Inversion and Mapping of Soil pH Valve Based on In-situ Hyperspectral Data in Cotton field

Cai Haihui; Peng Jie; Liu Weiyang; Luo Defang; Wang Yuzhen; Bai Jianduo; Bai Zijin

doi:10.13961/j.cnki.stbctb.2021.04.027

您当前的位置：

首页 >

文章列表页 >

Inversion and Mapping of Soil pH Valve Based on In-situ Hyperspectral Data in Cotton field

- Inversion and Mapping of Soil pH Valve Based on In-situ Hyperspectral Data in Cotton field
- Bulletin of Soiland Water Conservation Vol. 41, Issue 4, Pages: 189-195(2021)
- 作者机构：
  
  塔里木大学植物科学学院,新疆,阿拉尔,843300
- 作者简介：
- 基金信息：
- DOI：10.13961/j.cnki.stbctb.2021.04.027
  CLC： S153.4
- Published：2021
- 稿件说明：
移动端阅览
Cai Haihui, Peng Jie, Liu Weiyang, et al. Inversion and Mapping of Soil pH Valve Based on In-situ Hyperspectral Data in Cotton field[J]. Bulletin of Soiland Water Conservation, 2021, 41(4): 189-195.
DOI：

Cai Haihui, Peng Jie, Liu Weiyang, et al. Inversion and Mapping of Soil pH Valve Based on In-situ Hyperspectral Data in Cotton field[J]. Bulletin of Soiland Water Conservation, 2021, 41(4): 189-195. DOI： 10.13961/j.cnki.stbctb.2021.04.027.

摘要

[目的

]

研究快速、准确大面积监测农田土壤pH值，为大面积土壤改良和实现农田精细化管理提供科学支持。[方法

]

以南疆阿拉尔市十二团棉田为研究区，采用网格采样法采集231个样点的原位高光谱数据，并同步采集其中116个样点的土壤样品；分析了原位高光谱反射率数据经不同预处理模式后的光谱数据与土壤pH值的相关性；采用偏最小二乘回归、支持向量机回归和随机森林3种建模方法分别建立了土壤pH值的高光谱反演模型，根据模型评价指标优选出最优模型对未采集土壤样点的pH值进行反演制图。[结果

]

反射率经微分处理后可有效改善其与土壤pH值的相关性；反射率二阶微分的随机森林模型为所有模型中的最优模型，其验证集的R

为0.87，RMSE为0.04，RPD为2.53；最优模型反演的pH值数据插值所得数字图与实测pH值插值图的空间分布特征高度吻合，能客观反映土壤碱化的空间分布状况。[结论

]

随机森林模型为原位反演南疆棉田土壤pH值的最优模型，克里金插值能够客观可视化表达研究区土壤pH值的分布状况。

Abstract

[Objective] Rapid and accurate monitoring of farmland soil pH value were explored for large-scale soil improvement and achieving fine management of farmland. [Methods] The cotton fileds of the 12 th regiment at Alar City in the South of Xinjiang Uygur Autonomous Region were selected as the study area

in-situ hyperspectral data of 231 sample points were collected by grid sampling method

and soil samples at 116 sampling points were collected simultaneously. The correlation between in-situ hyperspectral reflectance data after different pretreatment modes and soil pH value was analyzed. Partial least squares regression

support vector machine regression and random forest were used to establish the hyperspectral inversion model of soil pH

respectively. According to the model evaluation indexes

the optimal model was selected and used for inversion and mapping of the pH value of the uncollected soil sample points. [Results] The reflectance after the differentia treatment could effectively improve its correlation with soil pH value. The random forest model with second-order derivative of reflectance was the optimal model among all models with R2 of 0.87

RMSE of 0.04

and RPD of 2.53. The digital map interpolated by the pH value of optimal model inversion was highly consistent with the spatial distribution characteristics of the actual measurement pH value

which could objectively reflect the spatial distribution of soil alkalinization. [Conclusion] The random forest model is the optimal model for in-situ inversion of soil pH value in cotton fields in South Xinjiang Uygur Autonomous Region

and Kriging interpolation could objectively visualize the soil pH value distribution in the study area.

关键词

Keywords

references

李保强, 陈绍荣, 邵建华, 等. 新疆土壤盐渍化的综合治理与改良[J].新疆农业科技, 2013(6):15-21.

林毅, 梁颁捷, 朱其清.三明烟区土壤pH值与土壤有效养分的相关性[J].烟草科技, 2003(6):35-37.

Filippi P, Cattle S R, Bishop T F A, et al. Digital soil monitoring of top-and sub-soil pH with bivariate linear mixed models[J]. Geoderma, 2018, 322:149-162.

张维, 李启权, 王昌全, 等. 川中丘陵县域土壤pH空间变异及影响因素分析:以四川仁寿县为例[J].长江流域资源与环境, 2015, 24(7):1192-1199.

张芳, 熊黑钢, 栾福明, 等. 土壤碱化的实测光谱响应特征[J].红外与毫米波学报, 2011, 30(1):55-60.

文虎, 盛建东, 颜安, 等. 绿洲农田盐碱斑土壤光谱特征分析与建模[J].新疆农业大学学报, 2016, 39(2):143-148.

李诗朦, 包妮沙, 刘善军, 等. 土壤电导率和pH值光谱特征及反演模型:以呼伦贝尔草原干旱半干旱土壤为例[J].测绘科学, 2018, 43(8):14-22, 44.

徐驰, 曾文治, 伍靖伟, 等. 内蒙古河套灌区土壤含盐量和pH高光谱反演研究[J].灌溉排水学报, 2013, 32(3):39-43.

Miles Grafton, Therese Kaul, Alan P, et al. Technical note:Regression analysis of proximal hyperspectral data to predict soil pH and olsen P[J]. Agriculture, 2019, 9(3):1-18.

翟茂彤.基于原位Vis-NIR高光谱的鄱阳湖湿地土壤有机碳预测研究[D].江西南昌:江西财经大学, 2020.

乔娟峰, 熊黑钢, 王小平, 等. 新疆阜康荒地土壤有机质高光谱特征及其反演模型研究[J].干旱地区农业研究, 2018, 36(5):207-214.

贾科利, 张俊华, 秦君琴.典型龟裂碱土光谱特征分析及碱化程度预测[J].干旱地区农业研究, 2013, 31(4):187-192, 199.

王凯龙, 熊黑钢, 张芳.基于高光谱数据预测土壤碱化程度最佳模型及其影响因素的研究[J].土壤, 2014, 46(3):544-549.

周宏冀.江西省耕地土壤pH空间变异与管理分区研究[D].江西南昌:江西财经大学, 2019.

张淑杰, 朱阿兴, 刘京, 等. 基于样点的数字土壤属性制图方法及样点设计综述[J].土壤, 2012, 44(6):917-923.

廖琪, 胡月明, 胡小飞, 等. 广东省典型赤红壤区耕层土壤养分的空间变异[J].水土保持通报, 2015, 35(6):322-328.

Odhiambo B O, Kenduiywo B K, Were K. Spatial prediction and mapping of soil pH across a tropical afro-montane landscape[J]. Applied Geography, 2020, 114:102-129.

鲍士旦.土壤农化分析[M].3版.北京:中国农业出版社, 2013.

李阳, 刘新路, 彭杰, 等. 基于可见光近红外光谱的南疆荒漠土壤有机质反演研究[J].土壤通报, 2018, 49(4):767-772.

代希君, 彭杰, 张艳丽, 等. 基于光谱分类的土壤盐分含量预测[J].土壤学报, 2016, 53(4):909-918.

彭杰, 刘焕军, 史舟, 等. 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, 2014, 30(17):167-174.

史舟.土壤地面高光谱遥感原理与方法[M].北京:科学出版社, 2014.

马利芳, 熊黑钢, 张芳.基于野外Vis-NIR光谱的土壤盐分主要离子预测[J].土壤, 2020, 52(1):188-194.

尚天浩, 贾萍萍, 孙媛, 等. 宁夏银北地区盐碱化土壤水分光谱特征及模型拟合精度分析[J].水土保持通报, 2020, 40(4):183-189.

李培清.新疆土壤分析[M].新疆乌鲁木齐:新疆人民出版社, 1983.

雷志栋, 杨诗秀, 谢森传.土壤水动力学[M].北京:清华大学出版社, 1988.

纪文君.基于野外Vis-NIR高光谱的土壤属性预测及田间水分影响去除研究[D].浙江杭州:浙江大学, 2014.

郭燕, 纪文君, 吴宏海, 等. 基于野外Vis-NIR光谱的土壤有机质预测与制图[J].光谱学与光谱分析, 2013, 33(4):1135-1140.

Rossel R A V, Cattle S R, Ortega A, et al. In situ measurements of soil colour, mineral composition and clay content by Vis-NIR spectroscopy[J]. Geoderma, 2009, 150(3/4):253-266.

杨忠芳, 陈岳龙, 钱鑂, 等. 土壤pH对镉存在形态影响的模拟试验研究[J].地学前缘, 2005, 12(1):252-260.

魏雨露, 刘金宝, 李劲彬.基于PLS的陕西关中地区土壤pH高光谱预测[J].西部大开发(土地开发工程研究), 2018, 3(4):51-57.

刘炜, 常庆瑞, 郭曼, 等. 小波变换在土壤有机质含量可见/近红外光谱分析中的应用[J].干旱地区农业研究, 2010, 28(5):241-246.

彭杰, 向红英, 王家强, 等. 基于野外实测高光谱数据的干旱区耕作土壤含水量反演研究[J].干旱地区农业研究, 2013, 31(2):241-246.

郭鹏, 李华, 陈红艳, 等. 基于光谱指数优选的土壤盐分定量光谱估测[J].水土保持通报, 2018, 38(3):193-199, 205.

张振华, 丁建丽, 王敬哲, 等. 集成土壤-环境关系与机器学习的干旱区土壤属性数字制图[J].中国农业科学, 2020, 53(3):563-573.

Dharumarajan S, Hegde R, Singh S K. Spatial prediction of major soil properties using Random Forest techniques:A case study in semi-arid tropics of South India[J]. Geoderma Regional, 2017, 10:154-162.

Vågen T G, Winowiecki L A, Tondoh J E, et al. Mapping of soil properties and land degradation risk in Africa using MODIS reflectance[J]. Geoderma, 2016, 263:216-225.

马晓东.基于加权决策树的随机森林模型优化[D].湖北武汉:华中师范大学, 2017.

刘亚秋, 陈红艳, 王瑞燕, 等. 基于可见/近红外光谱的黄河口区土壤盐分及其主要离子的定量分析[J].中国农业科学, 2016, 49(10):1925-1935.

Views

943

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Remote sensing monitoring and soil and water conservation effects of abandoned farmland in core black soil protection area of Jilin Province from 2000 to 2023

Comparative analysis of landslide susceptibility based on different evaluation units——A case study of Ledu District in Haidong City， Qinghai Province

Spatiotemporal variations and driving forces of vegetation coverage in Three Gorges reservoir area during 2013—2023——A case study at Badong County， Hubei Province

Quantitative Spectral Estimation of Soil Salinity Based on Optimum Spectral Indices

Research on Influencing Factors of Soil Erosion Based on Random Forest Algorithm—A Case Study in Upper Reaches of Ganjiang River Basin

Related Author

Fu Jianing

Wang Jingyi

Sun Xihao

Yu Hailin

Jiang Hailing

Feng Xinhui

Li Huamin

Li Yuanyuan

Related Institution

College of Geographic Science and Tourism， Jilin Normal University

School of Energy， Henan Polytechnic University

School of Resources and Security， Henan Vocational College of Industry and Information Technology

Changjiang Institute of Survey Technical Research， Ministry of Water Resources

Taian Bureau of Agriculture, Taian

⁰