基于变量筛选的典型三江平原耕地土壤肥力属性光谱预测

doi:10.3964/j.issn.1000-0593(2025)05-1422-10

摘要
参考文献
相关文章 (15)

全文: PDF (20608 KB)
输出: BibTeX | EndNote (RIS)

摘要：三江平原是东北黑土地的重要粮食产区，自开垦以来区域耕地土壤肥力下降明显。传统化学测量方法效率低，难以满足快速精准监测需求。光谱技术具有土壤肥力预测潜力，而已有研究中较少同时针对多种土壤肥力属性，且部分土壤肥力属性的预测精度偏低。本研究以三江平原典型耕地区域——友谊农场为研究区，采用可见光-近红外光谱，结合SG（Savitzky-Golay）光谱平滑、一阶微分、标准正态变换和多元散射校正四种光谱预处理方法及竞争性自适应重加权（CARS）波段筛选算法，采用偏最小二乘回归模型同时针对有机质（SOM）、全氮（TN）、全磷（TP）和全钾（TK）四种土壤关键肥力属性进行预测，探讨光谱预测多种土壤肥力属性的潜力，并探索变量筛选在精度提升中的作用。结果表明：（1）未经变量筛选使用全波段（400~2 400 nm）时，SOM和TN的预测精度较高，交叉验证R²在不同光谱预处理方法间差异不大，分别介于0.85~0.89和0.86~0.89之间，TK的预测精度也相对较高，R²介于0.63~0.72，而TP的预测精度较低，R²介于0.08~0.34；（2）经CARS波段筛选后四种土壤肥力属性预测精度均有所提升，TP的提高幅度最大，SOM、TN、TP、TK的最优交叉验证R²分别为0.97、0.96、0.82、0.92；（3）CARS变量筛选方法能够识别出SOM和TN相关特征官能团对应的波段，TN的预测同时采用其与SOM之间的关系和自身特征波段信息，TP的预测主要采用了土壤光谱信息，而TK则同时采用土壤光谱以及其与SOM和TN之间的关系。本研究证实了光谱技术在三江平原典型耕地区域同时进行多种土壤关键肥力属性预测的潜力，发现变量筛选能够显著提高不具备明显光谱特征土壤属性（TP）的预测精度，为黑土地土壤肥力快速监测提供参考。

关键词：三江平原；土壤肥力属性；可见光-近红外光谱；变量筛选

Abstract：The Sanjiang Plain is an important grain production area in the black soil region of Northeast China. However, since its reclamation, the soil fertility of cultivated lands has declined significantly. Traditional chemical measurement methods are inefficient and difficult to meet the needs of rapid and accurate monitoring of soil fertility attributes. Spectral technology has the potential to predict soil fertility. Still, few existing studies have targeted multiple soil fertility attributes simultaneously, and the prediction accuracy of some soil fertility attributes is relatively low. Therefore, this study took the typical cropland area of the Sanjiang Plain, Youyi Farm, as the study area. We utilized visible and near-infrared spectroscopy, combined with four spectral preprocessing methods, including SG (Savitzky-Golay) spectral smoothing, first-order derivation, standard normal variate transformation, and multiplicative scatter correction, as well as the competitive adaptive reweighted sampling (CARS) band selection algorithm. The partial least squares regression model was employed to simultaneously predict four key soil fertility attributes: soil organic matter (SOM), total nitrogen (TN), total phosphorus (TP), and total potassium (TK). The study aimed to explore the potential of spectral prediction for multiple soil fertility attributes and investigate the role of variable selection in improving prediction accuracy. The results showed that: (1) When using the full spectral range (400~2 400 nm) without variable selection, the prediction accuracy of SOM and TN was relatively high, with cross-validation R² values ranging from 0.85 to 0.89 and 0.86 to 0.89, respectively. The prediction accuracy of TK was also relatively high, with R² ranging from 0.63 to 0.72, but the prediction accuracy of TP was lower, with R² ranging from 0.08 to 0.34. (2) After CARS band selection, the prediction accuracy of all four soil fertility attributes improved, with the largest improvement found in TP. The optimal cross-validation R² was 0.97, 0.96, 0.82, and 0.92 for SOM, TN, TP, and TK, respectively. (3) The CARS variable selection method identified the spectral bands corresponding to the characteristic functional groups related to SOM and TN. The prediction of TN utilized both its relationship with SOM and its intrinsic characteristic bands. The prediction of TP mainly relied on soil spectral information, while the prediction of TK utilized both soil spectral information and its relationship with SOM and TN. This study demonstrated the potential of spectral technology for simultaneously predicting multiple key soil fertility attributes in the typical cropland area of the Sanjiang plain and found that variable selection can significantly improve the prediction accuracy of soil attributes(TP) that do not have obvious spectral characteristics, providing a methodological reference for rapid monitoring of soil fertility in black soil regions.

Key words：Sanjiang plain; Soil fertility attributes; Visible and near-infrared spectroscopy; Band selection

收稿日期: 2024-05-31 修订日期: 2024-09-01

中图分类号:

S151.9

基金资助: 国家重点研发计划项目（2021YFD1500102），国家自然科学基金项目（42107145）资助

通讯作者: 王昌昆 E-mail: ckwang@issas.ac.cn

作者简介: 姚成硕，2000年生，中国科学院南京土壤研究所及中国科学院大学现代农业科学学院农业资源与环境系硕士研究生
e-mail: yaochengshuo@issas.ac.cn

引用本文:

姚成硕，王昌昆，刘杰，郭志英，马海艺，袁自然，王晓盼，潘贤章. 基于变量筛选的典型三江平原耕地土壤肥力属性光谱预测[J]. 光谱学与光谱分析, 2025, 45(05): 1422-1431.
YAO Cheng-shuo, WANG Chang-kun, LIU Jie, GUO Zhi-ying, MA Hai-yi, YUAN Zi-ran, WANG Xiao-pan, PAN Xian-zhang. Spectral Prediction of Soil Fertility Attributes in Typical Croplands of Sanjiang Plain Based on Band Selection. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1422-1431.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2025)05-1422-10 或 https://www.gpxygpfx.com/CN/Y2025/V45/I05/1422

[1] LIU Xing-tu, MA Xue-hui(刘兴土, 马学慧). Scientia Geographica Sinica(地理科学), 2000, 20(1): 14.
[2] LIANG Xiao-yao, YUAN Li-hua, NING Li-xin, et al(梁晓瑶, 袁丽华, 宁立新, 等). Journal of Beijing Normal University (Natural Science)[北京师范大学学报(自然科学版)], 2020, 56(6): 864.
[3] HAN Xiao-zeng, ZOU Wen-xiu(韩晓增, 邹文秀). Acta Pedologica Sinica(土壤学报), 2021, 58(6): 1341.
[4] Soriano-Disla J M, Janik L J, Rossel R A V, et al. Applied Spectroscopy Reviews, 2014, 49(2): 139.
[5] Stenberg B, Rossel R A V, Mouazen A M, et al. Advances in Agronomy, 2010, 107: 163.
[6] Malley D F, Yesmin L, Wray D, et al. Communications in Soil Science and Plant Analysis, 1999, 30(7-8): 999.
[7] Zheng G H, Wang A S, Zhao C Y, et al. Geoderma, 2023, 429: 116258.
[8] LI Guan-wen, GAO Xiao-hong, XIAO Neng-wen, et al(李冠稳, 高小红, 肖能文, 等). Chinese Journal of Luminescence(发光学报), 2019, 40(8): 1030.
[9] LI Xue-lan, LI De-cheng, ZHENG Guang-hui, et al(李学兰, 李德成, 郑光辉, 等). Acta Pedologica Sinica(土壤学报), 2024, 61(3): 687.
[10] Zhang M, Han J L, Jiao J, et al. Agronomy, 2023, 13(10): 2533.
[11] XU Ying-de, PEI Jiu-bo, LI Shuang-yi, et al(徐英德, 裴久渤, 李双异, 等). Chinese Journal of Soil Science(土壤通报), 2023, 54(2): 495.
[12] YU Xiao, WU Ke-ning, YUN Wen-ju, et al(于潇, 吴克宁, 郧文聚, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2016, 32(8): 253.
[13] Luo C, Zhang W Q, Zhang X L, et al. Catena, 2023, 231: 107336.
[14] Yang M H, Mouazen A, Zhao X M, et al. European Journal of Soil Science, 2020, 71(4): 615.
[15] Li H D, Liang Y Z, Xu Q S, et al. Analytica Chimica Acta, 2009, 648(1): 77.
[16] Hong Y S, Chen Y Y, Yu L, et al. Remote Sensing, 2018, 10(3): 479.
[17] QI Hai-jun, LI Shao-wen, KARNIELI A, et al(齐海军, 李绍稳, KARNIELI A, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2018, 49(2): 166.
[18] ZHOU Wei, WANG Wen-jie, ZHANG Bo, et al(周伟, 王文杰, 张波, 等). Acta Ecologica Sinica(生态学报), 2017, 37(4): 1211.
[19] QIAO Lu, CHEN Li-xin, DONG Cheng-ming(乔璐, 陈立新, 董诚明). Forest Engineering(森林工程), 2018, 34(6): 25.
[20] Rossel R A V, Behrens T. Geoderma, 2010, 158(1-2): 46.
[21] Martin P D, Malley D F, Manning G, et al. Canadian Journal of Soil Science, 2002, 82(4): 413.
[22] Hou M J, Ai Z M, Li X H, et al. Ecological Informatics, 2024, 79: 102429.
[23] SHI Zhou, WANG Qian-long, PENG Jie, et al(史舟, 王乾龙, 彭杰, 等). Scientia Sinica(Terrae)(中国科学: 地球科学), 2014, 44(5): 978.
[24] GOU Yu-xuan, ZHAO Yun-ze, LI Yong, et al(勾宇轩, 赵云泽, 李勇, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2022, 53(3): 331.
[25] Wang Y X, Yang S, Yan X B, et al. Journal of Soils and Sediments, 2023, 23(2): 634.