基于无人机的巴音布鲁克草原甘肃马先蒿多时相提取

doi:10.13866/j.azr.2025.07.13

干旱区研究 ›› 2025, Vol. 42 ›› Issue (7): 1301-1312.doi: 10.13866/j.azr.2025.07.13 cstr: 32277.14.AZR.20250713

基于无人机的巴音布鲁克草原甘肃马先蒿多时相提取

张佳荣¹^,²^,³(), 赵金¹^,⁴, 李海宁³^,⁵, 公延明¹^,³, 柳妍妍¹^,³, 林峻⁶, 李凯辉¹^,³()

1.中国科学院新疆生态与地理研究所，新疆乌鲁木齐 830011
2.中国科学院大学，北京 100049
3.巴音布鲁克高寒草原生态系统新疆野外科学观测研究站，新疆巴音布鲁克 841314
4.新疆遥感与地理信息系统应用重点实验室，新疆乌鲁木齐 830011
5.新疆农业大学草业学院，新疆乌鲁木齐 830052
6.新疆维吾尔自治区草原生物灾害防控中心，新疆乌鲁木齐 830000

收稿日期:2024-11-27 修回日期:2025-04-08 出版日期:2025-07-15 发布日期:2025-07-07
通讯作者: 李凯辉. E-mail: likh@ms.xjb.ac.cn
作者简介:张佳荣（1996-），女，硕士研究生，主要从事草原植被遥感研究. E-mail: zhangjiarong21@mails.ucas.ac.cn
基金资助:
国家自然科学基金项目(32271747)

Multitemporal extraction of Pedicularis kansuensis in the Bayinbuluk grassland based on UAV images

ZHANG Jiarong¹^,²^,³(), ZHAO Jin¹^,⁴, LI Haining³^,⁵, GONG Yanming¹^,³, LIU Yanyan¹^,³, LIN Jun⁶, LI Kaihui¹^,³()

1. Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, Xinjiang, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Bayinbuluk Alpine Grassland Observation and Research Station of Xinjiang, Bayinbuluk 841314, Xinjiang, China
4. Xinjiang Key Laboratory of RS & GIS Application, Urumqi 830011, Xinjiang, China
5. College of Grassland Science, Xinjiang Agricultural University, Urumqi 830052, Xinjiang, China
6. Center for Grassland Biological Disaster Prevention and Control of Xinjiang Uygur Autonomous Region, Urumqi 830000, Xinjiang, China

Received:2024-11-27 Revised:2025-04-08 Published:2025-07-15 Online:2025-07-07

摘要/Abstract

摘要： 入侵植物已严重影响着全球生态系统功能和生物多样性。而现有研究主要集中于植物单一时相的监测与分类，对关键物候期的多时相持续性监测，特别是针对早期物候期监测的研究相对较少。因此，本文以新疆巴音布鲁克草原入侵植物甘肃马先蒿（Pedicularis kansuensis）为研究对象，采用无人机多光谱遥感数据和机器学习算法，对甘肃马先蒿的关键物候期（苗期、初花期、盛花期和结实期）空间分布进行了提取。结果表明：（1）生长初期（苗期和初花期）的空间分布结果与盛花期具有较高的空间重合率，采用随机森林算法能够有效实现早期甘肃马先蒿的分布制图；（2）甘肃马先蒿的空间分布规律具有显著的年际变化特征，年际间的空间分布重合率不足15%；（3）在生长季（结实期除外）基于555 nm波段和720 nm波段计算的归一化植被指数重要性最高，其次为可见绿波段。研究结果表明无人机多光谱遥感技术在甘肃马先蒿早期物候期监测的可行性，为早期预警和防控提供了技术支持。

关键词: 甘肃马先蒿, 无人机, 多光谱数据, 随机森林, 多时相, 关键物候期

Abstract:

Invasive plants have significantly impacted the function and biodiversity of the global ecosystem. In the context of global climate change, the effective control of invasive plants is important for maintaining the stability of grassland ecosystems. The spectral differences between invasive plants and native dominant species during phenological stages provide an opportunity for remote sensing technology to monitor their spatiotemporal distribution. Previous studies have primarily focused on single-phase monitoring and the classification of plants, with relatively fewer studies on multitemporal continuous monitoring, particularly during early phenological stages. In this study, we focused on Pedicularis kansuensis, an invasive species of the Bayinbuluk grassland of Xinjiang, using UAV-based multispectral data and machine learning algorithms to extract spatial distribution data for P. kansuensis during key phenological stages in 2023 (emergence, initial flowering, peak flowering, and senescence stages) and the peak flowering stage in 2024. We examined the feasibility of extracting P. kansuensis at each phenological stage and analyzed changes in inter-annual spatial distribution. The results indicated that (1) The random forest algorithm slightly outperformed the support vector machine, with model accuracy varying with the growth stages of P. kansuensis; specifically, peak flowering stage (late July to late August) > initial flowering stage (late June to early July) > emergence stage (mid-June) > senescence stage (mid-September). Throughout the growth season, spatial distribution during the early growth stages (emergence and initial flowering) exhibited a high spatial overlap with the peak flowering stage, and the key features were consistent with those of the peak flowering stage. This suggests that the random forest algorithm can effectively map the distribution of P. kansuensis during the emergence stage, which provides important technical support for the early-stage monitoring of invasive plants; (2) The spatial distribution of P. kansuensis exhibited significant inter-annual variation, with less than 15% spatial overlap between the two years; (3) During the growth season, the most important feature for distinguishing P. kansuensis (excluding the senescence stage), from other co-occurring species was the normalized difference index, calculated from the 555 nm and 720 nm bands, followed by the green band. Because P. kansuensis had entered the senescence stage, there was a noticeable change in feature importance, with significant differences in various background environments. These results demonstrate the feasibility of using UAV-based multispectral remote sensing technology for monitoring the early phenological stages of P. kansuensis and offer technical support for early warning and control measures.

Key words: Pedicularis kansuensis, unmanned aerial vehicles, multispectral data, random forest, multi-temporal imagery, key phenological stages

张佳荣, 赵金, 李海宁, 公延明, 柳妍妍, 林峻, 李凯辉. 基于无人机的巴音布鲁克草原甘肃马先蒿多时相提取[J]. 干旱区研究, 2025, 42(7): 1301-1312.

ZHANG Jiarong, ZHAO Jin, LI Haining, GONG Yanming, LIU Yanyan, LIN Jun, LI Kaihui. Multitemporal extraction of Pedicularis kansuensis in the Bayinbuluk grassland based on UAV images[J]. Arid Zone Research, 2025, 42(7): 1301-1312.

图/表 11

图1

表1

表2

表3

表4

表5

表6

图2

表7

图3

图4

参考文献 37

[1]	Vetter V M S, Kreyling J, Dengler J, et al. Invader presence disrupts the stabilizing effect of species richness in plant community recovery after drought[J]. Global Change Biology, 2020, 26(6): 3539-3551. doi: 10.1111/gcb.15025 pmid: 32011046
[2]	Wang C, Jiang K, Liu J, et al. Moderate and heavy Solidago canadensis L. invasion are associated with decreased taxonomic diversity but increased functional diversity of plant communities in East China[J]. Ecological Engineering, 2018, 112: 55-64.
[3]	阿德力·麦地, 柳妍妍, 古丽努尔, 等. 乌鲁木齐县天然草地毒害植物初步调查及防治对策[J]. 干旱区研究, 2013, 30(6): 1044-1048.
	[Adeli Maidi, Liu Yanyan, Guli Nuer, et al. Poisonous plants in natural grasslands in Urumqi County and their control measures[J]. Arid Zone Research, 2013, 30(6): 1044-1048.]
[4]	鞠瑞亭, 李慧, 石正人, 等. 近十年中国生物入侵研究进展[J]. 生物多样性, 2012, 20(5): 581-611. doi: 10.3724/SP.J.1003.2012.31148
	[Ju Ruiting, Li Hui, Shih Chengjen, et al. Progress of biological invasions research in China over the last decade[J]. Biodiversity Science, 2012, 20(5): 581-611.] doi: 10.3724/SP.J.1003.2012.31148
[5]	Weisberg P J, Dilts T E, Greenberg J A, et al. Phenology-based classification of invasive annual grasses to the species level[J]. Remote Sensing of Environment, 2021, 263: 112568.
[6]	Liu X, Liu H, Datta P, et al. Mapping an invasive plant Spartina alterniflora by combining an ensemble one-class classification algorithm with a phenological NDVI time-series analysis approach in middle coast of Jiangsu, China[J]. Remote Sensing, 2020, 12(24): 4010.
[7]	Sun C, Li J, Liu Y, et al. Plant species classification in salt marshes using phenological parameters derived from Sentinel-2 pixel-differential time-series[J]. Remote Sensing of Environment, 2021, 256: 112320.
[8]	Graenzig T, Fassnacht F E, Kleinschmit B, et al. Mapping the fractional coverage of the invasive shrub Ulex europaeus with multi-temporal Sentinel-2 imagery utilizing UAV orthoimages and a new spatial optimization approach[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 96: 102281.
[9]	Valero-Jorge A, Zayas R G D, Matos-Pupo F, et al. Mapping and monitoring of the invasive species Dichrostachys cinerea (Marabú) in central Cuba using Landsat imagery and machine learning (1994-2022)[J]. Remote Sensing, 2024, 16(5): 798.
[10]	Xing F, An R, Guo X, et al. Mapping invasive noxious weed species in the alpine grassland ecosystems using very high spatial resolution UAV hyperspectral imagery and a novel deep learning model[J]. GIScience & Remote Sensing, 2024, 61(1): 2327146.
[11]	Innangi M, Marzialetti F, Di Febbraro M, et al. Coastal dune invaders: Integrative mapping of Carpobrotus sp. pl. (Aizoaceae) using UAVs[J]. Remote Sensing, 2023, 15(2): 503.
[12]	Zhao J, Li K, Zhang J, et al. Mapping invasive species Pedicularis and background grassland using UAV and machine learning algorithms[J]. Drones, 2024, 8(11): 639.
[13]	Yang X, Smith A M, Bourchier R S, et al. Mapping flowering leafy spurge infestations in a heterogeneous landscape using unmanned aerial vehicle Red-Green-Blue images and a hybrid classification method[J]. International Journal of Remote Sensing, 2021, 42(23): 8930-8951.
[14]	Valente J, Hiremath S, Ariza-Sentis M, et al. Mapping of Rumex obtusifolius in nature conservation areas using very high resolution UAV imagery and deep learning[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102864.
[15]	Wijesingha J, Astor T, Schulze-Brueninghoff D, et al. Mapping invasive Lupinus polyphyllus Lindl. in semi-natural grasslands using object-based image analysis of UAV-borne images[J]. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2020, 88(5): 391-406.
[16]	Kupková L, Červená L, Potůčková M, et al. Towards reliable monitoring of grass species in nature conservation: Evaluation of the potential of UAV and PlanetScope multi-temporal data in the Central European tundra[J]. Remote Sensing of Environment, 2023, 294: 113645.
[17]	孙法福, 赖宁, 耿庆龙, 等. 基于无人机高光谱影像的冬小麦叶片氮浓度遥感估测[J]. 干旱区研究, 2024, 41(6): 1069-1078. doi: 10.13866/j.azr.2024.06.15
	[Sun Fafu, Lai Ning, Geng Qinglong, et al. Estimation of nitrogen contentration in winter wheat leaves based on hyperspectral images of UAV[J]. Arid Zone Research, 2024, 41(6): 1069-1078.] doi: 10.13866/j.azr.2024.06.15
[18]	Knapp L S P, Coyle D R, Dey D C, et al. Invasive plant management in eastern North American forests: A systematic review[J]. Forest Ecology and Management, 2023, 550: 121517.
[19]	Wang D, Cui B, Duan S, et al. Moving north in China: The habitat of Pedicularis kansuensis in the context of climate change[J]. Science of the Total Environment, 2019, 697: 133979.
[20]	鲍根生, 王宏生. 甘肃马先蒿对高寒地区几种优良牧草的化感作用[J]. 中国草地学报, 2011, 33(2): 88-94.
	[Bao Gensheng, Wang Hongsheng. Allelopathic effects of Pedicularis kansuensis Maxim. on several graminaceous grass species on alpine meadow[J]. Chinese Journal of Grassland, 2011, 33(2): 88-94.]
[21]	Li H, Gong Y, Fang F, et al. Effects of nutrient addition on Pedicularis kansuensis invasion of alpine grassland[J]. Atmosphere, 2023, 14(2): 367.
[22]	Sui X, Kuss P, Li W, et al. Identity and distribution of weedy Pedicularis kansuensis Maxim. (Orobanchaceae) in Tianshan Mountains of Xinjiang: Morphological, anatomical and molecular evidence[J]. Journal of Arid Land, 2016, 8(3): 453-461.
[23]	Li W, Huang L, Yang L, et al. Phenotypic plasticity drives the successful expansion of the invasive plant Pedicularis kansuensis in Bayanbulak, China[J]. Diversity, 2023, 15(3): 313.
[24]	Wang W, Tang J, Zhang N, et al. Spatiotemporal pattern of invasive Pedicularis in the Bayinbuluke Land, China, during 2019-2021: An analysis based on PlanetScope and Sentinel-2 data[J]. Remote Sensing, 2023, 15(18): 4383.
[25]	Wang W, Tang J, Zhang N, et al. Automated detection method to extract Pedicularis based on UAV images[J]. Drones, 2022, 6(12): 399.
[26]	Liu Y, Li W, Sui X, et al. An exotic plant successfully invaded as a passenger driven by light availability[J]. Frontiers in Plant Science, 2022, 13: 1047670.
[27]	柳妍妍. 巴音布鲁克草原甘肃马先蒿种群扩张的生态因子研究[D]. 乌鲁木齐: 新疆大学, 2018.
	[Liu Yanyan. Ecological Factors of Pedicularis kansuensis Maxim. Expansion in Bayanbulak Grassland[D]. Urumqi: Xinjiang University, 2018.]
[28]	Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[29]	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[30]	詹国旗, 杨国东, 王凤艳, 等. 基于特征空间优化的随机森林算法在GF-2影像湿地分类中的研究[J]. 地球信息科学学报, 2018, 20(10): 1520-1528. doi: 10.12082/dqxxkx.2018.180119
	[Zhan Guoqi, Yang Guodong, Wang Fengyan, et al. The random forest classification of wetland from GF-2 imagery based on the optimized feature space[J]. Journal of Geo-information Science, 2018, 20(10): 1520-1528.]
[31]	Chen X, Ishwaran H. Random forests for genomic data analysis[J]. Genomics, 2012, 99(6): 323-329. doi: 10.1016/j.ygeno.2012.04.003 pmid: 22546560
[32]	Strobl C, Boulesteix A L, Zeileis A, et al. Bias in random forest variable importance measures: illustrations, sources and a solution[J]. BMC Bioinformatics, 2007, 8: 25. pmid: 17254353
[33]	Boulesteix A L, Bender A, Lorenzo Bermejo J, et al. Random forest Gini importance favours SNPs with large minor allele frequency: Impact, sources and recommendations[J]. Briefings in Bioinformatics, 2012, 13(3): 292-304.
[34]	Dronova I, Spotswood E N, Suding K N. Opportunities and constraints in characterizing landscape distribution of an invasive grass from very high resolution multi-spectral imagery[J]. Frontiers in Plant Science, 2017, 8: 890. doi: 10.3389/fpls.2017.00890 pmid: 28611806
[35]	高莎, 林峻, 马涛, 等. 新疆巴音布鲁克草原马先蒿光谱特征提取与分析[J]. 遥感技术与应用, 2018, 33(5): 908-914. doi: 10.11873/j.issn.1004-0323.2018.5.0908
	[Gao Sha, Lin Jun, Ma Tao, et al. Extraction and analysis of hyperspectral data and characteristics from Pedicularis on Bayanbulak grassland in Xinjiang[J]. Remote Sensing Technology and Application, 2018, 33(5): 908-914.]
[36]	李海宁, 柳妍妍, 公延明, 等. 甘肃马先蒿入侵对巴音布鲁克高寒草原凋落物分解的影响[J]. 草原与草坪, 2023, 43(1): 1-11.
	[Li Haining, Liu Yanyan, Gong Yanming, et al. Effects of Pedicularis kansuensis invasion on litter decomposition in Bayanbulak alpine steppe[J]. Grassland and Turf, 2023, 43(1): 1-11.]
[37]	Hu J, Li K, Deng C, et al. Seed germination ecology of semiparasitic weed Pedicularis kansuensis in alpine grasslands[J]. Plants, 2022, 11(13): 1777.

样地编号	样地位置	主要物种	杂类草	其他地物
1号样地	83°44′19.8″E, 42°54′26.7″N, 2470 m	紫花针茅（Stipa purpurea）、寒生羊茅（Festuca kryloviana）、溚草（Koeleria cristata）、天山赖草（Leymus tianschanicus）、垂穗披碱草（Elymus nutans）、多裂委陵菜（Potentilla multifida）等	甘肃马先蒿（Pedicularis kansuensis）	裸地
2号样地	83°43′0.5″E, 42°54′2.3″N, 2466 m	紫花针茅、垂穗披碱草、多裂委陵菜等	甘肃马先蒿、新疆假龙胆（Gentianella turkestanorum）	裸地河道
3号样地	83°17′2.6″E, 42°42′29.8″N, 2410 m	垂穗披碱草、多裂委陵菜等	甘肃马先蒿、新疆假龙胆	裸地河道

	1号样地	2号样地	3号样地
2023年6月中旬	6月16日	6月16日	6月19日
2023年6月下旬	6月30日	-	7月3日
2023年7月中旬	7月13日	7月13日	7月14日
2023年7月下旬	7月23日	7月23日	7月24日
2023年8月上旬	8月2日	8月02日	8月6日
2023年8月中旬	8月19日	8月19日	8月20日
2023年8月下旬	8月30日	8月31日	8月30日
2023年9月中旬	9月12日	9月12日	9月8日
2024年8月	8月12日	8月21日	8月1日

地物	1号样地	2号样地	3号样地
甘肃马先蒿	10295	3444	7284
其他地物（裸地、多年生草本绿草、枯草、其他）	60536	-	-
其他地物（裸地、多年生草本绿草、枯草、河道、其他）	-	15547	22759

分类器	时间	OA/%	PA/%		UA/%		F1-score	Kappa系数
分类器	时间	OA/%	甘肃马先蒿	其他地物	甘肃马先蒿	其他地物	F1-score	Kappa系数
SVM	2023年6月中旬	97.19	83.34	99.52	96.70	97.26	0.9131	0.8792
	2023年6月下旬	98.02	88.31	99.66	97.76	98.06	0.9393	0.9165
	2023年7月中旬	98.23	89.71	99.66	97.79	98.29	0.9457	0.9255
	2023年7月下旬	99.16	95.59	99.76	98.52	99.26	0.9744	0.9654
	2023年8月上旬	99.49	97.29	99.86	99.13	99.55	0.9844	0.9790
	2023年8月中旬	99.58	98.24	99.80	98.82	99.70	0.9872	0.9828
	2023年8月下旬	99.36	96.41	99.86	99.13	99.40	0.9806	0.9738
	2023年9月中旬	98.56	93.21	99.46	96.68	98.86	0.9564	0.9407
RF	2023年6月中旬	97.36	85.04	99.43	96.20	97.53	0.9188	0.8875
	2023年6月下旬	97.91	86.90	99.76	98.41	97.84	0.9355	0.9110
	2023年7月中旬	98.14	88.63	99.74	98.30	98.12	0.9428	0.9214
	2023年7月下旬	99.01	93.86	99.87	99.21	98.98	0.9697	0.9588
	2023年8月上旬	99.39	96.83	99.82	98.90	99.47	0.9814	0.9750
	2023年8月中旬	99.43	97.13	99.81	98.87	99.52	0.9826	0.9766
	2023年8月下旬	99.16	95.10	99.85	99.05	99.18	0.9745	0.9655
	2023年9月中旬	98.45	92.98	99.37	96.12	98.82	0.9531	0.9362

分类器	时间	OA/%	PA/%		UA/%		F1-score	Kappa系数
分类器	时间	OA/%	甘肃马先蒿	其他地物	甘肃马先蒿	其他地物	F1-score	Kappa系数
SVM	2023年6月中旬	99.18	96.22	99.65	97.78	99.40	0.9745	0.9652
	2023年7月中旬	99.09	96.71	99.56	97.78	99.35	0.9746	0.9670
	2023年7月下旬	99.02	96.58	99.51	97.51	99.32	0.9727	0.9646
	2023年8月上旬	99.48	97.67	99.84	99.17	99.54	0.9853	0.9810
	2023年8月中旬	99.16	97.26	99.54	97.66	99.46	0.9765	0.9696
	2023年8月下旬	98.64	95.21	99.32	96.53	99.05	0.9619	0.9505
	2023年9月中旬	97.77	90.00	99.32	96.33	98.04	0.9373	0.9173
RF	2023年6月中旬	99.22	97.47	99.55	97.57	99.53	0.9776	0.9706
	2023年7月中旬	99.21	97.57	99.57	98.05	99.47	0.9789	0.9733
	2023年7月下旬	99.09	96.99	99.55	97.94	99.34	0.9756	0.9691
	2023年8月上旬	99.37	97.57	99.76	98.92	99.47	0.9830	0.9786
	2023年8月中旬	99.19	96.80	99.72	98.71	99.30	0.9783	0.9725
	2023年8月下旬	98.95	95.44	99.72	98.69	99.00	0.9717	0.9640
	2023年9月中旬	98.26	93.50	99.31	96.78	98.58	0.9534	0.9406

基于无人机的巴音布鲁克草原甘肃马先蒿多时相提取

Multitemporal extraction of Pedicularis kansuensis in the Bayinbuluk grassland based on UAV images

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 37

相关文章 13

Metrics

本文评价

推荐阅读 0

面积/m²		1号样地		合计	2号样地		合计	3号样地		合计
		2024年			2024年			2024年
		甘肃马先蒿	其他地物		甘肃马先蒿	其他地物		甘肃马先蒿	其他地物
2023年	甘肃马先蒿	79.10	571.59	650.69	524.44	7732.42	8256.87	5.37	266.21	271.58
2023年	其他地物	557.78	10586.27	11144.05	253.32	13931.63	14184.94	776.83	23522.22	24299.05
合计		636.88	11157.86	11794.74	777.76	21664.05	22441.81	782.20	23788.43	24570.63

[1]	张彬, 郑新军, 王玉刚, 唐立松, 李彦, 杜澜, 田胜川. 1990—2022年天山北坡地区不同开垦年限耕层土壤盐分变化[J]. 干旱区研究, 2024, 41(9): 1435-1445.
[2]	孙法福, 赖宁, 耿庆龙, 李永福, 吕彩霞, 信会男, 李娜, 陈署晃. 基于无人机高光谱影像的冬小麦叶片氮浓度遥感估测[J]. 干旱区研究, 2024, 41(6): 1069-1078.
[3]	李小雨, 贾科利, 魏慧敏, 陈睿华, 王怡婧. 基于随机森林算法的土壤含盐量预测[J]. 干旱区研究, 2023, 40(8): 1258-1267.
[4]	薛智暄, 张丽, 王新军, 李永康, 张冠宏, 李沛尧. 古尔班通古特沙漠SMAP土壤水分产品降尺度分析[J]. 干旱区研究, 2023, 40(4): 583-593.
[5]	张天意, 刘杰, 杨治纬, 王斌, 程秋连. 基于空-地协同调查的西天山阿尔先沟雪崩过程数值模拟[J]. 干旱区研究, 2023, 40(11): 1729-1743.
[6]	刘欢欢, 陈印, 刘悦, 刚成诚. 基于随机森林模型的黄土高原草地净初级生产力时空格局及未来演变趋势模拟[J]. 干旱区研究, 2023, 40(1): 123-131.
[7]	肖森天, 依力亚斯江·努尔麦麦提, 努尔比耶·穆合塔尔, 赵静, 阿迪莱·阿卜来提. 基于光学和雷达多源遥感的于田绿洲土壤盐渍化时空分析[J]. 干旱区研究, 2023, 40(1): 59-68.
[8]	庞海威,余殿,任成宝,张玉,郑彩之,郭佳诚,边振,桑国庆. 宁夏东部半干旱区典型植物群落遥感分类特征[J]. 干旱区研究, 2022, 39(6): 1930-1941.
[9]	祝存兄,史飞飞,乔斌,张娟,陈国茜. 基于高分1号卫星数据的青海湖扩张及湖滨沙地变化特征分析[J]. 干旱区研究, 2022, 39(4): 1076-1089.
[10]	宋奇,史舟,冯春晖,马自强,纪文君,彭杰,高琪,蒋学玮. 基于1990—2019年多时相影像的干旱区绿洲景观格局分析[J]. 干旱区研究, 2022, 39(2): 594-604.
[11]	刘畅,张红,张霄羽,杨国婷,刘勇. 半干旱地区矿区土地利用时空演变与预测[J]. 干旱区研究, 2022, 39(1): 292-300.
[12]	李梓钰,陈启慧,黄峰,郭振天. 吐鲁番盆地骆驼刺保护区植被覆盖度时空演变[J]. 干旱区研究, 2021, 38(4): 1104-1110.
[13]	曹文梅,刘廷玺,王喜喜,王冠丽,李东方,童新. 科尔沁沙丘草甸相间地区土地利用与覆被识别[J]. 干旱区研究, 2021, 38(2): 526-535.

分类器	时间	OA/%	PA/%		UA/%		F1-score	Kappa系数
分类器	时间	OA/%	甘肃马先蒿	其他地物	甘肃马先蒿	其他地物	F1-score	Kappa系数
SVM	2023年6月中旬	95.13	85.92	97.83	92.06	95.95	0.8836	0.8577
	2023年6月下旬	97.49	93.77	98.58	95.10	98.18	0.9399	0.9281
	2023年7月中旬	98.54	96.88	99.02	96.68	99.09	0.9649	0.9583
	2023年7月下旬	99.25	98.07	99.60	98.65	99.43	0.9819	0.9787
	2023年8月上旬	99.10	97.64	99.54	98.43	99.30	0.9784	0.9745
	2023年8月中旬	98.67	96.67	99.26	97.51	99.01	0.9681	0.9622
	2023年8月下旬	97.41	94.52	98.25	94.06	98.39	0.9381	0.9261
	2023年9月中旬	93.47	84.26	96.17	86.58	95.42	0.8469	0.8120
RF	2023年6月中旬	95.75	88.52	98.03	93.41	96.44	0.9007	0.8813
	2023年6月下旬	97.65	94.26	98.72	95.86	98.20	0.9448	0.9351
	2023年7月中旬	98.38	96.21	99.07	97.01	98.81	0.9619	0.9554
	2023年7月下旬	99.32	98.20	99.68	98.97	99.43	0.9840	0.9814
	2023年8月上旬	99.08	97.64	99.53	98.51	99.26	0.9782	0.9747
	2023年8月中旬	98.48	96.48	99.11	97.16	98.89	0.9642	0.9582
	2023年8月下旬	97.35	94.86	98.13	94.12	98.38	0.9382	0.9275
	2023年9月中旬	94.01	85.84	96.58	88.80	95.58	0.8619	0.8338