利用多源遥感数据对伊朗针叶人工林的森林地上生物量进行深度和机器学习预测

IF 2.6 2区 农林科学 Q1 FORESTRY
Hassan Ali, Jahangir Mohammadi, Shaban Shataee Jouibary
{"title":"利用多源遥感数据对伊朗针叶人工林的森林地上生物量进行深度和机器学习预测","authors":"Hassan Ali, Jahangir Mohammadi, Shaban Shataee Jouibary","doi":"10.1007/s10342-024-01721-w","DOIUrl":null,"url":null,"abstract":"<p>Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R<sup>2</sup> using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R<sup>2</sup> using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R<sup>2</sup>).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.</p>","PeriodicalId":11996,"journal":{"name":"European Journal of Forest Research","volume":"232 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran\",\"authors\":\"Hassan Ali, Jahangir Mohammadi, Shaban Shataee Jouibary\",\"doi\":\"10.1007/s10342-024-01721-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R<sup>2</sup> using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R<sup>2</sup> using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R<sup>2</sup>).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.</p>\",\"PeriodicalId\":11996,\"journal\":{\"name\":\"European Journal of Forest Research\",\"volume\":\"232 1\",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Forest Research\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1007/s10342-024-01721-w\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"FORESTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Forest Research","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s10342-024-01721-w","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FORESTRY","Score":null,"Total":0}
引用次数: 0

摘要

地上生物量(AGB)是用于估算、监测和评估全球碳储存的最常用森林属性之一。准确估算 AGB 是可持续森林管理、气候政策和管理效率决策中最重要的步骤之一。因此,利用卫星数据开发精确的 AGB 估算模型至关重要。本研究评估了相控阵型 L 波段合成孔径雷达(ALOS-PALSAR)和 SPOT-6 数据利用深度学习(DL)、随机森林(RF)和多元线性回归(MLR)算法在伊朗北部针叶林种植区建立 AGB 模型的能力。采用系统聚类取样法收集田间小块数据。共测量了 180 块圆形地块,以计算每公顷的 AGB。DL 算法、RF 算法和 MLR 算法被用于 AGB 建模。使用 ALOS-PALSAR 数据计算的相对均方根误差(rRMSE)和 R2 分别为:DL 为 21.99% 和 0.21,RF 为 48.46% 和 0.18,MLR 为 50.20% 和 0.11。此外,使用 SPOT-6 数据的 RMSE% 和 R2 分别为:DL 为 18.31% 和 0.44,RF 为 39.64% 和 0.43,MLR 为 44.08% 和 0.38。与分别使用 ALOS-PALSAR 和 SPOT-6 数据建立 AGB 模型相比,ALOS-PALSAR 和 SPOT-6 数据的组合提高了 AGB 预测效果(RMSE% 降低了 1.14-23%,R2 提高了 0.11-0.33)。根据这些结果,我们得出结论,使用 ALOS-PALSAR 和 SPOT-6 数据以及 DL 组合建立 AGB 模型,可用于估计针叶人工林的 AGB。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran

Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran

Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R2 using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R2 using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R2).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.10
自引率
3.60%
发文量
77
审稿时长
6-16 weeks
期刊介绍: The European Journal of Forest Research focuses on publishing innovative results of empirical or model-oriented studies which contribute to the development of broad principles underlying forest ecosystems, their functions and services. Papers which exclusively report methods, models, techniques or case studies are beyond the scope of the journal, while papers on studies at the molecular or cellular level will be considered where they address the relevance of their results to the understanding of ecosystem structure and function. Papers relating to forest operations and forest engineering will be considered if they are tailored within a forest ecosystem context.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信