Hyperspectral Inversion of Soil Organic Matter Content Based on Continuous Wavelet Transform，SHAP，and XGBoost

被引：0
|
作者：
Ye M. [1 ,2 ,3 ]
Zhu L. [1 ,2 ,3 ]
Liu X.-D. [1 ,2 ,3 ]
Huang Y. [4 ]
Chen B.-B. [1 ,2 ,3 ]
Li H. [4 ]
机构：
[1] College of Resources Environment and Tourism, Capital Normal University, Beijing
[2] Laboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing
[3] Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing
[4] Beijing Institute of Ecological Geology, Beijing
来源：
Huanjing Kexue/Environmental Science | 2024年 / 45卷 / 04期
关键词：
continuous wavelet transform; hyperspectral inversion; SHAP method; soil organic matter （SOM）; XGBoost model;
D O I：
10.13227/j.hjkx.202304100
中图分类号：
学科分类号：
摘要：
Aiming to address the problems of weak spectral signals and redundant spectral information existing in hyperspectral inversion of soil organic matter content，a hyperspectral inversion framework combining continuous wavelet transform，SHAP，and XGBoost was proposed. Taking the permanent basic farmland soil in Yanqing District and Fangshan District of Beijing as the research object，an initial XGBoost model was first constructed based on the spectral reflectance data of soil processed by continuous wavelet transform. Then，the SHAP method was used to analyze the contribution of each band in the model to select the characteristic bands. Finally，the XGBoost model was reconstructed and optimized based on the characteristic bands to realize the hyperspectral inversion of soil organic matter content. It was found that the XGBoost model based on the 40 characteristic bands of continuous wavelet transform at the 25 scale selected by the SHAP method showed the highest accuracy，with the R2 and RMSE between the inversed and measured value of the organic matter content being 0. 80 and 3. 60 g·kg−1，respectively. The R2 first increased and then decreased with the increase in the scale of continuous wavelet transform，and the R2 at the 25 scale was 0. 37 higher than that at the 21 scale. The number of characteristic bands selected by the SHAP method was 682 less than that by the Pearson correlation analysis method，and the RMSE was 0. 69 g·kg−1 lower. The R2 of the XGBoost model was 4% and 8% higher than that of the random forest and support vector machine models，respectively. The results demonstrated the effectiveness of the combination of continuous wavelet transform，SHAP，and XGBoost in the hyperspectral inversion of soil organic matter content，which provides technical support for rapid and accurate monitoring of soil organic matter content. © 2024 Science Press. All rights reserved.
引用
收藏
页码：2280 / 2291
页数：11
相关论文
共 45 条
  • [1] Wang J K, Xu Y D, Ding F，, Et al., Process of plant residue transforming into soil organic matter and mechanism of its stabilization：a review［J］, Acta Pedologica Sinica, 56, 3, pp. 528-540, (2019)
  • [2] Yazdanshenas H，, Tavili A，, Jafari M，, Et al., Evidence for relationship between carbon storage and surface cover characteristics of soil in rangelands［J］, CATENA, 167, pp. 139-146, (2018)
  • [3] Zhang Z S, Wang J J，, Lyu X，, Et al., Impacts of land use change on soil organic matter chemistry in the Everglades， Florida-a characterization with pyrolysis-gas chromatography – mass spectrometry［J］, Geoderma, 338, pp. 393-400, (2019)
  • [4] Picariello E，, Baldantoni D，, Izzo F，, Et al., Soil organic matter stability and microbial community in relation to different plant cover：A focus on forests characterizing Mediterranean area［J］, Applied Soil Ecology, (2021)
  • [5] Chu C, Wu Z Y, Huang Q R，, Et al., Effect of organic matter promotion on nitrogen-cycling genes and functional microorganisms in acidic red soils［J］, Environmental Science, 41, 5, pp. 2468-2475, (2020)
  • [6] (2000)
  • [7] Horta A，, Azevedo L，, Neves J，, Et al., Integrating portable X-ray fluorescence （pXRF） measurement uncertainty for accurate soil contamination mapping［J］, Geoderma, (2021)
  • [8] Nawar S，, Buddenbaum H，, Hill J，, Et al., Estimating the soil clay content and organic matter by means of different calibration methods of vis-NIR diffuse reflectance spectroscopy［J］, Soil and Tillage Research, 155, pp. 510-522, (2016)
  • [9] Conforti M，, Castrignano A，, Robustelli G，, Et al., Laboratory-based Vis - NIR spectroscopy and partial least square regression with spatially correlated errors for predicting spatial variation of soil organic matter content ［J］, CATENA, 124, pp. 60-67, (2015)
  • [10] Sun W C，, Liu S，, Zhang X，, Et al., Estimation of soil organic matter content using selected spectral subset of hyperspectral data［J］, Geoderma, (2022)
12345