新疆师范大学地理科学与旅游学院 / 新疆干旱区湖泊环境与资源实验室,新疆 乌鲁木齐 830054
樊泳灼(1999年生),女;研究方向:土壤资源变化及其遥感应用;E-mail:yzfan@stu.xjnu.edu.cn
李新国(1971年生),男;研究方向:干旱区资源变化及遥感应用;E-mail:lxg@xjnu.edu.cn
纸质出版日期:2023-11-25,
网络出版日期:2023-07-26,
收稿日期:2023-04-06,
录用日期:2023-04-26
扫 描 看 全 文
樊泳灼,李新国.新疆博斯腾湖湖滨绿洲不同土地利用类型土壤电导率高光谱估算[J].中山大学学报(自然科学版),2023,62(06):31-39.
FAN Yongzhuo,LI Xinguo.Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):31-39.
樊泳灼,李新国.新疆博斯腾湖湖滨绿洲不同土地利用类型土壤电导率高光谱估算[J].中山大学学报(自然科学版),2023,62(06):31-39. DOI: 10.13471/j.cnki.acta.snus.2023D024.
FAN Yongzhuo,LI Xinguo.Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):31-39. DOI: 10.13471/j.cnki.acta.snus.2023D024.
为了更精准了解博斯腾湖湖滨绿洲不同土地利用类型的土壤含盐量,应用竞争性自适应重加权采样(CARS)、连续投影算法(SPA)、竞争性自适应重加权-连续投影算法(CARS-SPA)3种方法筛选不同土地利用类型土壤电导率高光谱数据的特征波段,基于全波段和特征波段结合BP神经网络分别构建湖滨绿洲的耕地、林地、荒地和整体土地的土壤电导率估算模型,对比不同方式的估算模型精度。研究结果表明:1) 耕地、林地、荒地及整体土地的土壤电导率均值分别为0.84、5.43、5.78、3.26 mS/cm。湖滨绿洲整体土地的电导率相比耕地平均值增加了2.42 mS/cm,相比林地和荒地减少了2.17、2.52 mS/cm。2) 通过CARS-SPA方法可以降低输入模型的波段数,提高模型的效率,筛选耕地、林地、荒地及整体土地的土壤电导率的特征波段数仅占全波段的0.71%、0.59%、0.06%、1.00%。3) 对耕地、林地、荒地的土壤电导率构建单独的估算模型明显提高了研究区土壤电导率的估算精度,在FDR-CARS-BP、FDR-SPA-BP、FDR-CARS-SPA-BP共3种模型中,耕地、林地、荒地土壤电导率建模的平均
R
2
相比整体土地建模分别提高0.12、0.14、0.15,FDR-CARS-SPA-BP模型为研究区土壤电导率高光谱估算最优模型。
To more accurately understand the soil salinity of different land use types in the lakeside oasis of Bosten Lake, Xinjiang, three methods of competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), and competitive adaptive reweighted-successive projection algorithm (CARS-SPA) were applied to screen the characteristic bands of soil conductivity hyperspectral data of different land use types, based on the full band and characteristic bands. The estimation models of soil conductivity of the lakeshore oasis were constructed based on the full band and characteristic bands combined with BP neural network to compare the accuracy of estimation models in different ways. The results showed that: (1) the mean values of soil conductivity of cropland, forest land, wasteland, and overall land are 0.84, 5.43, 5.78, and 3.26 mS/cm, respectively; the overall soil conductivity of the lakeshore oasis is 2.42 mS/cm higher than the mean value of cropland, 2.17 and 2.52 mS/cm lower than forest land and wasteland. (2) The CARS-SPA method can reduce the number of bands input to the model and improve the efficiency of the model. The number of characteristic bands for screening the electrical conductivity of cropland, forestland, wasteland, and overall land soil only accounts for 0.71%, 0.59%, 0.06%, and 1.00% of the full bands. (3) Constructing separate estimation models for soil conductivity of cropland, forest land, and wasteland significantly improves the estimation accuracy of soil conductivity in the study area. Among the three models of FDR-CARS-BP, FDR-SPA-BP, and FDR-CARS-SPA-BP, the average
R
2
of soil conductivity modeling for cropland, forest land, and wasteland increased by 0.12, 0.14, and 0.15, respectively, compared with the overall soil modeling, the FDR-CARS-SPA-BP model is the optimal model for hyperspectral estimation of soil conductivity in the study area.
土壤电导率土地利用类型高光谱数据竞争性自适应重加权-连续投影算法BP神经网络
soil conductivityland use typeshyperspectral dataCARS-SPABP neural network
曹肖奕,丁建丽,葛翔宇,等, 2020.基于光谱指数与机器学习算法的土壤电导率估算研究[J].土壤学报,57(4):867-877.
陈红艳,赵庚星,李玉环,等,2018.消除水分因素影响的野外原状土壤盐分高光谱建模估测[J].农业工程学报,34(12):119-125.
李新国,李和平,任云霞,等,2012.开都河流域下游绿洲土壤盐渍化特征及其光谱分析[J].土壤通报,43(1):166-170.
李志,李新国,毛东雷,等,2018.博斯腾湖西岸湖滨带不同植被类型土壤剖面盐分特征分析[J].西北农业学报,27(2):260-268.
牛芳鹏,李新国,麦麦提吐尔逊·艾则孜,等,2021.基于连续投影算法的博斯腾湖西岸湖滨绿洲土壤有机碳含量的高光谱估算[J].浙江大学学报(农业与生命科学版),47(5):673-682.
彭杰,刘焕军,史舟,等,2014.盐渍化土壤光谱特征的区域异质性及盐分反演[J].农业工程学报,30(17):167-174.
孙亚楠,李仙岳,史海滨,等,2022.基于高光谱数据的盐荒地和耕地土壤盐分遥感反演优化[J].农业工程学报,38(23):101-111.
唐海涛,孟祥添,苏循新,等,2021.基于CARS算法的不同类型土壤有机质高光谱预测[J].农业工程学报,37(2):105-113.
田安红,付承彪,熊黑钢,等,2020.BPNN对不同人为活动区域的盐渍土Na+高光谱估测[J].水土保持研究,27(2):364-369.
田安红,熊黑钢,赵俊三,等,2019.分数阶微分对盐渍土野外光谱预处理精度提升的机理分析[J].光谱学与光谱分析,39(8):2495-2500.
王懂,杨玮,曹永研,等,2022.基于近红外光谱信息的土壤电导率预测模型研究[J].农业机械学报,53(S1):218-223.
王涛,喻彩丽,张楠楠,等,2019.基于去包络线和连续投影算法的枣园土壤电导率光谱检测研究[J].干旱地区农业研究,37(5):193-199+217.
吴俊,郭大千,李果,等,2022.基于CARS-BPNN的江西省土壤有机碳含量高光谱预测[J].中国农业科学,55(19):3738-3750.
肖云飞,高小红,李冠稳,2020.土壤有机质可见光-近红外光谱预测样本优化选择[J].土壤,52(2):404-413.
亚森江·喀哈尔,杨胜天,尼格拉·塔什甫拉提,等,2019.基于分数阶微分优化光谱指数的土壤电导率高光谱估算[J].生态学报,39(19):7237-7248.
张贤龙,张飞,张海威,等,2018.基于光谱变换的高光谱指数土壤盐分反演模型优选[J].农业工程学报,34(1):110-117.
张一清,王文娥,胡笑涛,等,2023.土壤电导率对土壤含盐量及施肥浓度的响应试验研究[J].中国农业大学学报,28(3):176-187.
赵慧,李新国,靳万贵,等,2021a.基于地理加权回归模型的博斯腾湖湖滨绿洲土壤盐分离子含量高光谱估算[J].土壤,53(3):646-653.
赵慧,李新国,靳万贵,等,2021b.基于分数阶微分的博斯腾湖湖滨绿洲土壤电导率高光谱估算[J].甘肃农业大学学报,56(1):118-125.
赵慧,李新国,牛芳鹏,等,2021c.博斯腾湖湖滨绿洲土壤电导率高光谱估算模型[J].中国土壤与肥料,(2):289-295.
朱成立,舒慕晨,张展羽,等,2017.咸淡水交替灌溉对土壤盐分分布及夏玉米生长的影响[J].农业机械学报,48(10):220-228+201.
BANNARI A, EL-BATTAY A, BANNARI R,et al,2018.Sentinel-MSI VNIR and SWIR bands sensitivity analysis for soil salinity discrimination in an arid landscape[J].Remote Sens,10(6):855.
CLOUTIS E A,1996.Hyperspectral geological remote sensing: Evaluation of analytical techniques[J].Int J Remote Sens,17(12):2215-2242.
FAN X W, LIU Y B, TAO J,et al,2015.Soil salinity retrieval from advanced multi-spectral sensor with partial least square regression[J]. Remote Sens,7(1):488-511.
FARIFTEH J, van der MEER F, ATZBERGER C,et al,2007.Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN)[J]. Remote Sens Environ,110(1): 59-78.
JIN P B, LI P H, WANG Q, et al,2015.Developing and applying novel spectral feature parameters for classifying soil salt types in arid land[J].Ecol Indic,54:116-123.
HEIL K, SCHMIDHALTER U,2019.Theory and guidelines for the application of the geophysical sensor EM38[J].Sensors,19(19):4293-4293.
SRIVASTAVA R, SETHI M, YADAV R K,et al,2017.Visible-near infrared reflectance spectroscopy for rapid characterization of salt-affected soil in the Indo-Gangetic Plains of Haryana,India[J].J Indian Soc Remote Sens,45(2):307-315.
0
浏览量
12
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构