基于ANN-CA的外来入侵植物互花米草的扩散趋势预测研究

doi:10.16258/j.cnki.1674-5906.2024.03.002

生态环境学报 ›› 2024, Vol. 33 ›› Issue (3): 341-350.DOI: 10.16258/j.cnki.1674-5906.2024.03.002

基于ANN-CA的外来入侵植物互花米草的扩散趋势预测研究

刘亚静¹^,²^,³^,⁴(), 刘明月¹^,²^,³^,⁴(), 李京¹, 周帅¹

1.华北理工大学矿业工程学院
2.唐山市资源与环境遥感重点实验室
3.河北省矿区生态修复产业技术研究院
4.河北省矿业开发与安全技术重点实验室

收稿日期:2023-01-09 出版日期:2024-03-18 发布日期:2024-05-08
通讯作者: *刘明月。E-mail: liumy917@ncst.edu.cn
作者简介:刘亚静（1977年生），女，教授，博士，主要研究方向为地理信息系统理论与技术应用。E-mail: lyj2206@126.com
基金资助:
国家自然科学基金青年基金项目(41901375);国家自然科学基金青年基金项目(42101393);河北省自然科学基金项目(D2019209322);河北省自然科学基金项目(D2022209005)

Prediction of Diffusion Trend of Invasive Plant Spartina Alterniflora Based on ANN-CA

LIU Yajing¹^,²^,³^,⁴(), LIU Mingyue¹^,²^,³^,⁴(), LI Jing¹, ZHOU Shuai¹

1. College of Mining Engineering, North China University of Science and Technology, Tangshan 063210, P. R. China
2. key Laboratory of Resources an Environmental Remote Sensing, Tangshan 063210, P. R. China
3. Hebei Industrial Technology Institute of Mine Ecological Remediation, Tangshan 063210, P. R. China
4. Hebei Key Laboratory Mining Development and Security Technology, Tangshan 063210, P. R. China

Received:2023-01-09 Online:2024-03-18 Published:2024-05-08

摘要/Abstract

摘要：

采用遥感技术手段对九段沙互花米草（Spartina alterniflora）信息提取与动态监测基础上，开展滨海地区互花米草入侵时空特征分析、入侵地区景观演变规律以及预测互花米草扩散趋势等研究对于沿海城市生态环境协调发展具有重要的意义。选取邻域因子、生态属性和地理属性等相关变量因子，耦合人工神经网络（ANN）与元胞自动机（CA），基于2015－2019年间九段沙互花米草与其他湿地景观类型数据构建ANN-CA模型，采用3层BP神经网络，在不断训练与校正与验证模型精度的基础上，对2019年九段沙区域互花米草进行模拟，采用Lee-Sallee形状指数来对比模拟分类结果与实际分类结果在空间分布层面的相似度，并进行相应的模型校正，在此基础上预测2025年九段沙互花米草扩散与群落分布格局，为互花米草的扩张趋势、景观演变以及分布扩散预测提供理论依据和科学基础。结果表明，1）1995－2025年间互花米草自从引种定居到不断扩张，所呈现的面积变化图近乎S型曲线，其中2015－2019年面积增长了847 hm²，2019－2025年面积增长了646 hm²，因此互花米草在九段沙自然保护区的动态扩散，分别为定居阶段、滞缓阶段、快速增长阶段以及缓慢增长阶段。2）2025年九段沙区域互花米草的扩张速率从趋势看已进入扩张的缓慢期，与前几年相比尽管有所增加，但趋势有所放缓。3）构建的ANN-CA模型能够较好地对九段沙自然保护区的植被演变进行模拟和预测。

关键词: 土地利用, ANN-CA, 元胞自动机, 九段沙, 互花米草

Abstract:

Dynamic monitoring and information extraction of Spartina alterniflora in Jiuduansha were conducted using remote-sensing technology. The analysis of the spatiotemporal characteristics of Spartina alterniflora invasion in coastal areas, landscape evolution patterns in invaded areas, and prediction of Spartina alterniflora diffusion trends are of great significance for the coordinated development of the ecological environment in coastal cities. By selecting relevant variable factors, such as neighborhood factors, ecological attributes, and geographical attributes, coupled with artificial neural networks (ANN) and Cellular Automata (CA), an ANN-CA model was constructed based on the data of Spartina alterniflora in the Jiuduansha area and other wetland landscape types from 2015 to 2019. A three-layer BP neural network was used to simulate Spartina alterniflora in the Jiuduansha area in 2019, and the Lee-Sallee shape index was used to compare the spatial similarity between simulated classification results and actual classification results, and to perform corresponding model corrections based on continuous training, correction, and validation of model accuracy. In this study, the diffusion and community distribution patterns of Spartina alterniflora in Jiuduansha were predicted for 2025, thereby providing a theoretical and scientific basis for predicting the expansion trends, landscape evolution, and distribution of Spartina alterniflora. The results showed that 1) from 1995 to 2025, the area change of Spartina alterniflora showed an almost S-shaped curve from its introduction and settlement to continuous expansion. The area increased by 847 hm² from 2015 to 2019 and 646 hm² from 2019 to 2025. Therefore, the dynamic diffusion of Spartina alterniflora in the Jiuduansha Nature Reserve could be divided into three stages: settlement, stagnation, rapid growth, and slow growth. 2) The expansion rate of Spartina alterniflora in the Jiuduansha area in 2025 has entered a slow period of expansion; although it has increased compared to previous years, the trend has slowed. 3) The constructed ANN-CA model could effectively simulate and predict vegetation evolution in the Jiuduansha Nature Reserve. The simulation results provide a theoretical and scientific basis for predicting the expansion trend of Spartina alterniflora, landscape evolution, and future distribution dynamics of Spartina alterniflora.

Key words: land use, ANN-CA, cellular automata, Jiuduansha, Spartina alterniflora

中图分类号:

Q948
X173

刘亚静, 刘明月, 李京, 周帅. 基于ANN-CA的外来入侵植物互花米草的扩散趋势预测研究[J]. 生态环境学报, 2024, 33(3): 341-350.

LIU Yajing, LIU Mingyue, LI Jing, ZHOU Shuai. Prediction of Diffusion Trend of Invasive Plant Spartina Alterniflora Based on ANN-CA[J]. Ecology and Environment, 2024, 33(3): 341-350.

图/表 14

图1 研究区概况图

Figure 1 Overview of the research area

表1 影像列表及其参数

Table 1 Image list and its parameters

年份	数据源	传感器	分辨率	获取时间	潮位
2015年	Sentinel	MSI	10	2015-12-03	低潮位
2019年	Sentinel	MSI	10	2019-06-15	低潮位
2019年	Sentinel	MSI	10	2018-10-28	低潮位

图2 2015年与2019年两期土地利用图

Figure 2 Land use map of two phases in 2015 and 2019

表2 模型采用的变量因子及其预处理

Table 2 Variable factors used in the model and their preprocessing

类别	空间变量	获取方法	数据范围	标准化范围
邻域因子	邻近互花米草单元数量		0‒48单元	0‒1
	邻近芦苇单元数量	根据CA模型及ANN输入层因子计算提取 (7×7窗口)
	邻近海三棱藨草单元数量
	邻近光滩单元数量
	邻近水体单元数量
生态属性	植被覆盖度	像元二分模型	0‒1	0‒1
地理属性	X、Y坐标		1‒857	0‒1

图3 人工神经网络结构图

Figure 3 Structure diagram of artificial neural network

图4 植被演化模拟结构图

Figure 4 Structure diagram of vegetation evolution simulation

图5 神经网络训练迭代次数及误差曲线

Figure 5 Iteration times and error curve of neural network training

表3 不同参数组合下模拟精度

Table 3 Simulation accuracy under different parameter combinations

序号	随机变量a	转换概率阈值T	模拟精度/%
1	0	0.3	90.01
2	1	0.3	90.02
3	1.5	0.3	90.01
4	1	0.4	90.00
5	1.5	0.4	89.99

图6 不同参数组合下九段沙自然保护区2019年景观类型模拟效果

Figure 6 Landscape type simulation effect of Jiuduansha Nature Reserve in 2019 under different parameter combinations

表4 2019年各景观类型模拟类正确率及Kappa系数

Table 4 Accuracy and Kappa coefficient of simulation classes for various landscape types in 2019

类型	互花米草	芦苇	海三棱藨草	光滩	水体	总体
2019实际个数	65159	23109	14527	9844	186466	299105
2019模拟个数	66645	23934	14073	8994	184332	297978
正确个数	64035	22655	12513	8211	183611	291025
正确率/%	98.27	98.04	86.14	83.14	98.47	97.30
Kappa系数	0.98	0.97	0.82	0.78	0.98	0.96

表5 研究区域2019年模拟各地类单元数量情况及误差值

Table 5 Number and error values of simulated units in different regions of the study area in 2019 units

类别	互花米草	芦苇	海三棱藨草	光滩	水体
2019分类值	65159	23109	14527	9844	186466
2019模拟值	66645	23934	14073	8994	184332
误差值	−2.28	−3.57	3.13	8.63	1.14

图7 2025年九段沙自然保护区景观类型分布预测图

Figure 7 Landscape type distribution forecast of Jiuduansha nature reserve in 2025

表6 2019年各景观类型实际分布面积与2025年各景观模拟分布面积变化对比

Table 6 Comparison of the actual distribution area of each landscape type in 2019 and the simulated distribution area of each landscape in 2025 hm2

类别	互花米草	芦苇	海三棱藨草	光滩
2019分类值	5856.85	2081.39	1308.19	877.80
2025模拟值	6503.03	2128.41	948.19	786.95

图8 1995－2025年互花米草面积变化图

Figure 8 Area change of sporobolus alterniflorus from 1995 to 2025

参考文献 35

[1]	BRENNER J C, CHRISTMAN Z, ROGAN J, 2012. Segmentation of Landsat Thematic Mapper imagery improves buffelgrass (Pennisetum ciliare) pasture mapping in the Sonoran Desert of Mexico[J]. Applied Geography, 34(2): 569-575. DOI URL
[2]	CAI Z, WANG X, 2009. Research on Vegetation Dynamic Change Simulation Based on Spatial Data Mining of ANN-CA Model Using Time Series of Remote Sensing Images[C]// International Conference on Computer and Computing Technologies in Agriculture. Springer, Berlin, Heidelberg: 551-557.
[3]	DEDE M, ASDAK C, SETIAWAN I, 2021. Spatial dynamics model of land use and land cover changes: A comparison of CA, ANN, and ANN-CA[J]. Register Jurnal Ilmiah Teknologi Sistem Informasi, 8(1): 38-49. DOI URL
[4]	HUANG X, DUAN Y T, TAO Y H, et al., 2022. Effects of Spartina alterniflora invasion on soil organic carbon storage in the Beihai Coastal Wetlands of China[J]. Frontiers in Marine Science, 9(6): 1-10.
[5]	QU F Y, WANG S Q, WANG W, et al., 2023. Macrobenthic community structure of Rudong coastal wetland, China: The impact of invasive Spartina alterniflora and its implication for migratory bird conservation[J]. Wetlands Ecology and Management, 31(1): 159-168. DOI
[6]	WANG J B, LIN Z Y, MA Y Q, et al., 2022. Distribution and invasion of Spartina alterniflora within the Jiaozhou Bay monitored by remote sensing image[J]. Acta Oceanologica Sinica, 41(6): 31-40.
[7]	YAN D D, LI J T, XIE S Y, et al., 2022. Examining the expansion of Spartina alterniflora in coastal wetlands using an MCE-CA-Markov model[J]. Frontiers in Marine Science, 9(7): 1-13.
[8]	ZHENG Z S, TIAN B, ZHANG L W, et al., 2015. Simulating the range expansion of Spartina alterniflora in ecological engineering through constrained cellular automata model and GIS[J]. Mathematical Problems in Engineering, 23: 1-8.
[9]	ZHU G P, GAO Y B, ZHU L, 2013. Delimiting the coastal geographic background to predict potential distribution of Spartina alterniflora[J]. Hydrobiologia, 717(1): 177-187. DOI URL
[10]	董婷婷, 左丽君, 张增祥, 2009. 基于ANN-CA模型的土壤侵蚀时空演化分析[J]. 地球信息科学学报, 11(1): 132-138.
	DONG T T, ZUO L J, ZHANG Z X, 2009. A Study on Spacetime Evolution of Soil Erosion Based on ANN-CA Model[J]. Journal of Geo-information Science, 11(1): 132-138. DOI URL
[11]	高冉, 2021. 互花米草入侵对黄家塘湾滨海湿地土壤理化性质的影响[D]. 曲阜: 曲阜师范大学.
	GAO R, 2021. Effects of Spartina alterniflora invasion on soil physicochemical properties in Huangjiatang Bay coastal wetland[D]. Qufu: Qufu Normal University.
[12]	江顺, 2019. 基于ANN-CA的洞庭湖流域土地利用模拟预测研究[D]. 长沙: 中南林业科技大学.
	JIANG S, 2019. Research on Land Use Simulation and Prediction of Dongting Lake Basin Based on ANN-CA[D]. Changsha: Central South University of Forestry and Technology.
[13]	鞠瑞亭, 李慧, 石正人, 等, 2012. 近十年中国生物入侵研究进展[J]. 生物多样性, 20(5): 581-611. DOI
	JU R T, LI H, SHI Z R, et al., 2012. Progress of biological invasions research in China over the last decade[J]. Biodiversity Science, 20(5): 581-611. DOI
[14]	李娜娜, 2020. 四川省湿地景观格局时空演变与驱动力研究[D]. 成都: 四川农业大学.
	LI N N, 2020. Study on the spatiotemporal evolution and driving forces of wetland landscape pattern in Sichuan Province[D]. Chengdu: Sichuan Agricultural University.
[15]	黎夏, 叶嘉安, 2005. 基于神经网络的元胞自动机及模拟复杂土地利用系统[J]. 地理研究, 24(1): 19-27.
	LI X, YE J A, 2005. Cellular automata for simulating complex land use systems using neural networks[J]. Geographical Research, 24(1): 19-27. DOI
[16]	李郑杰, 2014. 漳江口红树林区互花米草入侵及扩散机制研究[D]. 厦门: 厦门大学.
	LI Z J, 2014. A study on the invasion and diffusion mechanism of Spartina alterniflora in the Zhangjiangkou Mangrove Region[D]. Xiamen: Xiamen University.
[17]	刘明月, 2018. 中国滨海湿地互花米草入侵遥感监测及变化分析[D]. 哈尔滨: 中国科学院大学(中国科学院东北地理与农业生态研究所).
	[ LIU M Y, 2018. Remote Sensing analysis of Spartina alterniflora in the coastal areas of China during 1990 to 2015 [D]. Harbin: University of the Chinese Academy of Sciences (Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences).
[18]	刘展航, 2022. 互花米草入侵下黄河三角洲滨海湿地植被和土壤生态化学计量特征[D]. 烟台: 鲁东大学.
	LIU Z H, 2022. Ecological stoichiometric characteristics of vegetation and soil in coastal wetlands of the Yellow River Delta under the invasion of Spartina alterniflora[D]. Yantai: Ludong University.
[19]	沈恩穗, 胡晓艳, 陈星余, 2021. 基于ANN-CA的酉阳中心城区城市增长边界模拟研究[C]// 中国城市规划学会, 成都市人民政府. 面向高质量发展的空间治理 (5): 1053-1064.
	SHEN E H, HU X Y, CHEN X Y, 2021. Research on the Simulation of Urban Growth Boundary in the Central Urban Area of Youyang Based on ANN-CA[C]// China Urban Planning Society, Chengdu Municipal People's Government. Spatial Governance for High Quality Development-Proceedings of the 2021 China Urban Planning Annual Conference, Application of New Urban Planning Technologies (5): 1053-1064.
[20]	任广波, 刘艳芬, 马毅, 等, 2014. 现代黄河三角洲互花米草遥感监测与变迁分析[J]. 激光生物学报, 23(6): 596-603, 608.
	REN G B, LIU Y F, MA Y, et al., 2014. Spartina alterniflora Monitoring and Change Analysis in Yellow River Delta by Remote Sensing Technology[J]. Acta Laser Biology Sinica, 23(6): 596-603, 608.
[21]	任经纬, 2021. 长江中游城市群城镇用地扩展时空演变分析与模拟[D]. 武汉: 武汉大学.
	REN J W, 2021. Analysis and simulation of spatiotemporal evolution of urban land expansion in urban agglomerations in the middle reaches of the Yangtze River[D]. Wuhan: Wuhan University.
[22]	王东辉, 2007. 上海九段沙互花米草种群扩散动态CA模型研究[D]. 上海: 华东师范大学.
	WANG D H, 2007. Study on the CA model of population diffusion dynamics of Spartina alterniflora in Jiuduansha, Shanghai[D]. Shanghai: East China Normal University.
[23]	王东辉, 张利权, 管玉娟, 2007. CA模型的上海九段沙互花米草和芦苇种群扩散动态[J]. 应用生态学报, 18(12): 2807-2813.
	WANG D H, ZHANG L Q, GUAN Y J, 2007. Population expansion of Spartina alteniflora and Phragm ites australis at Jiuduansha, Shanghai based on cellular autom at a model[J]. Chinese Journal of Applied Ecology, 14(12): 2807-2813.
[24]	王磊, 王羊, 蔡运龙, 2012. 土地利用变化的ANN-CA模拟研究——以西南喀斯特地区猫跳河流域为例[J]. 北京大学学报(自然科学版), 48(1): 116-122.
	WANG L, WANG Y, CAI Y L, 2012. An ANN-CA modeling method for land cover change in the karst area of China: A case study of Maotiao River Basin[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 48(1): 116-122.
[25]	王卿, 安树青, 马志军, 等, 2006. 入侵植物互花米草——生物学、生态学及管理[J]. 植物分类学报, 44(5): 559-588.
	WANG Q, AN S Q, MA Z J, et al., 2006. Invasive Spartina alterniflora: Biology, ecology and management[J]. Journal of Systematics and Evolution, 44(5): 559-588. DOI
[26]	夏雯雯, 2020. 互花米草生态入侵过程中土壤因子的变化特征[D]. 南京: 南京大学.
	XIA W W, 2020. Changes in soil factors during the ecological invasion process of Spartina alterniflora[D]. Nanjing: Nanjing University.
[27]	谢宝华, 韩广轩, 2018. 外来入侵种互花米草防治研究进展[J]. 应用生态学报, 29(10): 3464-3476. DOI
	XIE B H, HAN G X, 2018. Control of invasive Spartina alterniflora: A review[J]. Chinese Journal of Applied Ecology, 29(10): 3464-3476.
[28]	徐昔保, 2007. 基于GIS与元胞自动机的城市土地利用动态演化模拟与优化研究[D]. 兰州: 兰州大学.
	XU X B, 2007. Urban Lind Use Dynamic. Evolution Simulation and Optimization Based on GIS and Cellular Automata: A case study of Lanzhou[D]. Lanzhou: Lanzhou University.
[29]	闫振宁, 2021. 入侵物种互花米草扩散机制研究[D]. 呼和浩特: 内蒙古大学.
	YAN Z N, 2021. Study on the diffusion mechanism of invasive species Spartina alterniflora[D]. Hohhot: Inner Mongolia University.
[30]	杨俊芳, 2017. 现代黄河三角洲入侵植物互花米草遥感监测与分析[D]. 青岛: 中国石油大学.
	YANG J F, 2017. Remote sensing monitoring and analysis of invasive plant Spartina alterniflora in the modern Yellow River Delta[D]. Qingdao: China University of Petroleum.
[31]	易嫦, 潘耀忠, 张锦水, 2007. 基于多尺度空间ANN-CA模型的遥感影像超分辨率制图方法研究[J]. 地理与地理信息科学, 23(3): 42-46.
	YI C, PAN Y Z, ZHANG J S, 2007. Research on super-resolution mapping for remote sensing images based on a multi-scale spatial ANN-CA model[J]. Geography and Geo-Information Science, 23(3): 42-46.
[32]	张美美, 张荣群, 张晓东, 等, 2013. 基于ANN-CA的湿地景观变化时空动态模拟研究[J]. 计算机工程与设计, 34(1): 377-381.
	ZHANG M M, ZHANG R Q, ZHAGN X D, et al., 2013. Research of space-time dynamic simulation of wetland landscape changes based on ANN-CA[J]. Computer Engineering & Design, 34(1): 377-381.
[33]	赵金涛, 马逸雪, 石云, 等, 2021. 基于ANN-CA模型的黄土丘陵区县域土壤侵蚀演变预测[J]. 中国水土保持科学(中英文), 19(6): 60-68.
	ZHAO J T, MA Y X, SHI Y, et al., 2021. Prediction of soil erosion evolution in loess hilly areas based on ANN-CA model[J]. Chinese Journal of Soil and Water Conservation Science, 19(6): 60-68.
[34]	赵睿, 塔西甫拉提·特依拜, 丁建丽, 等, 2007. 基于神经网络的元胞自动机支持下的干旱区LUCC模拟研究——以新疆于田绿洲为例[J]. 水土保持研究, 14(1): 151-154, 158.
	ZHAO R, TIXIPULATI T, DING J L, et al., 2007. LUCC simulation in arid area based on ANN-CA Model: Take Xinjiang Yutian Oasis as an example[J]. Research of Soil and Water Conservation, 14(1): 151-154, 158.
[35]	朱玉玲, 2020. 基于深度学习分类方法的山东省外来入侵物种互花米草遥感监测与分析[D]. 青岛: 自然资源部第一海洋研究所.
	ZHU Y L, 2020. Remote sensing monitoring and analysis of invasive alien species Spartina alterniflora in Shandong province based on deep learning classification method[D]. Qingdao: First Institute of Oceanography, Ministry of Natural Resources.

基于ANN-CA的外来入侵植物互花米草的扩散趋势预测研究

Prediction of Diffusion Trend of Invasive Plant Spartina Alterniflora Based on ANN-CA

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 35

相关文章 15

编辑推荐

Metrics

本文评价

[1]	罗庆, 何清, 吴慧秋, 寇力月, 方旭, 张鑫雨, 李缘, 柴育廷, 张瑞生, 代文举. 辽河口湿地土壤有机碳组分特征及其影响因素[J]. 生态环境学报, 2024, 33(3): 333-340.
[2]	田成诗, 孙瑞欣. 长江经济带市域生态环境质量空间分异与影响因素分析——基于三生空间的土地利用转型[J]. 生态环境学报, 2023, 32(7): 1173-1184.
[3]	王琳, 卫伟. 黄土高原典型县域生态系统服务变化特征及驱动因素[J]. 生态环境学报, 2023, 32(6): 1140-1148.
[4]	刘霞, 郭澍, 王琳. 区域一体化地区的土地利用与生态服务价值研究——以双莱先行区为例[J]. 生态环境学报, 2023, 32(6): 1163-1172.
[5]	王超, 杨倩楠, 张池, 刘同旭, 张晓龙, 陈静, 刘科学. 丹霞山不同土地利用方式土壤磷组分特征及其有效性[J]. 生态环境学报, 2023, 32(5): 889-897.
[6]	王铁铮, 瞿心悦, 刘春香, 李有志. 东江湖水质时空变化规律及其与流域土地利用的关系[J]. 生态环境学报, 2023, 32(4): 722-732.
[7]	李语诗, 夏志业, 张蕾. 基于SSPs多情景目标的2030年成渝经济圈土地利用碳排放预测及其空间优化[J]. 生态环境学报, 2023, 32(3): 535-544.
[8]	盛美君, 李胜君, 杨昕玥, 王蕊, 李洁, 李刚, 修伟明. 华北潮土农田土壤酶活性对土地利用强度的响应特征探讨[J]. 生态环境学报, 2023, 32(2): 299-308.
[9]	王全超, 吉恒宽, 李思敏, 李财生, 侯正伟, 邓万刚, 吴治澎, 王登峰. 海南东寨港流域土壤-溪流连续体溶解态黑碳分子特征及其界面转化机制[J]. 生态环境学报, 2023, 32(1): 139-149.
[10]	陈乐, 卫伟. 西北旱区典型流域土地利用与生境质量的时空演变特征[J]. 生态环境学报, 2022, 31(9): 1909-1918.
[11]	王超越, 郭先华, 郭莉, 白丽芳, 夏利林, 王春博, 李廷真. 基于FLUS-InVEST的西北地区土地利用变化及其对碳储量的影响——以呼包鄂榆城市群为例[J]. 生态环境学报, 2022, 31(8): 1667-1679.
[12]	刘展航, 张树岩, 侯玉平, 朱书玉, 王立冬, 施欣悦, 李培广, 韩广轩, 谢宝华. 互花米草入侵对黄河口湿地土壤碳氮磷及其生态化学计量特征的影响[J]. 生态环境学报, 2022, 31(7): 1360-1369.
[13]	李美娇, 何凡能, 赵彩杉, 杨帆. 全球历史LUCC数据集新疆地区耕地数据可靠性评估[J]. 生态环境学报, 2022, 31(6): 1215-1224.
[14]	王超, 杨倩楠, 张池, 李祥东, 陈静, 张晓龙, 陈金洁, 刘科学. 东南湿润区典型丹霞地貌土壤有机碳组分及其敏感性研究[J]. 生态环境学报, 2022, 31(6): 1132-1140.
[15]	陈金凤, 余世钦, 符加方, 徐国良, 于波, 赖晓群, 胡思源, 张开渠, 刘家华. 华南红层地貌区不同利用方式土壤质量特征及其影响因素——以南雄盆地为例[J]. 生态环境学报, 2022, 31(5): 918-930.