1 College of Water Conservancy, Yunnan Agricultural University, Kunming 650201, China
2 International College, Yunnan Agricultural University, Kunming 650201, China
3 College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China
Show less
文章历史+
Received
Published
Revised
2025-06-26
2026-08-28
2026-01-07
Online Date
2026-09-04
PDF (13856K)
摘要
土壤水分、介电常数与压实度是表征土壤关键物理属性的关键参数,在数字土壤制图(digital soil mapping,DSM)和精准农业与生态研究中具有重要意义。以昆明典型红黏土农田区为对象,同步获取高分辨率多光谱遥感影像并实地测定表层土壤体积含水量、介电常数及压实度。基于影像数据计算植被指数,并结合皮尔逊相关系数分析(Pearson correlation analysis, PCA)与变量重要性投影(variable importance in projection,VIP)算法筛选提取关键光谱特征,分别构建多元线性回归(multiple linear regression,MLR)和随机森林(random forest,RF)模型进行土壤参数定量反演并制图。结果表明:VIP算法能有效提取对参数预测贡献显著的光谱特征,RF模型预测性能显著优于MLR(R2>0.94)。参数空间分布图清晰揭示了水分、介电常数及压实度的空间分异特征:水分与介电常数空间分布高度一致,反映物理关联性,压实度则呈现更复杂的空间异质性。研究表明,基于无人机多光谱的反演模型可实现红壤物理参数的高精度协同反演,对提升土壤资源信息化管理及支撑可持续农业具有重要价值。
Abstract
Soil moisture, dielectric constant, and compaction degree are key physical parameters of soil, playing a great significance role in digital soil mapping (DSM), precision agriculture, and ecological research. A typical red clay farmland area in Kunming was selected as the study object. High-resolution multispectral remote sensing images were synchronously acquired. Field measurements of surface soil volumetric water content, dielectric constant, and compaction degree were conducted. Vegetation indices were calculated from the image data. Pearson correlation analysis and the variable importance in projection (VIP) algorithm were used to extract key spectral features. Multiple linear regression (MLR) and random forest (RF) models were constructed for quantitative inversion of soil parameters and for mapping. The results show that the VIP algorithm can effectively extract spectral features that significantly contribute to parameter prediction. The predictive performance of the RF model is found to be significantly better than that of the MLR model, with an R2 value greater than 0.94. The spatial differentiation characteristics of moisture, dielectric constant, and compaction degree are clearly revealed by the spatial distribution maps. A high consistency is observed between the spatial distributions of moisture and dielectric constant, reflecting their physical correlation. More complex spatial heterogeneity is exhibited by compaction degree. The inversion model based on UAV multispectral imagery is shown to enable high-precision simultaneous inversion of red soil physical parameters, which is of great value for improving the information management of soil resources and supporting sustainable agriculture.
多元线性回归(multiple linear regression,MLR)和RF作为典型参数与非参数建模方法,在土壤参数反演中各具优势。MLR具有结构简单、可解释性强的特点,适用于探索多光谱特征与土壤参数之间的线性关系,有助于识别关键敏感波段;而RF作为一种集成学习算法,能够处理高维、非线性数据,具备较强的抗过拟合能力和特征选择功能,适用于复杂地表条件下的土壤参数建模。结合二者可对比分析线性与非线性模型在反演精度与稳定性方面的差异,提升研究结果的科学性与适用性。将实验室测定的土壤含水率、介电常数和压实度数据作为标签,多光谱反射率和植被指数作为特征输入MLR和RF算法训练反演模型,其中125个样本随机选取80%作为训练集,20%作为测试集,算法均通过Python代码实现。
为了评价反演模型的效果,分别计算训练集和测试集的决定系数(R2)和均方根误差(root mean square error,RMSE)指标分析精度。计算公式为
MengX, BaoY, LiuH, et al. A new digital soil mapping method with temporal-spatial-spectral information derived from multi-source satellite images[J]. Geoderma, 2022, 425: 116065.
[2]
HussainS S, GanieA A, DarW A, et al. The role of digital soil mapping in soil survey and agricultural planning[J]. International Journal of Plant & Soil Science, 2024, 36(9): 438-449.
[3]
QuT, LiY, ZhaoQ, et al. Drone-based multispectral remote sensing inversion for typical crop soil moisture under dry farming conditions[J]. Agriculture, 2024, 14(3): 484.
[4]
WangY, MaY, ZhouF, et al. More precise monitoring of soil moisture content in agricultural fields by upscaling conversion of multispectral image data from unmanned aerial vehicles[J]. IEEE Access, 2024, 12: 79892-79904.
ZhaoGuiping, XuFajun. Monitoring of farmland soil moisture based on multispectral images from unmanned aerial vehicles[J]. Bulletin of Surveying and Mapping, 2024(11): 177-182.
WangYancang, LiXiaofang, ZhangWensheng, et al. Quantitative retrieval of highway subgrade soil compaction using hyperspectral technology[J]. Spectroscopy and Spectral Analysis, 2023, 43(7): 2294-2300.
[13]
YangW, LiZ, ChenG, et al. Soybean (Glycine max L.) leaf moisture estimation based on multisource unmanned aerial vehicle image feature fusion[J]. Plants, 2024, 13(11): 1498.
SunGang, HuangWenjiang, ChenPengfei, et al. Advances in multispectral remote sensing technology application for light and small unmanned aerial vehicles[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(3): 1-17.
ZhangDongxing, LiuJiang, YangLi, et al. Research on soil moisture sensors for seed furrows based on VIS-NIR technology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(2): 218-226.
WangYancang, GuXiaohe, ZhuJinshan, et al. Quantitative inversion of organic matter content in northern fluvo-aquic soil using reflectance spectroscopy and simulated multispectral data[J]. Spectroscopy and Spectral Analysis, 2014, 34(1): 201-206.
DingQidong, WangYijing, ZhangJunhua, et al. Estimation of soil moisture and organic matter content in saline-alkali farmland using the cars algorithm combined with covariates[J]. Acta Ecologica Sinica, 2024, 35(5): 1321-1330.
[22]
ArayaS N, Fryjoff-HungA, AndersonA, et al. Advances in soil moisture retrieval from multispectral remote sensing using unoccupied aircraft systems and machine learning techniques[J]. Hydrology and Earth System Sciences, 2021, 25(5): 2739-2758.
XuXingqian, WangHaijun, ZhaoXi, et al. Experimental study on dielectric constant model of red clay[J]. Chinese Journal of Civil Engineering, 2023, 56(11): 165-173, 183.
YaoKuo, GuoXudong, ZhouDong, et al. Research progress on extracting land quality indicators from hyperspectral remote sensing data[J]. Geography and Geoinformation Science, 2014, 30(6): 7-12.
ZhangChengcai, HouJiatong, WangRui, et al. Inversion of winter wheat soil moisture based on multispectral and thermal infrared data from unmanned aerial vehicles[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(5): 111-118.
LiHu, ZhongYun, FengYating, et al. Multi-vegetation index soil moisture retrieval model based on UAV remote sensing[J]. Spectroscopy and Spectral Analysis, 2024, 44(1): 207-214.
[31]
ChenZ, ChenH, DaiQ, et al. Estimation of soil moisture during different growth stages of summer maize under various water conditions using UAV multispectral data and machine learning[J]. Agronomy, 2024, 14(9): 2008.
[32]
ZhuS, CuiN, ZhouJ, et al. Digital mapping of root-zone soil moisture using UAV-based multispectral data in a kiwi fruit orchard of northwest China[J]. Remote Sensing, 2023, 15(3): 646.
XingMingjie, XuXingqian, XuWeiheng, et al. Study on red soil moisture inversion model based on optimized spectral features[J]. Journal of Irrigation and Drainage, 2025, 44(11): 70-79.
DengYun, WuWei, ShiYuanyuan, et al. Research on predicting organic matter content in red soil based on hollow convolutional neural networks[J]. Spectroscopy and Spectral Analysis, 2024, 44(10): 2941-2952.
LiXuan, SongKaishan, LiuJiping, et al. Method for retrieving chlorophyll content in maize leaves based on fused remote sensing data[J]. Science Technology and Engineering, 2025, 25(11): 4428-4437.
[39]
KongD, LuoC, LiuH. Enhancing soil organic matter mapping in saline-alkali and black soil areas with prior knowledge and multi-temporal remote sensing[J]. Journal of Integrative Agriculture, 2026, 25(4): 1700-1715.
ZhaoWenju, DuanWeicheng, WangYinfeng, et al. Research on multispectral vegetation water content inversion model based on sensitive variable screening[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(9): 343-351, 385.
SunManli, FuFei, ShenYunxia. Review of methods for determining soil moisture content[J]. Journal of Northwest University (Natural Science Edition), 2019, 49(2): 219-229.
[45]
GuanY, GroteK, SchottJ, et al. Prediction of soil water content and electrical conductivity using random forest methods with UAV multispectral and ground-coupled geophysical data[J]. Remote Sensing, 2022, 14(4): 1023.
[46]
JanbazialamdariS, FlippoD, RidderE, et al. Soil compaction prediction in precision agriculture using cultivator shank vibration and soil moisture data[J]. Agriculture, 2025, 15(17): 1896.
[47]
KudumoL P, ItannaF, ThierfelderC. Field soil moisture content under conventional tillage and conservation agriculture practices in Liselo, Namibia[J]. International Journal of Agriculture and Technology, 2025, 5(1): 1-5.