Keywords
Copula entropy
lete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)
Environmental factors
Submitted : 2026-04-21
Accepted : 2026-05-06
Published : 2026-05-21
Abstract
Copula entropyTree trunk sap flow is jointly affected by environmental factors and physiological mechanisms, showing nonlinear and random characteristics, which makes it difficult for traditional methods to achieve high-precision prediction. To address this problem, this paper introduces CEEMDAN to decompose the sap flow sequence at multiple scales, combines Copula entropy and signal energy to construct a modal component reconstruction strategy, and further uses LSTM to realize prediction. Experimental results show that the proposed model achieves 0.6759 and 0.9755 in MAPE and R2 indicators respectively, which is superior to the comparison models, providing a new idea for sap flow prediction and transpiration flux estimation.
References
Xie Z, et al., 2019, Climate Feedback of Human Water Use Activities and Its Impact on Terrestrial Water Cycle: Progress and Challenges. Advances in Earth Science, 34(8): 801–813.
Sun S, et al., 2021, Unraveling the Effect of Inter-Basin Water Transfer on Reducing Water Scarcity and its Inequality in China. Water Research, 2021(194): 116931.
Tang Q, et al., 2019, Comprehensive Integration and Simulation of Terrestrial Water Cycle Processes. Advances in Earth Science, 34(2): 115–123.
Gharbia S, et al., 2018, Spatially Distributed Potential Evapotranspiration Modeling and Climate Projections. Science of The Total Environment, 2018(633): 571–592.
Huang Y, et al., 2021, Dynamics of Populus euphratica Sap Flow Rate and Its Relationship with Meteorological Factors in the Growing Season in the Southeast of the Kumtag Desert. Journal of Plant Sciences, 39(3): 247–257.
Yao Y, et al., 2021, Comparison and Application of Calculation Methods for Forest Transpiration Water Consumption. Chinese Journal of Applied Ecology, 32(8): 2989–2998.
Teng H, et al., 2020, Analysis of Water Consumption Characteristics and Construction of Prediction Model of Ziziphus jujuba. Journal of Central South University of Forestry and Technology, 40(1): 22–29.
Bai Z, et al., 2016, Dynamic Changes of Stem Sap Flow of Larix sibirica. Journal of Hebei Agricultural University, 39(3): 49–54.
Li X, et al., 2014, Relationship Between Transpiration Water Consumption of Ginkgo biloba and Environmental Factors. Journal of Beijing Forestry University, 36(4): 23–29.
Lü S, Sun Y, 2022, Short-Term Load Forecasting Method Based on EMD-RVM Model. Microcomputer Applications, 38(10): 22–24+31.
Fu Z, et al., 2022, Research on Degradation Degree Prediction Method of Hydropower Units Based on EEMD and LSTM. Acta Energiae Solaris Sinica, 43(2): 75–81.
Torres M, et al., 2011, A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, IEEE International Conference on Acoustics, Speech and Signal Processing, 4144–4147.
Ma J, 2022, Copula Entropy: Theory and Applications.
Yanling L, Yunpeng Z, Ling Z, 2017, Variations Detection of Bivariate Dependence Based on Copulas Model. International Journal of Applied Mathematics, 47(2): 255–260.
Hochreiter S, Schmidhuber J, 1997, Long Short-Term Memory. Neural Computation, 9(8): 1735–1780.
Poyatos R, et al., 2016, SAPFLUXNET: Towards a Global Database of Sap Flow Measurements. Tree Physiology, 36(12): 1449–1455.
Iwasaki A, 2020, Deriving the Variance of the Discrete Fourier Transform Test Using Parseval’s Theorem. IEEE Transactions on Information Theory, 66(2): 1164–1170.