FOREST RESOURCES WANAGEMENT ›› 2022›› Issue (2): 117-125.doi: 10.13466/j.cnki.lyzygl.2022.02.016
Previous Articles Next Articles
HUANG Jincheng1(), LIU Hongsheng1, NING Jinkui2, OUYANG Xunzhi2, ZANG Hao2()
Received:
2022-01-21
Revised:
2022-04-06
Online:
2022-04-28
Published:
2022-06-13
Contact:
ZANG Hao
E-mail:37996182@qq.com;b12345abba@163.com
CLC Number:
HUANG Jincheng, LIU Hongsheng, NING Jinkui, OUYANG Xunzhi, ZANG Hao. Study of Adaptability of the Primary Afforestation Species in Chongyi County,Jiangxi Province Based on Random Forest[J]. FOREST RESOURCES WANAGEMENT, 2022, (2): 117-125.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.lyzygl.com.cn/EN/10.13466/j.cnki.lyzygl.2022.02.016
Tab.1
Statistics for primary stand factors
树种 | 小班数量 /块 | 平均胸径/cm | 平均树高/m | 基准年龄 /a | ||||
---|---|---|---|---|---|---|---|---|
平均值 | 最小值 | 最大值 | 平均值 | 最小值 | 最大值 | |||
杉木Cunninghamia lanceolata | 8780 | 10.6 | 5.2 | 26.8 | 7.5 | 1.4 | 19.7 | 20 |
马尾松Pinus massoniana | 3040 | 15.5 | 5.6 | 37.8 | 11.5 | 1.5 | 21.2 | 20 |
木荷Schima superba | 112 | 9.8 | 5.6 | 50.4 | 7.8 | 2 | 22.5 | 30 |
苦楝Melia azedarach | 114 | 10.5 | 7.0 | 16.2 | 8.9 | 3.4 | 15.3 | 15 |
南酸枣Choerospondias axillaris | 277 | 11.0 | 5.8 | 25.2 | 8.8 | 1.1 | 20.4 | 15 |
Tab.2
The parameters for site class indices
树种 | β1 | β2 | ||
---|---|---|---|---|
估计值 | 标准差 | 估计值 | 标准差 | |
杉木Cunninghamia lanceolata | 0.0859 | 0.0025 | 1.7706 | 0.0381 |
马尾松Pinus massoniana | 0.0790 | 0.0070 | 2.0433 | 0.2353 |
木荷Schima superba | 0.0601 | 0.0169 | 1.4999 | 0.3646 |
苦楝Melia azedarach | 0.4054 | 0.2029 | 32.7764 | 14.6363 |
南酸枣Choerospondias axillaris | 0.0226 | 0.0105 | 1.1012 | 0.2831 |
Tab.3
The tuning results for adaptability models based on five folds cross validation
树种 | 分类树的数量 | 随机变量个数 | 总精度/% | 分类精度/% | |
---|---|---|---|---|---|
不适宜 | 适宜 | ||||
杉木Cunninghamia lanceolata | 1000 | 2 | 72.79 | 78.84 | 66.06 |
马尾松Pinus massoniana | 400 | 2 | 84.18 | 78.82 | 89.28 |
木荷Schima superba | 400 | 1 | 77.99 | 87.83 | 63.39 |
苦楝Melia azedarach | 300 | 5 | 81.22 | 84.74 | 76.14 |
南酸枣Choerospondias axillaris | 200 | 2 | 80.56 | 83.80 | 77.15 |
Tab.4
Training accuracy for different types
树种 | 实际类别 | 预测类别 | 分类精度/% | 总精度/% | |
---|---|---|---|---|---|
不适宜 | 适宜 | ||||
杉木Cunninghamia lanceolata | 不适宜 | 4087 | 528 | 88.56 | 98.92 |
适宜 | 465 | 3700 | 88.84 | ||
马尾松Pinus massoniana | 不适宜 | 1328 | 159 | 89.31 | 93.13 |
适宜 | 50 | 1503 | 96.78 | ||
木荷Schima superba | 不适宜 | 67 | 1 | 98.53 | 95.54 |
适宜 | 4 | 40 | 90.91 | ||
苦楝Melia azedarach | 不适宜 | 58 | 5 | 92.06 | 93.86 |
适宜 | 2 | 49 | 96.08 | ||
南酸枣Choerospondias axillaris | 不适宜 | 143 | 1 | 99.31 | 98.92 |
适宜 | 2 | 131 | 98.50 |
Tab.5
Predicting results for adaptability models
地类 | 海拔/m | 坡向 | 坡位 | 坡度/ (°) | 成土 母岩 | 土壤 类型 | 土层厚度 /cm | 腐殖层厚度 /cm | 模型预测结果 | ||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
马尾松 | 杉木 | 木荷 | 苦楝 | 南酸枣 | |||||||||
有林地 | 300 | 东坡 | 上部 | 29 | 花岗岩 | 黄壤 | 50 | 5 | 不适宜 | 不适宜 | 适宜 | 不适宜 | 不适宜 |
有林地 | 600 | 北坡 | 中部 | 20 | 花岗岩 | 黄壤 | 70 | 5 | 适宜 | 不适宜 | 适宜 | 适宜 | 不适宜 |
有林地 | 530 | 西坡 | 中部 | 30 | 花岗岩 | 黄壤 | 70 | 5 | 不适宜 | 不适宜 | 适宜 | 不适宜 | 适宜 |
有林地 | 250 | 东坡 | 下部 | 15 | 花岗岩 | 黄壤 | 50 | 10 | 不适宜 | 不适宜 | 不适宜 | 不适宜 | 不适宜 |
有林地 | 251 | 东坡 | 下部 | 15 | 花岗岩 | 黄壤 | 50 | 10 | 不适宜 | 不适宜 | 不适宜 | 不适宜 | 不适宜 |
有林地 | 300 | 东南坡 | 下部 | 3 | 花岗岩 | 黄壤 | 80 | 20 | 适宜 | 适宜 | 不适宜 | 不适宜 | 不适宜 |
有林地 | 300 | 南坡 | 下部 | 20 | 花岗岩 | 黄壤 | 50 | 15 | 适宜 | 不适宜 | 适宜 | 适宜 | 适宜 |
有林地 | 270 | 东南坡 | 下部 | 23 | 砂岩 | 黄壤 | 80 | 10 | 适宜 | 不适宜 | 适宜 | 适宜 | 不适宜 |
有林地 | 170 | 东坡 | 下部 | 6 | 花岗岩 | 红壤 | 80 | 10 | 不适宜 | 不适宜 | 不适宜 | 不适宜 | 适宜 |
地类 | 海拔/m | 坡向 | 坡位 | 坡度/ (°) | 成土 母岩 | 土壤 类型 | 土层厚度 /cm | 腐殖层厚度 /cm | 模型预测结果 | ||||
马尾松 | 杉木 | 木荷 | 苦楝 | 南酸枣 | |||||||||
有林地 | 180 | 东南坡 | 下部 | 10 | 花岗岩 | 红壤 | 80 | 10 | 不适宜 | 不适宜 | 适宜 | 不适宜 | 适宜 |
有林地 | 290 | 东南坡 | 下部 | 15 | 花岗岩 | 红壤 | 70 | 10 | 适宜 | 不适宜 | 适宜 | 适宜 | 适宜 |
有林地 | 290 | 南坡 | 上部 | 28 | 花岗岩 | 黄壤 | 50 | 10 | 不适宜 | 适宜 | 不适宜 | 不适宜 | 不适宜 |
有林地 | 280 | 西坡 | 中部 | 29 | 花岗岩 | 黄壤 | 50 | 5 | 不适宜 | 适宜 | 适宜 | 不适宜 | 不适宜 |
有林地 | 240 | 东北坡 | 下部 | 18 | 花岗岩 | 黄壤 | 50 | 20 | 不适宜 | 不适宜 | 不适宜 | 不适宜 | 适宜 |
有林地 | 280 | 西北坡 | 下部 | 20 | 花岗岩 | 黄壤 | 50 | 15 | 不适宜 | 不适宜 | 适宜 | 适宜 | 适宜 |
有林地 | 340 | 东坡 | 下部 | 25 | 页岩 | 黄壤 | 70 | 10 | 适宜 | 适宜 | 适宜 | 适宜 | 不适宜 |
宜林地 | 600 | 东南坡 | 中部 | 28 | 花岗岩 | 黄壤 | 80 | 15 | 适宜 | 适宜 | 不适宜 | 适宜 | 适宜 |
宜林地 | 250 | 东北坡 | 下部 | 30 | 砂岩 | 黄壤 | 55 | 5 | 适宜 | 适宜 | 适宜 | 不适宜 | 不适宜 |
[1] |
Eckes-Shephard A H, Tiavlovsky E, Chen Y, et al. Direct response of tree growth to soil water and its implications for terrestrial carbon cycle modelling[J]. Global Change Biology, 2021, 27(1):121-135.
doi: 10.1111/gcb.15397 pmid: 33065763 |
[2] |
Zhao Qiong, Zeng Dehui. Nitrogen addition effects on tree growth and soil properties mediated by soil phosphorus availability and tree species identity[J]. Forest Ecology and Management, 2019, 449:117478.
doi: 10.1016/j.foreco.2019.117478 |
[3] | 陆海飞, 刘望舒, 徐建民, 等. 广西中南部尾巨桉人工林立地类型划分及立地质量评价[J]. 林业科学, 2021, 57(5):13-24. |
[4] | 郭艳荣, 刘洋, 吴保国. 福建省宜林地立地质量的分级与数量化评价[J]. 东北林业大学学报, 2014, 42(10):54-59. |
[5] | 雷相东, 唐守正, 符利勇, 等. 森林立地质量定量评价——理论、方法、应用[M]. 北京: 中国林业出版社, 2020:3-9. |
[6] | 唐诚, 王春胜, 庞圣江. 广西大青山西南桦人工林立地类型划分及评价[J]. 西北林学院学报, 2018, 33(4):52-57. |
[7] | 朱光玉, 康立. 森林立地生产力评价指标与方法[J]. 西北林学院学报, 2016, 31(6):275-281. |
[8] | Weiskittel A R, Hann D W, Kershaw J A, et al. Forest growth and yield modeling[M]. Chichester: John Wiley & Sons, Ltd, 2011:38-47. |
[9] | 刘洵, 曾思齐, 龙时胜, 等. 湖南省栎类天然次生林胸径地位指数表研制[J]. 森林与环境学报, 2019, 39(3):265-272. |
[10] | 李斌成, 许业洲, 袁慧, 等. 湖北省日本落叶松差分型立地指数模型构建[J]. 森林与环境学报, 2020, 40(4):433-441. |
[11] | 张博, 陈科屹, 周来, 等. 基于分位数回归的杉木人工林地位级划分方法研究[J]. 林业科学研究, 2021, 34(4):103-110. |
[12] |
Liu Xianzhao, Duan Guangshuang, Chhin S, et al. Evaluation of potential versus realized site productivity of Larix principis-rupprechtii plantations across northern China[J]. Forest Ecology and Management, 2021, 479:118608.
doi: 10.1016/j.foreco.2020.118608 |
[13] | 李凤日. 测树学[M]. 4版. 北京: 中国林业出版社, 2019:138-140. |
[14] | 顾云春, 李永武, 杨承栋. 森林立地分类与评价的立地要素原理与方法[M]. 北京: 科学出版社, 1993:13-16. |
[15] | 姚茂和, 盛炜彤, 熊有强. 杉木人工林林下植被对立地的指示意义[J]. 林业科学, 1992, 28(3):208-212. |
[16] | Jumwong N, Wachrinrat C, Sungkaew S, et al. Site indicator species for predicting the productivity of teak plantations in Phrae Province,Thailand[J]. Biotropia, 2020, 27(5):104-114. |
[17] | 刘聘, 乔一娜, 李静文, 等. 安溪县福建柏人工林立地质量数量化评价[J]. 云南农业大学学报:自然科学版, 2021, 36(2):324-329. |
[18] |
Fiandino S, Plevich J, Tarico J, et al. Modeling forest site productivity using climate data and topographic imagery in Pinus elliottii plantations of central Argentina[J]. Annals of Forest Science, 2020, 77:95.
doi: 10.1007/s13595-020-01006-3 |
[19] |
Afif-Khouri E, Álvarez-Álvarez P, Fernández-López M J, et al. Influence of climate,edaphic factors and tree nutrition on site index of chestnut coppice stands in north-west Spain[J]. Forestry, 2011, 84(4):385-396.
doi: 10.1093/forestry/cpr025 |
[20] |
Kint V, Vos B D, Deckers J, et al. Predicting forest site productivity in temperate lowland from forest floor,soil and litterfall characteristics using boosted regression trees[J]. Plant and Soil, 2012, 354:157-172.
doi: 10.1007/s11104-011-1052-z |
[21] |
Sabatia C O, Burkhart H E. Predicting site index of plantation loblolly pine from biophysical variables[J]. Forest Ecology and Management, 2014, 326:142-156.
doi: 10.1016/j.foreco.2014.04.019 |
[22] |
Coomes D A, Allen R B. Effects of size,competition and altitude on tree growth[J]. Journal of Ecology, 2007, 95:1084-1097.
doi: 10.1111/j.1365-2745.2007.01280.x |
[23] | 雷相东. 机器学习算法在森林生长收获预估中的应用[J]. 北京林业大学学报, 2019, 41(12):1-14. |
[24] |
Jevšenak J, Skudnik M. A random forest model for basal area increment predictions from national forest inventory data[J]. Forest Ecology and Management, 2021, 479:118601.
doi: 10.1016/j.foreco.2020.118601 |
[25] |
Jiang Huiquan, Radtke P J, Weiskittel A R, et al. Climate- and soil-based models of site productivity in eastern US tree species[J]. Canadian Journal of Forest Research, 2015, 45:325-342.
doi: 10.1139/cjfr-2014-0054 |
[26] | 高若楠, 苏喜友, 谢阳生, 等. 基于随机森林的杉木适生性预测研究[J]. 北京林业大学学报, 2017, 39(12):36-43. |
[27] | 杜雨菲, 吴保国, 陈玉玲. 基于机器学习算法的广西桉树适宜性研究[J]. 浙江农林大学学报, 2020, 37(1):122-128. |
[28] | 郭鸿郡. 基于GWR的黑龙江大兴安岭森林立地质量的遥感分析[D]. 哈尔滨: 东北林业大学, 2017,15-18. |
[29] | 郭颖婕, 刘晓燕, 郭茂祖, 等. 植物抗性基因识别中的随机森林分类方法[J]. 计算机科学与探索, 2012, 6(1):67-77. |
[30] | 李嘉珏, 于洪波. 甘肃黄土高原立地分类与适地适树[M]. 北京: 北京科学技术出版社, 1990:91-93. |
[31] | 谢阳生, 陆元昌, 刘宪钊, 等. 多功能森林经营方案编制技术及案例[M]. 北京: 中国林业出版社, 2019. |
[32] | 刘丹. 基于分布适宜性和潜在生产力的定量适地适树研究[D]. 北京: 中国林业科学研究院, 2018:1-3. |
[33] |
Chen Yuling, Wu Baoguo, Chen Dong, et al. Using machine learning to assess site suitability for afforestation with particular species[J]. Forests, 2019, 10(9):739.
doi: 10.3390/f10090739 |
[34] | 蔡学林, 张志云, 欧阳勋志. 江西森林立地质量数量化评价研究[J]. 江西农业大学学报, 1997, 19(6):81-89. |
[35] | 李绍忠, 孟康敏, 赵冰, 等. 东北珍贵阔叶树适地适树的研究[J]. 应用生态学报, 1992, 3(3):195-201. |
[36] | 罗也, 王君, 杨雨春, 等. 利用随机效应模型模拟东北三省胡桃楸地位指数[J]. 应用生态学报, 2020, 31(8):2549-2557. |
[1] | TANG Jiajun, CHAI Zongzheng. Remote Sensing Estimation of Average Diameter at Breast Height of Forest Stands Based on Airborne LiDAR and Machine Learning Algorithms [J]. Forest and Grassland Resources Research, 2024, 0(1): 56-64. |
[2] | ZHANG Guoli, CI Xuelun, YANG Xueqing, JIANG Chunying, SUN Zhichao, MENG Haiding. Study on Spatio-Temporal Distribution Characteristics and Susceptibility Analysis of Forest Fire [J]. Forest and Grassland Resources Research, 2023, 0(5): 48-55. |
[3] | LIANG Licheng, FU Xiaoqiang, ZHANG Bin, CHENG Guxun, LI Zuohui. Dynamic Monitoring of Spartina alterniflora in Xiangshan Harbor Based on GEE and Random Forest [J]. FOREST RESOURCES WANAGEMENT, 2023, 0(3): 38-45. |
[4] | WANG Xiaohui, ZHANG Huiru, PANG Yong, QIN Xianlin, LI Haikui, MENG Shili, YU Tao. Forest Vegetation Type Monitoring in the Natural Forest Protection Project Area [J]. FOREST RESOURCES WANAGEMENT, 2023, 0(2): 96-103. |
[5] | GAO Jinping, YU Huina, ZHAI Zhaokun. Application of High Resolution Multi-Mode Satellite in Forest Land Types and Tree Species Identification [J]. FOREST RESOURCES WANAGEMENT, 2023, 0(1): 127-132. |
[6] | WANG Xiaoyang, JIANG Youyi, LI Xiao, HU Yaxuan, ZHANG Jiazheng, LIU Bowei. A Multi-Temporal and Multi-Feature Larch Plantation Extraction Study Based on GF-1 Images [J]. FOREST RESOURCES WANAGEMENT, 2022, 0(4): 109-118. |
[7] | HUANG Bingqian, YUE Cairong, ZHU Bodong. Estimation of Forest Volume Based on Multi-Scale Remote Sensing Features of GF-1 [J]. FOREST RESOURCES WANAGEMENT, 2022, 0(3): 54-59. |
[8] | LONG Zhihao, LUO Peng, XU Dengping, LI Zhen, DAI Huabin. Inversion Research of Forest Stock Volume Using the Red Edge Bands of Sentinel-2A [J]. FOREST RESOURCES WANAGEMENT, 2022, 0(2): 126-134. |
[9] | TANG Jinhao, ZHANG Jialong, CHEN Liye, CHENG Tao. Research on Estimation of Aboveground Biomass and Scale Conversion for Pinus densata Mast [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(6): 83-89. |
[10] | DU Zhi, CHEN Zhenxiong, MA Kaisen, LIU Ziwei, GU Xinggui. Estimating Standing Volume in Southern Collective Forest Region Based on the Unmanned Aerial Vehicle LiDAR Characteristic Variables [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(4): 157-165. |
[11] | XIAO Yue, XU Xiaodong, LONG Jiangping, LIN Hui. Research on Inversion of Forest Volume Based on Domestic High-Resolution Data [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(3): 101-107. |
[12] | LI Bin, LI Chonggui, LI Yu. Research on Larch Extraction in Saihanba Mechanical Forest Farm Based on Sentinel-2 Data [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(2): 117-123. |
[13] | XU Bingbing, BIAN Gengzhan, YI Xuan, ZHU Guangyu, QI Zhantao, LV Yong. Study on the Characteristics and Influencing Factors of the Single Tree Stem Form of Cunninghamia lanceolata Plantation in Hunan Province [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(5): 82-88. |
[14] | HAN Rui, WU Dasheng, FANG Luming, HUANG Yuling. Estimation of Forest Reserves Based on Boruta and Extra-trees Methods [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(4): 127-133. |
[15] | LI Jiangwei, LIU Xueying, XIAO Zhibiao, HUANG Honglan. A Study on Introduction and Adaptation of Magnoliaceae Plants and its Landscape Evaluation [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(4): 161-168. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||