Investigation of the Algorithm for Detecting Rodent-Damaged Areas in Desert Grasslands Using Unmanned Aerial Vehicle Remote Sensing Images

doi:10.11733/j.issn.1007-0435.2026.10.021

Acta Agrestia Sinica ›› 2026, Vol. 34 ›› Issue (10): 3750-3760.DOI: 10.11733/j.issn.1007-0435.2026.10.021

Investigation of the Algorithm for Detecting Rodent-Damaged Areas in Desert Grasslands Using Unmanned Aerial Vehicle Remote Sensing Images

FAN Yu-quan¹, CAI Bin¹, SUN Jian¹, DONG Long-ming¹, LIU Ji-ze¹, XUE Fei-yang¹, YUAN Shuai², HUANG Zi-jie³, LIU Zhen-bao⁴, HUA Li-min¹

1. College of Pratacultural Science, Gansu Agricultural University/Key Laboratory of Grassland Rodent and Pika Pest Control of National Forestry and Grassland Administration/Engineering and Technology Research Center for Alpine Rodent Pest Control, National Forestry and Grassland Administration, Lanzhou, Gansu Province 730070, China;
2. College of Grassland Science, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia, Inner Mongolia 010040, China;
3. Forestry and Grassland Bureau of Minle County, Zhangye, Gansu Province 734500, China;
4. Forestry and Grassland Bureau of Jingyuan County, Baiyin, Gansu Province 730600, China

Received:2025-07-21 Revised:2026-01-11 Online:2026-10-15 Published:2026-10-10

基于无人机遥感影像的荒漠草原鼠害地特征识别算法研究

范雨荃¹, 蔡斌¹, 孙舰¹, 董隆明¹, 刘济泽¹, 薛飞扬¹, 袁帅², 黄子杰³, 刘振宝⁴, 花立民¹

1. 甘肃农业大学草业学院/草业生态系统教育部重点实验室/草原鼠兔害治理国家林业和草原局重点实验室, 甘肃兰州 730070;
2. 内蒙古农业大学草业学院, 内蒙古呼和浩特 010040;
3. 民乐县林业和草原局, 甘肃张掖 734500;
4. 靖远县林业和草原局, 甘肃白银 730600

通讯作者: 花立民, E-mail: hualm@gsau.edu.cn
作者简介:范雨荃（2000-），女，藏族，甘肃兰州人，硕士研究生，主要从事草地保护研究，E-mail：3195764089@qq.com
基金资助:
草业生态系统教育部重点实验室“揭榜挂帅”项目（KLGE-2024-06）；鼠害高效、精准监测基础研究及新技术开发项目（2024YFD1400500）；甘肃省教育厅优秀研究生“创新之星”项目（2023CXZX-664）资助

Abstract

Abstract: Monitoring rodent damage in desert grasslands is of great significance for biodiversity conservation and rodent pest control. This study selected rodent-damaged desert grasslands in Jingyuan County， Gansu Province， China， as the research area. A total of 20 rodent-damaged plots were established， and UAV（unmanned aerial vehicle）-based visible-light （RGB） imagery was acquired for analysis. Five supervised classification models were employed to identify three land-cover types， including vegetation， bare ground， and rodent holes. A total of 1，578 training samples and 683 validation samples were used. The classification performance was evaluated using overall accuracy （OA）， Kappa coefficient （Kappa）， producer’s accuracy （PA）， and user’s accuracy （UA）. The results showed that the support vector machine （SVM） model achieved the best overall performance， with an overall accuracy of 99.68% and a Kappa coefficient of 0.99. For rodent hole recognition， the producer’s accuracy and user’s accuracy reached 83.96% and 87.51%， respectively. The SVM model demonstrated high classification accuracy and stability across all three land-cover types， particularly achieving accuracies above 99% for bare ground and vegetation classification. Overall， within the study area， the SVM model exhibited superior performance in identifying rodent-damaged features， indicating its potential application in desert grassland rodent monitoring and management and providing technical support for rodent pest prevention and control.

Key words: Desert grassland, Rodent pest area, Drone, Supervised classification

摘要： 荒漠草原鼠害监测对于生物多样性保护和鼠害防控具有重要意义。本研究以甘肃省靖远县荒漠草原鼠害地为研究对象，在研究区内选取20块鼠害地，利用无人机采集可见光（RGB）影像，采用5种监督分类模型识别鼠害地植被、裸地及鼠洞3种地物，训练样本1578个，验证样本683个。以总体分类精度（Overall Accuracy， OA）、Kappa系数（Kappa）、生产者精度（Producer’s Accuracy， PA）和用户精度（User’s Accuracy， UA）评价分类模型精度。结果表明，SVM模型在整体分类表现上最优，其总体精度达99.68%，Kappa系数为0.99，鼠洞识别的生产者精度与用户精度分别为83.96%和87.51%。SVM模型在3类地物中均表现出较高的分类精度和稳定性，特别在裸地与植被识别中精度均达到99%以上。综上，在本研究区内，SVM模型表现出更优的识别效果，显示出其在荒漠草原鼠害地识别中的应用潜力，为荒漠草原鼠害监测与防控提供技术支撑。

关键词: 荒漠草原, 鼠害地, 无人机, 监督分类

CLC Number:

S443.9

FAN Yu-quan, CAI Bin, SUN Jian, DONG Long-ming, LIU Ji-ze, XUE Fei-yang, YUAN Shuai, HUANG Zi-jie, LIU Zhen-bao, HUA Li-min. Investigation of the Algorithm for Detecting Rodent-Damaged Areas in Desert Grasslands Using Unmanned Aerial Vehicle Remote Sensing Images[J]. Acta Agrestia Sinica, 2026, 34(10): 3750-3760.

范雨荃, 蔡斌, 孙舰, 董隆明, 刘济泽, 薛飞扬, 袁帅, 黄子杰, 刘振宝, 花立民. 基于无人机遥感影像的荒漠草原鼠害地特征识别算法研究[J]. 草地学报, 2026, 34(10): 3750-3760.

References

[1] WU H X，WANG Z Y，YIN Q，et al. Research progress on degradation of desert steppe in northern China[J]. Journal of Inner Mongolia Forestry Science and Technology，2017，43（2）：58-62 武海霞，王则宇，尹强，等. 我国北方荒漠草原退化研究进展[J]. 内蒙古林业科技，2017，43（2）：58-62
[2] XU H J，ZHAO C Y，WANG X P. Elevational differences in the net primary productivity response to climate constraints in a dryland mountain ecosystem of northwestern China[J]. Land Degradation & Development，2020，31（15）：2087-2103
[3] MA Z H. Study on desert-steppe eco-environment quality evaluation of Inner Mongolia[D]. Beijing：Chinese Academy of Agricultural Sciences，2008：20-30 马治华. 内蒙古荒漠草原生态环境质量评价研究[D]. 北京：中国农业科学院，2008：20-30
[4] CHENG L L，QUE X E，YANG L，et al. China’s desert ecosystem： functions rising and services enhancing[J]. Bulletin of the Chinese Academy of Sciences，2020，35（6）：690-698 程磊磊，却晓娥，杨柳，等. 中国荒漠生态系统：功能提升、服务增效[J]. 中国科学院院刊，2020，35（6）：690-698
[5] HUA L M，CHAI S Q. Rodent pest control on grasslands in China： current state，problems and prospects[J]. Journal of Plant Protection，2022，49（1）：415-423 花立民，柴守权. 中国草原鼠害防治现状、问题及对策[J]. 植物保护学报，2022，49（1）：415-423
[6] ZHOU R. The response of individuals and populations in plateau pika （Ochotona curzoniae） to predation risk and changes of habitat vegetation communities[D]. Lanzhou：Gansu Agricultural University，2020：7-15 周睿.高原鼠兔个体和种群对捕食风险的响应及其栖息地植物群落的变化[D]. 兰州：甘肃农业大学，2020：7-15
[7] SUN F D，ZHANG C B，ZHANG H H，et al. Establishment of “standard rodent unit”and its application in grassland rodents control[J]. Acta Agrestia Sinica， 2026，34（2）：553-558 孙飞达，张蔡斌，张欢欢，等.“标准鼠单位”的确立及其在草原鼠害防控中的应用[J].草地学报，2026，34（2）：553-558
[8] KANG H B，WANG D X，CHANG M J，et al. Selection mechanism of rodents on the removal and predation microhabitats of seeds from different tree species[J]. Acta Ecologica Sinica，2017，37（22）：7604-7613 康海斌，王得祥，常明捷，等. 啮齿动物对不同林木种子的搬运和取食微生境选择机制[J]. 生态学报，2017，37（22）：7604-7613
[9] ZHOU Q Q，XIANG Y Z，LI D B，et al. Global patterns and controls of soil nematode responses to nitrogen enrichment： A meta-analysis[J]. Soil Biology and Biochemistry，2021，163：108433
[10] ZHANG Y M，ZHANG Z B，LIU J K. Burrowing rodents as ecosystem engineers： the ecology and management of plateau zokors Myospalax fontanierii in alpine meadow ecosystems on the Tibetan Plateau[J]. Mammal Review，2003，33（3-4）：284-294
[11] XIA W P. Field survey method of rodent population[J]. Bulletin of Biology，1956（6）：16-18 夏武平. 鼠类数量的野外調查法[J]. 生物学通报，1956（6）：16-18
[12] HUA R，ZHOU R，BAO D，et al. A study of UAV remote sensing technology for classifying the level of plateau pika damage to Alpine rangeland[J]. Acta Prataculturae Sinica，2022，31（4）：165-176 花蕊，周睿，包达尔罕，等. 基于旋翼无人机低空遥感的高原鼠兔危害等级划分技术研究[J]. 草业学报，2022，31（4）：165-176
[13] LIAN H H，HOU X M，YI S H. Research of using the uav to carry out field investigation and monitoring of grassland rodents[J]. Qinghai Prataculture，2021，30（4）：38-43 连欢欢，侯秀敏，宜树华. 利用无人机开展草原鼠害调查监测的研究[J]. 青海草业，2021，30（4）：38-43
[14] ZHOU S，HAN L L，YANG S W，et al. A study of rodent monitoring in Ruoergai grassland based on convolutional neural network[J]. Prataculture & Animal Husbandry，2021（2）：15-25 周俗，韩立亮，杨思维，等. 基于卷积神经网络的若尔盖草原鼠害监测应用研究[J]. 草学，2021（2）：15-25
[15] GAO J T，SUN F D，HUO F，et al. Application and evaluation of unmanned aerial vehicle remote sensing in grassland animal and plant monitoring[J]. Acta Agrestia Sinica，2021，29（1）：1-9 高娟婷，孙飞达，霍霏，等. 无人机遥感技术在草地动植物调查监测中的应用与评价[J]. 草地学报，2021，29（1）：1-9
[16] ZHAO X Q，YANG G J，YANG H，et al. Digital detection of grassland rodent holes in Inner Mongolia based on UAV remote sensing data[C]. Proceedings of the Fourth China Grassland Conference. 2016： 257-265 赵晓庆，杨贵军，杨浩，等. 基于无人机遥感数据的内蒙古草原鼠洞数字化检测[C]. 第四届中国草业大会论文集. 2016：257-265
[17] CUI B C，ZHENG J H，LIU Z J，et al. YOLOv3 mouse hole recognition based on remote sensing images from technology for unmanned aerial vehicle[J]. Scientia Silvae Sinicae，2020，56（10）：199-208 崔博超，郑江华，刘忠军，等. 无人机遥感影像的YOLOv3鼠洞识别技术[J]. 林业科学，2020，56（10）：199-208
[18] YU H，WU Y F，NIU L T. Estimation of vegetation coverage of desert grassland based on images from an unmanned aerial vehicle[J]. Pratacultural Science，2021，38（8）：1432-1438 于惠，吴玉锋，牛莉婷. 基于无人机可见光图像的荒漠草地覆盖度估算[J]. 草业科学，2021，38（8）：1432-1438
[19] HU Q，WU W B，SONG Q，et al. Recent progresses in research of crop patterns mapping by using remote sensing[J]. Scientia Agricultura Sinica，2015，48（10）：1900-1914 胡琼，吴文斌，宋茜，等. 农作物种植结构遥感提取研究进展[J]. 中国农业科学，2015，48（10）：1900-1914
[20] HU Y，ABA X，REN S E，et al. Monitoring the degree of Gansu zokor damage in Chinese pine by hyperspectral remote sensing[J]. Forests，2024，15（12）：2074
[21] XIONG R D，CHENG W X，XIONG Y D，et al. Research on extraction of rodent damage information in Alpine Grassland based on UAV images[J]. China Agricultural Informatics，2020，32（5）：27-37 熊瑞东，程武学，熊钰丹，等. 基于无人机影像的高寒草地鼠害信息提取研究[J]. 中国农业信息，2020，32（5）：27-37
[22] DONG G，DI W，CHENG W X. Information extraction and comparison of zokor damage in zoige grassland based on low-altitude remote sensing[J]. Journal of Sichuan Normal University （Natural Science），2022，45（1）：110-118 董光，狄威，程武学. 基于低空遥感的若尔盖草地鼢鼠鼠害信息提取方法及对比研究[J]. 四川师范大学学报（自然科学版），2022，45（1）：110-118
[23] XU W W，MA Q Q，CAI L Q. Evaluation of cultivated land quality grade in Jingyuan County Based on 'cultivated land quality grade'（GB/T33469-2016）[J]. Grassland and Turf，2021，41（1）：94-102，112 许旺旺，马倩倩，蔡立群. 基于《耕地质量等级》的靖远县耕地质量等级评价[J]. 草原与草坪，2021，41（1）：94-102，112
[24] WANG T K. Analysis of types，distribution and dominant species of grassland resources in Jingyuan County[J]. Rural Science and Technology，2017，8（10）：72-73 王同奎. 靖远县草原资源的类型、分布及优势种分析[J]. 乡村科技，2017，8（10）：72-73
[25] LI G Q. Present situation of rodent infestation in Baiyin forestry and its control countermeasures[J]. Forestry of Gansu，2019（5）：44-45 李桂琴. 白银林业鼠害发生现状与防治对策[J]. 甘肃林业，2019（5）：44-45
[26] HUA R. Study on the technology for classifying damage level of plateau pika （Ochotona curzoniae） to Alpine rangeland based on UAV remote sensing[D]. Lanzhou：Gansu Agricultural University，2020：15-20 花蕊. 基于旋翼无人机低空遥感的高原鼠兔（Ochotona curzoniae）危害等级划分技术研究[D]. 兰州：甘肃农业大学，2020：15-20
[27] HUA L M，ZHANG X H. Practice guide for grassland survey planning[M]. Beijing： China Agriculture Press， 2021：30-50 花立民，张鲜花. 草地调查规划学实习指导[M]. 北京：中国农业出版社，2021：30-50
[28] TANG G A. Digital processing of remote sensing images[M]. Beijing： Science Press， 2004：40-45 汤国安. 遥感数字图像处理[M]. 北京：科学出版社，2004：40-45
[29] CAI B，DONG R，HUA R，et al. Screening of identification algorithm for rodent-induced bare patches based on the drone imagery[J]. Chinese Journal of Applied Ecology，2024，35（7）：1951-1958 蔡斌，董瑞，花蕊，等. 基于无人机影像的鼠害地秃斑识别算法筛选[J]. 应用生态学报，2024，35（7）：1951-1958
[30] ZENG W J，ZHOU K，XIONG Y Q. Advances and review of machine learning applications in urban studies from 2005 to 2020[J]. Chinese Geography Sciences Review，2023，1（1）：16-30 曾文菁，周恺，熊益群. 2005—2020年城市研究中机器学习方法应用进展与综述[J]. 中国地理科学评论，2023，1（1）：16-30
[31] YANG H Y，DU J M，WANG Y，et al. Classification method of grassland species based on unmanned aerial vehicle remote sensing and convolutional neural network[J]. Transactions of the Chinese Society for Agricultural Machinery，2019，50（4）：188-195 杨红艳，杜健民，王圆，等. 基于无人机遥感与卷积神经网络的草原物种分类方法[J]. 农业机械学报，2019，50（4）：188-195
[32] ZHENG Y P，LI G Y，LI Y. Survey of application of deep learning in image recognition[J]. Computer Engineering and Applications，2019，55（12）：20-36 郑远攀，李广阳，李晔. 深度学习在图像识别中的应用研究综述[J]. 计算机工程与应用，2019，55（12）：20-36
[33] HAN Y. Grassland rodent infestion minitoring research based on UAV remote sensing and deep learning[D]. Hohhot：Inner Mongolia University，2024：5-20 韩宇. 基于无人机遥感与深度学习的草原鼠害监测研究[D]. 呼和浩特：内蒙古大学，2024：5-20
[34] FUKUNAGA K. Introduction to statistical pattern recognition[M]. New York：Academic Press，1972：7-25
[35] MAHALANOBIS P C. On the generalised distance in statistics[J]. Proceedings of the National Institute of Sciences of India，1936，2：49-55
[36] SUN K，LU T D. Comparison of supervised classification methodsin remote sensing image classification[J]. Jiangxi Science，2017，35（3）：367-371，468 孙坤，鲁铁定. 监督分类方法在遥感影像分类处理中的比较[J]. 江西科学，2017，35（3）：367-371，468
[37] RUMELHART D E，HINTON G E，WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature，1986，323（6088）：533-536
[38] JIA J F. Compare of ENVI remote sensing image classification methods[J]. Resources，2014（6）：133-136 贾建峰. ENVI遥感图像监督分类方法比较[J]. 西部资源，2014（6）：133-136
[39] CAO C Y，TIAN M，XU X Y，et al. Application progress of machine learning in point-of-care testing[J]. SCIENTIA SINICA Chimica，2021，51（12）：1590-1614 曹超羽，田苗，许夏瑜，等. 机器学习在即时诊断中的应用进展[J]. 中国科学（化学），2021，51（12）：1590-1614
[40] FU J，HUANG H J，YANG X G. Comparison of land use classification methods used in analysis of the Tangshan Bay three islands using remote sensing images based on ENVI[J]. Marine Sciences，2014，38（1）：20-26 付佳，黄海军，杨曦光. 基于ENVI的唐山湾三岛土地利用遥感分类方法的比较分析[J]. 海洋科学，2014，38（1）：20-26
[41] HUANG X. Research on multi-scale texture and shape feature extraction and object-oriented classification of high-resolution remote sensing images[D]. Wuhan：Wuhan University，2009：15-18 黄昕. 高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D]. 武汉：武汉大学，2009：15-18

Investigation of the Algorithm for Detecting Rodent-Damaged Areas in Desert Grasslands Using Unmanned Aerial Vehicle Remote Sensing Images

基于无人机遥感影像的荒漠草原鼠害地特征识别算法研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	REN Lei, WU Qian, HAN Guo-dong. Effects of Grazing intensity and Grazing Time on the Nutritional Quality of Dominant Forages in Desert Grassland [J]. Acta Agrestia Sinica, 2026, 34(8): 3026-3036.
[2]	ZHANG Hui, Lü Shi-jie, ZHANG Fan, LIU Hong-mei, LI Zhi-guo, HAN Guo-dong. Response of the Correlation between Dominant Species and Functional Groups to Grazing Intensity in Desert Steppe [J]. Acta Agrestia Sinica, 2026, 34(6): 2277-2286.
[3]	SHUAI Zheng-feng, LEI Xian-dao, WANG Chang-ming, HUANG Chen, WEI Xue-wen, WU Rui, LIN Chang-cun. Study on the Impact Mechanism of Photovoltaic Power Plant Construction on Plant Diversity in the Northern Desert Grassland Area [J]. Acta Agrestia Sinica, 2026, 34(4): 1137-1145.
[4]	DONG Hao, ZHANG Xiao-jia, HAN Guo-dong. Effects of Different Grazing Intensities on Plant Community Composition and Species Ecological Niches in Desert Steppe [J]. Acta Agrestia Sinica, 2026, 34(3): 761-769.
[5]	MA Peng, ZHOU Lei, SUN Zong-jiu, Asitaiken·Julihaiti, WEI Peng. Effects of Litter Addition on Soil Enzyme Activitie and Stoichiometric Ratio in Sagebrush Desert Grassland [J]. Acta Agrestia Sinica, 2026, 34(2): 643-652.
[6]	DENG Yang-zhen, WANG Xi-yuan, LI Shao-yu, ZHENG Jia-hua, ZHANG Feng, ZHAO Meng-li, ZHANG Bin. The Change Rules of Soil Multifunctionality and its Relationship with Biodiversity During the Secondary Succession of Abandoned Farmland on Desert Grassland [J]. Acta Agrestia Sinica, 2025, 33(9): 2863-2872.
[7]	ZHOU Hui-min, GAO Zhi-wei, ZHANG Xiao-jia, WU Jia-xin, WANG Wei-feng, HAN Guo-dong. Effects of Different Grazing Intensity on Soil Bacterial Community in Inner Mongolian Desert Grasslands [J]. Acta Agrestia Sinica, 2025, 33(6): 1764-1770.
[8]	Didar·Bisulidan, SUN Zong-jiu, YU Bing-jie, Asitaiken·Julihaiti, LI Mei-sha, JING Yi-sheng. Effects of Grazing Enclosure on Soil Aggregates Stability in Sagebrush Desert Grassland [J]. Acta Agrestia Sinica, 2025, 33(5): 1534-1543.
[9]	LI Wen-xiong, JIN Gui-li, LIU Wen-hao, LI Jia-xin, WANG Sheng-ju, CHEN Meng-tian, LI Chao, DU Wen-lin, Davuletti Khaled Samugal, Serik Eli Yeridana. Research on Aboveground Biomass Inversion of Desert Grassland Based on UAV Remote Sensing [J]. Acta Agrestia Sinica, 2025, 33(4): 1258-1266.
[10]	CUI Le, LI Zhi-guo, LYU Shi-jie, DUAN Lei-yu, WANG Xin-yu, SUN Xue-yan. Effects of Grazing Intensity on Soil Bacterial Communities Composition and Diversity in Different Microhabitats of Desert Steppe [J]. Acta Agrestia Sinica, 2025, 33(11): 3571-3580.
[11]	SUN Xue-yan, LI Zhi-guo, LYU Shi-jie, WANG Xin-yu, DUAN Lei-yu, CUI Le. Determination of Wind Erosion and Vegetation Characteristics Under Grazing Disturbance in Desert Steppe Based on Terrestrial LiDAR [J]. Acta Agrestia Sinica, 2025, 33(11): 3698-3710.
[12]	WU Jia-xin, ZHANG Yu-han, LI Shao-yu, HAN Guo-dong. Effects of Long-Term Grazing on Different Fractions of Organic Phosphorus Content in Desert Grassland in Inner Mongolia [J]. Acta Agrestia Sinica, 2024, 32(5): 1479-1488.
[13]	ZHOU Lei, SUN Zong-jiu, NIE Ting-ting, YU Bing-jie, ZHENG Li, ZHOU Chen-ye. Effects of Litter Additions on Soil Carbon, Nitrogen and Phosphorus Contents and Their Stoichiometric Characteristics in Sagebrush Desert Grassland [J]. Acta Agrestia Sinica, 2024, 32(2): 462-469.
[14]	GUO Zhen-ning, TAN Jian-guo, SUN Shi-xian, ZHUANG Ling, CHEN Yi-fei. Study on Fractal Dimension and Nutrient Characteristics in Different Grazing Intensity [J]. Acta Agrestia Sinica, 2024, 32(12): 3698-3705.
[15]	LI Hong-yu, GAO Cui-ping, LYU Guang-yi, YANG Chang-xiang, ZHANG Chun-ying, WANG Cheng-jie. Effects of Grazing and Nitrogen Addition on Desert Grassland Plants and Soil Carbon and Nitrogen [J]. Acta Agrestia Sinica, 2024, 32(1): 239-247.