Prediction of sap flow with historical environmental factors based on deep learning technology
Prediction of sap flow with historical environmental factors based on deep learning technology
复制标题
基于深度学习技术的历史环境因素液流预测
DOI：
10.1016/j.compag.2022.107400
复制
发表时间：
2022-11
影响因子：
8.3
通讯作者：
Hailin Feng
中科院分区：
文献类型：
--
作者：
Yane Li;Jianxin Ye;Dayu Xu;Guomo Zhou;Hailin Feng
树干液流是反映土壤-植物-大气连续循环的重要中间环节。因此，预测树干液流，分析树木的蒸腾量，对估算树木的耗水量具有重要意义。在本文中，我们提出了一种基于卷积神经网络门控递归单元（CGRU）混合深度学习方法的新的液流评估方法。该模型使用来自公共SAPFLUXNET数据集的17，568组观察结果的液流和环境因素进行训练和测试。这些组观测从2012年1月1日到2012年12月31日，采集间隔为30分钟，为新西兰的一棵树。在设计了卷积神经网络（CNN）和门控递归单元（GRU）神经网络的CGRU结构后，通过对液流与环境因子的相关性分析，选择了输入变量。此外，先前条件的数量被引入到模型的输入中。结果表明，当先验条件数为16，Adam优化算法的学习率为0.01时，CGRU模型的均方误差、平均绝对百分误差和决定系数分别为0.00231、22.31和0.948。比较结果表明，基于CGRU的树干液流预测模型比其他八个参与测试的模型，包括独立的CNN，GRU，CNN-长短期记忆（LSTM）和五个传统的基于机器学习的模型具有更高的准确性。花在训练上的时间最少的也是CGRU模型。本文提出的基于CGRU的树干液流预测模型可以捕捉复杂的非线性相关性，并产生准确的评估。本文建立的模型对研究林分蒸腾、耗水和土壤-植物-大气循环具有一定的参考价值。
Sap flow is an important intermediate link that reflects the continuous soil–plant-atmosphere cycle. Therefore, it is important to predict the sap flow to analyze the amount of tree transpiration for assessing of water consumption. In this paper, we propose a new sap flow assessment using environmental factors based on a convolutional neural network-gated recurrent unit (CGRU) hybrid deep learning method. The model was trained and tested with the sap flow and environmental factors from 17,568 group observations from public SAPFLUXNET dataset. These group observations measured from January 1, 2012 to December 31, 2012, with acquisition interval of 30 min for one tree of New Zealand Agathis australis. After designed the CGRU structure by integrated a convolutional neural network (CNN) and a gated recurrent unit (GRU) neural network, the input variables were selected with a correlation analysis between sap flow and environmental factors. Additionally, the number of previous conditions were introduced into the input of the model. Results showed that when the number of previous conditions set to 16, the learning rate set to 0.01 with Adam optimization algorithm, the mean squared error, mean absolute percentage error, and coefficient of determination of the CGRU model were 0.00231, 22.31 and 0.948 respectively. Comparing results showed that the CGRU-based sap flow prediction model has more accuracy than other eight models participating in the test including the independent CNN, GRU, CNN-Long short-term memory (LSTM) and five traditional machine learning based models. The least time spent on training is also the CGRU model. The CGRU-based sap flow prediction model proposed in this paper can capture complex nonlinear dependencies and yield accurate assessments of sap flow. Our model we established in this paper can be useful for research on forest stand transpiration, water consumption and the soil–plant-atmosphere cycle.
登录
查看更多内容
使用有限加热持续时间测量液流的改进单探针方法
影响因子：
6.2
作者：
Ren Ruiqi;von der Crone Jonas;Horton Robert;Liu Gang;Steppe Kathy
通讯作者：
Steppe Kathy
影响因子：
3.7
作者：
V. Hernandez-Santana;H. Asbjornsen;T. Sauer;T. Isenhart;K. Schilling;R. Schultz
通讯作者：
V. Hernandez-Santana;H. Asbjornsen;T. Sauer;T. Isenhart;K. Schilling;R. Schultz
影响因子：
6.7
作者：
Aranda, Ismael;Forner, Alicia;Valladares, Fernando
通讯作者：
Valladares, Fernando
影响因子：
5.2
作者：
Zhongwang Wei;K. Yoshimura;Lixin Wang;D. Miralles;S. Jasechko;X. Lee
通讯作者：
Zhongwang Wei;K. Yoshimura;Lixin Wang;D. Miralles;S. Jasechko;X. Lee
我国长三角地区液流密度与环境因子的关系
影响因子：
2.9
作者：
Liu Xin;Zhang Bo;Zhuang Jia-Yao;Han Cheng;Zhai Lu;Zhao Wen-Rui;Zhang Jin-Chi
通讯作者：
Zhang Jin-Chi