[1]郝泉龄,徐国祺*,王立海,等.基于Logistic回归模型的红松立木腐朽分级预测[J].南京林业大学学报(自然科学版),2020,44(02):150-158.[doi:10.3969/j.issn.1000-2006.201903017.]
 HAO Quanling,XU Guoqi*,WANG Lihai,et al.Logistic regression-based prediction of wood decay in standing Korean pine(Pinus koreiensis)[J].Journal of Nanjing Forestry University(Natural Science Edition),2020,44(02):150-158.[doi:10.3969/j.issn.1000-2006.201903017.]
点击复制

基于Logistic回归模型的红松立木腐朽分级预测
分享到:

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

卷:
44
期数:
2020年02期
页码:
150-158
栏目:
研究论文
出版日期:
2020-03-31

文章信息/Info

Title:
Logistic regression-based prediction of wood decay in standing Korean pine(Pinus koreiensis)
文章编号:
1000-2006(2020)02-0150-09
作者:
郝泉龄1徐国祺1*王立海2时小龙1许明贤1纪文文1张广晖1
(1.东北林业大学工程技术学院,黑龙江 哈尔滨 150040; 2.东北林业大学,森林持续经营与环境微生物工程黑龙江省重点实验室,黑龙江 哈尔滨 150040)
Author(s):
HAO Quanling1 XU Guoqi1* WANG Lihai2 SHI Xiaolong1 XU Mingxian1 JI Wenwen1 ZHANG Guanghui1
(1.College of Engineering and Technology, Northeast Forestry University, Harbin 150040, China; 2.Key Laboratory of Forest Sustainable Management and Environmental Microorganism Engineering of Heilongjiang Province, Northeast Forestry University, Harbin 150040, China)
关键词:
红松 腐朽程度 无损检测 ERT图像处理 多分类有序Logistic回归 概率预测模型
Keywords:
Korean pine decay grade nondestructive testing ERT image identify multi-category ordered-dependent-variable Logistic regression probabilistic prediction model
分类号:
S791.247
DOI:
10.3969/j.issn.1000-2006.201903017.
文献标志码:
A
摘要:
【目的】红松活立木在生长过程中极易受到各种生物的侵袭,其中木腐菌造成的腐朽是最为广泛和严重的危害之一,活立木腐朽将会造成木材资源的损失,降低木材的力学性能。为了监测红松活立木的健康状况,减少因腐朽引起的相关损失,须定期检测红松活立木腐朽状况,并采用腐朽分级的方法进行评估。【方法】使用阻抗仪和电阻断层成像技术(ERT)两种无损检测手段对黑龙江省五营国家森林公园内的红松活立木进行检测,并在检测截面使用生长锥钻取木芯。将野外测量数据导入电脑,获取立木的阻力曲线和电阻断层图像,分析处理微针阻力的下降幅度,得到样木的阻力损失;根据立木心材与边材腐朽在ERT图像上呈现的不同特征,首次采用一种基于OpenCV的图像处理技术识别腐朽样木电阻断层图像缺陷部分,实现了心材和边材缺陷面积的定量表征;采用烘干法测定质量损失率,根据每株样木的质量损失率将所有样木分为5个腐朽等级。将多分类有序因变量的Logistic回归分析引入到立木腐朽程度分级问题中,以阻力损失、心材缺陷面积比和边材缺陷面积比为自变量,腐朽等级为因变量,建立腐朽分级预测模型。检验模型的有效性、拟合优度及预测能力。【结果】Logistic回归模型性能良好,五营国家森林公园30株红松样木的综合预测准确率为86.67%,各等级预测准确率分布不均,高等级腐朽的预测准确率相对较高。【结论】运用提取心材与边材腐朽的方法处理ERT图像,有效地提高了利用ERT图像识别腐朽的准确率。建立Logistic回归模型可以较准确地预测出立木腐朽的等级,较之烘干法测定腐朽程度,其腐朽评估效率有了明显提高,且对立木损伤更小
Abstract:
【Objective】The Korean pine(Pinus koraiensis)is an ancient and valuable tree species with high research value. Living Korean pine trees are prone to attack by various organisms during their growth; the decay caused by wood rot fungi is one of the most extensive and serious growth hazards. The decay of living wood results in the loss of wood resources and reduces the mechanical properties of the wood. To monitor the health status of Korean pine trees and reduce the loss caused by rotting, the decay status of Korean pine was detected periodically and evaluated by the method of decay grading. 【Method】Thirty standing Korean pine trees in Wuying National Forest Park of Heilongjiang Province were tested using a resistograph and electrical resistance tomography(ERT). The cores drilling were made at the same section to obtain the resistograph readings. The field measurement data were imported into a computer and the resistance curve and resistance tomography images were obtained. After analyzing and processing the drop range of the microneedle resistance, the resistance loss of the sample wood was obtained. According to the different characteristics presented by the decayed heartwood and sapwood in the ERT images, an image processing technique based on OpenCV was used to identify the defected part of the resistance tomographic image of the decayed sample wood; further, quantitative characterization of the defected area of the heartwood and sapwood was performed. The defect area ratios of the heartwood and sapwood were calculated separately. The mass loss rate was determined using the drying method. According to the mass loss rate of each sample wood, all samples were divided into five decadent grades. Multi-category ordered-dependent-variable Logistic regression was introduced into the decay grade classification of the standing trees. The prediction model of decay classification was established by considering resistance loss, area ratio of heartwood defect, and area ratio of sapwood defect as independent variables and the decay grade as the dependent variable. The validity, goodness of fit, and prediction ability of the model were tested.【Result】The performance of the Logistic regression model was good. The comprehensive prediction accuracy of the thirty Korean pine trees was 86.67%, and the accuracy rate of each grade prediction was uneven. The prediction accuracy of high-grade decay was relatively high. 【Conclusion】The Logistic regression model could accurately predict the rank of decay in standing trees. Compared with the drying method, the evaluation efficiency of Logistic regression model was higher and the damage to the standing trees was less

参考文献/References:


[1] 兰思仁,戴永务,沈必胜.中国森林公园和森林旅游的三十年[J].林业经济问题,2014,34(2):97-106. LAN S R,DAI Y W,SHEN B S.Three decades of forest park and forest tourism in China[J].Issues For Econ,2014,34(2):97-106.DOI:10.16832/j.cnki.1005-9709.2014.02.001.
[2] 王兴国,王建军.森林公园与生态旅游[J].旅游学刊,1998,13(2):15-18,61. WANG X G,WANG J J.Forest parks and ecological tourism[J].Tour Tribune,1998,13(2):15-18,61.
[3] 杨财根.基于休闲旅游的城郊森林公园旅游规划研究[D].南京:南京林业大学,2009. YANG C G.Study on tourism planning of forest park in city and its suburb[D].Nanjing:Nanjing Forestry University,2009.
[4] SMITH K, SHORTIE W. A first look at tree decay an introduction to how injury and decay affect trees[R]. Northeastern Area, State and Private Forestry, NA-PR-02-98.
[5] 吴福社. 树木无损检测方法和安全性评估初探[D]. 合肥:安徽农业大学,2011. WU F S. Preliminary study on non-destructive method and safety assessment of tree[D]. Hefei:Anhui Agricultural University,2011.
[6] 王立海,杨学春,徐凯宏.木材无损检测技术的研究现状与进展[J].森林工程,2001,17(6):1-3. WANG L H,YANG X C,XU K H.Current situations and research development of non-destructive testing for wood properties[J].For Eng,2001,17(6):1-3.DOI:10.3969/j.issn.1001-005X.2001.06.001.
[7] ZAHNER V,SIKORA L,PASINELLI G.Heart rot as a key factor for cavity tree selection in the black woodpecker[J].For Ecol Manag, 2012, 271: 98-103. DOI: 10.1016/j.foreco.2012.01.041.
[8] 孙天用.小兴安岭红松活立木树干腐朽定量检测及与立地条件关系[D].哈尔滨:东北林业大学,2015. SUN T Y.Quantitative detection for the degree of decay inside trunks of Korean pine live standing trees and relationships between the degree of decay and site conditons in Xiaoxinganling Mountains[D].Harbin: Northeast Forestry University,2015.
[9] WEIHS U, DUBBEL V, KRUMMHEUER F, et al. The electrical resistivity tomography: a promising technique for the detection of colored heart wood on standing beech trees[J]. Forst Und Holz, 1999,54:166-170.
[10] 岳小泉,王立海,王兴龙,等.电阻断层成像、应力波及阻抗仪3种无损检测方法对活立木腐朽程度的定量检测[J].林业科学,2017,53(3):138-146. YUE X Q,WANG L H,WANG X L,et al.Quantitative detection of internal decay degree for standing trees based on three NDT methods:electric resistance tomography,stress wave imaging and resistograph techniques[J].Sci Silvae Sin,2017,53(3):138-146.
[11] 李央央.福州古树名木健康状况调查及木材腐朽菌的研究[D].福州:福建农林大学,2014. LI Y Y.Health survey and wood-decay fungi investigation of old and valuable trees in Fuzhou[D].Fuzhou:Fujian Agriculture and Forestry University,2014.
[12] 葛晓雯.腐朽对杨树木材及活立木干基截面弯曲特性的影响[D].哈尔滨:东北林业大学,2017. GE X W.Effects of decay on section bending properties of poplar wood and trunks of standing trees[D].Harbin:Northeast Forestry University,2017.
[13] 袁慧,姚应水,金岳龙.急性白血病危险因素的多元Logistic回归分析[J].中国公共卫生,2004,20(11):1328-1329. YUAN H,YAO Y S,JIN Y L.Logistic regression analysis on risk factors of acute leukemia[J].China Public Heal,2004,20(11):1328-1329.
[14] 彭寿康.分层抽样条件下Logistic回归模型的参数估计方法[J].统计研究,2002,19(11):24-27. PENG S K.Parameter estimation method of Logistic regression model in the condition of stratum sample survey[J].Stat Res, 2002, 19(11): 24-27. DOI: 10.19343/ j.cnki.11-1302/c.2002.11.006.
[15] 熊巍,赵海娟,程红莉.累积Logistic 回归在企业竞争力评价中的应用[J].统计与信息论坛,2004,19(1):85-88. XIONG W,ZHAO H J,CHENG H L.Application of cumulative Logistic regression in evaluation of enterprise compet itive power[J].Stat Inf Tribune,2004,19(1):85-88.DOI:10.3969/j.issn.1007-3116.2004.01.023.
[16] 于立勇,詹捷辉.基于Logistic回归分析的违约概率预测研究[J].财经研究,2004,30(9):15-23. YU L Y,ZHAN J H.A research on probability of default prediction based on Logistic regression analysis[J].J Finance Econ,2004,30(9):15-23.DOI:10.3969/j.issn.1001-9952.2004.09.002.
[17] 黄茂祝,徐波,张杰,等.五营国家森林公园游憩价值评价研究[J].中国林业经济,2009(5):25-28. HUANG M Z,XU B,ZHANG J,et al. Research of evaluation of recreation value of Wuying National Forest Park[J]. China For Econ, 2009(5):25-28.DOI: 10.3969/j.issn. 1673-5919.2009.05.007.
[18] 黄茂祝.伊春区域生态旅游资源评价及开发对策研究[D].哈尔滨:东北林业大学,2006. HUANG M Z. Evaluation and development strategy research on eco-tourism resources of Yichun region[D]. Harbin:Northeast Forestry University,2006.
[19] 张杰,贾小换,高庆国.黑龙江省伊春市五营国家森林公园负离子研究[J].哈尔滨师范大学自然科学学报,2007,23(4):89-92,102. ZHANG J,JIA X H,GAO Q G.The correlative study on negative air ion in the Wuying National Forest Park of Yichun City,Heilongjiang[J].Nat Sci J Harbin Norm Univ,2007,23(4):89-92,102.
[20] 宋国华,毕连柱,张华,等.红松针阔混交林空间格局分布及保护重要性——以黑龙江丰林自然林保护区为例[J].林业经济,2009(11):46-48. SONG G H, BI L Z, ZHANG H, et al. Korean pine needles mixed broad spatial pattern distribution and the importance of protection: a case study of Fenglin Nature Reserve of Heilongjiang Province[J]. Forestry Economics, 2009(11):46-48.
[21] 时小龙,王立海,徐华东,等. 基于阻抗仪和ERT技术的红松内部腐朽定量检测[J].北京林业大学学报, 2017, 39(9): 102-111. SHI X L, WANG L H, XU H D, et al. Quantitative characterization of decay detection in standing trees of Korean pine based on Resistograph and ERT[J].Journal of Beijing Forestry University, 2017, 39(9):102-111. DOI:10.13332/ j.1000- 1522.20170196.
[22] 吴华桥,周启友,刘汉乐.树干水分分布及运移的高密度电阻率成像法时空监测[J].地球物理学进展,2008,23(4):1310-1316. WU H Q,ZHOU Q Y,LIU H L.Temporal and spatial monitoring of water distribution and migration in a tree trunk using electrical resistivity tomography[J].Prog Geophys,2008,23(4):1310-1316.
[23] 王兴龙,王立海.白桦模拟缺陷材的电阻层析成像规律探究[J].林业工程学报,2016,1(2):106-111. WANG X L,WANG L H.Research on electrical resistance tomography of birch logs with artificial simulating defects[J].China For Sci Technol,2016,1(2):106-111.DOI:10.13360/j.issn.2096-1359.2016.02.019.

相似文献/References:

[1]陈永亮,韩士杰.应用电子探针研究苗木根土界面元素微区分布[J].南京林业大学学报(自然科学版),2009,33(03):065.[doi:10.3969/j.jssn.1000-2006.2009.03.015]
 CHEN Yong liang,HAN Shi jie.Distribution characteristics of elements in rootsoil interface of Pinus koraiensis seedlings by electron probe Xray microanalysis[J].Journal of Nanjing Forestry University(Natural Science Edition),2009,33(02):065.[doi:10.3969/j.jssn.1000-2006.2009.03.015]
[2]朱 磊,张厚江*,孙燕良,等.基于应力波和微钻阻力的红松类木构件力学性能的无损检测[J].南京林业大学学报(自然科学版),2013,37(02):156.[doi:10.3969/j.issn.1000-2006.2013.02.028]
 ZHU Lei,ZHANG Houjiang*,SUN Yanliang,et al.Mechanical properties non-destructive testing of wooden components of Korean pine based on stress wave and micro-drilling resistance[J].Journal of Nanjing Forestry University(Natural Science Edition),2013,37(02):156.[doi:10.3969/j.issn.1000-2006.2013.02.028]
[3]陈永亮,刘明河,李修岭.不同形态氮素配比对红松幼苗光合特性的影响[J].南京林业大学学报(自然科学版),2005,29(03):077.[doi:10.3969/j.jssn.1000-2006.2005.03.020]
 CHEN Yong-liang,LIU Ming-he,LI Xiu-ling.Effects of Different Nitrogen Forms and Ratios on the Photosynthetic Characteristics of Pinus koraiensis Seedlings[J].Journal of Nanjing Forestry University(Natural Science Edition),2005,29(02):077.[doi:10.3969/j.jssn.1000-2006.2005.03.020]
[4]彭淑静,谭柏奇,张大成,等.红松种子综合利用的研究——Ⅰ.红松种仁油脂成分分析[J].南京林业大学学报(自然科学版),1986,10(04):024.[doi:10.3969/j.jssn.1000-2006.1986.04.004]
 Peng Shujing,Tan Boqi,Zhang Dacheng,et al.THE COMPREHENSIVE UTILIZATION OF PINUS KORAIENSIS (SIEB. ET ZUCC.) SEED I. ANALYSIS OF THE COMPOSITION OF KERNEL OIL[J].Journal of Nanjing Forestry University(Natural Science Edition),1986,10(02):024.[doi:10.3969/j.jssn.1000-2006.1986.04.004]
[5]李学文,三清君,年秀红.不同混交比对红松人工林林分质量影响的研究[J].南京林业大学学报(自然科学版),1992,16(03):115.[doi:10.3969/j.jssn.1000-2006.1992.03.031]
 Li Xuewen Wang Qingjun Nian Xiuhong.STUDIES ON THE EFFECT OF DIFFERENT MIXED PROPORTION ON STAND QUALITY IN KOREAN PINE PLANTATION[J].Journal of Nanjing Forestry University(Natural Science Edition),1992,16(02):115.[doi:10.3969/j.jssn.1000-2006.1992.03.031]
[6]陈永亮.不同氮源处理对红松苗木根际pH及养分有效性的影响[J].南京林业大学学报(自然科学版),2004,28(01):042.[doi:10.3969/j.jssn.1000-2006.2004.01.010]
 CHEN Yong-liang.The Effects of Different Nitreon Sources on pH and the Nutrient Availability in the Rhizosphere of Korean Pine[J].Journal of Nanjing Forestry University(Natural Science Edition),2004,28(02):042.[doi:10.3969/j.jssn.1000-2006.2004.01.010]
[7]徐华东,徐国祺,王立海*.低温对红松和大青杨木材力学性质的影响[J].南京林业大学学报(自然科学版),2014,38(05):025.[doi:10.3969/j.issn.1000-2006.2014.05.006]
 XU Huadong,XU Guoqi,WANG Lihai*.Effect of low temperature on the mechanical properties of Pinus koraiensis and Populus ussuriensis timber[J].Journal of Nanjing Forestry University(Natural Science Edition),2014,38(02):025.[doi:10.3969/j.issn.1000-2006.2014.05.006]
[8]高 芳,沈海龙*,刘春苹,等.红松成熟胚愈伤组织诱导外植体选择及培养条件优化[J].南京林业大学学报(自然科学版),2017,41(03):043.[doi:10.3969/j.issn.1000-2006.201605034]
 GAO Fang,SHEN Hailong*,LIU Chunping,et al.Optimization of culture conditions and selection of suitable explants for callus induction from mature embryo of Pinus koraiensis[J].Journal of Nanjing Forestry University(Natural Science Edition),2017,41(02):043.[doi:10.3969/j.issn.1000-2006.201605034]
[9]苗 铮,董利虎,李凤日*,等.基于GLMM的人工林红松二级枝条分布数量模拟[J].南京林业大学学报(自然科学版),2017,41(04):121.[doi:10.3969/j.issn.1000-2006.201604066]
 MIAO Zheng,DONG Lihu,LI Fengri*,et al.Modelling the vertical variation in the number of second order branches of Pinus koraiensis plantation trees through GLMM[J].Journal of Nanjing Forestry University(Natural Science Edition),2017,41(02):121.[doi:10.3969/j.issn.1000-2006.201604066]
[10]高慧淋,董利虎,李凤日*.黑龙江省红松和长白落叶松人工林树冠外部轮廓模拟[J].南京林业大学学报(自然科学版),2018,42(03):010.[doi:10.3969/j.issn.1000-2006.201703112]
 GAO Huilin,DONG Lihu,LI Fengri*.Modelling outer crown profile for planted Pinus koraiensis andLarix olgensis trees in Heilongjiang Province, China[J].Journal of Nanjing Forestry University(Natural Science Edition),2018,42(02):010.[doi:10.3969/j.issn.1000-2006.201703112]

备注/Memo

备注/Memo:
收稿日期:2019-03-06 修回日期:2019-05-14基金项目:国家自然科学基金项目(31570547,31500470)。 第一作者:郝泉龄(7579269@qq.com),ORCID(0000-0003-1572-9032)。*通信作者:徐国祺(xuguoqi_2004@126.com), 副教授, ORCID(0000-0003-3272-9261)。
更新日期/Last Update: 2019-03-25