An Improved Sap Flow Prediction Model Based on CNN-GRU-BiLSTM and Factor Analysis of Historical Environmental Variables

Abstract

Sap flow is widely used to estimate the transpiration and water consumption of canopies and to manage water resources. In this paper, an improved time series prediction model was proposed by integrating three basic networks—CNN, GRU and BiLSTM—to assess sap flow with historical environment variables. A dataset with 17,569 records of each, including 9 environment variables and 1 sap flow, was applied from a public database of SAPFLUXNET. After normalization, the environment variables were analyzed and composed with the factor analysis method. After the CNN-GRU-BiLSTM structure was designed, N records of three main factors were computed from environment variables, which were measured at N previous moments, and the sap flow was measured at the current moment, and they were applied for each training, validation, and testing cycle. To improve and compare the CNN-GRU-BiLSTM-based model, nine other models, using the methods of multiple linear regression, support vector regression, random forest, LSTM, GRU, BiLSTM, CNN-GRU, CNN-BiLSTM, and CNN-GRU-LSTM, were constructed in this study, respectively. Results show that the performance of the CNN-GRU-BiLSTM-based model has more accuracy than the other nine models we built in this paper, with the mean absolute error, mean squared error, mean absolute percentage error, and coefficient of determination (R2) being 0.0410, 0.0029, 0.2708 and 0.9329, respectively. Furthermore, for a comparison of the descending dimension method of factor analysis, principal component analysis (PCA) and singular value decomposition (SVD) methods were applied and compared, respectively. Results show that the performance of the factor analysis-based model is better than the PCA- or SVD-based model, with the R2 results of the factor analysis-based model being higher than the PCA- and SVD-based models by 5.06% and 10.63%, respectively. This study indicates that the CNN-GRU-BiLSTM-based sap flow prediction model established with a factor analysis of historical environmental variables has optimistic applications for analyzing the transpiration of trees and evaluating water consumption.

A Copula Approach for Predicting Tree Sap Flow Based on Vapor Pressure Deficit

“…While this is a viable approach, field experimental data for heat pulse are required. Recently, Li et al [12] developed an integrated network model by combining CNN (convolutional neural network)-GRU (gated recurrent unit)-BiLSTM (bidirectional long-short-term memory) networks to predict sap flow. However, this network model would require a large amount of experimental data.…”

Estimation of Greenhouse Tomato Transpiration through Mathematical and Deep Neural Network Models Learned from Lysimeter Data

“…Other mathematical models that include regression models, such as linear, exponential, logarithmic, polynomial, and power, have been used to estimate the evaporation and transpiration of crops such as Maize (Saedi, 2022). Multiple linear regression (MLR) (Tu et al, 2019;Bera et al, 2021;Li et al, 2023) was also used to predict transpiration in canopies. However, applications of mathematical models are still limited because their parameterization is very complex and needs a large number of observation data (Fan et al, 2021) and thus impractical in regions where data collection facilities are incomplete (Chia et al, 2022).…”

“…Moreover, the machine learning techniques can capture hydrological time series such as evapotranspiration by utilizing solely a series of predictors without any knowledge of their physical processes (Mehdizadeh et al, 2021;Mohammadi and Mehdizadeh, 2020;Mohammadi et al, 2021;Elbeltagi et al, 2021). Several machine learning models to estimate the transpiration of different crops were assessed, such as artificial neural network (ANN) (Ferreira and da Cunha, 2020;Yong et al, 2023;Tunali et al, 2023), convolutional neural network (CNN) (Ferreira and da Cunha, 2020;Li et al, 2023), long short-term memory (LSTM) (Chen et al, 2020;Chia et al, 2022;Li et al, 2023), gate recurrent unit (GRU) (Chia et al, 2022;Li et al, 2023). The studies above showed the promising performance of machine learning models in estimating transpiration.…”