Research on Biomass Inversion of Multiple Vegetation Types on the Surface of Mining Areas

doi:10.16258/j.cnki.1674-5906.2024.07.004

Ecology and Environment ›› 2024, Vol. 33 ›› Issue (7): 1027-1035.DOI: 10.16258/j.cnki.1674-5906.2024.07.004

• Research Article [Ecology] • Previous Articles Next Articles

Research on Biomass Inversion of Multiple Vegetation Types on the Surface of Mining Areas

YANG Keming¹(), PENG Lishun¹^,^*(), ZHANG Yanhai², GU Xinru¹, CHEN Xinyang¹, JIANG Kegui¹

1. College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, P. R. China
2. General Defense Geological Survey Department, Huaibei Mining Co., Ltd., Huaibei 235000, P. R. China

Received:2024-04-15 Online:2024-07-18 Published:2024-09-04
Contact: PENG Lishun

淮北矿区多种类型植被地上生物量反演研究

杨可明¹(), 彭里顺¹^,^*(), 张燕海², 谷新茹¹, 陈新阳¹, 江克贵¹

1.中国矿业大学（北京）地球科学与测绘工程学院，北京 100083
2.淮北矿业股份有限公司通防地测部，安徽淮北 235000

通讯作者: 彭里顺
作者简介:杨可明（1969年生），男，教授，博士研究生导师，主要从事高光谱遥感、矿山地理与形变信息研究。E-mail: ykm69@163.com
基金资助:
国家科技基础资源调查专项(2022FY101905);事业单位委托项目(2023-129);国家自然科学基金项目(41971401)

Abstract

Abstract:

Biomass is an important component of vegetation carbon, and is crucial for evaluating the effectiveness of ecological restoration in mining areas. In the Zhahe mining area of Huaibei Mining, ecological destruction and restoration coexist with a rich variety of surface vegetation types including trees, herbs, and crops. Traditional single-species biomass models are difficult to apply in areas where multiple vegetation types overlap. To accurately invert the biomass of the composite vegetation in this region, this study used Sentinel satellite data and constructed a spectral index feature dataset using vegetation indices and band operation methods. Different features and model combinations were used to construct biomass inversion models for each region. In the feature selection stage, two methods, random forest and correlation analysis, were used to evaluate the features comprehensively. Ultimately, five key spectral indices (enhanced vegetation index, normalized difference water index, improved normalized difference water index, Sentinel-2 red edge position, and land chlorophyll index) and five self-constructed spectral features based on band operations (1/B1, 1/B2, 1/B7, B1/B2, B5/B6) were selected. Based on these selected features, five different feature combination schemes were designed, and biomass inversion models were constructed separately for forest and composite vegetation data by combining the traditional equation regression and machine learning models. The results showed that compared with traditional regression models, machine learning models have higher accuracy in biomass inversion. Self-constructed spectral features based on band operations can improve the accuracy of biomass inversion using machine learning models. Among them, the support vector regression (SVR) model combined with self-constructed spectral features and original bands achieved the highest accuracy in inversion results, with a determination coefficient R² of 0.74 and a root mean square error of 8.14 kg∙m⁻² for the model validation set. Applying the SVR model to biomass inversion in the study area yielded results highly consistent with local vegetation distribution characteristics. The results of this study not only provide data support for the evaluation of ecological restoration in mining areas but also provide reference and experience for subsequent studies on similar ecosystems.

Key words: mining area, multi-vegetation overlap area, composite biomass, machine learning, inversion model, vegetation type

摘要：

生物量是植被碳的重要组成部分，对于评估矿山生态环境修复效果至关重要。在淮北矿业闸河矿区，生态破坏与修复并存，地表植被类型丰富多样，有林木、草本和农作物等。在这种多植被类型交叉覆盖的地区，传统的单一物种生物量模型难以应用。为准确反演该区域综合植被的生物量，以sentinel卫星数据为基础，利用植被指数和波段运算方法构建的光谱指数作为特征数据集，通过不同特征和模型的组合构建该区域生物量反演模型。在特征选择阶段，利用随机森林和相关性分析两种方法对特征进行综合评价，最终筛选出关键的5个光谱指数（增强植被指数、归一化差分水体指数、改进的归一化差分水体指数、Sentinel-2红边位置、陆地叶绿素指数）以及5个基于波段运算的自建光谱特征（1/B1、1/B2、1/B7、B1/B2、B5/B6）。基于这些筛选出的特征，设计了5种不同的特征组合方案，并结合传统方程回归和机器学习模型，在林地和综合植被数据上分别构建了生物量反演模型。研究结果表明，相较于传统回归模型，机器学习模型在生物量反演领域具有更高的精度。基于波段运算的自建光谱特征可以提高机器学习模型生物量反演的精度，其中支持向量回归（SVR）模型结合自建光谱特征与原始波段得到的反演结果精度最高，模型验证集的决定系数R²为0.74，均方根误差为8.14 kg∙m⁻²。将SVR模型应用于研究区进行生物量反演，得到的结果与当地植被分布特征高度一致。本研究成果不仅为矿区生态修复评价提供了数据支撑，而且为类似生态系统的后续研究提供了借鉴和经验。

关键词: 矿山, 多植被交叉覆盖区, 综合生物量, 机器学习, 反演模型, 植被类型

CLC Number:

YANG Keming, PENG Lishun, ZHANG Yanhai, GU Xinru, CHEN Xinyang, JIANG Kegui. Research on Biomass Inversion of Multiple Vegetation Types on the Surface of Mining Areas[J]. Ecology and Environment, 2024, 33(7): 1027-1035.

杨可明, 彭里顺, 张燕海, 谷新茹, 陈新阳, 江克贵. 淮北矿区多种类型植被地上生物量反演研究[J]. 生态环境学报, 2024, 33(7): 1027-1035.

Figures/Tables 10

References 43

[1]	ALI A, IMRAN M, ALI A, et al., 2022. Evaluating Sentinel-2 red edge through hyperspectral profiles for monitoring LAI & chlorophyll content of Kinnow Mandarin orchards[J]. Remote Sensing Applications: Society and Environment, 26: 100719.
[2]	ALVES O R, MARCATO J J, SOARES C, et al., 2022. Silage grass sward nitrogen concentration and dry matter yield estimation using deep regression and RGB images captured by UAV[J]. Agronomy, 12(6): 1352.
[3]	CHEN J, ZHU W N, TIAN Y Q, et al., 2017. Remote estimation of colored dissolved organic matter and chlorophyll-a in Lake Huron using Sentinel-2 measurements[J]. Journal of Applied Remote Sensing, 11(3): 036007.
[4]	DASH J, CURRAN P J, 2004. The MERIS terrestrial chlorophyll index[J]. International Journal of Remote Sensing, 25(23): 5403-5413.
[5]	DUBE T, SHOKO C, GARA T W, 2021. Remote sensing of aboveground grass biomass between protected and non-protected areas in savannah rangelands[J]. African Journal of Ecology, 59(3): 687-695.
[6]	GITELSON A A, MERZLYAK M N, 1994. Quantitative estimation of chlorophyll-a using reflectance spectra: Experiments with autumn chestnut and maple leaves[J]. Journal of Photochemistry and Photobiology B: Biology, 22(3): 247-252.
[7]	GITELSON A A, KAUFMAN Y J, MERZLYAK M N, 1996. Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sensing of Environment, 58(3): 289-298.
[8]	HABOUDANE D, MILLER J R, TREMBLAY N, et al., 2002. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture[J]. Remote Sensing of Environment, 81(2-3): 416426.
[9]	HABOUDANE D, MILLER J R, PATTEY E, et al., 2004. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture[J]. Remote Sensing of Environment, 90(3): 337-352.
[10]	HAMA A, TANAKA K, MOCHIZUKI A, et al., 2020. Estimating the protein concentration in rice grain using UAV imagery together with agroclimatic data[J]. Agronomy, 10(3): 431.
[11]	HUANG Z M, TIAN Y C, ZHANG Q, et al., 2022. Estimating mangrove above-ground biomass at Maowei Sea, Beibu Gulf of China using machine learning algorithm with Sentinel-1 and Sentinel-2 data[J]. Geocarto International, 37(27): 15778-15805.
[12]	LUO S, REN H R, ZHANG Y Q, 2023. Estimation of Grassland Green Biomass Using Sentinel-1A SLC Image Spectral Characteristics[J]. Spectroscopy and Spectral Analysis, 43(3): 955-961.
[13]	MCFEETERS S K, 1996. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 17(7): 1425-1432.
[14]	MIURA T, HUETE A R, Yoshioka H, 2000. Evaluation of sensor calibration uncertainties on vegetation indices for MODIS[J]. IEEE Transactions on Geoscience and Remote Sensing, 38(3): 1399-1409.
[15]	QI J G, CHEHBOUNI A, HUETE A R, et al., 1994. A modified soil adjusted vegetation index[J]. Remote Sensing of Environment, 48(2): 119-126.
[16]	TANG Z J, GUO J J, LU X H, et al., 2022. Estimation of leaf area index and above-ground biomass of winter wheat based on optimal spectral index[J]. Agronomy, 12(7): 1729.
[17]	TIAN Y C, ZHANG Q, HUANG H, et al., 2022. Aboveground biomass of typical invasive mangroves and its distribution patterns using UAV-LiDAR data in a subtropical estuary: Maoling River estuary, Guangxi, China[J]. Ecological Indicators, 136: 108694.
[18]	TONG X, DUAN L M, LIU T X, et al., 2023. Estimation of grassland aboveground biomass combining optimal derivative and raw reflectance vegetation indices at peak productive growth stage[J]. Geocarto International, 38(1): 2186497.
[19]	WANG H M, TAN K, WU FY, et al., 2020. Study of the retrieval and adsorption mechanism of soil heavy metals based on spectral absorption characteristics[J]. Spectroscopy and Spectral Analysis, 40(1): 316-323.
[20]	XU H Q, 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery[J]. International Journal of Remote Sensing, 27(14): 3025-3033.
[21]	YANG Y T, FAN Y M, BASANG C M, et al., 2022. Different biomass production and soil water patterns between natural and artificial vegetation along an environmental gradient on the Loess Plateau[J]. Science of the Total Environment, 814: 152839.
[22]	ZHA Y, GAO J Q, NI S, 2003. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery[J]. International Journal of Remote Sensing, 24(3): 583-594.
[23]	ZHANG Y L, WANG N, WANG Y L, et al., 2023. A new strategy for improving the accuracy of forest aboveground biomass estimates in an alpine region based on multi-source remote sensing[J]. GIScience & Remote Sensing, 60(1): 2163574.
[24]	陈鹏飞, Nicolas Tremblay, 王纪华, 等, 2010. 估测作物冠层生物量的新植被指数的研究[J]. 光谱学与光谱分析, 30(2): 512-517.
	CHEN P F, NICOLAS T, WANG J H, et al., 2010. Study on new vegetation index for estimating crop canopy biomass[J]. Spectroscopy and Spectral Analysis, 30(2): 512-517.
[25]	冯志立, 肖锋, 卢小平, 等, 2022. 基于随机森林特征优选的冬小麦分类方法[J]. 测绘通报, 68(3): 70-75.
	FENG Z L, XIAO F, LU X P, et al., 2022. Classification method of winter wheat based on random forest feature selection[J]. Surveying and Mapping Bulletin, 68(3): 70-75.
[26]	黄家兴, 吴静, 李纯斌, 等, 2021. 基于Sentinel-2和Landsat 8数据的天祝县草地地上生物量遥感反演[J]. 草地学报, 29(9): 2023-2030. DOI
	HUANG J X, WU J, LI C B, et al., 2021. Remote sensing inversion of grassland aboveground biomass in Tianzhu County based on Sentinel-2 and Landsat 8 data[J]. Acta Agrestia Sinica, 29(9): 2023-2030.
[27]	黄天宝, 欧光龙, 吴勇, 等, 2024. 基于机器学习算法的森林生物量多源遥感估测[J/OL]. 西北林学院学报, 39(1): 1-9.
	HUANG T B, OU G L, WU Y, et al., 2024. Multi-source remote sensing estimation of forest biomass based on machine learning algorithms[J/OL]. Journal of Northwest Forestry University, 39(1): 1-9.
[28]	黄彦, 田庆久, 耿君, 等, 2016. 遥感反演植被理化参数的光谱和空间尺度效应[J]. 生态学报, 36(3): 883-891.
	HUANG Y, TIAN Q J, GENG J, et al., 2016. Spectral and spatial scale effects of remote sensing inversion of vegetation physicochemical parameters[J]. Acta Ecologica Sinica, 36(3): 883-891.
[29]	黄友菊, 田义超, 张强, 等, 2023. 资源一号02D高光谱数据红树林地上生物量反演[J]. 光谱学与光谱分析, 43(12): 3906-3915.
	HUANG Y J, TIAN Y C, ZHANG Q, et al., 2023. Inversion of aboveground biomass of mangrove forest from 02D hyperspectral data of Resource No.1[J]. Spectroscopy and Spectral Analysis, 43(12): 3906-3915.
[30]	惠嘉伟, 白中科, 刘凯杰, 等, 2023. 归一化植被指数 (NDVI) 在草原露天煤矿区的适用性分析[J]. 工程科学学报, 45(1): 54-63.
	HUI J W, BAI Z K, LIU K J, et al., 2023. Analysis of the Applicability of Normalized Difference Vegetation Index (NDVI) in Grassland Open-pit Coal Mining Areas. Journal of Engineering Sciences, 45(1): 54-63.
[31]	刘杨, 张涵, 冯海宽, 等, 2021. 无人机成像高光谱的马铃薯地上生物量估算[J]. 光谱学与光谱分析, 41(9): 2657-2664.
	LIU Y, ZHANG H, FENG H K, et al., 2021. Estimation of potato aboveground biomass using unmanned aerial vehicle hyperspectral imaging[J]. Spectroscopy and Spectral Analysis, 41(9): 2657-2664.
[32]	李成举, 刘寅笃, 秦天元, 等, 2024. 基于机器学习的马铃薯叶片叶绿素含量估算[J]. 光谱学与光谱分析, 44(4): 1117-1127.
	LI C J, LIU Y D, QIN T Y, et al., 2024. Estimation of chlorophyll content in potato leaves based on machine learning[J]. Spectroscopy and Spectral Analysis, 44(4): 1117-1127.
[33]	李富平, 贾淯斐, 夏冬, 等, 2021. 石矿迹地生态修复技术研究现状与发展趋势[J]. 金属矿山, 56(1): 168-184.
	LI F P, JIA Y F, XIA D, et al., 2021. Research status and development trend of ecological restoration technology for stone mining sites[J]. Metal Mine, 56(1): 168-184.
[34]	罗森, 任鸿瑞, 张悦琦, 2023. 利用Sentinel-1A SLC影像光谱特征估算草地绿色生物量[J]. 光谱学与光谱分析, 43(3): 955-961.
	LUO S, REN H R, ZHANG Y Q, 2023. Estimation of grassland green biomass using spectral features of Sentinel-1A SLC images[J]. Spectroscopy and Spectral Analysis, 43(3): 955-961.
[35]	陶冶, 张元明, 2013. 荒漠灌木生物量多尺度估测——以梭梭为例[J]. 草业学报, 22(6): 1-10. DOI
	TAO Y, ZHANG Y M, 2013. Multi-scale estimation of desert shrub biomass: A case study of Haloxylon ammodendron[J]. Acta Prataculturae Sinica, 22(6): 1-10. DOI
[36]	王超, 贾翔, 赵莹, 等, 2019. 森林生物量估算方法研究进展[J]. 北华大学学报(自然科学版), 20(3): 391-394.
	WANG C, JIA X, ZHAO Y, et al., 2019. Research progress on estimation methods of forest biomass[J]. Journal of Beihua University (Natural Science Edition), 20(3): 391-394.
[37]	王晗, 向友珍, 李汪洋, 等, 2023. 基于无人机多光谱遥感的冬油菜地上部生物量估算[J]. 农业机械学报, 54(8): 218-229.
	WANG H, XIANG Y Z, LI W Y, et al., 2023. Estimation of aboveground biomass of winter oilseed rape based on multi-spectral remote sensing of unmanned aerial vehicles[J]. Transactions of the Chinese Society for Agricultural Machinery, 54(8): 218-229.
[38]	汪静平, 吴小丹, 马杜娟, 等, 2023. 基于机器学习的遥感反演: 不确定性因素分析[J]. 遥感学报, 27(3): 790-801.
	WANG J P, WU X D, MA D J, et al., 2023. Remote sensing inversion based on machine learning: Analysis of uncertainty factors[J]. Journal of Remote Sensing, 27(3): 790-801.
[39]	王雪梅, 杨雪峰, 赵枫, 等, 2023. 基于机器学习算法的干旱区绿洲地上生物量估算[J]. 生态环境学报, 32(6): 1007-1015. DOI
	WANG X M, YANG X F, ZHAO F, et al., 2023. Estimation of Aboveground Biomass in the Arid Oasis Based on the Machine Learning Algorithm[J]. Chinese Journal of Ecology and Environmental Sciences, 32(6): 1007-1015.
[40]	杨元合, 饶胜, 胡会峰, 等, 2004. 青藏高原高寒草地植物物种丰富度及其与环境因子和生物量的关系[J]. 生物多样性, 12(1): 200-205.
	YANG Y H, RAO S, HU H F, et al., 2004. Plant species richness of alpine grassland in the Qinghai-Tibet Plateau and its relationship with environmental factors and biomass[J]. Biodiversity Science, 12(1): 200-205.
[41]	赵越, 徐大伟, 范凯凯, 等, 2022. Landsat 8和机器学习估算蒙古高原草地地上生物量[J]. 农业工程学报, 38(24): 138-144.
	ZHAO Y, XU D W, FAN K K, et al., 2022. Estimation of grassland aboveground biomass in the Mongolian Plateau using Landsat 8 and machine learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 38(24): 138-144.
[42]	国家林业局造林绿化管理司, 2014. 造林项目碳汇计量监测指南[M]. 北京: 中国林业出版社: 60-68.
	Department of Afforestation and Greening Management of the State Forestry Administration, 2014. Guidelines for carbon sink measurement and monitoring of afforestation projects[M]. Beijing: China Forestry Press: 60-68.
[43]	周国逸, 尹光彩, 唐旭利, 等, 2018. 中国森林生态系统碳储量——生物量方程[M]. 北京: 科学出版社: 40-80.
	ZHOU GY, YIN G C, TANG X L, et al., 2018. Carbon Storage of Forest Ecosystems in China: Biomass Equations[M]. Beijing: Science Press: 40-80.

特征名称	计算公式	引用
增强植被指数	2.5×[(B₈−B₄)/(B₈+6×B₄−7.5×B₂+1)]	Miura et al., 2000
归一化差值水体指数	(B₃−B₈)/(B₃+B₈)	Mcfeeters, 1996
比值植被指数	B₈/B₄	Huang et al., 2022
差值植被指数	B₈−B₄	王雪梅等, 2023
归一化植被指数	(B₈−B₄)/(B₈+B₄)	惠嘉伟等, 2023
修正归一化差值水体指数	(B₃−B₁₁)/(B₃+B₁₁)	Xu, 2006
叶绿素指数-绿光	(B₈/B₃)−1	Gitelson et al., 1996
Sentinel-2红边位置	705+35×{{[(B₇+B₄)/2]−B₅}/(B₆−B₅)}	Ali et al., 2022
修正土壤调节植被指数	0.5×{2×(B₈+1)−sqrt[(2×B₈+1)×2−8×(B₈−B₄)]}	Qi et al., 1994
归一化差值建筑用地指数	(B₁₁−B₈)/(B₁₁+B₈)	Zha et al., 2003
叶绿素指数-红边	(B₈/B₅)−1	Gitelson et al., 1994
陆地叶绿素指数	(B₆−B₅)/(B₅+B₄)	Dash et al., 2004
红边三角植被指数	100×(B₈−B₅)−10×(B₈−8₃)	Haboudane et al., 2004
修正型三角植被指数	1.5×[1.2(B₈−B₃)−2.5×(B₄−B₃)]sqrt{(2×B₈+1)²−[6×B₈−5sqrt(B₄)]−0.5}	Haboudane et al., 2002

特征名称	计算公式	引用
增强植被指数	2.5×[(B₈−B₄)/(B₈+6×B₄−7.5×B₂+1)]	Miura et al., 2000
归一化差值水体指数	(B₃−B₈)/(B₃+B₈)	Mcfeeters, 1996
比值植被指数	B₈/B₄	Huang et al., 2022
差值植被指数	B₈−B₄	王雪梅等, 2023
归一化植被指数	(B₈−B₄)/(B₈+B₄)	惠嘉伟等, 2023
修正归一化差值水体指数	(B₃−B₁₁)/(B₃+B₁₁)	Xu, 2006
叶绿素指数-绿光	(B₈/B₃)−1	Gitelson et al., 1996
Sentinel-2红边位置	705+35×{{[(B₇+B₄)/2]−B₅}/(B₆−B₅)}	Ali et al., 2022
修正土壤调节植被指数	0.5×{2×(B₈+1)−sqrt[(2×B₈+1)×2−8×(B₈−B₄)]}	Qi et al., 1994
归一化差值建筑用地指数	(B₁₁−B₈)/(B₁₁+B₈)	Zha et al., 2003
叶绿素指数-红边	(B₈/B₅)−1	Gitelson et al., 1994
陆地叶绿素指数	(B₆−B₅)/(B₅+B₄)	Dash et al., 2004
红边三角植被指数	100×(B₈−B₅)−10×(B₈−8₃)	Haboudane et al., 2004
修正型三角植被指数	1.5×[1.2(B₈−B₃)−2.5×(B₄−B₃)]sqrt{(2×B₈+1)²−[6×B₈−5sqrt(B₄)]−0.5}	Haboudane et al., 2002

方案分组名称	光谱特征组合 (特征数)
A	原始波段 (12个)
B	原始波段+光谱指数 (17个)
C	原始波段+自建光谱特征 (17个)
D	原始波段+光谱指数+自建光谱特征 (22个)
E	光谱指数+自建光谱特征 (17个)

方案分组名称	光谱特征组合 (特征数)
A	原始波段 (12个)
B	原始波段+光谱指数 (17个)
C	原始波段+自建光谱特征 (17个)
D	原始波段+光谱指数+自建光谱特征 (22个)
E	光谱指数+自建光谱特征 (17个)

方程名称	函数形式
线性	y=ax+b
二次多项式	y=ax²+bx+c
复合曲线	y=a×b^x
三次曲线	y=ax³+bx²+bx+d
指数	y=b×e^ax
幂函数	y=b×x^a

Research on Biomass Inversion of Multiple Vegetation Types on the Surface of Mining Areas

淮北矿区多种类型植被地上生物量反演研究

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 43

Related Articles 11

Recommended Articles

Metrics

Comments

传统方程回归模型	拟合波段	训练集			验证集
传统方程回归模型	拟合波段	R²	σ_RMSE/(kg∙m⁻²)	σ_RPD	R²	σ_RMSE/(kg∙m⁻²)	σ_RPD
线性	B1/B12	0.47	11.92	1.37	0.34	9.30	1.23
二次方程	(B1−B5)/(B1+B5)	0.54	11.07	1.47	0.35	9.24	1.24
复合曲线	B3+B12	0.52	11.36	1.44	0.49	8.18	1.40
三次曲线	B6/B8A	0.60	10.39	1.58	0.49	8.18	1.40
指数方程	B1/B5	0.51	11.47	1.43	0.35	9.21	1.24

机器学习回归模型	R²					σ_RMSE/(kg∙m⁻²)					σ_RPD
机器学习回归模型	A	B	C	D	E	A	B	C	D	E	A	B	C	D	E
SVR	0.69	0.73	0.74	0.73	0.67	8.84	8.22	8.14	8.25	9.07	1.80	1.92	1.96	1.92	1.74
DTR	0.65	0.65	0.65	0.65	0.43	9.87	9.87	9.87	9.87	16.57	1.69	1.69	1.69	1.69	1.32
KNNR	0.69	0.55	0.66	0.59	0.45	8.86	10.67	10.34	11.2	11.78	1.80	1.49	1.71	1.56	1.35
Ridge-R	0.57		0.68			10.37		8.96			1.52		1.77
Lasso-R	0.35		0.47			12.56		11.4			1.24		1.37
RFR	0.63	0.63	0.66	0.64	0.51	9.86	9.81	9.93	9.69	12.43	1.64	1.64	1.71	1.67	1.43
GBR	0.62	0.68	0.67	0.68	0.53	9.79	9.53	9.16	8.95	11.96	1.62	1.77	1.74	1.77	1.46

机器学习回归模型	R²					σ_RMSE/(kg∙m⁻²)					σ_RPD
机器学习回归模型	A	B	C	D	E	A	B	C	D	E	A	B	C	D	E
SVR	0.79	0.80	0.79	0.80	0.76	5.95	5.83	5.98	5.91	6.48	2.16	2.41	2.22	2.12	2.35
DTR	0.46	0.46	0.46	0.46		9.59	9.59	9.59	9.59		1.34	1.47	1.28	1.31
KNNR	0.75	0.77	0.73	0.73	0.69	6.52	6.30	6.80	6.81	7.31	1.97	2.23	1.73	1.85	2.07
Ridge-R	0.74	0.80	0.73	0.75	0.78	6.66	5.87	6.76	6.54	6.21	1.93	2.39	1.57	1.92	2.45
Lasso-R	0.46	0.30	0.35	0.09	0.76	9.61	11.00	10.54	14.27	6.40	1.34	1.28	1.14	1.01	2.37
RFR	0.55	0.55	0.54	0.54	0.40	9.1	8.88	8.91	8.89	11.97	1.43	1.58	1.46	1.42	1.35
GBR	0.47	0.49	0.34	0.48	0.35	9.56	9.34	10.61	9.44	10.60	1.35	1.50	1.18	1.33	1.43

[1]	JIANG Runhai, WEN Shaofu, ZHU Chengqiang, ZHANG Mei, YANG Runling, WANG Chunxue, HOU Xiuli. Research on the Promotion of Maize Growth and Immobilization of Pb in the Rhizosphere by Pb-tolerant Phosphate Solubilizing Bacteria in Pb-contaminated Mining Areas [J]. Ecology and Environment, 2024, 33(2): 291-300.
[2]	LI Jiajing, LIANG Yongliang, LI Jingyao, LI Xiaowei, YANG Junlong. Analysis of Plant Ecological Strategies Based on Leaf Functional Traits on the Western Slope of Helan Mountain [J]. Ecology and Environment, 2024, 33(1): 45-53.
[3]	WANG Xuemei, YANG Xuefeng, ZHAO Feng, AN Baisong, HUANG Xiaoyu. Estimation of Aboveground Biomass in the Arid Oasis Based on the Machine Learning Algorithm [J]. Ecology and Environment, 2023, 32(6): 1007-1015.
[4]	ZHANG Lijin, DU Hu, ZENG Fuping, HUANG Guoqin, SONG Min, SONG Tongqing. Discussion on the Relationship between Productivity and Diversity during Vegetation Restoration in the Karst Peak-cluster Depression [J]. Ecology and Environment, 2023, 32(1): 26-35.
[5]	SHI Wenjing, ZHOU Hanpeng, SUN Tao, HUANG Jintao, YANG Wenhuan, LI Weiping. Research on Priority Control Factors and Health Risk Assessment of Heavy Metal Pollution in Soil Around Mining Areas [J]. Ecology and Environment, 2022, 31(8): 1616-1628.
[6]	MA Huiying, LI Xinzhu, MA Xinyu, GONG Lu. Characteristics and Driving Factors of Soil Organic Carbon Fractions under Different Vegetation Types of the mid-Northern Piedmont of the Tianshan Mountains, Xinjiang [J]. Ecology and Environment, 2022, 31(6): 1124-1131.
[7]	YANG Xianfang, CHEN Zhao, ZHENG Lin, WAN Zhiwei, CHEN Yonglin, WANG Yuandong. Characteristics and Network of Soil Bacterial Communities in Different Land Use Types in Rare Earth Mining Areas [J]. Ecology and Environment, 2022, 31(4): 793-801.
[8]	JIANG Peng, QIN Mei’ou, LI Rongping, MENG Ying, YANG Feiyun, WEN Rihong, SUN Pei, FANG Yuan. Seasonal Variability of GPP and Its Influencing Factors in the Typical Ecosystems in China [J]. Ecology and Environment, 2022, 31(4): 643-651.
[9]	YANG Hu, WANG Peiyao, LI Xiaowei, WANG Jifei, YANG Junlong. Distribution of Soil Fungal Diversity and Community Structure in Different Vegetation Types on the Eastern Slopes of Helan Mountains [J]. Ecology and Environment, 2022, 31(2): 239-247.
[10]	XING Shuwen, XU Jiamin, HUANG Bin, GAO Jingting, HAN Li. Effect of Heavy Metal Pollution on the Community Structure and Diversity of Soil Animals in Tea Garden Located in A Tungsten Mining Area [J]. Ecology and Environment, 2021, 30(9): 1903-1915.
[11]	SUN Xuejiao, LI Jimei, ZHANG Yutao, LI Xiang, LU Jianjiang, SHE Fei. Characteristics and Influence of Runoff and Sediment Yield in Mountain Forest on the North Slope of Tianshan Mountains [J]. Ecology and Environment, 2021, 30(9): 1821-1830.