近年来，受人类活动尤其是放牧等因素的影响，黄土高原荒漠草地部分区域出现了退化问题，在植物方面主要表现为草地植物多样性和生产力下降，以及群落结构改变等。因此，科学评估放牧对草地群落特征特征的影响对实现区域可持续发展具有重要意义。本研究以宁夏回族自治区盐池县为对象，设置了对照组（CK）、轻度（LG）、中度（MG）、重度（HG）不同牧压梯度的实验样地，通过为期两年的控制放牧实验，采用野外调查和室内分析相结合的方法，系统分析了放牧强度对群落特征及其高光谱特征影响。本研究结合特征波段优选算法与机器学习技术，建立了草地植物多样性与放牧压力的遥感监测，为草地生态系统高效管理提供了理论与技术支持。在模型构建中，采用SNV、MSC和SG算法对高光谱数据进行预处理，通过CARS和SPA特征选择方法筛选敏感波段，结合ELM、SVM和BP三种机器学习回归算法构建植物多样性估测模型。同时，基于CNN、LSTM和RBF算法，利用高光谱特征建立牧压梯度的分级模型，并结合高光谱数据和传统实测数据优化模型，提升草地生态监测的精度和效率，最终构建了植物多样性的预测模型和牧压梯度的分级模型。主要研究结果如下：

（1）放牧强度对株高的影响最为显著，2023年MG处理的株高最高，CK处理最低。但随放牧时间延长，2024年各处理下的株高普遍降低，尤其HG处理降至5.0 cm。但植物密度表现出与株高相反的变化趋势。2024年HG处理的密度高达780.33 株/m²，显著高于其他处理。不同牧压梯度下，生物量变化呈现明显的梯度变化规律。LG处理在两年间均保持较高的地上生物量，而HG处理则显著降低。2024年HG处理地下生物量急剧下降84.8 %。

（2）MG处理的物种丰富度在2024年显著提升34.2 %。而HG处理的多样性各项指标均为最低。MG处理在2023年的β多样性最高，但2024年各处理间差异缩小。不同牧压梯度和年份下的植物群落β多样性存在显著差异。牧压梯度和年份对植物群落的物种组成和结构具有显著影响，植物群落特征在不同放牧梯度和年份间的分异显著。

（3）基于高光谱技术，建立了草地植物多样性的估测模型。在所有模型中，SG-CARS-SVM模型（R²=0.95，RMSE=0.05）表现出最佳的估测效果，表明该组合能够以较高的预测性能实现草地植物多样性的估测，具有良好的稳定性和泛化能力，可用于放牧草地植物多样性的快速监测管理。

（4）基于高光谱技术，建立了草地植物的牧压梯度分类模型。在所有模型中， SG-CARS-CNN分类模型的表现最优，预测准确率达到97.22 %。这表明该组合能够以较高的分类性能实现对草地所处牧压梯度的监测。

以上研究结果表明，在中等牧压梯度下，植物多样性最高，较适宜植物生长。此外，通过结合高光谱技术，构建了放牧草地植物多样性和牧压梯度的预测模型，为草地放牧管理提供可靠的技术支持。

In recent years, due to human activities, especially grazing and other factors, some areas of desert grassland in the Loess Plateau have experienced degradation. In terms of plants, it is mainly manifested in the decline of grassland plant diversity and productivity, as well as the change of community structure. Therefore, scientifically assessing the impact of grazing on the characteristics of grassland communities is of great significance for achieving regional sustainable development. In this study, Yanchi County, Ningxia Hui Autonomous Region was taken as the object, and experimental plots with different grazing pressure gradients of control group (CK), mild (LG), moderate (MG) and severe (HG) were set up. Through a two-year controlled grazing experiment, the effects of grazing intensity on community characteristics and hyperspectral characteristics were systematically analyzed by combining field investigation and indoor analysis. In this study, remote sensing monitoring of grassland plant diversity and grazing pressure was established by combining feature band optimization algorithm and machine learning technology, which provided theoretical and technical support for efficient management of grassland ecosystem. In the model construction, SNV, MSC and SG algorithms were used to preprocess hyperspectral data. Sensitive bands were screened by CARS and SPA feature selection methods, and plant diversity estimation models were constructed by combining ELM, SVM and BP machine learning regression algorithms. At the same time, based on CNN, LSTM and RBF algorithms, the classification model of grazing pressure gradient was established by using hyperspectral features, and the accuracy and efficiency of grassland ecological monitoring were improved by combining hyperspectral data and traditional measured data optimization model. Finally, the prediction model of plant diversity and the classification model of grazing pressure gradient were constructed. The main results are as follows :

(1) In 2023, the plant height of MG treatment was the highest, and that of CK treatment was the lowest. However, with the extension of grazing time, the plant height under each treatment generally decreased in 2024, especially the HG treatment decreased to 5.0 cm. However, plant density showed an opposite trend with plant height. In 2024, the density of HG treatment was as high as 780.33 plants/m², which was significantly higher than other treatments. Under different grazing pressure gradients, biomass changes showed obvious gradient changes. LG treatment maintained high aboveground biomass during the two years, while HG treatment decreased significantly. In 2024, the underground biomass of HG treatment decreased sharply by 84.8 %.

(2) The species richness of MG treatment increased significantly by 34.2 % in 2024. The diversity indexes of HG treatment were the lowest. The β diversity of  MG treatment was the highest in 2023, but the difference between treatments decreased in 2024. There were significant differences in β diversity of plant communities under different grazing gradients and years. Grazing pressure gradients and years had significant effects on the species composition and structure of plant communities, and the characteristics of plant communities were significantly different between different grazing gradients and years.

(3) Based on hyperspectral technology, the estimation model of grassland plant diversity was established. Among all the models, the SG-CARS-SVM model (R²=0.95, RMSE=0.05) showed the best estimation effect, indicating that the combination could achieve the estimation of grassland plant diversity with high prediction performance, and had good stability and generalization ability, which could be used for rapid monitoring and management of plant diversity in grazing grassland.

(4) Based on hyperspectral technology, the grazing pressure gradient classification model of grassland plants was established. Among all the models, the SG-CARS-CNN classification model has the best performance, with a prediction accuracy of 97.22 %. This indicates that the combination can monitor the grazing pressure gradient of grassland with high classification performance.

The above results showed that the plant diversity was the highest under the moderate grazing pressure gradient, which was more suitable for plant growth. In addition, a prediction model of plant diversity and grazing pressure gradient in grazing grassland was constructed by combining hyperspectral technology, which provided reliable technical support for grassland grazing management.

[1] Lu W, Shikui D, Yuanyuan L, et al. Effect of Degradation Intensity on Grassland Ecosystem Services in the Alpine Region of Qinghai-Tibetan Plateau, China [J]. 2013, 8(3): e58432.

[2] Eldridge D J, Delgado‐Baquerizo M. Continental‐scale impacts of livestock grazing on ecosystem supporting and regulating services [J]. Land Degradation & Development, 2017, 28(4): 1473-1481.

[3] Yan L, Li Y, Wang L, et al. Grazing significantly increases root shoot ratio but decreases soil organic carbon in Qinghai‐Tibetan Plateau grasslands: A hierarchical meta‐analysis [J]. Land Degradation & Development, 2020, 31(16): 2369-2378.

[4] Cao J, Yeh E T, Holden N M, et al. The effects of enclosures and land-use contracts on rangeland degradation on the Qinghai–Tibetan plateau [J]. Journal of Arid Environments, 2013, 97: 3-8.

[5] Zheng R, Liu Y, Yao Z. Research Progress on the Effects of Grazing on the Structures and Function of Typical Grassland Ecosystems. [J]. Journal of Green Science and Technology, 2024, 26(04): 51-57.

[6] Deng L, Zhang Z, Shangguan Z. Long-term fencing effects on plant diversity and soil properties in China [J]. Soil and Tillage Research, 2014, 137: 7-15.

[7] Liu C, Li W, Xu J, et al. Response of soil nutrients and stoichiometry to grazing management in alpine grassland on the Qinghai-Tibet Plateau [J]. Soil and Tillage Research, 2021, 206: 104822.

[8] Zhong Z, Li X, Sanders D, et al. Soil engineering by ants facilitates plant compensation for large herbivore removal of aboveground biomass [J]. Ecology, 2021, 102(5): e03312.

[9] Sitters J, Kimuyu D M, Young T P, et al. Negative effects of cattle on soil carbon and nutrient pools reversed by megaherbivores [J]. Nature Sustainability, 2020, 3(5): 360-366.

[10] Zhong Z, Li X, Smit C, et al. Large herbivores facilitate a dominant grassland forb via multiple indirect effects [J]. Ecology, 2022, 103(4): e3635.

[11] Fetzel T, Havlik P, Herrero M, et al. Seasonality constraints to livestock grazing intensity [J]. Global Change Biology, 2017, 23(4): 1636-1647.

[12] Sloat L L, Gerber J S, Samberg L H, et al. Increasing importance of precipitation variability on global livestock grazing lands [J]. Nature Climate Change, 2018, 8(3): 214-218.

[13] Liang M, Gornish E S. Rainfall regulation of grazed grasslands [J]. Proceedings of the National Academy of Sciences, 2019, 116(48): 23887-23888.

[14] Schönbach P, Wan H, Gierus M, et al. Grassland responses to grazing: effects of grazing intensity and management system in an Inner Mongolian steppe ecosystem [J]. Plant and Soil, 2011, 340: 103-115.

[15] Alkemade R, Reid R S, Van Den Berg M, et al. Assessing the impacts of livestock production on biodiversity in rangeland ecosystems [J]. Proceedings of the National Academy of Sciences, 2013, 110(52): 20900-20905.

[16] Liang M, Liang C, Hautier Y, et al. Grazing‐induced biodiversity loss impairs grassland ecosystem stability at multiple scales [J]. Ecology Letters, 2021, 24(10): 2054-2064.

[17] Mcnaughton S J, Oesterheld M, Frank D A, et al. Ecosystem-level patterns of primary productivity and herbivory in terrestrial habitats [J]. Nature, 1989, 341(6238): 142-144.

[18] Leriche H, Le Roux X, Desnoyers F, et al. Grass response to clipping in an African savanna: testing the grazing optimization hypothesis [J]. Ecological Applications, 2003, 13(5): 1346-1354.

[19] Fedrigo J K, Ataide P F, Filho J A, et al. Temporary grazing exclusion promotes rapid recovery of species richness and productivity in a long‐term overgrazed Campos grassland [J]. Restoration Ecology, 2018, 26(4): 677-685.

[20] 胥慧, 包玉海, 包刚，等. 内蒙古典型草原干草生物量高光谱遥感估算研究[J].阴山学刊(自然科学版), 2014, 28(04): 22-27.

[21] Myers N, Mittermeier R A, Mittermeier C G, et al. Biodiversity hotspots for conservation priorities [J]. Nature, 2000, 403(6772): 853-858.

[22] Duro D C, Coops N C, Wulder M A, et al. Development of a large area biodiversity monitoring system driven by remote sensing [J]. Progress in physical geography, 2007, 31(3): 235-260.

[23] 朱超, 方颖, 周可新，等. 生态系统红色名录——一种新的生物多样性保护工具[J].生态学报, 2015, 35(09): 2826-2836.

[24] Nicholson E, Mace G M, Armsworth P R, et al. Priority research areas for ecosystem services in a changing world [J]. Journal of Applied Ecology, 2009, 46(6): 1139-1144.

[25] 黄友昕, 刘修国, 沈永林，等. 农业干旱遥感监测指标及其适应性评价方法研究进展[J].农业工程学报, 2015, 31(16): 186-195.

[26] 李皓露. 基于深度学习的新疆棉田遥感识别与产量预测研究 [D]. 南京: 南京信息工程大学, 2021.

[27] 马瑜蔓, 段博, 徐宾灿，等. 基于分数阶微分和无人机高光谱指数优选的油菜产量预测[J].农业工程学报, 2025: 1-10.

[28] 张富华. 锡林郭勒草地多样性遥感识别与评价研究 [D]. 北京: 首都师范大学, 2014.

[29] Boochs F, Kupfer G, Dockter K, et al. Shape of the red edge as vitality indicator for plants [J]. Remote sensing, 1990, 11(10): 1741-1753.

[30] Li Y, Ji J. Framework of a regional impacts assessment model and its application on arid/semi-arid region [J]. 2002. 08(03): 121-127

[31] Akiyama T, Kawamura K. Grassland degradation in China: methods of monitoring, management and restoration [J]. Grassland science, 2007, 53(1): 1-17.

[32] 丁金梅, 王维珍, 米文宝，等. 宁夏草地土壤有机碳空间特征及其影响因素[J].生态学报, 2023, 43(05): 1913-1922.

[33] 孙凤玲. 植物多样性对园林景观设计的影响和应用策略 [J]. 分子植物育种, 2023, 21(17): 5906-5910.

[34] Liu Y, Zhao X, Dong Q, et al. Research Progress on the Effects of Grazing on Grassland Ecosystem Structure and Function [J]. Acta Agrestia Sinica, 2023, 31(08): 2253-2262.

[35] Herrero M, Grace D, Njuki J, et al. The roles of livestock in developing countries [J]. Animal, 2013, 7(s1): 3-18.

[36] Aodun G, Baoyin T. Effects of Different Grazing Periods onAboveground Community Productivity ofa Typical Steppe Grassland [J]. Chinese Journal of Grassland, 2015, 37(02): 28-34.

[37] Pan Y, Wu J, Xu Z. Analysis of the tradeoffs between provisioning and regulating services from the perspective of varied share of net primary production in an alpine grassland ecosystem [J]. Ecological Complexity, 2014, 17: 79-86.

[38] Daniel R, Viviana S N. Combined effects of environment and grazing on vegetation structure in Argentine granite grasslands [J]. journal of Vegetation Science, 2003, 14(2): 223-232.

[39] Wu Q, Ju X, Wang Y, et al. Grazing intensity affects livestock behavior and diet selection in a desert steppe. [J]. Chin Sci Bull, 2024: 1-14.

[40] Török P, Penksza K, Tóth E, et al. Vegetation type and grazing intensity jointly shape grazing effects on grassland biodiversity [J]. Ecology and Evolution, 2018, 8(20): 10326-10335.

[41] 冯雷. 古尔班通古特沙漠土壤理化性质的空间变异及对植物多样性的影响 [D]. 石河子: 石河子大学, 2015.

[42] Koerner S E, Smith M D, Burkepile D E, et al. Change in dominance determines herbivore effects on plant biodiversity [J]. Nature Ecology & Evolution, 2018, 2(12): 1925-1932.

[43] Olff H, Ritchie M E. Effects of herbivores on grassland plant diversity [J]. Trends in ecology & evolution, 1998, 13(7): 261-265.

[44] Proulx M, Mazumder A. Reversal of grazing impact on plant species richness in nutrient‐poor vs. nutrient‐rich ecosystems [J]. Ecology, 1998, 79(8): 2581-2592.

[45] Worm B, Lotze H K, Hillebrand H, et al. Consumer versus resource control of species diversity and ecosystem functioning [J]. Nature, 2002, 417(6891): 848-851.

[46] Bakker E S, Ritchie M E, Olff H, et al. Herbivore impact on grassland plant diversity depends on habitat productivity and herbivore size [J]. Ecology letters, 2006, 9(7): 780-788.

[47] Connell J H. Diversity in tropical rain forests and coral reefs: high diversity of trees and corals is maintained only in a nonequilibrium state [J]. Science, 1978, 199(4335): 1302-1310.

[48] Milchunas D G, Sala O E, Lauenroth W K. A generalized model of the effects of grazing by large herbivores on grassland community structure [J]. The American Naturalist, 1988, 132(1): 87-106.

[49] Grime J P. Competitive exclusion in herbaceous vegetation [J]. Nature, 1973, 242(5396): 344-347.

[50] Mackey R L, Currie D J. The diversity–disturbance relationship: is it generally strong and peaked? [J]. Ecology, 2001, 82(12): 3479-3492.

[51] Cingolani A M, Noy-Meir I, Díaz S. Grazing effects on rangeland diversity: a synthesis of contemporary models [J]. Ecological applications, 2005, 15(2): 757-773.

[52] 宋耀邦, 宣传忠, 唐朝辉，等. 基于无人机高光谱和机器学习的荒漠草原地上生物量估算[J].农业工程学报, 2025, 41(04): 135-143.

[53] 金利山, 王秀梅, 董建军，等. 结合ASD和无人机高光谱的内蒙古典型草原植被氮反演[J].中国环境科学, 2025, 45(05): 2713-2723.

[54] Qian S-E. Hyperspectral satellites, evolution, and development history [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 7032-7056.

[55] Laugier E J, Casana J. Integrating satellite, UAV, and ground-based remote sensing in archaeology: An exploration of pre-modern land use in Northeastern Iraq [J]. Remote Sensing, 2021, 13(24): 5119.

[56] 苗春丽, 伏帅, 刘洁，等. 基于UAV成像高光谱图像的高寒草甸地上生物量——以海北试验区为例[J].草业科学, 2022, 39(10): 1992-2004.

[57] 孔钰如, 王李娟, 冯海宽，等. 无人机高光谱波段选择的叶面积指数反演[J].光谱学与光谱分析, 2022, 42(03): 933-939.

[58] Li B, Xu X, Zhang L, et al. Above-ground biomass estimation and yield prediction in potato by using UAV-based RGB and hyperspectral imaging [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162: 161-172.

[59] Wendel A, Underwood J. Illumination compensation in ground based hyperspectral imaging [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 129: 162-178.

[60] Su H, Wu Z, Zhang H, et al. Hyperspectral anomaly detection: A survey [J]. IEEE Geoscience and Remote Sensing Magazine, 2021, 10(1): 64-90.

[61] Vali A, Comai S, Matteucci M. Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: A review [J]. Remote Sensing, 2020, 12(15): 2495.

[62] 谭先明, 张佳伟, 王仲林，等. 基于PLS的不同水氮条件下带状套作玉米产量预测[J].中国农业科学, 2022, 55(06): 1127-1138.

[63] 高金龙. 青藏高原东缘高寒天然草地牧草氮磷养分和生长状况的高光谱遥感研究 [D]. 兰州: 兰州大学, 2020.

[64] Das D, Pradhan S, Sehgal V, et al. Spectral reflectance characteristics of healthy and yellow mosaic virus infected soybean (Glycine max L.) leaves in a semiarid environment [J]. Journal of Agrometeorology, 2013, 15(1): 36-38.

[65] Huang W, Li W, Xu J, et al. Hyperspectral monitoring driven by machine learning methods for grassland above-ground biomass [J]. Remote Sensing, 2022, 14(9): 2086.

[66] 姚阔, 郭旭东, 南颖，等. 植被生物量高光谱遥感监测研究进展[J].测绘科学, 2016, 41(08): 48-53.

[67] Zhao J, Zhou Y, Shi B, et al. Multi-stage fusion and multi-source attention network for multi-modal remote sensing image segmentation [J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2021, 12(6): 1-20.

[68] Wang W, Ma Q, Huang J, et al. Remote sensing monitoring of grasslands based on adaptive feature fusion with multi-source data [J]. Remote Sensing, 2022, 14(3): 750.

[69] Maron M, Gordon A, Mackey B G. Agree on biodiversity metrics to track from space [J]. Nature, 2015, 523: 403-405.

[70] Wei D, Liu K, Xiao C, et al. A systematic classification method for grassland community division using China’s ZY1-02D hyperspectral observations [J]. Remote Sensing, 2022, 14(15): 3751.

[71] Wu Z, Zhang J, Deng F, et al. Superpixel-based regional-scale grassland community classification using genetic programming with Sentinel-1 SAR and Sentinel-2 multispectral images [J]. Remote Sensing, 2021, 13(20): 4067.

[72] 张影. 卫星高光谱遥感农作物精细分类研究 [D]. 北京: 中国农业科学院, 2021.

[73] Zhu X, Bi Y, Du J, et al. Research on deep learning method recognition and a classification model of grassland grass species based on unmanned aerial vehicle hyperspectral remote sensing [J]. Grassland Science, 2023, 69(1): 3-11.

[74] 孔嘉鑫, 张昭臣, 张健. 基于多源遥感数据的植物物种分类与识别:研究进展与展望 [J]. 生物多样性, 2019, 27(07): 796-812.

[75] Bailey D W, Trotter M G, Knight C W, et al. Use of GPS tracking collars and accelerometers for rangeland livestock production research [J]. Translational Animal Science, 2018, 2(1): 81-88.

[76] 卫智军, 白云军, 乌日图，等. 荒漠草原不同放牧方式绵羊牧食策略研究[J].草地学报, 2005, (S1): 57-61.

[77] 王宏博, 丁学智, 郎侠，等. 甘南玛曲夏季牧场欧拉型藏羊牧食行为的研究[J].草地学报, 2012, 20(03): 583-588.

[78] Yoshitoshi R, Watanabe N, Kawamura K, et al. Distinguishing cattle foraging activities using an accelerometry-based activity monitor [J]. Rangeland ecology & management, 2013, 66(3): 382-386.

[79] Feng X, Zhao Y. Grazing intensity monitoring in Northern China steppe: Integrating CENTURY model and MODIS data [J]. Ecological Indicators, 2011, 11(1): 175-182.

[80] Song M-H, Zhu J-F, Li Y-K, et al. Shifts in functional compositions predict desired multifunctionality along fragmentation intensities in an alpine grassland [J]. Ecological Indicators, 2020, 112: 106095.

[81] 谢芮, 吴秀芹. 内蒙古草地放牧强度遥感估测 [J]. 北京大学学报(自然科学版), 2014, 50(05): 919-924.

[82] 王萨仁娜, 韩国栋, 张圣微，等. 基于3S技术的绵羊牧食行为与草地环境相互作用研究[J].中国生态农业学报, 2015, 23(07): 860-867.

[83] 杜永兴, 何朋, 李宝山，等. 基于海量牧区羊群轨迹的区域属性挖掘研究[J].计算机应用研究, 2018, 35(04): 1033-1036.

[84] 申波. 无人机技术评估相对放牧强度分布趋势初探 [D]. 兰州: 兰州大学, 2019.

[85] 王艺积. 基于低空遥感的高寒草原牧场利用现状分析 [D]. 成都: 四川师范大学, 2020.

[86] 陈黔. 基于Google Earth Engine的中国北方四大沙地灌木覆盖度估算 [D]. 贵阳: 贵州师范大学, 2019.

[87] 王琪, 吴成永, 陈克龙，等. 基于MODIS NPP数据的青海湖流域产草量与载畜量估算研究[J].生态科学, 2019, 38(04): 178-185.

[88] 姚兴成, 曲恬甜, 常文静，等. 基于MODIS数据和植被特征估算草地生物量[J].中国生态农业学报, 2017, 25(04): 530-541.

[89] 杨晋云, 张莎, 白雲，等. 基于机器学习融合多源遥感数据模拟SPEI监测山东干旱[J].中国农业气象, 2021, 42(03): 230-242.

[90] Ge J, Meng B, Liang T, et al. Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River, China [J]. Remote Sensing of Environment, 2018, 218: 162-173.

[91] 邢素丽, 张广录. 我国农业遥感的应用现状与展望 [J]. 农业工程学报, 2003, (06): 174-178.

[92] 刘金宇. 基于无人机高光谱遥感的草原地表微斑块识别与反演 [D]. 呼和浩特: 内蒙古农业大学, 2024.

[93] 潘占兵, 蒋齐, 温学飞，等. 长城沿线农牧交错区退化草场恢复对策——以宁夏盐池沙地退化草场为例[J].西北农业学报, 2004, (04): 115-119.

[94] 陈小红, 段争虎, 谭明亮，等. 沙漠化逆转过程中土壤颗粒分形维数的变化特征——以宁夏盐池县为例[J].干旱区研究, 2010, 27(02): 297-302.

[95] 马睿. 宁夏盐池县土地利用变化对生态系统服务价值影响分析 [D]. 北京: 北京林业大学, 2019.

[96] 高苏日固嘎, 斯琴朝克图, 乌兰图雅，等. 克氏针茅草原群落物种多样性与生物量关系对放牧强度的响应[J].生态学报, 2022, 42(23): 9736-9746.

[97] 李科. 典型草原和草甸草原植物群落及土壤高光谱特征研究 [D]. 南京: 南京信息工程大学, 2020.

[98] 赵菡. 苹果叶片高光谱生化参数高通量反演模型研究 [D]. 阿拉尔: 塔里木大学, 2022.

[99] 刘燕丹, 乌日力嘎, 李元恒，等. 不同放牧制度下典型草原生产效益与生态效应[J].内蒙古大学学报(自然科学版), 2021, 52(04): 425-436.

[100] 高露, 张圣微, 朱仲元，等. 放牧对干旱半干旱草原植物群落结构和生态功能的影响[J].水土保持研究, 2019, 26(06): 205-211.

[101] 张宇, 侯路路, 闫瑞瑞，等. 放牧强度对草甸草原植物群落特征及营养品质的影响[J].中国农业科学, 2020, 53(13): 2550-2561.

[102] 田芸, 吉祖稳, 王党伟，等. 黄河三角洲植被覆盖度与生态需水量研究[J].水土保持研究, 2025, 32(04): 168-175+188.

[103] 王凯, 王聪, 冯晓明，等. 生物多样性与生态系统多功能性的关系研究进展[J].生态学报, 2022, 42(01): 11-23.

[104] 张璐璐, 王孝安, 朱志红，等. 模拟放牧强度与施肥对青藏高原高寒草甸群落特征和物种多样性的影响[J].生态环境学报, 2018, 27(03): 406-415.

[105] 刘忠宽, 智建飞, 李英杰，等. 休牧后土壤养分空间异质性和植物群落α多样性[J].河北农业科学, 2004, (04): 1-8.

[106] Lin Y, Hong M, Han G, et al. Grazing intensity affected spatial patterns of vegetation and soil fertility in a desert steppe [J]. Agriculture, Ecosystems & Environment, 2010, 138(3-4): 282-292.

[107] 蒯晓妍, 邢鹏飞, 张晓琳，等. 短期放牧强度对半干旱草地植物群落多样性和生产力的影响[J].草地学报, 2018, 26(06): 1283-1289.

[108] 赵生龙, 左小安, 张铜会，等. 乌拉特荒漠草原群落物种多样性和生物量关系对放牧强度的响应[J].干旱区研究, 2020, 37(01): 168-177.

[109] Zuo X, Zhang J, Lv P, et al. Effects of plant functional diversity induced by grazing and soil properties on above-and belowground biomass in a semiarid grassland [J]. Ecological indicators, 2018, 93: 555-561.

[110] 刘嘉慧. 草原灌丛对土壤种子库的影响及其对放牧的响应 [D]. 北京: 中国农业科学院, 2024.

[111] 牛钰杰, 杨思维, 王贵珍，等. 放牧干扰下高寒草甸物种和生活型丰富度与地上及地下生物量的关系[J].生态学报, 2018, 38(08): 2791-2801.

[112] Wang C, Tang Y. A global meta-analyses of the response of multi-taxa diversity to grazing intensity in grasslands [J]. Environmental Research Letters, 2019, 14(11): 114003.

[113] 郭茹. 环境对植物叶功能性状筛选的多尺度效应与群落构建 [D]. 杨凌: 中国科学院大学(中国科学院教育部水土保持与生态环境研究中心), 2016.

[114] Wang C, Tang Y. A global meta-analyses of the response of multi-taxa diversity to grazing intensity in grasslands [J]. Environ Res Lett, 2019, 14(11): 137-142.

[115] 雷蕾, 张峰, 郑佳华，等. 放牧强度对短花针茅荒漠草原生态系统多功能性的影响[J].草地学报, 2024, 32(01): 275-283.

[116] Ruiyang, Zhangsupa, B/Sup, et al. Grazing induced changes in plant diversity is a critical factor controlling grassland productivity in the Desert Steppe, Northern China [J]. Agriculture, Ecosystems and Environment, 2018, 13(265) 223-231.

[117] Xiaoan, Zuo, Jing, et al. Effects of plant functional diversity induced by grazing and soil properties on above- and belowground biomass in a semiarid grassland [J]. Ecological indicators: Integrating, monitoring, assessment and management, 2018, 93(10): 555-561.

[118] Hao X, Yang J, Dong S, et al. Impacts of short-term grazing intensity on the plant diversity and ecosystem function of alpine steppe on the Qinghai–Tibetan Plateau [J]. Plants, 2022, 11(14): 1889.

[119] Grime J P. Evidence for the existence of three primary strategies in plants and its relevance to ecological and evolutionary theory [J]. The american naturalist, 1977, 111(982): 1169-1194.

[120] Van Der Wal R, Bardgett R D, Harrison K A, et al. Vertebrate herbivores and ecosystem control: cascading effects of faeces on tundra ecosystems [J]. Ecography, 2004, 27(2): 242-252.

[121] Semmartin M, Garibaldi L A, Chaneton E J. Grazing history effects on above-and below-ground litter decomposition and nutrient cycling in two co-occurring grasses [J]. Plant and Soil, 2008, 303: 177-189.

[122] Klein J A, Harte J, Zhao X Q. Experimental warming causes large and rapid species loss, dampened by simulated grazing, on the Tibetan Plateau [J]. Blackwell Science Ltd, 2004, 10(12): 265-274.

[123] Marty J T. Effects of Cattle Grazing on Diversity in Ephemeral Wetlands [J]. Conservation Biology, 2005, 19(5): 1626-1632.

[124] Oba G, Vetaas O, Stenseth N C. Relationship between biomass and plant species richness in arid-zone grazing lands [J]. 2001, 11(12) 323-336

[125] Inderjit. Plant Invasions: Habitat Invasibility and Dominance of Invasive Plant Species [J]. Plant & Soil, 2005, 277(1-2): 1-5.

[126] Holdo R M, Holt R D, Coughenour M B, et al. Plant productivity and soil nitrogen as a function of grazing, migration and fire in an African savanna [J]. Journal of Ecology, 2007, 95(1): 115-128.

[127] Schippers P, Joenje W. Modelling the effect of fertiliser, mowing, disturbance and width on the biodiversity of plant communities of field boundaries [J]. Agriculture Ecosystems & Environment, 2002, 93(1-3): 351-365.

[128] Zhou G, Luo Q, Chen Y, et al. Effects of livestock grazing on grassland carbon storage and release override impacts associated with global climate change [J]. Global Change Biology, 2019, 25(3): 1119-1132.

[129] 陈超. 典型草原植物β多样性及功能性状对放牧方式和放牧强度的响应 [D]. 呼和浩特: 内蒙古大学, 2024.

[130] Zhang R, Wang Z, Han G, et al. Grazing induced changes in plant diversity is a critical factor controlling grassland productivity in the Desert Steppe, Northern China [J]. Agriculture, Ecosystems & Environment, 2018, 265: 73-83.

[131] 马文静, 张庆, 牛建明，等. 物种多样性和功能群多样性与生态系统生产力的关系——以内蒙古短花针茅草原为例[J].植物生态学报, 2013, 37(07): 620-630.

[132] 孙迎涛, 岳艳鹏, 成龙，等. 毛乌素沙地油蒿（Artemisia ordosica）生长及生物量分配对沙漠化的响应[J].中国沙漠, 2022, 42(01): 123-133.

[133] Winck B R, Rigotti V M, De Sá E L S. Effects of different grazing intensities on the composition and diversity of Collembola communities in southern Brazilian grassland [J]. Applied Soil Ecology, 2019, 144: 98-106.

[134] Xiong D, Shi P, Zhang X, et al. Effects of grazing exclusion on carbon sequestration and plant diversity in grasslands of China—A meta-analysis [J]. Ecological Engineering, 2016, 94: 647-655.

[135] De Girolamo A, Cervellieri S, Mancini E, et al. Rapid authentication of 100% italian durum wheat pasta by FT-NIR spectroscopy combined with chemometric tools [J]. Foods, 2020, 9(11): 1551.

[136] Liu F, Zhang F, Jin Z, et al. Determination of acetolactate synthase activity and protein content of oilseed rape (Brassica napus L.) leaves using visible/near-infrared spectroscopy [J]. Analytica chimica acta, 2008, 629(1-2): 56-65.

[137] Faber N M. Multivariate sensitivity for the interpretation of the effect of spectral pretreatment methods on near-infrared calibration model predictions [J]. Analytical Chemistry, 1999, 71(3): 557-565.

[138] Su W-H, Bakalis S, Sun D-W. Chemometrics in tandem with near infrared (NIR) hyperspectral imaging and Fourier transform mid infrared (FT-MIR) microspectroscopy for variety identification and cooking loss determination of sweet potato [J]. Biosystems Engineering, 2019, 180: 70-86.

[139] Nie P, Dong T, He Y, et al. Detection of soil nitrogen using near infrared sensors based on soil pretreatment and algorithms [J]. Sensors, 2017, 17(5): 1102.

[140] 张沁宇, 胡志刚, 徐子健，等. 基于粒子群优化算法优化反向传播神经网络构建冷藏草鱼新鲜度的近红外光谱预测模型[J].食品安全质量检测学报, 2023, 14(22): 200-209.

[141] 唐天雨. 宽波段光伏组件积灰检测系统及校准方法 [D]. 南京: 南京信息工程大学, 2024.

[142] Mishra P, Nikzad-Langerodi R. Partial least square regression versus domain invariant partial least square regression with application to near-infrared spectroscopy of fresh fruit [J]. Infrared Physics & Technology, 2020, 111: 103547.

[143] Bonah E, Huang X, Yi R, et al. Vis-NIR hyperspectral imaging for the classification of bacterial foodborne pathogens based on pixel-wise analysis and a novel CARS-PSO-SVM model [J]. Infrared Physics & Technology, 2020, 105: 103220.

[144] 农佳明. 大数据技术在计算机信息安全领域中的应用 [J]. 自动化应用, 2023, 64(10): 242-244.

[145] 赵春林, 尹治棚, 张文斌，等. 基于可见/近红外透射光谱结合蜜獾算法优化支持向量机的糖心苹果鉴别[J].食品科技, 2023, 48(11): 253-259.

[146] 涂建. 基于PCA-GA-BP神经网络的高校学生宿舍火灾安全风险评价 [J]. 四川职业技术学院学报, 2025, 35(01): 162-168.

[147] 杨洋, 徐熙平, 薛航，等. 基于SPA-PSO-BP的花生高光谱图像分类方法研究[J].激光技术, 2024, 48(04): 556-564.

[148] 丁启东, 王怡婧, 张俊华，等. 利用CARS算法联合协变量估算盐碱农田土壤水分和有机质含量[J].应用生态学报, 2024, 35(05): 1321-1330.

[149] 李晋, 张琛, 刘红，等. 近红外光谱联合化学计量学在柑橘类水果质量无损检测方面的最新研究及应用进展[J].食品与发酵工业, 2024, 50(05): 367-379.

[150] 许冠南, 陈璐璐, 康宁，等. 基于网络嵌入与深度学习的潜在竞争对手识别[J].情报杂志, 2025: 1-9.

[151] 刘航. 基于高光谱成像的大蒜品种分类与品质无损检测方法研究 [D]. 泰安: 山东农业大学, 2024.

[152] 郑建宁. 基于深度学习的窃电行为检测方法 [J]. 信息技术, 2019, (02): 156-159.

[153] 葛文昌. 基于深度学习的有源噪声控制研究 [D]. 南京: 南京信息工程大学, 2024.

[154] 刘婷, 张艳. 神经网络PID控制在液压泵马达速度控制系统中的研究 [J]. 通信电源技术, 2018, 35(05): 4-7.

[155] 张玉杰. 智慧牧场中目标检测与分类的轻量级算法研究 [D]. 太原: 中北大学, 2024.