留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

王宇,  杨丽萍,  任杰,  张静,  孔金玲,  侯成磊

downloadPDF
文章导航 > 武汉大学学报 ( 信息科学版)  > 优先出版
王宇, 杨丽萍, 任杰, 张静, 孔金玲, 侯成磊. 联合ALOS-2和Landsat-8的绿洲土壤水分反演模型研究[J]. 武汉大学学报 ( 信息科学版). doi: 10.13203/j.whugis20220008
引用本文: 王宇, 杨丽萍, 任杰, 张静, 孔金玲, 侯成磊. 联合ALOS-2和Landsat-8的绿洲土壤水分反演模型研究[J]. 武汉大学学报 ( 信息科学版). doi: 10.13203/j.whugis20220008
shu
WANG Yu, YANG Liping, REN Jie, ZHANG Jing, KONG Jinling, HOU Chenglei. Integration Study on Oasis Soil Moisture Inversion Using ALOS-2 and Landsat-8[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20220008
Citation: WANG Yu, YANG Liping, REN Jie, ZHANG Jing, KONG Jinling, HOU Chenglei. Integration Study on Oasis Soil Moisture Inversion Using ALOS-2 and Landsat-8[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20220008
shu

联合ALOS-2和Landsat-8的绿洲土壤水分反演模型研究

doi: 10.13203/j.whugis20220008

  • 1 长安大学地质工程与测绘学院 陕西 西安 710054;

  • 2 山东农业工程学院国土资源与测绘工程学院 山东 济南 250100

基金项目: 

国家自然科学基金（41371220，42071345）；中央高校基本科研业务费专项资金（300102269112）。

详细信息
    作者简介:

    王宇,硕士生,主要从事土壤水分遥感研究。wangyu_9711@163.com

    通讯作者: 杨丽萍,博士,副教授,硕士生导师。zylpyang@chd.edu.cn

  • 中图分类号: P237

Integration Study on Oasis Soil Moisture Inversion Using ALOS-2 and Landsat-8

  • 1 School of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China;

  • 2 College of Land Resources and Surveying&Mapping Engineering, Shandong Agriculture and Engineering University, Jinan 250100, China

  • 摘要: 机器学习和多源数据融合是土壤水分反演研究的热点方向，但已有工作对L波段SAR数据的研究较少。以额济纳绿洲为研究区，利用ALOS-2 PALSAR-2和Landsat-8影像，提取雷达和光学特征参数，通过参数重要性评分进行特征筛选，采用随机森林建立基于雷达、光学以及雷达-光学特征参数协同的土壤水分反演模型，对比模型精度，反演绿洲土壤水分。结果表明：（1）与C波段相比，L波段SAR数据对干旱荒漠绿洲区土壤水分含量敏感性更高。（2）雷达特征参数中重要性较高的为表面散射和体散射分量，二面角散射和螺旋体散射分量相对偏低；光学特征参数中植被供水指数重要性最高，增强型植被指数重要性最低。（3）雷达特征参数方案最优模型R2、RMSE分别为0.67、2.16%。光学特征参数方案模型精度普遍较低且精度相当，R2、RMSE在0.5、2.47%左右。（4）雷达-光学参数协同反演的最优模型R2、RMSE分别为0.72、1.99%。相比单一数据源，R2分别提升7.46%、38.4%，RMSE分别降低8.54%、22.6%。研究证明基于多源数据融合的随机森林模型在干旱荒漠绿洲区具有较高的预测精度和良好的适用性。
    Abstract: Objectives:Integration of machine learning and multi-source data has become one of the hot topics in soil moisture inversion, where relatively few studies have been performed on L-band SAR imagery. Methods:In this paper, ALOS-2 PALSAR-2 and Landsat-8 imagery of the Ejina Oasis were used to extract the radar and optical characteristic parameters which were then screened according to the importance score. Random forest was adopted to establish different soil moisture inversion models based on radar, optical, and radar-optical integrated parameters. Model accuracies were evaluated and soil moisture content in Ejina Oasis was inversed. Results:(1) Compared with C-band data, L-band SAR data is more sensitive to soil moisture content in arid desert oasis. (2) With regard to radar characteristic parameters, surface and volume scattering components have higher important scores. Dihedral and helix scattering component are less important. As for optical characteristic parameters, vegetation water supply index takes the most important place while enhanced vegetation index is the least important one. (3) The optimal models R2 and RMSE of radar characteristic parameter scheme were 0.67 and 2.16% respectively. The accuracy of optical characteristic parameter scheme model is generally low and the accuracy is equivalent, R2 and RMSE were about 0.5 and 2.47%. (4) The optimal model R2 and RMSE of radar optical parameter integrated inversion were 0.72 and 1.99%, respectively. Compared with a single data source, R2 increased by 7.46% and 38.4%, and RMSE decreased by 8.54% and 22.6%, respectively. Conclusions:The research proves that the random forest model based on multi-source data fusion has higher prediction accuracy and better applicability in arid desert oasis area.
  • [1] Li Zhanjie, Chen Jipei, Liu Yanmin, et al. Soil Moisture Retrieval from Remote Sensing[J]. Journal of Beijing Normal University(Natural Science),2020,56(3):474-481(李占杰,陈基培,刘艳民,等.土壤水分遥感反演研究进展[J].北京师范大学学报(自然科学版), 2020,56(3):474-481)
    [2] Wang H, Magagi R, Goïta K. Potential of a Two-Component Polarimetric Decomposition at C-band for Soil Moisture Retrieval over Agricultural Fields[J]. Remote Sensing of Environment, 2018,217:38-51
    [3] Bourgeau-Chavez L L, Leblon B, Charbonneau F, et al. Evaluation of Polarimetric Radarsat-2 SAR Data for Development of Soil Moisture Retrieval Algorithms over a Chronosequence of Black Spruce Boreal Forests[J]. Remote Sensing of Environment, 2013,132:71-85
    [4] Breiman L. Random Forest[J]. Machine Learning, 2001,45:5-32
    [5] Ahmad S, Kalra A, Stephen H. Estimating Soil Moisture Using Remote Sensing Data:A Machine Learning Approach[J]. Advances in Water Resources, 2010,33(1):69-80
    [6] Skc A, Pks A, Dkg A, et al. Machine Learning Algorithms for Soil Moisture Estimation Using Sentinel-1:Model Development and Implementation[J]. Advances in Space Research, 2021
    [7] Li Pingxiang, Liu Zhiqu, Yang Jie, et al. Soil Moisture Retrieval of Winter Wheat Fields Based on Random Forest Regression Using Quad-Polarimetric SAR Images[J]. Geomatics and Information Science of Wuhan University, 2019,44(3):405-412(李平湘,刘致曲,杨杰,等.利用随机森林回归进行极化SAR土壤水分反演[J].武汉大学学报(信息科学版), 2019,44(3):405-412)
    [8] Zhao Jianhui, Zhang Bei, Li Ning, et al. Cooperative Inversion of Winter Wheat Covered Surface Soil Moisture Based on Sentinel-1/2 Remote Sensing Data[J]. Journal of Electronics & Information Technology, 2021,43(3):692-699(赵建辉,张蓓,李宁,等.基于Sentinel-1/2遥感数据的冬小麦覆盖地表土壤水分协同反演[J].电子与信息学报, 2021,43(3):692-699)
    [9] Guo Jiao, Liu Jian, Ning Jifeng, et al. Construction and Validation of Soil Moisture Retrieval Model in Farmland Based on Sentinel Multi-source Data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019,35(14):71-78(郭交,刘健,宁纪锋,等.基于Sentinel多源数据的农田地表土壤水分反演模型构建与验证[J].农业工程学报, 2019,35(14):71-78)
    [10] Holtgrave A K, Frster M, Greifeneder F, et al. Estimation of Soil Moisture in Vegetation-Covered Floodplains with Sentinel-1 SAR Data Using Support Vector Regression[J]. PFG-Journal of Photogrammetry Remote Sensing and Geoinformation Science, 2018,86(1):1-17
    [11] Liu C A, Chen Z X, Shao Y, et al. Research Advances of SAR Remote Sensing for Agriculture Applications:A Review[J]. Journal of Integrative Agriculture, 2019,18(3):506-525
    [12] Robinson D A, Campbell C S, Hopmans J W, et al. Soil Moisture Measurement for Ecological and Hydrological Watershed-Scale Observatories:A Review[J]. Vadose Zone Journal, 2008,7(1):358-389
    [13] Wang D, Liu C, Zeng Y, et al. Dryland Crop Classification Combining Multitype Features and Multitemporal Quad-Polarimetric RADARSAT-2 Imagery in Hebei Plain, China[J]. Sensors, 2021,21(2):332.
    [14] Freeman A, Durden S L. A Three-Component Scattering Model for Polarimetric SAR Data[J]. IEEE Transactions on Geoscience & Remote Sensing, 1998,36(3):963-973
    [15] Cloude S R, Pottier E, A Review of Target Decomposition Theorems in Radar Polarimetry[J]. IEEE Trans.Geosci. Remote Sens. 1996,34(2), 498-518
    [16] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-Component Scattering Model for Polarimetric SAR Image Decomposition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005,43(8):1699-1706
    [17] An W,Cui Y,Yang J. Three-Component Model-Based Decomposition for Polarimetric SAR Data[J]. IEEE Transactions on Geoscience & Remote Sensing, 2010,48(6):2732-2739
    [18] Cloude S R, Pottier E. An Entropy Based Classification Scheme for Land Applications of Polarimetric SAR[J]. IEEE Trans. Geo. Remote Sens, 1997,35(1):68-78
    [19] Vanzyl J J. Application of Cloude's Target Decomposition Theorem to Polarimetric Imaging Radar Data[J]. Radar Polarimetry, 1993:184-191
    [20] Bhattacharya A, Muhuri A, De S, et al. Modifying the Yamaguchi Four-Component Decomposition Scattering PowersUsing a Stochastic Distance[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2015,8(7):3497-3506
    [21] Rouse J W,Haas R H,Schell J A, et al. Monitoring Vegetation Systems in the Great Plains with ERTS[J]. Nasa Special Publication,1974:309-351
    [22] Fernández-Buces N, Siebe C, Cram S, et al. Mapping Soil Salinity Using a Combined Spectral Response Index for Bare Soil and Vegetation:A Case Study in the Former Lake Texcoco, Mexico[J]. Journal of Arid Environments, 2006,65(4):644-667
    [23] Huete A, Justice C, Liu H. Development of Vegetation and Soil Indices for MODIS-EOS[J]. Remote Sensing of Environment, 1994,49(3):224-234.
    [24] Louhaichi M, Borman M M, Johnson D E. Spatially Located Platform and Aerial Photography for Documentation of Grazing Impacts on Wheat[J]. Geocarto International, 2001,16(1):65-70
    [25] Ceccato P, Gobron N, Flasse S, et al. Designing a Spectral Index to Estimate Vegetation Water Content from Remote Sensing Data:Part 1:Theoretical Approach[J]. Remote Sensing of Environment, 2002,82(2-3):188-197
    [26] Crippen R E. Calculating the Vegetation Index Faster[J]. Remote Sensing of Environment, 1990,34(1):71-73.
    [27] Feng Rui, Zhang Yushu, Li Danghong. Using AVHRR Data to Monitor Vegetation Soil Moisture Content[J]. Journal of Meteorology and Environment. 1998(4):30-31(冯锐,张玉书,李党红.利用AVHRR资料监测植被土壤含水量[J].气象与环境学报, 1998(4):30-31)
    [28] Qi J G, Chehbouni A R, Huete A R, et al. A Modified Soil Adjusted Vegetation Index[J]. Remote Sensing of Environment, 1994,48(2):119-126
    [29] Sandholt I, Rasmussen K, Andersen J. 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
    [30] Luo Ling, Mao Dehua,Zhang Bai,et al.Remote Sensing Estimation for Light Use Efficiency of Phragmites australis Based on Landsat OLI over Typical Wetlands[J].Geomatics and Information Science of Wuhan University,2020,45(4):524-533.(罗玲,毛德华,张柏,等.基于Landsat OLI影像的典型湿地芦苇植被光能利用率遥感反演方法初探[J].武汉大学学报·信息科学版,2020,45(4):524-533)
    [31] Duan Sibo, Ru Chen, Li Zhaoliang, et al.Reviews of Methods for Land Surface Temperature Retrieval from Landsatthermal Infrared Data[J]. National Remote Sensing Bulletin. 2021,25(8):1591-1617(段四波,茹晨,李召良,等. Landsat卫星热红外数据地表温度遥感反演研究进展[J].遥感学报, 2021,25(8):1591-1617)
    [32] Yu Tingting, Dong Youfu. Correcting Elevation Error of ASTER GDEM Using Random Forest Regression Algorithm[J].Geomatics and Information Science of Wuhan University,2021,46(7):1098-1105.(余婷婷,董有福.利用随机森林回归算法校正ASTER GDEM高程误差[J].武汉大学学报·信息科学版,2021,46(7):1098-1105.)
    [33] Cheng Xiaoguang. Research of Model-based Polarimetric SAR Decomposition Constrained for Nonnegative Eigenvalues[D].[Ph.D. dissertation], Wuhan University, 2014(程晓光.特征值非负约束下的基于模型的极化SAR分解研究[D].[博士论文],武汉大学, 2014)
    [34] Chen Liang, Wang Xuelei, Yang Chao, et al. Spatio-Temporal Variation Characteristics of Vegetation EVI and Their Topographic Effects in the West Mountain Regions of Hubei Province from 2000 to 2018[J]. Resources and Environment in the Yangtze Basin, 2021,30(2):419-426(陈亮,王学雷,杨超,等. 2000~2018年鄂西山区植被EVI时空变化特征及其地形效应[J].长江流域资源与环境, 2021,30(2):419-426)
    [35] Huang Youxi, Liu Xiuguo, Shen Yonglin, et al. Advances in Remote Sensing Derived Agricultural Drought Monitoring Indices and Adaptability Evaluation Methods[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(16):186-195(黄友昕,刘修国,沈永林,等.农业干旱遥感监测指标及其适应性评价方法研究进展[J].农业工程学报, 2015,31(16):186-195)
    [36] Yang Liping, Wang Tong, Su Zhiqiang, et al. An Optimized Dimensionality Reduction Method of Characteristic Parameters for Retrieving Oasis Soil Moisture Using Random Forest[J]. Journal of Northwest University(Natural Science Edition), 2022,52(2):181-191(杨丽萍,王彤,苏志强,等.随机森林反演绿洲土壤水分的特征参数优化降维方法[J].西北大学学报(自然科学版), 2022,52(2):181-191.)
    [37] El Hajj M, Baghdadi N, Bazzi H, et al. Penetration Analysis of SAR Signals in the C and L Bands for Wheat, Maize, and Grasslands[J]. Remote Sensing, 2019,11(1):31.
    [38] Ayari E, Kassouk Z, Lili-Chabaane Z, et al. Cereal Crops Soil Parameters Retrieval Using L-Band ALOS-2 and C-Band Sentinel-1 Sensors[J]. Remote Sensing, 2021,13(7):1393.
    [39] Zhou Peng, Ding Jianli, Wang Fei, et al. Retrieval Methods of Soil Water Content in Vegetation Covering Areas Based on Multi-Source Remote Sensing Data[J]. Journal of Remote Sensing. 2010,14(5):959-973. (周鹏,丁建丽,王飞等.植被覆盖地表土壤水分遥感反演[J].遥感学报, 2010,14(5):959-973)
    [40] Wang Hao, Luo Geping, Wang Weisheng, et al. Inversion of Soil Moisture Content in the Farmland in Middle and Lower Reaches of Syr Darya River Basin Based on Multi-Source Remotely Sensed Data[J]. Journal of Natural Resources,, 2019,34(12):2717-2731(王浩,罗格平,王伟胜,等.基于多源遥感数据的锡尔河中下游农田土壤水分反演[J].自然资源学报, 2019,34(12):2717-2731)
  • [1] 吴京航, 桂志鹏, 申力, 吴华意, 刘洪波, 李锐, 梅宇翱, 彭德华.  顾及格网属性分级与空间关联的人口空间化方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200379
    [2] 张嘉琪, 杜开虎, 任书良, 王瑞凡, 关庆锋, 陈文辉, 姚尧.  多源空间大数据场景下的家装品牌线下广告选址 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20190468
    [3] 余婷婷, 董有福.  利用随机森林回归算法校正ASTER GDEM高程误差 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20190245
    [4] 柳林, 宋豪峰, 杜亚男, 冯光财, 刘清瑶, 孙敏.  联合哨兵2号和Landsat 8估计白格滑坡时序偏移量 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200596
    [5] 种洋, 柴洪洲, 刘帆, 王旭, 杜祯强.  模糊决策理论的地磁图适配性分析 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20180280
    [6] 吴晓萍, 徐涵秋, 蒋乔灵.  GF-1、GF-2与Landsat-8卫星多光谱数据的交互对比 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20190084
    [7] 黄谟涛, 刘敏, 欧阳永忠, 邓凯亮, 马越原, 翟国君, 吴太旗.  海洋重力场特征统计模型计算与分析 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20160529
    [8] 李秋萍, 刘逸诗, 巩诗瑶, 周素红, 卓莉, 陶海燕, 栾学晨.  基于居民出行活动特征的个体经济水平推断方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20170426
    [9] 李平湘, 刘致曲, 杨杰, 孙维东, 黎旻懿, 任烨仙.  利用随机森林回归进行极化SAR土壤水分反演 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20160531
    [10] 刘坚, 李树林, 陈涛.  基于优化随机森林模型的滑坡易发性评价 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20160515
    [11] 顾海燕, 闫利, 李海涛, 贾莹.  基于随机森林的地理要素面向对象自动解译方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20140102
    [12] 金绍华, 肖付民, 边刚, 王沫, 孙文川.  利用多波束反向散射强度角度响应曲线的底质特征参数提取算法 . 武汉大学学报 ( 信息科学版),
    [13] 余凡, 李海涛, 张承明, 万紫, 刘江, 赵颖.  利用双极化微波遥感数据反演土壤水分的新方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20120527
    [14] 孙杰, 赖祖龙.  利用随机森林的城区机载LiDAR数据特征选择与分类 . 武汉大学学报 ( 信息科学版),
    [15] 裴欢, 房世峰, 覃志豪, 侯春良.  干旱区绿洲生态脆弱性评价方法及应用研究——以吐鲁番绿洲为例 . 武汉大学学报 ( 信息科学版),
    [16] 张显峰, 赵杰鹏.  干旱区土壤水分遥感反演与同化模拟系统研究 . 武汉大学学报 ( 信息科学版),
    [17] 刘海, 陈晓玲, 宋珍, 殷守敬.  MODIS影像雪深遥感反演特征参数选择与模型研究 . 武汉大学学报 ( 信息科学版),
    [18] 吴宏安, 汤益先, 张红, 王超.  基于ALOS/PALSAR轨道参数的干涉平地效应消除研究 . 武汉大学学报 ( 信息科学版),
    [19] 余凡, 赵英时.  合成孔径雷达反演裸露地表土壤水分的新方法 . 武汉大学学报 ( 信息科学版),
    [20] 毛丽君, 李明诗.  GEE环境下联合Sentinel主被动遥感数据的国家公园土地覆盖分类 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200633
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  153
  • HTML全文浏览量:  23
  • PDF下载量:  3
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-10-04
  • 网络出版日期:  2022-10-21

doi: 10.13203/j.whugis20220008
  • 1 长安大学地质工程与测绘学院 陕西 西安 710054;
  • 2 山东农业工程学院国土资源与测绘工程学院 山东 济南 250100
    • 基金项目:

    国家自然科学基金（41371220，42071345）；中央高校基本科研业务费专项资金（300102269112）。

    作者简介:

    王宇,硕士生,主要从事土壤水分遥感研究。wangyu_9711@163.com

  • 收稿日期: 2022-10-04
  • 网络出版日期: 2022-10-21

  • 中图分类号: P237

摘要: 机器学习和多源数据融合是土壤水分反演研究的热点方向，但已有工作对L波段SAR数据的研究较少。以额济纳绿洲为研究区，利用ALOS-2 PALSAR-2和Landsat-8影像，提取雷达和光学特征参数，通过参数重要性评分进行特征筛选，采用随机森林建立基于雷达、光学以及雷达-光学特征参数协同的土壤水分反演模型，对比模型精度，反演绿洲土壤水分。结果表明：（1）与C波段相比，L波段SAR数据对干旱荒漠绿洲区土壤水分含量敏感性更高。（2）雷达特征参数中重要性较高的为表面散射和体散射分量，二面角散射和螺旋体散射分量相对偏低；光学特征参数中植被供水指数重要性最高，增强型植被指数重要性最低。（3）雷达特征参数方案最优模型R2、RMSE分别为0.67、2.16%。光学特征参数方案模型精度普遍较低且精度相当，R2、RMSE在0.5、2.47%左右。（4）雷达-光学参数协同反演的最优模型R2、RMSE分别为0.72、1.99%。相比单一数据源，R2分别提升7.46%、38.4%，RMSE分别降低8.54%、22.6%。研究证明基于多源数据融合的随机森林模型在干旱荒漠绿洲区具有较高的预测精度和良好的适用性。

English Abstract

王宇, 杨丽萍, 任杰, 张静, 孔金玲, 侯成磊. 联合ALOS-2和Landsat-8的绿洲土壤水分反演模型研究[J]. 武汉大学学报 ( 信息科学版). doi: 10.13203/j.whugis20220008
引用本文: 王宇, 杨丽萍, 任杰, 张静, 孔金玲, 侯成磊. 联合ALOS-2和Landsat-8的绿洲土壤水分反演模型研究[J]. 武汉大学学报 ( 信息科学版). doi: 10.13203/j.whugis20220008
shu
WANG Yu, YANG Liping, REN Jie, ZHANG Jing, KONG Jinling, HOU Chenglei. Integration Study on Oasis Soil Moisture Inversion Using ALOS-2 and Landsat-8[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20220008
Citation: WANG Yu, YANG Liping, REN Jie, ZHANG Jing, KONG Jinling, HOU Chenglei. Integration Study on Oasis Soil Moisture Inversion Using ALOS-2 and Landsat-8[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20220008
shu

    全文HTML

参考文献 (40)

目录

    /

    返回文章
    返回

    我要投稿

    投稿攻略

    联系我们

    二维码

    版权所有 © 2013 《武汉大学学报·信息科学版》编辑部

    地址：武汉大学文理学部本科生院楼北5楼邮政编码：430072

    电话：027-68778465,68778045E-mail:whuxxb@vip.163.com

    本系统由 北京仁和汇智信息技术有限公司 开发    百度统计