基于光谱技术的典型互花米草入侵湿地土壤属性预测研究

doi:10.3964/j.issn.1000-0593(2025)01-0197-07

Abstract
References
Related Citation (15)

Download: PDF (9126 KB)
Export: BibTeX | EndNote (RIS)

Abstract This study aimed to effectively monitor the changes in soil properties after Spartina alterniflora invasion on coastal wetland ecosystems. The study area is a typical Spartina alterniflora wetland in the Yancheng Wetland Rare Birds National Nature Reserve of Jiangsu Province. A total of 15 sites were identified by a stratified-random sampling method, and 45 soil samples were collected from three depth intervals (0~30, 30～60, and 60~100 cm). The visible-near infrared spectral reflectance and 10 soil physicochemical properties were measured. The performance of partial least squares regression (PLSR) and random forest (RF) was studied, spectral transformation forms' influence on prediction accuracy was analyzed, and the potential of invasion years and soil depth as auxiliary predictors were discussed. The results show that: (1) the visible-near infrared spectral reflectance can be used to predict organic carbon, inorganic carbon, total nitrogen, water content, pH, bulk density, salinity, and clay contents in soils with reasonable accuracy; (2) the method of partial least squares generally outperform random forest algorithm, the R² of prediction models developed using the PLSR method was between 0.341 and 0.979, and the biggest R² of random forest models was 0.722; (3) Differential transformation and reciprocal transformation of spectral reflectance can substantially improve the model performance. The optimal prediction model of full nitrogen can be obtained based on the original spectra (R² is 0.769 and RMSE is 0.091 g·kg^-1). In contrast, the optimal models for other soil properties are mostly based on differential or reciprocal transformation of the original spectra. (4) In general, the model performance can be improved by adding variables of invasion years and soil depth, and the prediction accuracy of organic carbon, total nitrogen, salinity, pH and bulk density models are more sensitive to the two variables. The prediction model accuracy (R²) for estimating soil organic carbonincreased from 0.794 to 0.806, the accuracy (R²) of the pH model increased from 0.838 to 0.884, and the accuracy (R²) of the salt optimal model increased from 0.978 to 0.997. To sum up, visible-near infrared spectroscopy can be applied to predict key soil physicochemical properties in Spartina alterniflora wetlands, and soil change monitoring of invaded Spartina alterniflora wetlands can be achieved through appropriate spectral transformation, and variable selection and model selection.

Key words：Spartina alterniflora invasion; Visible-near infrared spectroscopy; Soil monitoring; Partial least squares regression; Random forest; Spectral transformation

Received: 2023-02-21 Accepted: 2024-03-26

ZTFLH:

S153.6

Corresponding Authors: XU Lu E-mail: luxa1023@jsnu.edu.cn

Cite this article:

CHEN Xu,CAO Si-heng,YANG Ren-min, et al. Using Spectroscopy to Predict Soil Properties on Coastal Wetlands Invaded by Spartina Alterniflora[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(01): 197-203.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)01-0197-07 OR https://www.gpxygpfx.com/EN/Y2025/V45/I01/197

[1] Yang Renmin, Guo Wenwen. Soil Science Society of America Journal, 2018, 82(4): 901.
[2] CHEN Qiu-yu, YANG Ren-min, ZHU Chang-ming(陈秋宇, 杨仁敏, 朱长明). Acta Pedologica Sinica(土壤学报), 2021, 58(3): 694.
[3] Anna Christina Tyler, John G Lambrinos, Edwin D Grosholz. Ecological Applications, 2007, 17(7): 1886.
[4] LIU Zi-gang(刘子刚). Scientia Geographica Sinica(地理科学), 2004, 24(5): 634.
[5] Yang Renmin, Wang Liangjie, Chen Liumei, et al. Environmental Earth Sciences, 2022, 81: 19.
[6] ZHANG Wen-juan, WANG Shao-qiang, CHANG Hua, et al(张文娟, 王绍强, 常华, 等). Progress in Geography(地理科学进展), 2005，(3): 118.
[7] WENG Yong-ling, QI Hao-ping, FANG Hong-bin, et al(翁永玲, 戚浩平, 方洪宾, 等). Acta Pedologica Sinica(土壤学报), 2010, 47(6): 1255.
[8] Zhao Dongxue, Maryem Arshad, Wang Jie, et al. Computers and Electronics in Agriculture, 2021, 182: 105990.
[9] Seema，Ghosh A K, Das B S, et al. Geoderma Regional, 2020, 23: e00349.
[10] Nawar S, Mouazen A M. Soil and Tillage Research, 2019, 190: 120.
[11] Lin Lixin，Liu Xixi. Computers and Electronics in Agriculture, 2022, 192: 106634.
[12] WANG Miao, XIE Xian-li, ZHOU Rui, et al(王淼, 解宪丽, 周睿, 等). Acta Pedologica Sinica(土壤学报), 2011, 48(5): 1083.
[13] Said Nawar, Henning Buddenbaum, Joachim Hill, et al. Soil & Tillage Research, 2016, 155: 510.
[14] Arve J Iversen, Torgny Palm. Applied Spectroscopy, 1985, 39(4): 641.
[15] ZHANG Xian-long, ZHANG Fei, ZHANG Hai-wei, et al(张贤龙, 张飞, 张海威, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(1): 110.
[16] Antoine Stevens, Thomas Udelhoven, Antoine Denis, et al. Geoderma, 2010, 158(1): 32.
[17] ZHU Yun, SHEN Guang-rong, XIANG Qiao-qiao, et al(朱赟, 申广荣, 项巧巧, 等). Chinese Journal of Soil Science(土壤通报), 2017, 48(3): 560.
[18] SUN Yue-qi, SUN Xiao-mei, WU Zhen-fu, et al(孙越琦, 孙笑梅, 巫振富, 等). Acta Pedologica Sinica(土壤学报), 2023, 60(6): 1595.
[19] YU Dong-xue, JIA Xiao-xu, HUANG Lai-ming, et al(于冬雪, 贾小旭, 黄来明, 等). Acta Pedologica Sinica(土壤学报), 2019, 56(1): 55.
[20] MA Yu-ying, LEI Ting-wu, ZHANG Xin-ping, et al(马玉莹, 雷廷武, 张心平, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(9): 86.
[21] Liu Lanfa, Ji Min, Manfred Buchroithner. Remote Sensing, 2017, 9(12): 1299.
[22] Yang Renmin, Guo Wenwen. International Journal of Applied Earth Observation and Geoinformation, 2019, 82: 101906.
[23] QIU Yue-feng, YANG Chao, LIN Fen-fang, et al(邱乐丰, 杨超, 林芬芳, 等). Chinese Journal of Applied Ecology(应用生态学报), 2010, 21(12): 3099.