基于随机森林模型的中国黑麦草适生区分布变化预测
Prediction of Changes in the Suitable Habitat Distribution of Lolium perenne L. in China Based on the Random Forest Model
摘要: 黑麦草(Lolium perenne L.)是禾本科一般入侵性植物，由于其具有强大的环境适应能力和竞争能力，对生态系统造成了一定的不良影响，为了有效防控黑麦草，利用随机森林模型(Random Forest)和ArcGIS，对黑麦草在当前以及2050年代(2041~2060)、2070年代(2061~2080)、2090年代(2081~2100)的SSP126、SSP370、SSP585三种气候情景下潜在的适生区分布格局和影响因素进行预测。结果表明：人类活动(hfp)和气候因子(尤其是温度相关因子)是影响黑麦草分布的关键因子。当前黑麦草适生区主要集中在我国东部、中部地区。在未来三种气候情景下，黑麦草的适生区呈现持续扩张的趋势，适生区显著向东北部、南部及高海拔地区迁移；此外，未来中、高适生区的面积逐渐增加，扩张区域面积显著增加，非适生区逐渐转化为适生区，尤其在SSP585情景下表现最为显著。本研究揭示了气候变化背景下黑麦草潜在适生区时空格局的变化，为入侵物种的防控与生态环境的保护提供科学依据。
Abstract: Lolium perenne L. is a commonly invasive plant species in the Poaceae family. Due to its strong environmental adaptability and competitive ability, it exerts certain adverse impacts on ecosystems. To support effective prevention and control of this species, this study employed the Random Forest model along with ArcGIS to predict the potential suitable habitat distribution patterns and influencing factors for Lolium perenne L. under current conditions and under three future climate scenarios (SSP126, SSP370, and SSP585) for the 2050s (2041~2060), 2070s (2061~2080), and 2090s (2081~2100). The results indicate that human activities (hfp) and climatic factors, particularly temperature-related variables, are key determinants affecting the distribution of Lolium perenne L. At present, suitable habitats for Lolium perenne L. are mainly concentrated in eastern and central China. Under all three future climate scenarios, the suitable habitats show a continuous expansion trend, with a notable shift toward northeastern and southern regions as well as higher altitude areas. Moreover, the extent of moderately and highly suitable habitats gradually increases, the area of expansion grows significantly, and non-suitable areas gradually transition into suitable habitats, a pattern most pronounced under the SSP585 scenario. This study reveals the spatiotemporal changes in potential suitable habitats for Lolium perenne L. under climate change, providing a scientific basis for the management of invasive species and the conservation of ecological environments.
文章引用：赵春滢. 基于随机森林模型的中国黑麦草适生区分布变化预测[J]. 农业科学, 2026, 16(2): 187-200. https://doi.org/10.12677/hjas.2026.162026

参考文献

[1] Beddows, A.R. (1967) Lolium perenne L. The Journal of Ecology, 55, 567-587. [Google Scholar] [CrossRef] 
[2] Luo, H., Li, H., Zhang, X. and Fu, J. (2011) Antioxidant Responses and Gene Expression in Perennial Ryegrass (Lolium perenne L.) under Cadmium Stress. Ecotoxicology, 20, 770-778. [Google Scholar] [CrossRef] [PubMed]
[3] 孙蕊, 钟鹏, 刘泽东, 等. 黑麦草的生产技术及其利用价值[J]. 饲料博览, 2023(3): 35-38.
[4] 冯阳, 吴程, 李祖然, 等. 多年生黑麦草对锌和2-巯基苯并噻唑复合胁迫的响应[J]. 草地学报, 2025, 33(8): 2548-2557.
[5] 鄢燕, 张新全, 张新跃. 黑麦草种子生产研究现状及发展对策[J]. 草业科学, 2003(2): 16-19.
[6] Aitken, S.N., Yeaman, S., Holliday, J.A., Wang, T. and Curtis‐McLane, S. (2008) Adaptation, Migration or Extirpation: Climate Change Outcomes for Tree Populations. Evolutionary Applications, 1, 95-111. [Google Scholar] [CrossRef] [PubMed]
[7] 吕玉玲, 潘文豪, 饶鑫媛, 等. 基于优化MaxEnt模型的火炬树在我国潜在适生区预测[J]. 生物安全学报(中英文), 2025, 34(3): 249-257.
[8] 袁艳超, 肖文发, 刘逸夫, 等. 气候变化下黄枝油杉与江南油杉的潜在适生区预测[J]. 北京林业大学学报, 2025, 47(6): 30-42.
[9] Li, Y., Shao, W. and Jiang, J. (2022) Predicting the Potential Global Distribution of Sapindus mukorossi under Climate Change Based on Maxent Modelling. Environmental Science and Pollution Research, 29, 21751-21768. [Google Scholar] [CrossRef] [PubMed]
[10] 刘赛静. 气候和土地利用变化对中国山茶科植物分布格局的影响[D]: [硕士学位论文]. 杭州: 浙江师范大学, 2024.
[11] 罗梦萍. 气候与土地利用变化下中国丹霞梧桐潜在适生区研究[D]: [硕士学位论文]. 长沙: 中南林业科技大学, 2024.
[12] 翟心语. 城市化影响下驻马店市植物物种多样性分布格局[D]: [硕士学位论文]. 郑州: 河南农业大学, 2024.
[13] 梁红. 城市化背景下青岛城市森林植被多样性格局成因及其维持[D]: [博士学位论文]. 上海: 华东师范大学, 2014.
[14] 柴思雨, 徐剑莹, 李铁华, 等. 基于优化MaxEnt模型的细叶桢楠潜在适生区预测[J]. 中南林业科技大学学报, 2025, 45(9): 94-105.
[15] 李政升, 马玉寿, 李有鑫, 等. 气候变化下青藏高原中亚紫菀木潜在适生区的时空动态变化[J]. 生态学杂志, 2024, 43(6): 1566-1575.
[16] Guisan, A., Thuiller, W. and Zimmermann, N.E. (2017) Habitat Suitability and Distribution Models: With Applications in R. Cambridge University Press. [Google Scholar] [CrossRef] 
[17] 刘逸夫, 王军辉, 谭灿灿, 等. 基于MaxEnt模型预测青杄和大果青杄潜在适生区[J]. 林业科学研究, 2025, 38(1): 169-180.
[18] 路文静, 彭佳, 陈鹏崟, 等. 气候变化对白及适生区分布的影响[J]. 西南农业学报, 2025, 38(1): 209-216.
[19] Gao, X., Liu, J. and Huang, Z. (2022) The Impact of Climate Change on the Distribution of Rare and Endangered Tree Firmiana kwangsiensis Using the Maxent Modeling. Ecology and Evolution, 12, e9165. [Google Scholar] [CrossRef] [PubMed]
[20] Zhang, H., Li, J., Zou, H., Wang, Z., Zhu, X., Zhang, Y., et al. (2024) Distribution Pattern of Suitable Areas and Corridor Identification of Endangered Ephedra Species in China. Plants, 13, Article 890. [Google Scholar] [CrossRef] [PubMed]
[21] 陈瑜, 杨毅哲, 陈丽丽, 等. 基于生态位模型的多花黑麦草入侵风险分析[J]. 陕西师范大学学报(自然科学版), 2024, 52(1): 2+70-78.
[22] Wu, K., Wang, Y., Liu, Z., Huo, W., Cao, J., Zhao, G., et al. (2024) Prediction of Potential Invasion of Two Weeds of the Genus Avena in Asia under Climate Change Based on Maxent. Science of The Total Environment, 950, Article 175192. [Google Scholar] [CrossRef] [PubMed]
[23] Miller, J. (2010) Species Distribution Modeling. Geography Compass, 4, 490-509. [Google Scholar] [CrossRef] 
[24] Guisan, A., Edwards, T.C. and Hastie, T. (2002) Generalized Linear and Generalized Additive Models in Studies of Species Distributions: Setting the Scene. Ecological Modelling, 157, 89-100. [Google Scholar] [CrossRef] 
[25] Stockwell, D. (1999) The GARP Modelling System: Problems and Solutions to Automated Spatial Prediction. International Journal of Geographical Information Science, 13, 143-158. [Google Scholar] [CrossRef] 
[26] O’Sullivan, F. (1991) Discussion: Multivariate Adaptive Regression Splines. The Annals of Statistics, 19, 1-67. [Google Scholar] [CrossRef] 
[27] Phillips, S.J., Dudík, M. and Schapire, R.E. (2004) A Maximum Entropy Approach to Species Distribution Modeling. Twenty-First International Conference on Machine Learning, Banff, 4-8 July 2004, 83. [Google Scholar] [CrossRef] 
[28] Loh, W. (2011) Classification and Regression Trees. WIREs Data Mining and Knowledge Discovery, 1, 14-23. [Google Scholar] [CrossRef] 
[29] Linderman, M., Liu, J., Qi, J., An, L., Ouyang, Z., Yang, J., et al. (2004) Using Artificial Neural Networks to Map the Spatial Distribution of Understorey Bamboo from Remote Sensing Data. International Journal of Remote Sensing, 25, 1685-1700. [Google Scholar] [CrossRef] 
[30] 贾一航, 舒会淋, 雷刚, 等. 物种分布模型: 概念类型、建模预测及生态系统管理应用[J/OL]. 中国水土保持科学(中英文), 2025: 1-13.
https://link.cnki.net/urlid/10.1449.S.20250811.1129.002, 2025-12-05.
[31] Biau, G. (2012) Analysis of a Random Forests Model. The Journal of Machine Learning Research, 13, 1063-1095.
[32] 金宇, 周可新, 方颖, 等. 基于随机森林模型预估气候变化对动物物种潜在生境的影响[J]. 生态与农村环境学报, 2014, 30(4): 416-422.
[33] Breiman, L. (2001) Random Forests. Machine Learning, 45, 5-32. [Google Scholar] [CrossRef] 
[34] Buskirk, T.D. (2018) Surveying the Forests and Sampling the Trees: An Overview of Classification and Regression Trees and Random Forests with Applications in Survey Research. Survey Practice, 11, 1-13. [Google Scholar] [CrossRef] 
[35] Garcia, S.C., Kemp, S., Clark, C., Ota, N., Islam, M. and Kriticos, D. (2021) What’s Next for the New Zealand Dairy Feed-Base? Learnings from Climate Analogues. NZGA: Research and Practice Series, 17, 149-162. [Google Scholar] [CrossRef] 
[36] Meyer, R., Sinnett, A., Perera, R., Cullen, B., Malcolm, B. and Eckard, R.J. (2021) The Potential of Deep Roots to Mitigate Impacts of Heatwaves and Declining Rainfall on Pastures in Southeast Australia. Plants, 10, Article 1641. [Google Scholar] [CrossRef] [PubMed]
[37] Streethran, N., Hickey, K., Wingler, A., et al. (2024) ClimAg: Multifactorial Causes of Fodder Crises in Ireland and Risks due to Climate Change. Agricultural Economics, 1-30.
http://www.epa.ie
[38] Yang, J., Huang, Y., Jiang, X., Chen, H., Liu, M. and Wang, R. (2022) Potential Geographical Distribution of the Edangred Plant Isoetes under Human Activities Using Maxent and Garp. Global Ecology and Conservation, 38, e02186. [Google Scholar] [CrossRef] 
[39] 张劳模, 罗鹏, 庞丽峰, 等. 运用最大熵模型和随机森林模型对东北红松分布的模拟[J]. 东北林业大学学报, 2020, 48(3): 60-66.
[40] Zhang, H., Zhou, Y., Ji, X., Wang, Z. and Liu, Z. (2025) Climate Change Drives the Adaptive Distribution and Habitat Fragmentation of Betula Albosinensis Forests in China. Forests, 16, Article 184. [Google Scholar] [CrossRef] 

为你推荐