Details of the Researcher

PHOTO

Peng Zhan
Section
Graduate School of Information Sciences
Job title
Specially Appointed Assistant Professor(Research)
Degree

  • Doctor of Philosophy (Information Sciences) (Tohoku University)

e-Rad No.
81019743
Researcher ID
NAZ-2419-2025

Research History 3

  • 2025/04 - Present
    Tohoku University　Graduate School of Information Sciences　Specially Appointed Assistant Professor

  • 2022/04 - 2025/03
    JST次世代研究者挑戦的研究プログラム

  • 2023/08 - 2024/02
    University of Maryland, College Park　School of Architecture, Planning & Preservation　Visiting Scholar

Education 3

  • Tohoku University　Graduate School of Information Sciences　Department of Human-Social Information Sciences

    2022/04 - 2025/03

  • Tohoku University　Graduate School of Information Sciences　Department of Human-Social Information Sciences

    2020/04 - 2022/03

  • Hohai University　School of Earth Sciences and Engineering　Geographical Information Science

    2015/09 - 2019/04

Research Interests 4

  • Spatial Statistics

  • Spatial analysis

  • Spatial Data Science

  • Geographic Information Science

Research Areas 2

  • Humanities & social sciences / Geography / Geographic Information Science

  • Social infrastructure (civil Engineering, architecture, disaster prevention) / Civil engineering (planning and transportation) /

Awards 2

  1. 第30回地理情報システム学会研究発表大会優秀発表賞

    2021/10　地理情報システム学会

  2. 公益財団法人鹿島育英会奨学生

    2020/06

Papers 9

  1. Modeling spatial variation across data distribution: a Moran eigenvector-based spatially varying quantile regression approach Peer-reviewed

    Zhan Peng, Ryo Inoue

    International Journal of Geographical Information Science　1-29　2025/11/26

    Publisher: Informa UK Limited

    DOI： 10.1080/13658816.2025.2590211 　

    ISSN： 1365-8816

    eISSN： 1362-3087

  2. Can Moran Eigenvectors Improve Machine Learning of Spatial Data? Insights From Synthetic Data Validation Peer-reviewed

    Ziqi Li, Zhan Peng

    Geographical Analysis　2025/10

    DOI： 10.1111/gean.70011 　

    More details Close

    Moran Eigenvector Spatial Filtering (ESF) approaches have shown promise in accounting for spatial effects in statistical models. Can this extend to machine learning? This paper examines the effectiveness of using Moran Eigenvectors as additional spatial features in machine learning models. We generate synthetic datasets with known processes involving spatially varying and nonlinear effects across two different geometries. Moran Eigenvectors calculated from different spatial weights matrices, with and without a priori eigenvector selection, are tested. We assess the performance of popular machine learning models, including Random Forests, LightGBM, XGBoost, and TabNet, and benchmark their accuracies in terms of cross-validated R2 values against models that use only coordinates as features. We also extract coefficients and functions from the models using GeoShapley and compare them with the true processes. Results show that machine learning models using only location coordinates achieve better accuracies than eigenvector-based approaches across various experiments and datasets. Furthermore, we discuss that while these findings are relevant for spatial processes that exhibit positive spatial autocorrelation, they do not necessarily apply when modeling network autocorrelation and cases with negative spatial autocorrelation, where Moran Eigenvectors would still be useful.

  3. Analysing Heterogeneity in Spatial Interactions Using Gravity Models with Spatially Varying Coefficients Peer-reviewed

    Ryo Inoue, Ando Natsuki, Zhan Peng

    2025/06

    DOI： 10.17605/OSF.IO/ABYQH 　

  4. Spatially varying relationships between Metrorail ridership and its determinants in the Washington Metropolitan Area Peer-reviewed

    Zhan Peng, Hiroyuki Iseki

    Transportation Research Board 2025 Annual Meeting (TRB 2025)　2025/01

  5. Multiscale continuous and discrete spatial heterogeneity analysis: The development of a local model combining eigenvector spatial filters and generalized lasso penalties Peer-reviewed

    Zhan Peng, Ryo Inoue

    Geographical Analysis　56　(2)　303-327　2023/09/12

    Publisher: Wiley

    DOI： 10.1111/gean.12375 　

    ISSN： 0016-7363

    eISSN： 1538-4632

    More details Close

    Two types of spatial heterogeneity can exist simultaneously: continuous variations across an entire space and significant changes that occur only in specific spatial units. Moreover, each of these can act across multiple spatial scales. To effectively detect both continuous and discrete spatial heterogeneity across different scales, this study proposes a novel approach that combines the random effects eigenvector spatially filtering‐based spatially varying coefficient (RE‐ESF‐SVC) model and the generalized lasso (GL) technique. Additionally, a restricted maximum likelihood estimation (REML)‐based two‐step iterative algorithm is developed for parameter estimation. Simulation experiments and an empirical application using rental price data confirm the ability of the proposed model to identify multiscale continuous and discrete spatial heterogeneity.

  6. Moran eigenvectors-based spatial heterogeneity analysis for compositional data Peer-reviewed

    Zhan Peng, Ryo Inoue

    Proceedings of 12th International Conference on Geographic Information Science (GIScience 2023)　277　59:1-59:6　2023/09

    DOI： 10.4230/LIPIcs.GIScience.2023.59 　

  7. Spatial heterogeneity analysis from the perspective of data distribution: An eigenvector spatial filtering-based spatially varying quantile regression model Peer-reviewed

    Zhan Peng, Ryo Inoue

    Proceedings of the 18th International Conference on Computational Urban Planning and Urban Management (CUPUM 2023)　2023/06

    DOI： 10.17605/OSF.IO/6YR5V 　

  8. Identifying multiple scales of spatial heterogeneity in housing prices based on eigenvector spatial filtering approaches Peer-reviewed

    Zhan Peng, Ryo Inoue

    ISPRS International Journal of Geo-Information　11　(5)　283-283　2022/04/28

    Publisher: MDPI AG

    DOI： 10.3390/ijgi11050283 　

    eISSN： 2220-9964

    More details Close

    Interest in studying the urban real estate market, especially in investigating the relationship between house prices and related housing characteristics, is rapidly growing. However, this increasing attention is handicapped by a limited consideration of the multi-scale spatial heterogeneity in these relationships. This study uses the rental price data of 72,466 apartments in the Tokyo metropolitan area to examine spatial heterogeneity in the real estate market at multiple spatial scales. Within the framework of spatially varying coefficient (SVC) modeling, we utilized a random effect eigenvector spatial filtering-based SVC (RE-ESF-SVC) model, an approach not previously employed in real estate studies, and compared it with the traditional ESF-SVC model, which has no random effects. Our results show that: (1) except for one housing characteristic that impacts prices consistently throughout the Tokyo metropolitan area, relationships between other characteristics and prices vary from local to global spatial scales; (2) because of the utilization of random effects, RE-ESF-SVC has the unique advantage of making estimations flexibly while maintaining a high performance.

  9. Specifying multi-scale spatial heterogeneity in the rental housing market: The case of the Tokyo metropolitan area Peer-reviewed

    Zhan Peng, Ryo Inoue

    Proceedings of the 11th International Conference on Geographic Information Science (GIScience 2021)　2021/09

    DOI： 10.25436/E2201T 　

Show all ︎Show first 5

Presentations 13

  1. Novel spatially varying coefficient models: Considering heterogeneity in data distribution

    Zhan Peng

    The 13th International Conference on Geographic Information Science (GIScience 2025)　2025/08/27

  2. A Moran eigenvector-based spatially varying quantile regression (MSVQR) model Invited

    Zhan Peng

    The 8th International Conference on Econometrics and Statistics (EcoSta 2025)　2025/08/23

  3. Analyzing heterogeneity in both geographical space and data distribution

    Zhan Peng

    The 19th International Conference on Computational Urban Planning and Urban Management (CUPUM 2025)　2025/06/25

  4. Analyzing spatial heterogeneity of compositional data: A method based on Moran’s eigenvector.

    Zhan Peng, Ryo Inoue

    The 10th edition of the International Workshop on Compositional Data Analysis (CoDaWork2024)　2024/06/05

  5. Disclosing the spatially varying effects of the curbside café design on spatial-temporal bikeshare cycling behavior in Toronto during Pandemic

    Qiwei Song, Zhan Peng, Meikang Li, Waishan Qiu

    The 2024 American Association of Geographers Annual Meeting (AAG 2024)

  6. Understanding the spatially heterogeneous impacts of determinants on metro rail ridership using geographically weighted Poisson regression

    Zhan Peng, Hiroyuki Iseki

    The 2024 American Association of Geographers Annual Meeting (AAG 2024)

  7. A fusion approach to identify spatial heterogeneity of geographic phenomena on multiple spatial scales

    Zhan Peng, Ryo Inoue

    The 16th World Conference of Spatial Econometrics Association (SEA 2022)

  8. Identifying multi-scale spatial heterogeneity in the urban housing market: A fusion approach combining random effects eigenvector spatially filtering-based spatially varying coefficient (RE-ESF-SVC) model with fused LASSO

    Zhan Peng, Ryo Inoue

    The 2022 Association of American Geographers Annual Meeting (AAG 2022)

  9. 価格帯と地域の異質性を考慮した不動産価格決定要因分析

    彭 湛, 井上 亮

    第33回地理情報システム学会研究発表大会

  10. データ構成割合の形成過程が有する空間的異質性分析手法の提案

    彭 湛, 井上 亮

    第69回土木計画学研究発表会・春大会

  11. 組成データの空間的異質性分析手法の提案

    彭 湛, 井上 亮

    第32回地理情報システム学会研究発表大会

  12. データ分布を考慮した空間的異質性分析－固有ベクトル空間フィルタリングに基づく可変係数分位点回帰モデル－組成データの空間的異質性分析手法の提案

    彭 湛, 井上 亮

    第67回土木計画学研究発表会・春大会

  13. 異なるスケールの連続的・離散的な空間的異質性の検出

    彭 湛, 井上 亮

    第 31 回地理情報システム学会研究発表大会

Show all Show first 5