Multi-Vegetation Index Soil Moisture Inversion Model Based on UAV
Remote Sensing
LI Hu1, ZHONG Yun1, 2, FENG Ya-ting1, LIN Zhen1, ZHU Shi-jiang1, 2*
1. College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang 443002, China
2. Engineering Research Center of Eco-environment in Three Gorges Reservoir Region, Ministry of Education, Yichang 443002, China
摘要： 土壤水分是影响农业生产的重要因素, 在作物生长发育和最终产量上起着至关重要的作用，快速、高效地估算土壤水分已成为农林水资源监测的热点问题。利用高光谱反射率的特征波段计算植被指数、构建土壤水分反演模型已获得广泛的认可和应用。针对反演土壤水分受植被覆盖度影响较大的问题，提出用多种植被指数组合削弱植被覆盖度对土壤水分反演的影响。在宜昌市仓屋榜试验基地选取30组柑橘树，在果树滴落线处收集土壤，通过烘干法测定土壤质量含水率，采样4次，共计120组土壤含水率；并利用ASD Field Spectral FR光谱仪（波长范围325~1 075 nm）及大疆精灵4多光谱版无人机获取了120组试验区蓝、绿、红、红边、近红外及短波红外波段光谱反射率，采用移动平均法对光谱数据进行降噪预处理，通过灰色关联法对9种植被指数进行比较分析，筛选出与土壤水分极显著相关的4种植被指数（p<0.01），各指数与土壤水分的相关性从高到低依次为裸土指数(BSI) 、归一化蓝绿差异植被指数(NGBDI) 、绿色归一化指数(GNDVI)、归一化差异植被指数(NDVI)，其中BSI与土壤水分的相关性最高，相关系数为-0.687（N=120）。采用线性逐步回归法和非线性BP神经网络法建立了基于多种植被指数的土壤水分反演模型，依据决定系数（R2）、相对误差绝对值（ARE）、均方根误差（RMSE）作为反演模型的精度评价指标。结果表明：逐步回归模型和BP神经网络模型的土壤水分反演值与实测值之间的R2分别为0.816、0.889，RMSE分别为2.54%、1.53%，ARE分别为21.13%、8.88%，利用多植被指数组合的非线性BP神经网络算法基于植被指数建模对土壤水分反演的精度更高，在一定程度上可以克服植被覆盖度不同对土壤水分反演精度的影响，作为直接测定土壤水分的有效替代方法，为农业灌溉定量决策及科学管理提供科学参数。
关键词：土壤水分；多光谱遥感；植被指数；逐步回归；BP神经网络
Abstract：Soil moisture is an important factor affecting agricultural production and plays a vital role in crop growth and final yield. Rapid and efficient estimation of soil water content has become a hot issue in agricultural and forestry water resources monitoring. It has been widely recognized and applied to calculate vegetation index and build soil water content inversion model by using the characteristic bands of hyperspectral reflectance. Because of the problem that the inversion of soil water content is greatly affected by vegetation coverage, we propose to use multi vegetation index combination to weaken the influence of vegetation coverage on the inversion of soil water content. Thirty groups of citrus trees were selected as samples in the Cangwubang test base of Yichang City. The soil was collected at the drip line of the fruit tree, and the soil mass moisture content was determined by the drying method. Four times of sampling, a total of 120 groups of soil moisture content. We use the ASD Field Spectral FR spectrometer (wavelength range: 325~1 075 nm) and the Dajiang Genie 4 multispectral UAV to obtain the spectral reflectance in the blue, green, red, red edge, near-infrared and short wave infrared bands of 120 groups of test areas. We pretreat the spectral data with the moving average method for noise reduction, compare and analyze 9 vegetation indices with gray correlation method, and screen out 4 vegetation indices that are highly significantly related to soil water content (p<0.01). The correlation between each index and soil water content from high to low is the bare soil index (BSI), normalized blue-green differential vegetation index (NGBDI), green normalized index (GNDVI) and normalized differential vegetation index (NDVI). The correlation between BSI and soil water content is the highest, and the correlation coefficient is -0.687. We use the linear stepwise regression method and nonlinear BP neural network method to build a soil water content inversion model based on multi vegetation index and take the determination coefficient (R2), root mean square error (RMSE) and relative error (ARE) as the evaluation indexes of the inversion accuracy of the model. The results show that the R2 between the inversion value of soil water content and the measured value of the stepwise regression model and BP neural network model are 0.816 and 0.889 respectively, the RMSE is 2.54% and 1.53% respectively, and the ARE is 21.13% and 8.88% respectively. It shows that the nonlinear BP neural network algorithm based on multi vegetation index combination has higher accuracy in soil moisture inversion based on vegetation index modeling, and can overcome the influence of different vegetation coverage on the accuracy of soil moisture inversion to a certain extent. As an effective alternative method to measure soil moisture directly, it provides theoretical support for quantitative decision-making and scientific agricultural irrigation management.
[1] ZHANG Chuan-bo, LI Wei-guo, WANG Jing, et al(张传波, 李卫国, 王 晶, 等). Jiangsu Journal of Agricultural Sciences(江苏农业学报), 2022, 38(1): 111.
[2] ZHAO Jia-tao, MA Yu-zhao, FAN Yan-li, et al(赵嘉涛, 马玉诏, 范艳丽, 等). Journal of Drainage and Irrigation Engineering(排灌机械工程学报), 2021, 39(1): 96.
[3] GAO Jia, ZHANG Hong-bin, ZHANG Heng-jia, et al(高 佳, 张宏斌, 张恒嘉, 等）. Journal of Drainage and Irrigation Engineering(排灌机械工程学报), 2021, 39(4): 404.
[4] WU Hai-long, YU Xin-xiao, ZHANG Zhen-ming, et al(吴海龙, 余新晓, 张振明, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(6): 1615.
[5] Ankeny M D. Journal of Environmental Quality, 1992, 21(2): 290.
[6] Hosseini M, Saradjian M R. International Journal of Remote Sensing, 2011, 32(21): 6799.
[7] GAO Lu, ZHANG Sheng-wei, ZHU Zhong-yuan, et al(高 露, 张圣微, 朱仲元, 等). Journal of Soil and Water Conservation(水土保持学报), 2020, 34(1): 195.
[8] XIONG Shi-wei, LI Wei-guo, JIA Tian-shan, et al(熊世为, 李卫国, 贾天山, 等). Jiangsu Journal of Agricultural Sciences(江苏农业学报), 2014, 30(5): 1044.
[9] YANG Li-ping, BAI Yu-xing, ZHU Jiang-shan, et al(杨丽萍, 白宇兴, 朱江山, 等). Journal of Lanzhou University(Natural Science Edition)[兰州大学学报(自然科学版)], 2021, 57(6): 727.
[10] BU Xiao-dong, GUO Hui, HUANG Ke-jing(卜小东, 郭 辉, 黄可京). Jiangsu Agricultural Sciences(江苏农业科学), 2020, 48(20): 25.
[11] YANG Na, GUO Xing-guo(杨 娜, 郭兴国). Research of Soil and Water Conservation(水土保持研究), 2022, 29(3): 147.
[12] KANG Wei-min, LUO Yu-xiang, XIANG Hong-qiong, et al(康为民, 罗宇翔, 向红琼, 等). Meteorological Monthly(气象), 2010, 36(10): 78.
[13] CAI Qing-kong, LI Er-jun, TAO Liang-liang, et al(蔡庆空, 李二俊, 陶亮亮, 等). Chinese Journal of Soil Science(土壤通报), 2021, 52(5): 1069.
[14] CHEN Ming-tao, FAN Jun-wei, PENG Ji-huang, et al(陈铭涛, 范俊伟, 彭继煌, 等). Modern Agricultural Science and Technology(现代农业科技), 2014，(6): 142.
[15] WANG De-wei, XU Li-yan, ZHOU Yun, et al(王德维, 徐立燕, 周 云, 等). Jiangsu Water Resources(江苏水利), 2017, (7): 68.
[16] YU Xin-hua, WANG Hong(余新华, 王 宏). The World of Survey and Research(调研世界), 2020，(6): 16.
[17] WANG Tong-tong, ZHAI Jun-hai, HE Huan, et al(王彤彤, 翟军海, 何 欢, 等). Research of Soil and Water Conservation(水土保持研究), 2017, 24(3): 86.
[18] WANG Rong-bing, XU Hong-yan, LI Bo, et al(王嵘冰, 徐红艳, 李 波, 等). Computer Technology and Development(计算机技术与发展), 2018, 28(4): 31.
[19] PENG Xiao-wei, ZHANG Ai-jun, YANG Xiao-nan, et al(彭晓伟, 张爱军, 杨晓楠, 等). Agricultural Research in the Arid Areas(干旱地区农业研究), 2022, 40(2): 69.
[20] ZHANG Jia-you, SONG Wan-wan, BAI Yu-zhen, et al(张家有, 宋万万, 白玉珍, 等). Diamond and Abrasive Engineering(金刚石与磨料磨具工程), 2021, 41(6): 63.
[21] HU Rong-ming, LI Shao-jie, MA Chun-xiao, et al(胡荣明，李少杰，马春笑，等). Journal of Xi'an University of Science and Technology(西安科技大学学报)，2020，40(3)：449.
[22] Navarro G, Caballero I, Silva G, et al. International Journal of Applied Earth Observation and Geoinformation, 2017, 58: 97.
[23] WANG Jian-guang, LÜ Xiao-dong, YAO Gui-ping, et al(王建光，吕小东，姚贵平，等). Chinese Journal of Grassland(中国草地学报)，2013，35(1)：35.
[24] CHEN Hong, XIE Ling, CHEN Lin-lin(陈 虹, 谢 玲, 陈林琳). Journal of Chinese Agricultural Machanization(中国农机化学报), 2021, 42(4): 170.
[25] Rondeaux G, Steven M, Baret F. Remote Sensing of Environment, 1996, 55(2): 95.
[26] QIAO Zhan-ming, WANG Xiao-bo, YANG Liu, et al(乔占明, 王晓波, 杨 柳, 等). Journal of Qinghai Normal University (Natural Science Edition)[青海师范大学学报(自然科学版)], 2019, 35(1): 54.
[27] Wang Z X, Liu C, Huete A. Acta Ecologica Sinica, 2003, 23(5): 979.
[28] DUAN Ji-wei, ZHONG Jiu-sheng, JIANG Li, et al(段纪维, 钟九生, 江 丽, 等). Forest Resources Management(林业资源管理), 2020，(6): 143.
[29] ZHANG Xian-feng, ZHAO Jie-peng, LIU Yu(张显峰, 赵杰鹏, 刘 羽). Progress in Geography(地理科学进展), 2013, 32(1): 78.
[30] YUAN Nian-nian, WU Juan, XIONG Yu-jiang, et al(袁念念, 吴 娟, 熊玉江, 等). Water Saving Irrigation(节水灌溉), 2021，(10): 84.
[31] YAO Yan-min, WEI Na, TANG Peng-qin, et al(姚艳敏, 魏 娜, 唐鹏钦, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2011, 27(8): 95.
[32] MA Jian-xin, LU Xiao-ping, MENG Qing-yan, et al(马建新, 卢小平, 孟庆岩, 等). Science of Surveying and Mapping(测绘科学), 2016, 41(2): 97.
[33] ZHU Yan-ru, ZHAO Hong-li, HUANG Yan-yan, et al(朱彦儒, 赵红莉, 黄艳艳, 等). South-to-North Water Transfer and Water Science & Technology[南水北调与水利科技(中英文)], 2020, 18(4): 71.
[34] KONG Jie, LI Chun-bin, WU Jing(孔 婕, 李纯斌, 吴 静). Pratacultural Science(草业科学), 2020, 37(12): 2463.
[35] WANG Jia-er, XIAO Yue, WANG Zhi-hao, et al(王佳儿, 肖 悦, 王志昊, 等). Water Saving Irrigation(节水灌溉), 2021，(12): 81.
[36] LIU Hong-bin, WU Wei, WEI Chao-fu(刘洪斌, 武 伟, 魏朝富). Journal of Soil and Water Conservation(水土保持学报), 2003，(5): 59.
[37] BIAN Hui-qin, WANG Xue-mei(边慧芹, 王雪梅). Journal of Arid Land Resources and Environment(干旱区资源与环境), 2022, 36(5): 110.
