基于分解重构与机器学习的华北平原杨树人工林净碳交换模拟

doi:10.11707/j.1001-7488.LYKX20240492

Abstract

Abstract:

Objective: The decomposition-reconstruction method is integrated with machine learning model to simulate the net carbon exchange capacity of plantation ecosystems, aiming to provide an effective tool for high-precision simulation and prediction of the carbon sequestration capacity of artificial forest ecosystems in the “Three North” region. Method: Based on the daily observation dataset from the poplar plantation flux observation system and the microclimate observation system in Gongqing Forest Farm, Shunyi, Beijing during the growing season (April?October) from 2015 to 2018, the main driving factors of net ecosystem carbon exchange (NEE) were identified by the random forest importance ranking method. The empirical mode decomposition (EMD) method was used to decompose and reconstruct the NEE and the main driving factors into fluctuation and trend series. Then, four machine learning models, BP neural network, support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost), were applied to simulate fluctuation and trend series of NEE. After comparing the model performance, the optimal model was selected to reconstruct the NEE time series. Result: 1) The NEE of poplar plantation ecosystem in Gongqing Forest Farm was significantly affected by total radiation and temperature. The soil volumetric water content (5 cm), saturated vapor pressure difference, and relative humidity had weak effects on NEE. The importance rank of environmental factors on NEE was ordered as: total radiation, average temperature, maximum temperature, minimum temperature, soil volumetric water content (5 cm), saturated vapor pressure difference and relative humidity. 2) After NEE decomposition and reconstruction, the models with the best simulation effects for the fluctuation term and trend series were the SVM and the RF model, respectively. 3) Compared with the simulation method without decomposition-reconstruction method, the accuracy of the simulated test set using decomposition-reconstruction method was significantly improved, with R² increasing from 0.520 to 0.676, RMSE decreasing from 1.998 to 1.646 μmol·m^?2 s^?1, and MAE decreasing from 1.578 to 1.273 μmol·m^?2 s^?1. Conclusion: Total radiation, mean air temperature, maximum air temperature and minimum air temperature are the most critical factors affecting the NEE daily variation of poplar plantation ecosystem in the study area. This method proposed in this paper, combining decomposition-reconstruction method with machine learning model, can effectively improve the simulation accuracy of NEE, and provide a new tool for simulating carbon sequestration capacity of forest ecosystem in the “Three North” regions.

Key words: net ecosystem carbon exchange (NEE), empirical mode decomposition (EMD), machine learning, poplar plantation

CLC Number:

S718.55

Qian Li,Fan Zhang,Xiangxue Meng,Xiaoyun Wu,Jianzhuang Pang,Hang Xu,Zhiqiang Zhang. Simulation of Net Carbon Exchange of Poplar Plantation in North China Plain Based on Decomposition-Reconstruction and Machine Learning[J]. Scientia Silvae Sinicae, 2025, 61(12): 72-82.

Figures/Tables 9

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Fig.4

Fig.5

Fig.6

Fig.7

References 0

	曹镓玺, 王　鑫, 雷光春. 基于遗传算法优化Bp神经网络的青藏高原海北高寒湿地CO₂通量模拟及其影响因子. 山东大学学报(理学版), 2021, 56 (5): 33- 41.
	Cao J X, Wang X, Lei G C. Simulation of alpine wetlands CO₂ flux and its influencing factors based on BP neural network optimized by genetic algorithm in Qinghai-Tibet Plateau. Journal of Shandong University (Natural Science), 2021, 56 (5): 33- 41.
	曹　轲, 谭　冲, 刘　洪, 等. 基于改进灰狼算法优化Bp神经网络的无线传感器网络数据融合算法. 中国科学院大学学报, 2022, 39 (2): 232- 239.
	Cao K, Tan C, Liu H, et al. Data fusion algorithm of wireless sensor network based on BP neural network optimized by improved grey wolf optimizer. Journal of University of Chinese Academy of Sciences, 2022, 39 (2): 232- 239.
	曹文康, 徐哈宁, 肖　慧, 等. 基于贝叶斯优化XGBoost的多元输入模型对滑坡位移预测效果研究. 测绘工程, 2024, 33 (2): 49- 55.
	Cao W K, Xu H N, Xiao H, et al. Study on the effect of Bayesian optimization XGBoost-based multi-input model on landslide displacement prediction. Engineering of Surveying and Mapping, 2024, 33 (2): 49- 55.
	陈　凯, 朱　钰. 2007. 机器学习及其相关算法综述. 统计与信息论坛, (5): 105−112.
	Chen K, Zhu Y. 2007. A Summary of Machine Learning and Related Algorithms. Journal of Statistics and Information, (5): 105−112. ［in Chinese］
	陈　亮, 周国模, 杜华强, 等. 基于随机森林模型的毛竹林CO₂通量模拟及其影响因子. 林业科学, 2018, 54 (8): 1- 12.
	Chen L, Zhou G M, Du H Q, et al. Simulation of CO₂ flux and controlling factors in Moso bamboo forest using random forest algorithm. Scientia Silvae Sinicae, 2018, 54 (8): 1- 12.
	方匡南, 吴见彬, 朱建平, 等. 随机森林方法研究综述. 统计与信息论坛, 2011, 26 (3): 32- 38. doi: 10.3969/j.issn.1007-3116.2011.03.006
	Fang K N, Wu J B, Zhu J P, et al. A review of technologies on random forests. Journal of Statistics and Information, 2011, 26 (3): 32- 38. doi: 10.3969/j.issn.1007-3116.2011.03.006
	冯新妍, 贾　昕, 黄金泽, 等. ANN-BiLSTM模型在温带荒漠灌丛碳通量数据缺失值插补中的应用. 北京林业大学学报, 2023, 45 (9): 62- 72.
	Feng X Y, Jia X, Huang J Z, et al. Application of ANN-BiLSTM model to long-term gap-filling of carbon flux data in temperate desert shrub. Journal of Beijing Forestry University, 2023, 45 (9): 62- 72.
	冯鑫炜, 张志强, 许　行, 等. 欧美杨人工林生态系统净碳交换对环境因子响应的时滞. 林业科学, 2020, 56 (2): 12- 23.
	Feng X W, Zhang Z Q, Xu H, et al. Time-lag responses of net ecosystem carbon exchange to environmental factors in a Populus × euramericana plantation. Scientia Silvae Sinicae, 2020, 56 (2): 12- 23.
	高怡凡, 宋长青, 王元慧, 等. 顾及土地利用强度和生态-经济权衡的四川省陆地生态系统碳储量预测与热点分析. 生态学报, 2024, 44 (9): 3958- 3969.
	Gao Y F, Song C Q, Wang Y H, et al. Carbon storage prediction of terrestrial ecosystems and hotspot analysis in Sichuan Province by considering land use intensity and eco-economic trade-offs. Acta Ecologica Sinica, 2024, 44 (9): 3958- 3969.
	顾亚祥, 丁世飞. 支持向量机研究进展. 计算机科学, 2011, 38 (2): 14- 17. doi: 10.3969/j.issn.1002-137X.2011.02.004
	Gu Y X, Ding S F. Advances of support vector machines (SVM). Computer Science, 2011, 38 (2): 14- 17. doi: 10.3969/j.issn.1002-137X.2011.02.004
	金盛杰, 包腾飞, 陈迪辉, 等. 基于EMD分解法的大坝变形预测模型及应用. 水利水电技术, 2017, 48 (12): 41- 44.
	Jin S J, Bao T F, Chen D H, et al. EMD decomposition method-based dam deformation prediction model and its application. Water Resources and Hydropower Engineering, 2017, 48 (12): 41- 44.
	康满春, 朱丽平, 许　行, 等. 基于Biome-BGC模型的北方杨树人工林碳水通量对气候变化的响应研究. 生态学报, 2019, 39 (7): 2378- 2390.
	Kang M C, Zhu L P, X H, et al. Modelling the responses of carbon and water fluxes with climate change for a poplar plantation in northern China based on the Biome-BGC model. Acta Ecologica Sinica, 2019, 39 (7): 2378- 2390.
	刘　扬, 王立虎. 基于改进EMD-LSTM的洪水预测方法研究. 水利水电技术(中英文), 2022, 53 (1): 35- 44.
	Liu Y, Wang L H. Flood forecasting method based on an improved EMD-LSTM. Water Resources and Hydropower Engineering, 2022, 53 (1): 35- 44.
	路　炜, 魏霖静. 基于EMD分解的黄河流域兰州水文站日径流预测. 水电能源科学, 2023, 41 (8): 19- 22.
	Lu W, Wei L J. Daily runoff prediction of lanzhou hydrological station in yellow river basin based on EMD decomposition. Water Resources and Power, 2023, 41 (8): 19- 22.
	吕富成, 酒名扬, 韩立钦, 等. 中国北方针叶林碳通量动态变化及其影响因素分析. 气候与环境研究, 2024, 29 (3): 243- 252. doi: 10.3878/j.issn.1006-9585.2024.24013
	Lü F C, Jiu M Y, Han L Q, et al. Dynamic changes in carbon fluxes of the boreal coniferous forests of China and influencing factor analysis. Climatic and Environmental Research, 2024, 29 (3): 243- 252. doi: 10.3878/j.issn.1006-9585.2024.24013
	朴世龙, 何　悦, 王旭辉, 等. 中国陆地生态系统碳汇估算: 方法、进展、展望. 中国科学: 地球科学, 2022, 52 (6): 1010- 1020.
	Piao S L, He Y, Wang X H, et al. Estimation of carbon sequestration in Chinese terrestrial ecosystems: methods, progress, and prospects. Scientia Sinica(Terrae), 2022, 52 (6): 1010- 1020.
	齐建东, 谭新新. 长白山红松阔叶林的净碳交换变化及基于时间卷积神经网络的模拟. 林业科学, 2022, 58 (2): 1- 12.
	Qi J D, Tan X X. Net carbon exchange of the forest of Korean pine and broad leaved forest trees in Changbai mountain and its simulation based on temporal convolutional network. Scientia Silvae Sinicae, 2022, 58 (2): 1- 12.
	沙靖岚. 2017. 基于LightGBM与XGBoost算法的P2P网络借贷违约预测模型的比较研究. 大连: 东北财经大学.
	Sha J L. 2017. Comparative study of P2P online lending default prediction models based on LightGBM and XGBoost algorithms. Dalian: Dongbei University of Finance and Economics. ［in Chinese］
	苏文胜. 2010. 滚动轴承振动信号处理及特征提取方法研究. 大连: 大连理工大学.
	Su W S. 2010. Research on vibration signal processing and feature extraction of rolling bearings. Dalian: Dalian University of Technology. ［in Chinese］
	唐　欢, 叶　剑, 高振翔, 等. 我国典型生态系统净CO₂交换量与蒸散量的多机器学习模型对比分析. 干旱区资源与环境, 2022, 36 (8): 92- 100.
	Tang H, Ye J, Gao Z X, et al. Comparative analysis of net CO₂ exchange and evapotranspiration in typical ecosystems of China using multi-machine learning models. Journal of Arid Land Resources and Environment, 2022, 36 (8): 92- 100.
	田惠玲, 朱建华, 何　潇, 等. 基于随机森林模型的东北三省乔木林生物质碳储量预测. 林业科学, 2022, 58 (4): 40- 50. doi: 10.11707/j.1001-7488.20220405
	Tian H L, Zhu J H, He X, et al. Projected biomass carbon stock of arbor forest of three provinces in northeastern China based on random forest model. Scientia Silvae Sinicae, 2022, 58 (4): 40- 50. doi: 10.11707/j.1001-7488.20220405
	王少影, 张　宇, 孟宪红, 等. 机器学习算法对涡动相关缺失通量数据的插补研究. 高原气象, 2020, 39 (6): 1348- 1360. doi: 10.7522/j.issn.1000-0534.2019.00142
	Wang S Y, Zhang Y, Meng X H, et al. Fill the gaps of eddy covariance fluxes using machine learning algorithms. Plateau Meteorology, 2020, 39 (6): 1348- 1360. doi: 10.7522/j.issn.1000-0534.2019.00142
	王　婷. 2010. EMD算法研究及其在信号去噪中的应用. 哈尔滨: 哈尔滨工程大学.
	Wang T. 2010. Research on the EMD algorithm and its application in signal denoising. Harbin: Harbin Engineering University. ［in Chinese］
	席本野. 杨树根系形态、分布、动态特征及其吸水特性. 北京林业大学学报, 2019, 41 (12): 37- 49. doi: 10.12171/j.1000-1522.20190400
	Xi B Y. Morphology, distribution, dynamic characteristics of poplar roots and its water uptake habits. Journal of Beijing Forestry University, 2019, 41 (12): 37- 49. doi: 10.12171/j.1000-1522.20190400
	许　行. 2021. 温带森林生态系统总初级生产力及其光能和水分利用效率的生物物理调控机制. 北京: 北京林业大学.
	Xu H. 2021. Biophysical regulation mechanisms of gross primary productivity and light and water use efficiency in temperate forest ecosystems. Beijing: Beijing Forestry University. ［in Chinese］
	闫东锋, 郭丹丹, 吴桂藏, 等. 间伐对杨树人工林表层根系分布及碳存储格局的影响. 西北林学院学报, 2017, 32 (2): 30- 36. doi: 10.3969/j.issn.1001-7461.2017.02.05
	Yan D F, Guo D D, Wu G Z, et al. Effects of thinning on the surface root system and carbon distribution pattern of Populus plantations. Journal of Northwest Forestry University, 2017, 32 (2): 30- 36. doi: 10.3969/j.issn.1001-7461.2017.02.05
	杨元合, 石　岳, 孙文娟, 等. 中国及全球陆地生态系统碳源汇特征及其对碳中和的贡献. 中国科学: 生命科学, 2022, 52 (4): 534- 574.
	Yang Y H, Shi Y, Sun W J, et al. Terrestrial carbon sinks in China and around the world and their contribution to carbon neutrality. Scientia Sinica(Vitae), 2022, 52 (4): 534- 574.
	邹　宁, 金杨超, 郭　成, 等. 基于EMD的井中雷达信号预处理. 电子科技大学学报, 2022, 51 (6): 875- 883. doi: 10.12178/1001-0548.2021379
	Zou N, Jin Y C, Guo C, et al. EMD-Based borehole radar signal preprocessing method. Journal of University of Electronic Science and Technology of China, 2022, 51 (6): 875- 883. doi: 10.12178/1001-0548.2021379
	Chen Y, Xu Y M, Chen T Y, et al. Exploring the spatiotemporal dynamics and driving factors of net ecosystem productivity in China from 1982 to 2020. Remote Sensing, 2024, 16 (1): 60.
	Chu X, Zhan J Y, Li Z H, et al. Assessment on forest carbon sequestration in the Three-North Shelterbelt Program Region, China. Journal of Cleaner Production, 2019, 215, 382- 389. doi: 10.1016/j.jclepro.2018.12.296
	Du G S, Liu Z X, Lu H F. Application of innovative risk early warning mode under big data technology in internet credit financial risk assessment. Journal of Computational and Applied Mathematics, 2021, 386, 113260. doi: 10.1016/j.cam.2020.113260
	Foken T. 2005. Angewandte meteorologie: mikrometeorologische methoden. Berlin: Springer Berlin Heidelberg.
	Fu Z, Stoy P C, Poulter B, et al. Maximum carbon uptake rate dominates the interannual variability of global net ecosystem exchange. Global Change Biology, 2019, 25 (10): 3381- 3394. doi: 10.1111/gcb.14731
	Gao D X, Yao J Y, Yu S T, et al. 2023. Eddy covariance CO₂ flux gap filling for long data gaps: a novel framework based on machine learning and time series decomposition. Remote Sensing, 15(10): 2695.
	Gasbarro F, Iraldo F, Daddi T. The drivers of multinational enterprises' climate change strategies: a quantitative study on climate-related risks and opportunities. Journal of Cleaner Production, 2017, 160, 8- 26. doi: 10.1016/j.jclepro.2017.03.018
	He L, Li J, Harahap M, et al. Scale-specific controller of carbon and water exchanges over wheat field identified by ensemble empirical mode decomposition. International Journal of Plant Production, 2018, 12 (1): 43- 52. doi: 10.1007/s42106-017-0005-8
	Huang I, Hsieh C. Gap-filling of surface fluxes using machine learning algorithms in various ecosystems. Water, 2020, 12 (12): 3415. doi: 10.3390/w12123415
	Huang N E, Shen Z, Long S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series anlysis. Proceedings of the Royal Society of London, 1998, 454, 903- 995.
	IPCC. 2021,. Climate change 2021: the physical science basis. Working group I contribution to the IPCC sixth assessment report of the intergovernmental panel on climate change.. Cambridge: Cambridge University Press, .
	Irvin J, Zhou S, Mcnicol G, et al. Gap-filling eddy covariance methane fluxes: comparison of machine learning model predictions and uncertainties at fluxnet-CH₄ wetlands. Agricultural and Forest Meteorology, 2021,
	Kormann R M F X. An analytical footprint model for non-neutral stratification. Boundary-Layer Meteorology, 2001, 99 (2): 207- 224. doi: 10.1023/A:1018991015119
	Lorena A C, de Carvalho A C F. 2004. An hybrid GA/SVM approach for multiclass classification with directed acyclic graphs. Advances in Artificial Intelligence – SBIA 2004, 366−375.
	Moffat A M, Papale D, Reichstein M, et al. Comprehensive comparison of gap-filling techniques for eddy covariance net carbon fluxes. Agricultural and Forest Meteorology, 2007, 147 (3/4): 209- 232. doi: 10.1016/j.agrformet.2007.08.011
	Schindler D E, Hilborn R. Prediction, precaution, and policy under global change. Science, 2015, 347 (6225): 953- 954. doi: 10.1126/science.1261824
	Xu H, Zhang Z Q, Chen J Q, et al. Regulations of cloudiness on energy partitioning and water use strategy in a riparian poplar plantation. Agricultural and Forest Meteorology, 2018, 262, 135- 146. doi: 10.1016/j.agrformet.2018.07.008
	Zhang D N, Zuo X X, Zang C F. Assessment of future potential carbon sequestration and water consumption in the construction area of the Three-North Shelterbelt Programme in China. Agricultural and Forest Meteorology, 2021, 303, 108377. doi: 10.1016/j.agrformet.2021.108377
	Zhang W G, Li H R, Han L, et al. Slope stability prediction using ensemble learning techniques: a case study in Yunyang county, Chongqing, China. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14 (4): 1089- 1099.

机器学习算法 Machine learning	波动项最优参数 Optimal parameters of fluctuation term	趋势项最优参数 Optimal parameters of trend term
支持向量机 Support vector machines	sigma=0.1；C=1	sigma=1；C=10
BP神经网络 BP neural network	size=10	size=10
随机森林 Random forest	mtry=2	mtry=5
极致梯度提升 Extreme gradient boosting	nrounds=10；max-depth =5；eta=0.1；gamma=0； colsample-bytree=0.8；min-child-weight=1；subsample=0.6	nrounds=50；max-depth =10；eta=0.1；gamma=0； colsample-bytree=0.8；min-child-weight=1；subsample=0.8

机器学习算法 Machine learning	波动项 Fluctuation term			趋势项 Trend term
机器学习算法 Machine learning	R²	RMSE/ （μmol·m^?2s^?1）	MAE/ （μmol·m^?2s^?1）	R²	RMSE/ （μmol·m^?2s^?1）	MAE/ （μmol·m^?2s^?1）
支持向量机 Support vector machines	0.384	1.664	1.291	0.960	0.384	0.238
BP神经网络 BP neural network	0.366	1.664	1.267	0.943	0.422	0.301
随机森林 Random forest	0.323	1.74	1.346	0.973	0.323	0.219
极致梯度提升 Extreme gradient boosting	0.310	1.834	1.432	0.967	0.359	0.238

[1]	Zhenghuang Shi,fangmiao Hou,Haokun Zhang,Guoxing Huang. Analysis of the Impact of the New Round of Collective Forest Tenure Reform on the Growth of Export Margins of China’s Wood-Based Forest Product [J]. Scientia Silvae Sinicae, 2025, 61(9): 211-222.
[2]	Yujiao Zhang,Hengqian Zhao,Hancong Fu,Ge Liu,Xiadan Huangfu,Xuanqi Liu. Inversion Model of Aboveground Biomass at Individual Tree Scale Based on the Multiple Features of UAV Remote Sensing [J]. Scientia Silvae Sinicae, 2025, 61(8): 129-141.
[3]	Zeyu Yuan,Hang Xu,Yi Ren,Yang Xu,Jianzhuang Pang,Xiaoyun Wu,Hanyao Zhang,Zhiqiang Zhang. Distribution Characteristics of Vegetation Resilience and its Driving Factors in the Three-North Shelterbelt Forest Program Region from 2001 to 2021 [J]. Scientia Silvae Sinicae, 2025, 61(7): 182-191.
[4]	Feifei Yang,Wangfei Zhang,Lei Zhao,Han Zhao,Yongjie Ji,Mengjin Wang. Two-Stage Remote Sensing Feature Optimization and GF-1 Data-Supported Forest Above-Ground Biomass Inversion [J]. Scientia Silvae Sinicae, 2025, 61(4): 9-19.
[5]	Xiaoning Ge,Xinqiao Xu,Huaiqing Zhang,Jing Zhang,Jie Yang,Zeyu Cui,Rurao Fu,Jinjie Liang,Tianhua Zou,Linlong Wang,Yang Liu. Progress and Reflection on Genotype-Environment Interaction Algorithms in Forest Tree Breeding [J]. Scientia Silvae Sinicae, 2025, 61(3): 1-15.
[6]	Dan Pan,Luyi Luo,Kaiwen Ji,Fanbin Kong. Impact of Rural E-Commerce Development on Intra-Regional Income Gap and Shared Prosperity in Forested Areas [J]. Scientia Silvae Sinicae, 2024, 60(5): 35-50.
[7]	Chenchen Shen,Wenfa Xiao,Jianhua Zhu,Lixiong Zeng,Jizhen Chen,Zhilin Huang. Characterization of Soil Organic Carbon and Key Influencing Factors of Natural Forests in Central China Based on Machine Learning Algorithms [J]. Scientia Silvae Sinicae, 2024, 60(3): 65-77.
[8]	Lei Xu,Xiaoyun Wu,Jiang Lü,Yun Shi,Mengxun Zhu,Hang Xu,Zhiqiang Zhang. Impacts of Diffuse Radiation Fraction on Energy Partitioning in a Poplar Plantation in the North China Plain [J]. Scientia Silvae Sinicae, 2024, 60(3): 100-110.
[9]	Qiangying Jiao,Zongfu Han,Weiye Wang,Di Liu,Pengxu Pan,Bo Li,Nianci Zhang,Ping Wang,Jinhua Tao,Meng Fan. Driving Factors and Forecasting Model of Lightning-Caused Forest Fires in Daxing’ anling Mountains Based on Multi-Sources Data and Machine Learning Method [J]. Scientia Silvae Sinicae, 2023, 59(6): 74-87.
[10]	Jiaming Wan,Jiang Lü,Yun Shi,Hang Xu,Zhiqiang Zhang. Effects of Diffuse Radiation on the Gross Primary Productivity of a Poplar Plantation [J]. Scientia Silvae Sinicae, 2023, 59(5): 1-10.
[11]	Ruirui Zhao,Yong Liu,Kai Wang. Effects of Biochar and Manure on Wood Decomposition and Soil Enzyme Activities Related Soil Nutrient Cycling in a triploid Populus tomentosa Plantation [J]. Scientia Silvae Sinicae, 2023, 59(11): 1-11.
[12]	Nannan Yang,Yan Bai,Suyi Jiang,Chunmei Yang,Kaihong Xu. Recognition Method of Plate and Wood Based on ALexNet Optimaization [J]. Scientia Silvae Sinicae, 2022, 58(3): 149-158.
[13]	Wang Wenbo, Wang Yanping, Wang Huatian, Ma Xuesong, Yi Wenhui. Effects of Different Continuous Cropping and Rotation of Poplar Plantation on Soil Nitrogen Bacteria Community and Nitrogen Metabolism [J]. Scientia Silvae Sinicae, 2016, 52(5): 45-54.
[14]	Xu Tan, Wang Huatian, Zhu Wanrui, Wang Yanping, Li Chuanrong, Jiang Yuezhong. Morphological and Anatomical Traits of Poplar Fine Roots in Successive Rotation Plantations [J]. Scientia Silvae Sinicae, 2015, 51(1): 119-126.
[15]	Fu Jianping, Lan Zaiping, Sun Shangwei, Liu Junqin, Zhang Yong. Soil Water Movement in a Poplar Plantation under Drip Irrigation [J]. Scientia Silvae Sinicae, 2013, 49(6): 25-29.

Simulation of Net Carbon Exchange of Poplar Plantation in North China Plain Based on Decomposition-Reconstruction and Machine Learning

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 0

Related Articles 15

Recommended Articles

Metrics

Comments