• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

利用机器学习技术对收获后的赫卡尼亚森林中风暴下树木失效进行建模。

Modeling of trees failure under windstorm in harvested Hyrcanian forests using machine learning techniques.

机构信息

Research Center of Environment and Sustainable Development, College of Environment, Tehran, Iran.

Department of Rangeland Management, College of Natural Resources, University of Tehran, Tehran, Iran.

出版信息

Sci Rep. 2021 Jan 13;11(1):1124. doi: 10.1038/s41598-020-80426-7.

DOI:10.1038/s41598-020-80426-7
PMID:33441895
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7806626/
Abstract

In managed forests, windstorm disturbances reduce the yield of timber by imposing the costs of unscheduled clear-cutting or thinning operations. Hyrcanian forests are affected by permanent winds, with more than 100 km/h which cause damage forest trees and in result of the tree harvesting and gap creation in forest stands, many trees failure accidents happen annually. Using machine learning approaches, we aimed to compare the multi-layer perceptron (MLP) neural network, radial basis function neural network (RBFNN) and support vector machine (SVM) models for identifying susceptible trees in windstorm disturbances. Therefore, we recorded 15 variables in 600 sample plots which are divided into two categories: 1. Stand variables and 2.Tree variables. We developed the tree failure model (TFM) by artificial intelligence techniques such as MLP, RBFNN, and SVM. The MLP model represents the highest accuracy of target trees classification in training (100%), test (93.3%) and all data sets (97.7%). The values of the mean of trees height, tree crown diameter, target tree height are prioritized respectively as the most significant inputs which influence tree susceptibility in windstorm disturbances. The results of MLP modeling defined TFM as a comparative impact assessment model in susceptible tree identification in Hyrcanian forests where the tree failure is in result of the susceptibility of remained trees after wood harvesting. The TFM is applicable in Hyrcanian forest management planning for wood harvesting to decrease the rate of tree failure after wood harvesting and a tree cutting plan could be modified based on designed environmental decision support system tool to reduce the risk of trees failure in wind circulations.

摘要

在管理森林中,风灾干扰通过强加计划外的砍伐或疏伐作业的成本来降低木材产量。咸海森林受到永久风的影响,风速超过 100 公里/小时,会对森林树木造成损害,结果是森林林分中的树木采伐和空隙形成,每年都会发生许多树木倒伏事故。我们使用机器学习方法,旨在比较多层感知器 (MLP) 神经网络、径向基函数神经网络 (RBFNN) 和支持向量机 (SVM) 模型,以识别风灾干扰中的易倒伏树木。因此,我们在 600 个样本中记录了 15 个变量,这些变量分为两类:1. 林分变量和 2. 树木变量。我们通过人工神经网络技术(如 MLP、RBFNN 和 SVM)开发了树木倒伏模型(TFM)。MLP 模型在训练(100%)、测试(93.3%)和所有数据集(97.7%)中表示目标树木分类的最高准确性。树木高度、树冠直径、目标树木高度的平均值的数值被优先视为影响风灾干扰中树木易倒伏性的最重要输入。MLP 建模的结果将 TFM 定义为识别咸海森林中易倒伏树木的比较影响评估模型,其中树木倒伏是由于采伐后剩余树木的易倒伏性所致。TFM适用于咸海森林管理规划中的木材采伐,以降低采伐后树木倒伏率,并且可以根据设计的环境决策支持系统工具修改树木采伐计划,以降低风循环中树木倒伏的风险。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/c7d3e18da6b5/41598_2020_80426_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/9b86ad4eedf8/41598_2020_80426_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/d934221eee36/41598_2020_80426_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/45c69b0eb312/41598_2020_80426_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/23afbcaf5878/41598_2020_80426_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/9aa12fcc62d6/41598_2020_80426_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/4a6c906594ed/41598_2020_80426_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/055b517ab020/41598_2020_80426_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/529cc6a2f315/41598_2020_80426_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/c7d3e18da6b5/41598_2020_80426_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/9b86ad4eedf8/41598_2020_80426_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/d934221eee36/41598_2020_80426_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/45c69b0eb312/41598_2020_80426_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/23afbcaf5878/41598_2020_80426_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/9aa12fcc62d6/41598_2020_80426_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/4a6c906594ed/41598_2020_80426_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/055b517ab020/41598_2020_80426_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/529cc6a2f315/41598_2020_80426_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df67/7806626/c7d3e18da6b5/41598_2020_80426_Fig9_HTML.jpg

相似文献

1
Modeling of trees failure under windstorm in harvested Hyrcanian forests using machine learning techniques.利用机器学习技术对收获后的赫卡尼亚森林中风暴下树木失效进行建模。
Sci Rep. 2021 Jan 13;11(1):1124. doi: 10.1038/s41598-020-80426-7.
2
Fine-scale topographic influence on the spatial distribution of tree species diameter in old-growth beech (Fagus orientalis Lipsky.) forests, northern Iran.细尺度地形对伊朗北部成熟山毛榉(Fagus orientalis Lipsky.)林树种直径空间分布的影响。
Sci Rep. 2022 May 10;12(1):7633. doi: 10.1038/s41598-022-10606-0.
3
Spatial distribution of six managed tree species is influenced by topography conditions in the Central Amazon.在亚马逊中部,六种人工林树种的空间分布受到地形条件的影响。
J Environ Manage. 2021 Mar 1;281:111835. doi: 10.1016/j.jenvman.2020.111835. Epub 2020 Dec 31.
4
Seminal quality prediction using data mining methods.使用数据挖掘方法进行精液质量预测。
Technol Health Care. 2014;22(4):531-45. doi: 10.3233/THC-140816.
5
Aboveground forest carbon shows different responses to fire frequency in harvested and unharvested forests.林冠层碳对火烧频率的响应在有收获和无收获的森林中表现不同。
Ecol Appl. 2019 Jan;29(1):e01815. doi: 10.1002/eap.1815. Epub 2018 Nov 26.
6
Mechanical stability of trees under static loads.树木在静态负载下的机械稳定性。
Am J Bot. 2006 Oct;93(10):1501-11. doi: 10.3732/ajb.93.10.1501.
7
Machine learning prediction of tree species diversity using forest structure and environmental factors: a case study from the Hyrcanian forest, Iran.基于森林结构和环境因素的机器学习对树种多样性的预测:来自伊朗赫卡尼亚森林的案例研究。
Environ Monit Assess. 2023 Oct 18;195(11):1334. doi: 10.1007/s10661-023-11969-1.
8
European forests under global climate change: Review of tree growth processes, crises and management strategies.欧洲森林在全球气候变化下:树木生长过程、危机和管理策略综述。
J Environ Manage. 2023 Apr 15;332:117353. doi: 10.1016/j.jenvman.2023.117353. Epub 2023 Jan 28.
9
Long-term tree inventory data from mountain forest plots in France.法国山地森林样地的长期树木清查数据。
Ecology. 2017 Apr;98(4):1180. doi: 10.1002/ecy.1759.
10
[Competition of key tree species with selective cutting at different intensities in broadleaved-korean pine mixed forest in the Changbai Mountain, China.].[中国长白山阔叶红松混交林不同强度择伐下主要树种的竞争]
Ying Yong Sheng Tai Xue Bao. 2019 May;30(5):1469-1478. doi: 10.13287/j.1001-9332.201905.017.

引用本文的文献

1
Injuries and deaths due to tree failure in The Netherlands: analysis of observational data from 1998-2021.荷兰因树木倒塌导致的伤害和死亡事件分析:1998-2021 年观测数据。
Sci Rep. 2024 Sep 28;14(1):22415. doi: 10.1038/s41598-024-73716-x.
2
Multilayer perceptron and support vector regression models for feline parturition date prediction.用于预测猫分娩日期的多层感知器和支持向量回归模型。
Heliyon. 2024 Mar 15;10(6):e27992. doi: 10.1016/j.heliyon.2024.e27992. eCollection 2024 Mar 30.
3
Clinical decision support system for quality of life among the elderly: an approach using artificial neural network.

本文引用的文献

1
Application of ANN modeling techniques in the prediction of the diameter of PCL/gelatin nanofibers in environmental and medical studies.人工神经网络建模技术在环境与医学研究中预测聚己内酯/明胶纳米纤维直径方面的应用。
RSC Adv. 2019 Aug 12;9(43):24858-24874. doi: 10.1039/c9ra04927d. eCollection 2019 Aug 8.
2
Seed germination prediction of Salvia limbata under ecological stresses in protected areas: an artificial intelligence modeling approach.保护区生态胁迫下丹参种子萌发预测:人工智能建模方法。
BMC Ecol. 2020 Aug 29;20(1):48. doi: 10.1186/s12898-020-00316-4.
3
An Study on Anticonvulsant, Anxiolytic, and Sedative-Hypnotic Effects of the Polyphenol-Rich Extract; Evidence for the Involvement of GABA Receptors.
用于老年人生活质量的临床决策支持系统:一种使用人工神经网络的方法。
BMC Med Inform Decis Mak. 2022 Nov 12;22(1):293. doi: 10.1186/s12911-022-02044-9.
4
Machine Learning Assisted Classification of Aluminum Nitride Thin Film Stress via In-Situ Optical Emission Spectroscopy Data.基于原位光发射光谱数据的机器学习辅助氮化铝薄膜应力分类
Materials (Basel). 2021 Aug 8;14(16):4445. doi: 10.3390/ma14164445.
富含多酚提取物的抗惊厥、抗焦虑和镇静催眠作用研究;γ-氨基丁酸(GABA)受体参与的证据
Iran J Pharm Res. 2019 Summer;18(3):1456-1465. doi: 10.22037/ijpr.2019.15579.13194.
4
MLR and ANN Approaches for Prediction of Synthetic/Natural Nanofibers Diameter in the Environmental and Medical Applications.用于环境和医疗应用中合成/天然纳米纤维直径预测的 MLR 和 ANN 方法。
Sci Rep. 2020 May 15;10(1):8117. doi: 10.1038/s41598-020-65121-x.
5
Landslide spatial modelling using novel bivariate statistical based Naïve Bayes, RBF Classifier, and RBF Network machine learning algorithms.基于新的二元统计的朴素贝叶斯、RBF 分类器和 RBF 网络机器学习算法的滑坡空间建模。
Sci Total Environ. 2019 May 1;663:1-15. doi: 10.1016/j.scitotenv.2019.01.329. Epub 2019 Jan 26.
6
Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China.运用遗传算法确定基于数据挖掘模型的森林火灾相关变量的最优组合,并对森林火灾易发性进行建模。以中国大禹县为例。
Sci Total Environ. 2018 Jul 15;630:1044-1056. doi: 10.1016/j.scitotenv.2018.02.278. Epub 2018 Mar 7.
7
Increasing forest disturbances in Europe and their impact on carbon storage.欧洲森林干扰的增加及其对碳储存的影响。
Nat Clim Chang. 2014 Sep 1;4(9):806-810. doi: 10.1038/nclimate2318.
8
Deep learning in neural networks: an overview.神经网络中的深度学习:综述。
Neural Netw. 2015 Jan;61:85-117. doi: 10.1016/j.neunet.2014.09.003. Epub 2014 Oct 13.
9
A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing.一种基于径向基函数分类器和进化模拟退火的医学诊断工具。
J Biomed Inform. 2014 Jun;49:61-72. doi: 10.1016/j.jbi.2014.03.008. Epub 2014 Mar 21.
10
Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes.使用人工神经网络与逻辑回归预测医学结果的优缺点。
J Clin Epidemiol. 1996 Nov;49(11):1225-31. doi: 10.1016/s0895-4356(96)00002-9.