Export

Link to this page

Please use this URL for citations.

Search Other Services

Statistics

  • Access to this page：6,273 times

＜departmental bulletin paper＞
Assessing Effective Sampling Method and Sample Size for Species Distribution Modeling of Korean Red Pine (Pinus densiflora)

Creator
Creator Name
SUNG, Sun–Yong
Affiliation
Affiliation Name
Interdisciplinary Program in Landscape Architecture, Seoul National University, Seoul | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
LEE, Dong–Kun
Affiliation
Affiliation Name
Department of Landscape Architecture and Rural Systems, Engineering, Seoul National University | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
PARK, Chan
Affiliation
Affiliation Name
Department of Landscape Architecture, University of Seoul | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
KIM, Ho–Gul
Affiliation
Affiliation Name
Division of Human Environmental Design, Cheongju University | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
KIL, Sung–Ho
Affiliation
Affiliation Name
Department of Ecological Landscape Architecture Design, Kangwon National University | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
CHAE, Hee–Mun
Affiliation
Affiliation Name
Department of Forest Environment Protection, Kangwon National University | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Creator Name
PARK, Gwan–Soo
Affiliation
Affiliation Name
Department of Forest Resources, Chungnam National University | Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
Author PID
K001681
Creator Name
OHGA, Shoji
大賀, 祥治
オオガ, ショウジ
Affiliation
Affiliation Name
Laboratory of Forest Resources Management, Division of Forest Environmental Sciences, Department of Agro–Environmental Sciences, Faculty of Agriculture, Kyushu University
九州大学大学院農学研究院環境農学部門 : 教授
Language
English
Publisher
Faculty of Agriculture, Kyushu University
九州大学大学院農学研究院
Date
2018-09-01
Source Title
Journal of the Faculty of Agriculture, Kyushu University
Vol
63
Issue
2
First Page
211
Last Page
221
Publication Type
Version of Record
Access Rights
open access
Crossref DOI
https://doi.org/10.5109/1955384

Hide fulltext details.

pdf p212 pdf 2.09 MB 743  

Details

PISSN
0023-6152
NCID
AA00697606
Record ID
1955384
Subject Terms
Area–weighted sampling
BIOMOD2
Analysis of variance
Korean red pine
Notes
Sampling method and sample size can alter the performance of species distribution models (SDMs). In this study, we identified an effective sampling method and sample size for modeling Korean red pine (Pinus densiflora). We used 3 sampling methods (simple random sampling, stratified sampling, and area– weighted sampling), 7 different sample sizes (30, 50, 100, 200, 500, 1000, and 3000), and 8 SDMs (GLM, GAM, CTA, ANN, GBM, RF, FDA, and MAXENT). The performance of each model was evaluated using the area under the receiver operating characteristic curve. Differences among the models were validated using ANOVA. We found that the area–weighted sampling method was the most effective and stable. As sample size increased, model performance increased in the random and stratified sampling methods. However, performance became saturated as sample size exceeded 200 in the area–weighted sample due to spatial autocorrelation among samples. All models exhibited different levels of performance. The RF and GBM models exhibited the highest performance (AUC = 0.838 and 0.839, respectively), while the ANN model exhibited the lowest performance (AUC = 0.658). Therefore, sampling method and sample size should be carefully considered when selecting SDMs depending on the objective of the study
Created Date 2018.09.04
Modified Date 2022.11.11

People who viewed this item also viewed