Journal of Geo-information Science >
Downscaling of CCI Soil Moisture in the Xiliaohe River Basin based on Random Forest
Received date: 2022-12-29
Revised date: 2023-03-21
Online published: 2023-07-14
Supported by
National Natural Science Foundation of China(42071040)
National Natural Science Foundation of China(U2243203)
National Key Research and Devel opment Program of China(2019YFC1510601)
Soil moisture is a key factor in the climate system and has important application in agricultural management, water resource management, and ecosystem monitoring and assessment. Although remote sensing-derived soil moisture products can provide soil moisture distribution on a large scale, they usually have coarse spatial resolution, making it difficult to meet the requirements of practical applications. Thus, downscaling of remote sensing-derived soil moisture products has become one of the hot topics recently. In this paper, the ESA CCI daily soil moisture at 0.25°resolution is used as the main data source, combined with the MODIS underlying surface data, topographic data, meteorological data, and other environmental factors at 1 km resolution. A random forest downscaling model is constructed to generate downscaled CCI daily soil moisture products at 1 km resolution in the Xiliaohe River Basin of China from 2013 to 2020. Results show that: (1) The analysis of the importance score of environmental factors shows that relative humidity and daytime surface temperature are the two most important factors influencing soil moisture, followed by topography and location factors; (2) The performance of the random forest downscaling model is verified by using the measured data of 22 stations within the study area, and the results show that the downscaled results considering multiple environmental factors (underlying surface, topography, and meteorology) are more accurate than that considering only surface elements. The RMSE of each site is below 0.048 8 m3/m3, the average correlation coefficient is 0.497 3, the absolute value of BIAS is 0.003 0~0.033 3 m3/m3, and the R2 of soil moisture after downscaling is 0.52~0.84 compared with the original CCI remote sensing soil moisture; (3) The downscaled soil moisture has similar temporal trends with the site-level measured soil moisture with less fluctuation in values. The downscaling method proposed in this study improves the spatial resolution of remote sensing-derived soil moisture data while preserving the spatial pattern of the original data set, which can meet the demand for high-resolution soil moisture data in practical applications and provide a reference for the selection of environmental factors in soil moisture downscaling studies.
CAO Yu , FANG Xiuqin , YANG Lulu , JIANG Xinyuan , LIAO Meiyu , REN Liliang . Downscaling of CCI Soil Moisture in the Xiliaohe River Basin based on Random Forest[J]. Journal of Geo-information Science, 2023 , 25(8) : 1669 -1681 . DOI: 10.12082/dqxxkx.2023.221013
表1 研究数据的基本信息Tab. 1 Information of the data |
数据类型 | 数据名称 | 时间分辨率 | 空间分辨率 | 时段/年 | 来源 |
---|---|---|---|---|---|
土壤湿度产品 | ESA CCI | 1 d | 0.25° | 2013—2020 | http://www.esasoilmosture-cci.org/ |
地表参数 | MOD11A1 | 1 d | 1 km | 2013—2020 | https://ladsweb.modaps.eosdis.nasa.gov/search/ |
MOD09GA | 1 d | 500 m | |||
MCD12Q1 | 1 y | 500 m | |||
气象因子 | 日最高温MaxT | 1 d | 0.083° | 2013—2020 | http://www.geodata.cn/ |
日均气温MeanT | 1 d | 0.083° | |||
日最低温MinT | 1 d | 0.083° | |||
日降水量PRE | 1 d | 0.083° | |||
相对湿度RH | 1 d | 0.083° | |||
风速WND | 1 d | 0.083° | |||
实际水汽压VAP | 1 d | 0.083° | |||
日照时长SSH | 1 d | 0.083° | |||
高程 | DEM | — | 90 m | 2013—2020 | http://www.gscloud.cn/search |
表2 2种情形下土壤湿度降尺度结果的精度对比Tab. 2 Comparison of the accuracy of soil moisture downscaling results in two conditions |
站点名称 | 情形一:地表参数作为降尺度因子 | 情形二:多环境要素(地表、地形和气象)作为降尺度因子 | |||||
---|---|---|---|---|---|---|---|
RMSE | CORR | BIAS | RMSE | CORR | BIAS | ||
克什克腾 | 0.042 6 | 0.359 8 | -0.022 9 | 0.035 1 | 0.412 8 | 0.009 1 | |
林西 | 0.037 6 | 0.315 9 | -0.006 7 | 0.035 6 | 0.600 5 | 0.018 2 | |
岗子 | 0.036 9 | 0.581 7 | 0.019 8 | 0.031 2 | 0.634 1 | -0.003 0 | |
巴林右 | 0.034 4 | 0.506 6 | -0.012 2 | 0.030 9 | 0.590 8 | 0.003 8 | |
喀喇沁 | 0.035 1 | 0.438 1 | 0.006 0 | 0.033 2 | 0.514 9 | 0.003 2 | |
八里罕 | 0.040 8 | 0.489 5 | 0.018 0 | 0.035 9 | 0.483 6 | -0.005 4 | |
赤峰 | 0.040 1 | 0.369 5 | -0.008 1 | 0.034 5 | 0.439 5 | 0.003 6 | |
翁牛特 | 0.036 5 | 0.523 4 | 0.005 9 | 0.036 1 | 0.496 9 | -0.004 1 | |
富河 | 0.041 0 | 0.180 7 | -0.011 0 | 0.039 7 | 0.358 2 | 0.017 0 | |
宁城 | 0.041 3 | 0.451 1 | 0.012 5 | 0.038 0 | 0.454 0 | -0.014 9 | |
巴林左 | 0.033 6 | 0.518 2 | -0.007 1 | 0.031 3 | 0.631 8 | 0.004 6 | |
霍林郭勒 | 0.047 9 | 0.217 7 | -0.009 7 | 0.045 8 | 0.325 3 | 0.012 8 | |
敖汉 | 0.040 3 | 0.355 9 | -0.002 0 | 0.030 6 | 0.617 5 | 0.012 5 | |
阿鲁科尔沁 | 0.040 5 | 0.300 5 | -0.002 1 | 0.034 9 | 0.545 6 | 0.013 0 | |
巴雅尔吐胡硕 | 0.043 1 | 0.319 0 | -0.004 9 | 0.037 3 | 0.631 5 | 0.017 7 | |
奈曼 | 0.040 1 | 0.159 6 | 0.007 5 | 0.037 0 | 0.427 3 | 0.019 7 | |
扎鲁特 | 0.044 3 | 0.421 2 | -0.017 1 | 0.033 3 | 0.667 9 | 0.013 8 | |
开鲁 | 0.053 5 | 0.031 9 | -0.012 5 | 0.048 3 | 0.305 1 | 0.031 1 | |
舍伯吐 | 0.053 1 | 0.328 1 | -0.028 7 | 0.040 3 | 0.543 2 | 0.018 7 | |
通辽 | 0.048 9 | 0.258 6 | -0.017 8 | 0.047 1 | 0.566 5 | 0.033 3 | |
科左中 | 0.065 9 | 0.109 4 | 0.033 5 | 0.048 9 | 0.177 7 | 0.020 9 | |
双辽 | 0.047 6 | 0.540 4 | 0.019 9 | 0.034 5 | 0.529 6 | -0.006 1 |
[1] |
耿庆田, 刘植, 李清亮, 等. 基于一种深度学习模型的土壤湿度预测研究[J/OL]. 吉林大学学报(工学版), 2022,1-10
[
|
[2] |
|
[3] |
高露, 张圣微, 赵鸿彬, 等. 退化草原土壤理化性质空间异质性及其对土壤水分的影响[J]. 干旱区研究, 2020, 37(3):607-617.
[
|
[4] |
聂艳, 马泽玥, 周逍峰, 等. 阿克苏河流域土壤湿度反演与监测研究[J]. 生态学报, 2019, 39(14):5138-5148.
[
|
[5] |
周壮, 赵少杰, 蒋玲梅. 被动微波遥感土壤水分产品降尺度方法研究综述[J]. 北京师范大学学报(自然科学版), 2016, 52(4):479-485.
[
|
[6] |
蒋玲梅, 崔慧珍, 王功雪, 等. 积雪、土壤冻融与土壤水分遥感监测研究进展[J]. 遥感技术与应用, 2020, 35(6):1237-1262.
[
|
[7] |
|
[8] |
|
[9] |
|
[10] |
|
[11] |
|
[12] |
J, Pellenq. A disaggregation scheme for soil moisture based on topography and soil depth[J]. Journal of Hydrology, 2003,276(1/2/3/4):112-127. DOI:10.1016/S0022-1694(03)00066-0
|
[13] |
盛佳慧, 饶鹏. 基于风云气象卫星的土壤湿度数据降尺度方法研究[J]. 红外与毫米波学报, 2021, 40(1):74-88.
[
|
[14] |
|
[15] |
|
[16] |
|
[17] |
Inge, Sandholt. A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status[J]. Remote Sensing of Environment, 2002, 79(2/3):213-224. DOI:10.1016/S0034-4257(01)00274-7
|
[18] |
曹永攀, 晋锐, 韩旭军, 等. 基于MODIS和AMSR-E遥感数据的土壤水分降尺度研究[J]. 遥感技术与应用, 2011, 26(5):590-597.
[
|
[19] |
辛强, 李兆富, 李瑞娟, 等. 基于温度植被干旱指数的华东地区AMSR-E土壤水分数据的空间降尺度研究[J]. 农业现代化研究, 2016, 37(5):956-963.
[
|
[20] |
王安琪, 解超, 施建成, 等. MODIS温度变化率与AMSR-E土壤水分的关系的提出与降尺度算法推广[J]. 光谱学与光谱分析, 2013, 33(3):623-627.
[
|
[21] |
|
[22] |
|
[23] |
Wei, Zhao. A spatial downscaling approach for the SMAP passive surface soil moisture product using random forest regression[J]. Journal of Hydrology, 2018, 563:1009-1024. DOI:10.1016/j.jhydrol.2018.06.081
|
[24] |
|
[25] |
|
[26] |
|
[27] |
荀其蕾, 董乙强, 安沙舟, 等. 基于MOD 09GA数据的新疆草地生长状况遥感监测研究[J]. 草业学报, 2018, 27(4):10-26.
[
|
[28] |
Olivier, Merlin. Towards deterministic downscaling of SMOS soil moisture using MODIS derived soil evaporative efficiency[J]. Remote Sensing of Environment, 2008, 112(10):3935-3946. DOI:10.1016/j.rse.2008.06.012
|
[29] |
方蓓婧. 华北平原蒸散发估算及其时空变化规律研究[D]. 北京: 清华大学, 2018.
[
|
[30] |
童成立, 张文菊, 汤阳, 等. 逐日太阳辐射的模拟计算[J]. 中国农业气象, 2005, 26(3):165-169.
[
|
[31] |
[32] |
任梅芳, 庞博, 徐宗学, 等. 基于随机森林模型的雅鲁藏布江流域气温降尺度研究[J]. 高原气象, 2018, 37(5):1241-1253.
[
|
[33] |
李婉, 牛陆, 陈虹, 等. 基于随机森林算法的地表温度鲁棒降尺度方法[J]. 地球信息科学学报, 2020, 22(8):1666-1678.
[
|
[34] |
李建明, 马燕飞, 李仁杰, 等. 基于随机森林的海河流域地表温度降尺度[J]. 遥感信息, 2021, 36(4):151-158.
[
|
[35] |
刘长春, 刘鹏举, 季烨云. 基于视频区域动态特征的林火烟雾检测技术研究[J]. 北京林业大学学报, 2021, 43(1):10-19.
[
|
[36] |
张玲, 安如, 王喆. 主/被动微波遥感数据融合的土壤湿度产品的CDF改进研究[J]. 科学技术与工程, 2015, 15(30):1-8.
[
|
[37] |
杜晓彤, 方秀琴, 汪伟, 等. 基于SMAR模型的半干旱区根系层土壤湿度估算[J]. 水土保持研究, 2020, 27(3):119-127,133.
[
|
/
〈 | 〉 |