Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University
Forest resources mapping is a prerequisite for sustainable forest management. Site productivity is a key indicator of forest ecosystem services like wood production, carbon sequestration, etc. Due to the extent of Hyrcanian forests and mountainous areas in these forests that are sometimes difficult...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | fas |
Published: |
Iranian Society of Forestry
2018-01-01
|
Series: | مجله جنگل ایران |
Subjects: | |
Online Access: | http://www.ijf-isaforestry.ir/article_57291_2c3593a2223854f92088d73362996b9e.pdf |
id |
doaj-e00a7e26250741f4890c079a3c6e110a |
---|---|
record_format |
Article |
spelling |
doaj-e00a7e26250741f4890c079a3c6e110a2021-06-26T07:03:05ZfasIranian Society of Forestryمجله جنگل ایران2008-61132423-44352018-01-019457158557291Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares UniversityZahra Ahadi0S.J. Alavi1Seyed Mohsen Hosseini2M.Sc. Student, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, I. R. IranAssistant Prof., Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, I. R. IranProfessor, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, I. R. IranForest resources mapping is a prerequisite for sustainable forest management. Site productivity is a key indicator of forest ecosystem services like wood production, carbon sequestration, etc. Due to the extent of Hyrcanian forests and mountainous areas in these forests that are sometimes difficult to access, it seems necessary to find suitable methods for mapping the quantitative parameters in these forests. In this study, site form index which is the most reliable criterion for evaluating site productivity of mixed and uneven stands was used. This study aims at mapping beech forest site productivity by using regression kriging in research forest of Tarbiat Modares University. For this purpose, 123 0.1 ha circular sample plots were laid out in beech dominated stands. The height and diameter of beech trees with DBH ≥ 7.5 cm within each plot was recorded. Some primary and secondary variables were also extracted from DEM in sample plots to be used in regression kriging. We investigated the differences between two predictive approaches: random forests and linear regression as the base model for regression kriging technique. Results of 10-fold cross-validation demonstrate that by using criteria such as mean error, mean absolute error, root mean square error, relative mean error, relative root mean square error, the random forests algorithm outperforms the linear regression and kriging techniques, with average decreases of ca. 70% in Root Mean Squared Error (RMSE). Hence, the regression kriging technique with random forest as the base model is recommended in order to better understand the more complex environment-beech forest site productivity relationships.http://www.ijf-isaforestry.ir/article_57291_2c3593a2223854f92088d73362996b9e.pdfgeostatisticsinterpolationkrigingmachine learningrandom forestregression |
collection |
DOAJ |
language |
fas |
format |
Article |
sources |
DOAJ |
author |
Zahra Ahadi S.J. Alavi Seyed Mohsen Hosseini |
spellingShingle |
Zahra Ahadi S.J. Alavi Seyed Mohsen Hosseini Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University مجله جنگل ایران geostatistics interpolation kriging machine learning random forest regression |
author_facet |
Zahra Ahadi S.J. Alavi Seyed Mohsen Hosseini |
author_sort |
Zahra Ahadi |
title |
Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University |
title_short |
Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University |
title_full |
Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University |
title_fullStr |
Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University |
title_full_unstemmed |
Investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of Tarbiat Modares University |
title_sort |
investigation on the potential of regression kriging for mapping oriental beech forest site productivity in research forest of tarbiat modares university |
publisher |
Iranian Society of Forestry |
series |
مجله جنگل ایران |
issn |
2008-6113 2423-4435 |
publishDate |
2018-01-01 |
description |
Forest resources mapping is a prerequisite for sustainable forest management. Site productivity is a key indicator of forest ecosystem services like wood production, carbon sequestration, etc. Due to the extent of Hyrcanian forests and mountainous areas in these forests that are sometimes difficult to access, it seems necessary to find suitable methods for mapping the quantitative parameters in these forests. In this study, site form index which is the most reliable criterion for evaluating site productivity of mixed and uneven stands was used. This study aims at mapping beech forest site productivity by using regression kriging in research forest of Tarbiat Modares University. For this purpose, 123 0.1 ha circular sample plots were laid out in beech dominated stands. The height and diameter of beech trees with DBH ≥ 7.5 cm within each plot was recorded. Some primary and secondary variables were also extracted from DEM in sample plots to be used in regression kriging. We investigated the differences between two predictive approaches: random forests and linear regression as the base model for regression kriging technique. Results of 10-fold cross-validation demonstrate that by using criteria such as mean error, mean absolute error, root mean square error, relative mean error, relative root mean square error, the random forests algorithm outperforms the linear regression and kriging techniques, with average decreases of ca. 70% in Root Mean Squared Error (RMSE). Hence, the regression kriging technique with random forest as the base model is recommended in order to better understand the more complex environment-beech forest site productivity relationships. |
topic |
geostatistics interpolation kriging machine learning random forest regression |
url |
http://www.ijf-isaforestry.ir/article_57291_2c3593a2223854f92088d73362996b9e.pdf |
work_keys_str_mv |
AT zahraahadi investigationonthepotentialofregressionkrigingformappingorientalbeechforestsiteproductivityinresearchforestoftarbiatmodaresuniversity AT sjalavi investigationonthepotentialofregressionkrigingformappingorientalbeechforestsiteproductivityinresearchforestoftarbiatmodaresuniversity AT seyedmohsenhosseini investigationonthepotentialofregressionkrigingformappingorientalbeechforestsiteproductivityinresearchforestoftarbiatmodaresuniversity |
_version_ |
1721359177152987136 |