Surface soil moisture inversion of farmland based on Sentinel multi-source remote sensing data
-
摘要: 【目的】 通过多源遥感数据协同作用分析滇中地区姚安灌区的农田地表土壤含水率，为后续对滇中高原地区的地表土壤水分研究提供参考。【方法】 选择Landsat 8、Sentinel遥感数据为数据源，构建土壤水分与特征参数关系式，比较线性回归模型、BP神经网络模型、粒子群优化（PSO）的BP（PSO-BP）神经网络模型、随机森林（RF）算法预测土壤含水率的精度，选择最佳方法反演姚安灌区农田地表土壤含水率。【结果】 协同Sentinel-1微波数据和Sentinel-2光学数据，水云模型作用下VV后向散射系数减少0.1～0.4 dB、VH后向散射系数减少0～0.05 dB；加入特征参数，对比线性回归模型，BP神经网络模型的决定系数（R2）提高0.4589、PSO-BP神经网络模型的R2提高0.3811、RF算法的R2提高0.4544，其中，BP神经网络模型的R2和均方根误差（RMSE）较优。依据BP神经网络模型反演的土壤含水率与监督分类的土地利用分类进行叠加分析，可知姚安灌区土壤含水率集中在20%～30%，位置主要集中在姚安灌区中部，土壤含水率10%～20%区域主要集中在姚安灌区北部，而土壤含水率30%～40%区域覆盖面积少且分散。姚安灌区的土壤类型根据土壤墒情的划分标准主要属于褐墒（合墒）和黑墒（饱墒）。【建议】优化模型及算法，增加土壤含水率实测数据量，提高反演精度；针对水资源分布不均的问题，融合无人机遥感数据，对土壤含水分进行实时监测，动态分配水资源，形成土壤水分评价机制与监测机制，实现水资源的合理分配。
-
关键词:
- 水云模型 /
- Sentinel数据 /
- 线性回归模型 /
- BP神经网络模型 /
- 土壤水分反演
Abstract: 【Objective】 The synergistic effect of multi-source remote sensing data was used to analyze the surface soil moisture rate of farmland in Yao’an irrigation area in central Yunnan,which could provide reference for surface soil moisture research in central Yunnan Plateau. 【Method】 Landsat 8 data,Sentinel microwave data were selected as data sources to construct the relationship between soil moisture and feature parameters,and the accuracy of linear regression model,BP neural network model and particle swarm optimization（PSO） BP（PSO-BP） neural network model and random forest（RF） algorithm in predicting soil moisture content was compared,the best method was selected to analyze the surface soil moisture content of farmland in Yao’an irrigation area.【Result】Combined with Sentinel-1 microwave data and Sentinel-2optical data,the VV backscatter coefficient was reduced by 0.1-0.4 dB and VH backscatter coefficient was reduced by 0-0.05 dB under the action of water cloud model. Adding feature parameters,compared with the linear regression model,the coefficient of determination（R2） of the BP neural network model was increased by 0.4589,R2 of PSO-BP neural network model was increased by 0.3811,and R2 of RF algorithm was improved by 0.4544,among which the root mean square error（RMSE） of the BP neural network model was better. According to the superposition analysis of soil moisture content and land use classification of supervised classification inverted by BP neural network model,it could be found that the soil moisture content in Yao’an irrigation area was concentrated in 20%-30%,and the location was mainly concentrated in the middle of Yao’an irrigation area,the area with soil moisture content of 10%-20% was mainly concentrated in the northern part of Yao’an irrigation area,and the area with soil moisture content of 30%-40% covered a small and scattered area. According to the classification criteria of soil moisture,the soil types in Yao’an irrigation area mainly belonged to brown moisture（combined moisture） and black moisture（full moisture）. 【Suggestion】Optimize the model and algorithm,increase the amount of measured data of soil moisture content,improve the accuracy of inversion; and integrate unmanned aerial vehicle（UAV） remote sensing data to monitor soil water rate in real time and dynamically allocate water resources in view of the problem of uneven distribution of water resources,so as to form a soil moisture evaluation mechanism and monitoring mechanism to achieve reasonable allocation of water resources. -
-
郭二旺,郭乙霏,罗蔚然,王文婷.2019.基于Landsat 8和Sen-tinel-1A数据的焦作广利灌区夏玉米土壤墒情监测方法研究[J].中国农村水利水电,(7):22-25.[Guo E W,Guo Y F,Luo W R,Wang W T.2019.Soil moisture retrieval of summer maize in the irrigation area based on Sentinel-1A[J].China Rural Water and Hydropower,(7):22-25.]doi: 10.3969/j.issn.1007-2284.2019.07.005. 郭交,刘健,宁纪锋,韩文霆.2019.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,35(14):71-78.[Guo J,Liu J,Ning J F,Han W T.2019.Construction and validation of soil moisture retrieval model in farmland based on Sentinel multi-source data[J].Transactions of the Chinese Society of Agricultural Engi-neering,35(14):71-78.]doi: 10.11975/j.issn.1002-6819.2019.14.009. 郭玉娣,李根,李春,梁冬坡.2023.基于多时相合成孔径雷达数据的水稻种植面积监测[J].江苏农业学报,39(5):1179-1188.[Guo Y D,Li G,Li C,Liang D P.2023.Rice planting area monitoring based on multi-temporal syn-thetic aperture radar (SAR) data[J].Jiangsu Journal of Agricultural Sciences,39(5):1179-1188.]doi: 10.3969/j.issn.1000-4440.2023.05.010. 李伯祥,陈晓勇.2020.基于Sentinel多源遥感数据的河北省景县农田土壤水分协同反演[J].生态与农村环境学报,36(6):752-761.[Li B X,Chen X Y.2020.Synergic use of Sentinel-1 and Sentinel-2 images for soil moisture retrieval in vegetation covered agricultural areas of Jingxian County of Heibei Province[J].Journal of Ecology and Rural Envi-ronment,36(6):752-761.]doi: 10.19741/j.issn.1673-4831.2019.0944. 李艳,张成才,罗蔚然.2019.利用改进的水云模型反演夏玉米拔节期土壤墒情方法研究[J].水利水电技术,50(3):212-218.[Li Y,Zhang C C,Luo W R.2019.Study on inverting soil moisture of summer corn jointing stage with improved water cloud model[J].Water Resources and Hydropower Engineering,50(3):212-218.]doi: 10.13928/j.cnki.wrahe.2019.03.029. 刘正春,冯美臣,徐立帅,荆耀栋,毕如田.2020.基于Sentinel多源数据的晋南农田地表土壤水分反演[J].中国农学通报,36(20):51-58.[Liu Z C,Feng M C,Xu L S,Jing YD,Bi R T.2020.Soil moisture retrieval of farmland in Southern Shanxi:Based on Sentinel multi-source data[J].Chinese Agricultural Science Bulletin,36(20):51-58.] 石莹,穆岑,田艳君,黄月如,郭润潇,孙晓雪.2022.基于Landsat-8数据对甘肃省金塔县主要农作物分类[J].测绘与空间地理信息,45(2):74-78.[Shi Y,Mu C,Tian YJ,Huang Y R,Guo R X,Sun X X.2022.Classification of main cropsin Jinta County,Gansu Province based on Landsat-8 data[J].Geomatics&Spatial Information Technology,45(2):74-78.]doi: 10.3969/j.issn.1672-5867.2022.02.020. 苏伟,侯宁,李琪,张明政,赵晓凤,蒋坤萍.2018.基于Senti-nel-2遥感影像的玉米冠层叶面积指数反演[J].农业机械学报,49(1):151-156.[Su W,Hou N,Li Q,Zhang MZ,Zhao X F,Jiang K P.2018.Retrieving leaf area index of corn canopy based on Sentinel-2 remote sensing image[J].Transactions of the Chinese Society for Agricultural Machinery,49(1):151-156.]doi: 10.6041/j.issn.1000-1298.2018.01.019. 余凡,翟亮,张承明.2016.主被动遥感协同反演地表土壤水分方法[M].北京:测绘出版社.[Yu F,Zhai L,Zhang CM.2016.Methods on land surface soil moisture retrieval based on intergrating active and passive remote sensing data[M].Beijing:Sino Maps Press.] 余凡,赵英时,李海涛.2012.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报,31(3):283-288.[Yu F,Zhao Y S,Li H T.2012.Soil moisture retrieval based on GA-BP neural networks algorithm[J].Journal of Infrared and Millimeter Waves,31(3):283-288.]doi: 10.3724/SP.J.1010.2012.00283. 杨贵军,岳继博,李长春,冯海宽,杨浩,兰玉彬.2016.基于改进水云模型和Radarsat-2数据的农田土壤含水量估算[J].农业工程学报,32(22):146-153.[Yang G J,Yue JB,Li C C,Feng H K,Yang H,Lan Y B.2016.Estimation of soil moisture in farmland using improved water cloud model and Radarsat-2 data[J].Transactions of the Chinese Society of Agricultural Engineering,32(22):146-153.]doi: 10.11975/j.issn.1002-6819.2016.22.020. 张景略.1980.黄泛平原的土壤墒情[J].河南农林科技,(10):6-8.[Zhang J L.1980.Soil moisture of the Yellow River flood plain[J].Henan Agriculture and Forestry Science and Technology,(10):6-8.] 张义峥,吴鹏海,段四波,杨辉,殷志祥.2021.Landsat 8地表温度产品降尺度深度学习方法研究[J].遥感学报,25(8):1767-1777.[Zhang Y Z,Wu P H,Duan S B,Yang H,Yin Z X.2021.Downscaling of Landsat 8 land surface temperature products based on deep learning[J].National Remote Sensing Bulletin,25(8):1767-1777.] Dubois P C,van Zyl J,Engman T.1995.Measuring soil mois-ture with imaging radars[J].IEEE Transactions on Geoscience and Remote Sensing,33(4):915-926.doi: 10.1109/36.406677.
Karthikeyan L,Pan M,Wanders N,Kumar D N,Wood E F.2017.Four decades of microwave satellite soil moisture observations:Part 1.A review of retrieval algorithms[J].Advances in Water Resources,109:106-120.doi: 10.1016/j.advwatres.2017.09.006.
Karam M A,Fung A K,Lang R H,Chauhan N S.1992.Amicrowave scattering model for layered vegetation[J].IEEE Transactions on Geoscience and Remote Sensing,30(4):767-784.doi: 10.1109/36.158872.
Legates D R,Mahmood R,Levia D F,DeLiberty T L,Quiring S M,Houser C,Nelson F E.2011.Soil moisture:A central and unifying theme in physical geography[J].Progress in Physical Geography,35(1):65-86.doi: 10.1177/0309133310386514.
Meng Q Y,Xie Q X,Wang C M,Ma J X,Sun Y X,Zhang L L.2016.A fusion approach of the improved Dubois model and best canopy water retrieval models to retrieve soil moisture through all maize growth stages from Radarsat-2and Landsat-8 data[J].Environmental Earth Sciences,75(20):1377.doi: 10.1007/s12665-016-6182-4.
Oh Y,Sarabandi K,Ulaby F T.1992.An empirical model and an inversion technique for radar scattering from bare soil surfaces[J].IEEE Transactions Geoscience and Remote Sensing,30(2):370-381.doi: 10.1109/36.134086.
Shi J C,Wang J,Hsu A Y,O’Neill P E,Engman E T.1995.Estimation of bare soil moisture and surface roughness parameters using L-band SAR image data[J].IEEE Transactions on Geoscience and Remote Sensing,33(5):1254-1266.doi: 10.1109/36.628792.
Song X D,Zhang G L,Liu F,Li D C,Zhao Y G,Yang J L.2016.Modeling spatio-temporal distribution of soil mois-ture by deep learning-based cellular automata model[J].Journal of Arid Land,8(5):734-748.doi: 10.1007/s40333-016-0049-0.
Torres R,Snoeij P,Geudtner D,Bibby D,Davidson M,Attema E,Potin P,Rommen B,Floury N,Brown M.2012.GMESSentinel-1 mission[J].Remote Sensing of Environment,120(6):9-24.doi: 10.1016/j.rse.2011.05.028.
计量
- 文章访问数: 9
- HTML全文浏览量: 0
- PDF下载量: 3
下载: