Estimating forest carbon fluxes using four different data-driven techniques based on long-term eddy covariance measurements: Model comparison and evaluation

Xianming Dou; Yongguo Yang

doi:10.1016/j.scitotenv.2018.01.202

Estimating forest carbon fluxes using four different data-driven techniques based on long-term eddy covariance measurements: Model comparison and evaluation

Sci Total Environ. 2018 Jun 15:627:78-94. doi: 10.1016/j.scitotenv.2018.01.202. Epub 2018 Jan 28.

Authors

Xianming Dou¹, Yongguo Yang²

Affiliations

¹ Key Laboratory of Coalbed Methane Resources and Reservoir Formation Process of Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China; School of Resources and Geosciences, China University of Mining and Technology, Xuzhou 221116, China.
² Key Laboratory of Coalbed Methane Resources and Reservoir Formation Process of Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China; School of Resources and Geosciences, China University of Mining and Technology, Xuzhou 221116, China. Electronic address: yongguoyang@hotmail.com.

PMID: 29426202
DOI: 10.1016/j.scitotenv.2018.01.202

Abstract

With the recent availability of large amounts of data from the global flux towers across different terrestrial ecosystems based on the eddy covariance technique, the use of data-driven techniques has been viable. In this study, two advanced techniques, namely adaptive neuro-fuzzy inference system (ANFIS) and extreme learning machine (ELM), were developed and investigated for their viability in estimating daily carbon fluxes at the ecosystem level. All the data used in this study were based upon the long-term chronosequence observations derived from the flux towers in eight forest ecosystems. Both ANFIS and ELM methods were further compared with the most widely used artificial neural network (ANN) and support vector machine (SVM) methods. Moreover, we also focused on probing into the effects of internal parameters on their corresponding approaches. Our estimates showed that most variation in each carbon flux could be effectively explained by the developed models at almost all the sites. Moreover, the forecasting accuracy of each method was strongly dependent upon their respective internal algorithms. The best training function for ANN model can be acquired through the trial and error procedure. The SVM model with the radial basis kernel function performed considerably better than the SVM models with the polynomial and sigmoid kernel functions. The hybrid ELM models achieved similar predictive accuracy for the three fluxes and were consistently superior to the original ELM models with different transfer functions. In most instances, both the subtractive clustering and fuzzy c-means algorithms for the ANFIS models outperformed the most popular grid partitioning algorithm. It was demonstrated that the newly proposed ELM and ANFIS models were able to produce comparable estimates to the ANN and SVM models for forecasting terrestrial carbon fluxes.

Keywords: Adaptive neuro-fuzzy inference system; Carbon fluxes; Data-driven techniques; Extreme learning machine; Flux towers; Forest ecosystems.