Estimating Forest Carbon Fluxes Using Machine Learning Techniques Based on Eddy Covariance Measurements

Abstract

Approximating the complex nonlinear relationships that dominate the exchange of carbon dioxide fluxes between the biosphere and atmosphere is fundamentally important for addressing the issue of climate change. The progress of machine learning techniques has offered a number of useful tools for the scientific community aiming to gain new insights into the temporal and spatial variation of different carbon fluxes in terrestrial ecosystems. In this study, adaptive neuro-fuzzy inference system (ANFIS) and generalized regression neural network (GRNN) models were developed to predict the daily carbon fluxes in three boreal forest ecosystems based on eddy covariance (EC) measurements. Moreover, a comparison was made between the modeled values derived from these models and those of traditional artificial neural network (ANN) and support vector machine (SVM) models. These models were also compared with multiple linear regression (MLR). Several statistical indicators, including coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), bias error (Bias) and root mean square error (RMSE) were utilized to evaluate the performance of the applied models. The results showed that the developed machine learning models were able to account for the most variance in the carbon fluxes at both daily and hourly time scales in the three stands and they consistently and substantially outperformed the MLR model for both daily and hourly carbon flux estimates. It was demonstrated that the ANFIS and ANN models provided similar estimates in the testing period with an approximate value of R2 = 0.93, NSE = 0.91, Bias = 0.11 g C m−2 day−1 and RMSE = 1.04 g C m−2 day−1 for daily gross primary productivity, 0.94, 0.82, 0.24 g C m−2 day−1 and 0.72 g C m−2 day−1 for daily ecosystem respiration, and 0.79, 0.75, 0.14 g C m−2 day−1 and 0.89 g C m−2 day−1 for daily net ecosystem exchange, and slightly outperformed the GRNN and SVM models. In practical terms, however, the newly developed models (ANFIS and GRNN) are more robust and flexible, and have less parameters needed for selection and optimization in comparison with traditional ANN and SVM models. Consequently, they can be used as valuable tools to estimate forest carbon fluxes and fill the missing carbon flux data during the long-term EC measurements.

Youth and forecasting of sustainable development pillars: An adaptive neuro-fuzzy inference system approach

“…Adaptive Neuro-Fuzzy Inference System (ANFIS) is the most commonly used neuro-fuzzy system [41] and it was introduced by Jang [42], based on two approaches: artificial neural networks (ANN) and fuzzy inference systems (FIS) [43, 44] in order to build a system that uses the advantages of both, neural networks and fuzzy logic. ANFIS safeguards the interpretability through if-then rules together with the adaptability, because the neural network optimizes the membership functions of fuzzy rules based on the input-output data that describe the system behavior.…”

“…Various sustainability performance indexes are used to evaluate and benchmark the effectiveness policies and for future planning. For this purpose, various methods have been applied to model the SD and sustainability performance assessment, from multi-criteria decision-making methods to machine learning methods [20, 21, 22, 27, 28, 29, 43–45]. In the past years the ANFIS method had yielded favourable results compared to other methods [30–32, 46].…”

An Artificial Intelligence Approach to Predict Gross Primary Productivity in the Forests of South Korea Using Satellite Remote Sensing Data

“…Forest GPP is a complex and nonlinear problem because its relationships with photosynthetic rates are spatially and temporally heterogeneous. Nowadays, artificial intelligence (AI) approaches are adopted because AI can efficiently handle the problems of nonlinearity and complexity related to forest ecosystems [18]. AI includes machine learning models, such as support vector machine (SVM) and random forest (RF), and neural network models, such as artificial neural network (ANN) and deep neural network (DNN).…”

Understanding and Modeling Climate Impacts on Photosynthetic Dynamics with FLUXNET Data and Neural Networks

“…Methods such as feedforward neural network (FFNN) [8], random forest [9], model trees ensemble [10][11][12] and support vector regression [13,14] have been utilized to estimate land surface-atmosphere fluxes from site level to regional or global scales [3,11,12,[14][15][16][17][18][19]. Adaptive neuro-fuzzy inference system and general regression neural network have also been used to estimate daily carbon fluxes in forest ecosystems [20]. However, very little research has yet leveraged algorithms that specialize in the integration of temporal dependencies, such as hidden Markov model (HMM), long-short term memory (LSTM) [21] or transformer [22].…”