数字农科院2.0

Integrating explainable machine learning to predict the ecological niche distribution of Cytospora chrysosperma in Xinjiang, China

文献类型： 外文期刊

作者： Quansheng Li;Ruixia Hou;Xianhua Zhang;Shanshan Cao;Wei Sun

作者机构：

关键词： Cytospora chrysosperma;Ecological niche modeling;Environmental thresholds;Machine learning;Model interpretability;SHAP analysis;Threshold interaction network

期刊名称： Forest Ecology and Management

ISSN： 0378-1127

年卷期： 2025 年 595 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Cytospora chrysosperma is a significant pathogenic fungus threatening forest trees in Xinjiang, causing substantial economic and ecological losses. Understanding its ecological niche distribution is crucial for developing effective control strategies, yet traditional models often lack interpretability. This study addresses these limitations by integrating five machine learning algorithms with SHAP (SHapley Additive exPlanation) methodology to predict and interpret the potential distribution of C. chrysosperma in Xinjiang, introducing the novel concept of a “threshold interaction network” for interpretable ecological niche modeling. We collected 545 presence records and generated 600 pseudo-absence points, selecting bioclimatic variables, topography, and NDVI as environmental predictors through stepwise feature selection, with model performance evaluated using both conventional and spatial block cross-validation approaches. All models performed well, with Random Forest demonstrating superior overall performance. SHAP analysis revealed critical ecological thresholds: vegetation condition (NDVI ≈ 0.15), precipitation seasonality (bio15 ≈ 73), mean temperature of the warmest quarter (bio10 ≈ 21°C), and elevation (≈ 1504 m) as key determinants of pathogen distribution, while interaction analysis discovered significant synergistic effects between environmental factors, with areas characterized by NDVI > 0.15 and bio15 < 73 representing the highest risk zones. Bootstrap analysis confirmed threshold stability (optimal classification threshold: 0.4905), enabling robust risk assessment with spatially differentiated maps identifying high-risk areas such as Tacheng and Yili regions for targeted management. This study establishes a new paradigm for interpretable ecological niche modeling by demonstrating how environmental factors collaboratively influence pathogen distribution through quantifiable threshold relationships, while providing forest managers with actionable, threshold-based intervention guidelines.

分类号：

  • 相关文献

[1]Predicting municipal solid waste gasification using machine learning: A step toward sustainable regional planning. Yadong Yang,Hossein Shahbeik,Alireza Shafizadeh,Shahin Rafiee,Amir Hafezi,Xinyi Du,Junting Pan,Meisam Tabatabaei,Mortaza Aghbashlo. 2023

[2]Targeted prediction of sensory preference for fermented pomegranate juice based on machine learning. Wenhui Zou,Fei Pan,Junjie Yi,Wenjun Peng,Wenli Tian,Linyan Zhou. 2024

[3]Prediction of the potential geographical distribution of Cytospora chrysosperma in Xinjiang, China under climate change scenarios. Quansheng Li,Shanshan Cao,Wei Sun,Zhiyong Zhang. 2024

[4]Multiple drivers synergistically shape the genetic differentiation pattern and invasion potential of Bactrocera umbrosa. Zhang, Yu,Wan, Weijie,Yang, Tianying,Cao, Fengqin,Cai, Bo,Francis, Frederic,Xian, Xiaoqing,Liu, Wanxue. 2025

[5]Machine learning assisted analysis: inorganic catalyzed hydrothermal carbonization to enhance biomass carbon stability. 晏婷,,张哲,,张哲睿,,王文赞,,张明震,,朱志平. 2025

[6]Machine learning assisted analysis: inorganic catalyzed hydrothermal carbonization to enhance biomass carbon stability. 晏婷,,张哲,,张哲睿,,王文赞,,张明震,,朱志平. 2025

[7]Evolutionarily Informed Deep Learning Methods F.or Predicting Relative Transcript A bundance From Dna Sequence. Washburn, Jacob D.,Wang, Hai,Wang, Hai,Wang, Hai,Valluru, Ravi,Ramstein, Guillaume,Mejia-Guerra, Maria Katherine,Kremling, Karl A.,Wang, Hai,Buckler, Edward S.,Buckler, Edward S.. 2019

[8]Using Machine Learning in Environmental Tax Reform Assessment for Sustainable Development: A Case Study of Hubei Province, China. Zheng, Yinger,Zheng, Yinger,Zheng, Haixia,Zheng, Haixia,Ye, Xinyue. 2016

[9]Determination of internal qualities of Newhall navel oranges based on NIR spectroscopy using machine learning. Liu, Cong,Yang, Simon X.,Liu, Cong,Deng, Lie.

[10]A comparative study for least angle regression on NIR spectra analysis to determine internal qualities of navel oranges. Liu, Cong,Yang, Simon X.,Liu, Cong,Deng, Lie. 2015

[11]Using evolutionary machine learning to characterize and optimize co-pyrolysis of biomass feedstocks and polymeric wastes. Shahbeik H.,Shafizadeh A.,Nadian M.H.,Jeddi D.,Mirjalili S.,Yang Y.,Lam S.S.,Pan J.,Tabatabaei M.,Aghbashlo M.. 2023

[12]Virtual screening strategy for anti-DPP-IV natural flavonoid derivatives based on machine learning. Lu, Gen,Pan, Fei,Li, Xiaotong,Zhu, Zehui,Zhao, Lei,Wu, Ya,Tian, Wenli,Peng, Wenjun,Liu, Jinling. 2023

[13]Effects of different floral periods and environmental factors on royal jelly identification by stable isotopes and machine learning analyses during non-migratory beekeeping. Zhaolong Liu,Xin Yin,Hongxia Li,Dong Qiao,Lanzhen Chen. 2023

[14]Several models combined with ultrasound techniques to predict breast muscle weight in broilers. Zhengda Li,Jumei Zheng,Bingxing An,Xiaochun Ma,Fan Ying,Fuli Kong,Jie Wen,Guiping Zhao. 2023

[15]Ecosystem responses dominate the trends of annual gross primary productivity over terrestrial ecosystems of China during 2000–2020. Xian Jin Zhu,Gui Rui Yu,Zhi Chen,Wei Kang Zhang,Lang Han,Qiu Feng Wang,Hua Qi,Meng Yang,Zhao Gang Liu,Xiao Jun Dou,Le Xin Ma,Shi Ping Chen,Shao Min Liu,Hui Min Wang,Jun Hua Yan,Jun Lei Tan,Fa Wei Zhang,Feng Hua Zhao,Ying Nian Li,Yi Ping Zhang,Pei Li Shi,Jiao Jun Zhu,Jia Bing Wu,Zhong Hui Zhao,Yan Bin Hao,Li Qing Sha,Yu Cui Zhang,Shi Cheng Jiang,Feng Xue Gu,Zhi Xiang Wu,Yang Jian Zhang,Li Zhou,Ya Kun Tang,Bing Rui Jia,Yu Qiang Li,Qing Hai Song,Gang Dong,Yan Hong Gao,Zheng De Jiang,Dan Sun,Jian Lin Wang,Qi Hua He,Xin Hu Li,Fei Wang,Wen Xue Wei,Zheng Miao Deng,Xiang Xiang Hao,Xiao Li Liu,Xi Feng Zhang,Zhi Lin Zhu. 2023

[16]Advances in the Study of Biochemical, Morphological and Physiological Traits of Wheat and Sorghum Crops in Australia Using Hyperspectral Data and Machine Learning. A. B. Potgieter,C. Camino,T. Poblete,X. Zhi,S. Reynolds-Massey-Reed,Y. Zhao,A. Belwalkar,J. Ruizhu,B. George-Jaeggli,S. Chapman,D. Jordan,A. Wu,G. L. Hammer,P. J. Zarco-Tejada. 2023

[17]Rapid and Non-Invasive Assessment of Texture Profile Analysis of Common Carp (Cyprinus carpio L.) Using Hyperspectral Imaging and Machine Learning. Yi Ming Cao,Yan Zhang,Shuang Ting Yu,Kai Kuo Wang,Ying Jie Chen,Zi Ming Xu,Zi Yao Ma,Hong Lu Chen,Qi Wang,Ran Zhao,Xiao Qing Sun,Jiong Tang Li. 2023

[18]Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization. Liang, Mang,An, Bingxing,Li, Keanning,Du, Lili,Deng, Tianyu,Cao, Sheng,Du, Yueying,Xu, Lingyang,Gao, Xue,Zhang, Lupei,Li, Junya,Gao, Huijiang. 2022

[19]Enhancing leaf area index and biomass estimation in maize with feature augmentation from unmanned aerial vehicle-based nadir and cross-circling oblique photography. Shuaipeng Fei,Shunfu Xiao,Qing Li,Meiyan Shu,Weiguang Zhai,Yonggui Xiao,Zhen Chen,Helong Yu,Yuntao Ma. 2023

[20]Biomass microwave pyrolysis characterization by machine learning for sustainable rural biorefineries. Yadong Yang,Hossein Shahbeik,Alireza Shafizadeh,Nima Masoudnia,Shahin Rafiee,Yijia Zhang,Junting Pan,Meisam Tabatabaei,Mortaza Aghbashlo. 2022

作者其他论文 更多>>