009 url: http://linkinghub.elsevier.com/retrieve/pii/S0034425711002331
[9]	Grist J, Nicholson S E, Mpolokang A . On the use of NDVI for estimating rainfall fields in the Kalahari of Botswana[J]. Journal of Arid Environments, 1997,35(2):195-214. doi: 10.1006/jare.1996.0172 url: http://linkinghub.elsevier.com/retrieve/pii/S014019639690172X
[10]	Onema J M K, Taigbenu A . NDVI-rainfall relationship in the Semliki watershed of the equatorial Nile[J]. Physics and Chemistry of the Earth,Parts A/B/C, 2009,34(13/16):711-721. doi: 10.1016/j.pce.2009.06.004 url: http://linkinghub.elsevier.com/retrieve/pii/S1474706509000527
[11]	Iwasaki H . NDVI prediction over Mongolian grassland using GSMaP precipitation data and JRA-25/JCDAS temperature data[J]. Journal of Arid Environments, 2009,73(4/5):557-562. doi: 10.1016/j.jaridenv.2008.12.007 url: http://linkinghub.elsevier.com/retrieve/pii/S0140196308003674
[12]	Kummerow C, Barnes W, Kozu T , et al. The Tropical Rainfall Measuring Mission (TRMM) sensor package[J]. Journal of Atmospheric and Oceanic Technology, 1998,15(3):809-817. doi: 10.1175/1520-0426(1998)015<0809:TTRMMT>2.0.CO;2 url: http://journals.ametsoc.org/doi/abs/10.1175/1520-0426%281998%29015%3C0809%3ATTRMMT%3E2.0.CO%3B2
[13]	Huffman G J, Bolvin D T, Nelkin E J , et al. The TRMM multisatellite precipitation analysis (TMPA):Quasi-global,multiyear,combined-sensor precipitation estimates at fine scales[J]. Journal of Hydrometeorology, 2007,8(1):38-55. doi: 10.1175/JHM560.1 url: http://journals.ametsoc.org/doi/abs/10.1175/JHM560.1
[14]	齐文文, 张百平, 庞宇 , 等. 基于TRMM数据的青藏高原降水的空间和季节分布特征[J]. 地理科学, 2013,33(8):999-1005.
[14]	Qi W W, Zhang B P, Pang Y , et al. TRMM-Data-Based spatial and seasonal patterns of precipitation in the Qinghai-Tibet Plateau[J]. Scientia Geographica Sinica, 2013,33(8):999-1005.
[15]	明均仁, 肖凯 . 基于R语言的面向需水预测的随机森林方法[J].统计与决策, 2012(9):81-83.
[15]	Ming J R, Xiao K . Random forest method for water demand prediction based on R language[J].Statistics & Decision, 2012(9):81-83.
[16]	常青, 赵晓莉 . 时间序列模型在降水量预测中的应用研究[J]. 计算机仿真, 2011,28(7):204-206,276.
[16]	Chang Q, Zhao X L . Research on precipitation prediction based on time series model[J]. Computer Simulation, 2011,28(7):204-206,276.
[17]	Andersen J, Dybkjaer G, Jensen K H , et al. Use of remotely sensed precipitation and leaf area index in a distributed hydrological model[J]. Journal of Hydrology, 2002,264(1/4):34-50. doi: 10.1016/S0022-1694(02)00046-X url: http://linkinghub.elsevier.com/retrieve/pii/S002216940200046X
[18]	Raynolds M K, Comiso J C, Walker D A , et al. Relationship between satellite-derived land surface temperatures,arctic vegetation types,and NDVI[J]. Remote Sensing of Environment, 2008,112(4):1884-1894. doi: 10.1016/j.rse.2007.09.008 url: http://linkinghub.elsevier.com/retrieve/pii/S0034425707004294
[19]	Bogh E, Sogaard H . Remote sensing based estimation of evapotranspiration rates[J]. International Journal of Remote Sensing, 2004,25(13):2535-2551. doi: 10.1080/01431160310001647975 url: http://www.tandfonline.com/doi/abs/10.1080/01431160310001647975
[20]	Onema J M K, Taigbenu A . NDVI-rainfall relationship in the Semliki watershed of the equatorial Nile[J]. Physics and Chemistry of the Earth,Parts A/B/C, 2009,34(13/16):711-721. doi: 10.1016/j.pce.2009.06.004 url: http://linkinghub.elsevier.com/retrieve/pii/S1474706509000527
[21]	李晓民, 张焜, 李冬玲 , 等. 青藏高原札达地区多年冻土遥感技术圈定方法与应用[J]. 国土资源遥感, 2017,29(1):57-64.doi: 10.6046/gtzyyg.2017.01.09.
[21]	Li X M, Zhang K, Li D L . et al.Remote sensing technology delineation method and its application to permafrost of Zhada area in the Tibetan Plateau[J]. Remote Sensing for Land and Resources, 2017,29(1):57-64.doi: 10.6046/gtzyyg.2017.01.09.

[1]	LI Weiguang, HOU Meiting. A review of reconstruction methods for remote-sensing-based time series data of vegetation and some examples[J]. Remote Sensing for Natural Resources, 2022, 34(1): 1-9.
[2]	SHI Feifei, GAO Xiaohong, XIAO Jianshe, LI Hongda, LI Runxiang, ZHANG Hao. Classification of wolfberry planting areas based on ensemble learning and multi-temporal remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(1): 115-126.
[3]	SONG Qi, FENG Chunhui, MA Ziqiang, WANG Nan, JI Wenjun, PENG Jie. Simulation of land use change in oasis of arid areas based on Landsat images from 1990 to 2019[J]. Remote Sensing for Natural Resources, 2022, 34(1): 198-209.
[4]	LAI Peiyu, HUANG Jing, HAN Xujun, MA Mingguo. An analysis of impacts from water impoundment in Three Gorges Dam Project on surface water in Chongqing area base on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2021, 33(4): 227-234.
[5]	YU Bing, TAN Qingxue, LIU Guoxiang, LIU Fuzhen, ZHOU Zhiwei, HE Zhiyong. Land subsidence monitoring based on differential interferometry using time series of high-resolution TerraSAR-X images and monitoring precision verification[J]. Remote Sensing for Natural Resources, 2021, 33(4): 26-33.
[6]	MIN Wenbin, PEN Jun, Li Shiying. The evaluation of FY-3C snow products in the Tibetan Plateau[J]. Remote Sensing for Land & Resources, 2021, 33(1): 145-151.
[7]	SUN Chao, CHEN Zhenjie, WANG Beibei. Expansion monitoring of construction land based on SAR time series: A case study of Xinbei District, Changzhou[J]. Remote Sensing for Land & Resources, 2020, 32(4): 154-162.
[8]	WANG Dejun, JIANG Qigang, LI Yuanhua, GUAN Haitao, ZHAO Pengfei, XI Jing. Land use classification of farming areas based on time series Sentinel-2A/B data and random forest algorithm[J]. Remote Sensing for Land & Resources, 2020, 32(4): 236-243.
[9]	WANG Lingyu, CHEN Quan, WU Yue, ZHOU Zhongfa, DAN Yusheng. Accurate recognition and extraction of karst abandoned land features based on cultivated land parcels and time series NDVI[J]. Remote Sensing for Land & Resources, 2020, 32(3): 23-31.
[10]	Liqiang TONG, Lixin PEI, Jienan TU, Zhaocheng GUO, Jiangkuan YU, Jinghui FAN, Dandan LI. A preliminary study of definition and classification of ice avalanche in the Tibetan Plateau region[J]. Remote Sensing for Land & Resources, 2020, 32(2): 11-18.
[11]	Biqing WANG, Wenquan HAN, Chi XU. Winter wheat planting area identification and extraction based on image segmentation and NDVI time series curve classification model[J]. Remote Sensing for Land & Resources, 2020, 32(2): 219-225.
[12]	Yuting YANG, Hailan CHEN, Jiaqi ZUO. Remote sensing monitoring of impervious surface percentage in Hangzhou during 1990—2017[J]. Remote Sensing for Land & Resources, 2020, 32(2): 241-250.
[13]	Guoce SONG, Zhi ZHANG. Remote sensing monitoring method for dust and wind accumulation in multi-metal mining area of Xin Barag Right Banner,Inner Mongolia[J]. Remote Sensing for Land & Resources, 2020, 32(2): 46-53.
[14]	Shuang ZHU, Jinshui ZHANG. Medium resolution remote sensing based winter wheat mapping corrected by low-resolution time series remote sensing images[J]. Remote Sensing for Land & Resources, 2020, 32(1): 19-26.
[15]	Junnan XIONG, Wei LI, Zhiqi LIU, Weiming CHENG, Chunkun FAN, Jin LI. Research on downscaling of TRMM data in the Tibetan Plateau based on GWR model[J]. Remote Sensing for Land & Resources, 2019, 31(4): 88-95.

Viewed

Full text

Abstract

Cited

Shared

Discussed