Comprehensive Evaluation of Machine Learning Techniques for Estimating the Responses of Carbon Fluxes to Climatic Forces in Different Terrestrial Ecosystems

Abstract

Accurately estimating the carbon budgets in terrestrial ecosystems ranging from flux towers to regional or global scales is particularly crucial for diagnosing past and future climate change. This research investigated the feasibility of two comparatively advanced machine learning approaches, namely adaptive neuro-fuzzy inference system (ANFIS) and extreme learning machine (ELM), for reproducing terrestrial carbon fluxes in five different types of ecosystems. Traditional artificial neural network (ANN) and support vector machine (SVM) models were also utilized as reliable benchmarks to measure the generalization ability of these models according to the following statistical metrics: coefficient of determination (R 2), index of agreement (IA), root mean square error (RMSE), and mean absolute error (MAE). In addition, we attempted to explore the responses of all methods to their corresponding intrinsic parameters in terms of the generalization performance. It was found that both the newly proposed ELM and ANFIS models achieved highly satisfactory estimates and were comparable to the ANN and SVM models. The modeling ability of each approach depended upon their respective internal parameters. For example, the SVM model with the radial basis kernel function produced the most accurate estimates and performed substantially better than the SVM models with the polynomial and sigmoid functions. Furthermore, a remarkable difference was found in the estimated accuracy among different carbon fluxes. Specifically, in the forest ecosystem (CA-Obs site), the optimal ANN model obtained slightly higher performance for gross primary productivity, with R 2 = 0.9622, IA = 0.9836, RMSE = 0.6548 g C m −2 day −1 , and MAE = 0.4220 g C m −2 day −1 , compared with, respectively, 0.9554, 0.9845, 0.4280 g C m −2 day −1 , and 0.2944 g C m −2 day −1 for ecosystem respiration and 0.8292, 0.9306, 0.6165 g C m −2 day −1 , and 0.4407 g C m −2 day −1 for net ecosystem exchange. According to the findings in this study, we concluded that the proposed ELM and ANFIS models can be effectively employed for estimating terrestrial carbon fluxes.

Experimental and Machine Learning Studies on Chitosan-Polyacrylamide Copolymers for Selective Separation of Metal Sulfides in the Froth Flotation Process

“…The performance of the developed models was evaluated using the coefficient of determination (R 2 ) as shown in Equation ( 5) and root mean square error (RMSE) shown in Equation ( 6) [17]. These methods are the most commonly used statistical indicators for evaluating the performance of models [56]. R 2 values range between 0 and 1, with values closer to 1 indicating that there is a high correlation.…”

Using machine learning to derive cloud condensation nuclei number concentrations from commonly available measurements

“…GEOS-Chem is a global 3D chemical transport model (CTM) driven by assimilated meteorological observations from the Goddard Earth Observing System (GEOS) of the NASA Global Modeling and Assimilation Office (GMAO). Several research groups develop and use this model, which contains numerous state-of-the-art modules treating emissions (van Donkelaar et al, 2008;Keller et al, 2014) and various chemical and aerosol processes (e.g., Bey et al, 2001;Evans and Jacob, 2005;Martin et al, 2003;Murray et al, 2012;Park, 2004;Pye and Seinfeld, 2010) for solving a variety of atmospheric composition research problems. The ISORROPIA II scheme (Fountoukis and Nenes, 2007) is used to calculate the thermodynamic equilibrium of inorganic aerosols.…”

Estimation of Daily Maize Gross Primary Productivity by Considering Specific Leaf Nitrogen and Phenology via Machine Learning Methods

“…It can effectively model complex processes using extensive field data [23]. Several popular ML methods such as decision tree (DT), random forest (RF), artificial neural network (ANN), and support vector machine (SVM) have demonstrated effectiveness in estimating ecosystem productivity [24][25][26][27]. Yet, existing studies mainly focus on simply utilizing topography, vegetation indices, and meteorological data as model inputs for GPP estimation.…”