中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
An entropogram-based Random Field model for categorical geospatial data prediction

文献类型：期刊论文

作者Zhang, Wen-Bin1,2,3; Ge, Yong2; Wan, Xuan2; Lai, Shengjie3; Atkinson, Peter M.1
刊名INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
出版日期2026-03-29
卷号N/A
关键词Entropogram categorical geospatial data geostatistics
ISSN号1365-8816
DOI10.1080/13658816.2026.2650365
产权排序2
文献子类Article ; Early Access
英文摘要Categorical geospatial data underpin applications from biodiversity monitoring to land-use planning, yet existing approaches often fail to recover rare classes while preserving realistic patch structures. We introduced an Entropogram-based Random Field (ERF) model that integrates intrinsic randomness from local class probabilities with entropogram-derived spatial dependence, balancing local class proportions with global neighborhood associations. Using a 10-class, 1-km land-cover map of Northern Ireland, we compared ERF against Indicator Kriging (IK), multi-phase Indicator Kriging (MIK), Compositional Data Analysis (CoDA) and a spatial multinomial logistic (SMLM) model. ERF matches IK and MIK in overall accuracy but achieves higher recall and F1 scores for minority classes, reducing the loss of small, coherent patches. While CoDA ensures compositional validity, it underperforms on rare classes and increases spatial aggregation; MIK improves rare-class recovery but still favors dominant types. SMLM performs comparably to ERF but with far higher computational demand. Landscape metrics showed that ERF and SMLM best preserved patch diversity and realistic geometry, whereas IK and CoDA produced more aggregated patterns. Together, these results highlight ERF as a computationally efficient, scalable and balanced solution for categorical mapping, particularly in applications where minority-class recovery and spatial realism are critical for biodiversity monitoring, habitat connectivity and land-use planning.
URL标识查看原文
WOS关键词CHAIN RANDOM-FIELDS ; SIMULATION
WOS研究方向Computer Science ; Geography ; Physical Geography ; Information Science & Library Science
语种英语
WOS记录号WOS:001728682900001
出版者TAYLOR & FRANCIS LTD
源URL[http://ir.igsnrr.ac.cn/handle/311030/221570]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Zhang, Wen-Bin
作者单位1.Univ Lancaster, Fac Sci & Technol, Lancaster Environm Ctr, Lancaster, England
2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China;
3.Univ Southampton, Sch Geog & Environm Sci, WorldPop, Southampton, England;
推荐引用方式
GB/T 7714		 Zhang, Wen-Bin,Ge, Yong,Wan, Xuan,et al. An entropogram-based Random Field model for categorical geospatial data prediction[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2026,N/A.
APA Zhang, Wen-Bin,Ge, Yong,Wan, Xuan,Lai, Shengjie,&Atkinson, Peter M..(2026).An entropogram-based Random Field model for categorical geospatial data prediction.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,N/A.
MLA Zhang, Wen-Bin,et al."An entropogram-based Random Field model for categorical geospatial data prediction".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE N/A(2026).

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。