Adaptive Neuro-Fuzzy Inference System integrated with solar zenith angle for forecasting sub-tropical Photosynthetically Active Radiation

作者：Deo, Ravinesh C.^*; Downs, Nathan J.; Adamowski, Jan F.; Parisi, Alfio, V

来源：Food and Energy Security, 2019, 8(1): e00151.

DOI：10.1002/fes3.151

• ANFIS-CM
• genetic programming
• M5 Tree
• multiple linear regression
• photosynthetically active radiation
• Random Forest
• real-time forecasting

Advocacy for climate mitigation aims to minimize the use of fossil fuel and to support clean energy adaptation. While alternative energies (e.g., biofuels) extracted from feedstock (e.g., micro-algae) represent a promising role, their production requires reliably modeled photosynthetically active radiation (PAR). PAR models predict energy parameters (e.g., algal carbon fixation) to aid in decision-making at PAR sites. Here, we model very short-term (5-min scale), sub-tropical region's PAR with an Adaptive Neuro-Fuzzy Inference System model with a Centroid-Mean (ANFIS-CM) trained with a non-climate input (i.e., only the solar angle, theta(Z)). Accuracy is benchmarked against genetic programming (GP), M5Tree, Random Forest (RF), and multiple linear regression (MLR). ANFIS-CM integrates fuzzy and neural network algorithms, whereas GP adopts an evolutionary approach, M5Tree employs binary decision, RF employs a bootstrapped ensemble, and MLR uses statistical tools to link PAR with theta(Z). To design the ANFIS-CM model, 5-min theta(Z) (01-31 December 2012; 0500H-1900H) for sub-tropical, Toowoomba are utilized to extract predictive features, and the testing accuracy (i.e., differences between measurements and forecasts) is evaluated with correlation (r), root-mean-square error (RMSE), mean absolute error (MAE), Willmott (WI), Nash-Sutcliffe (E-NS), and Legates & McCabes (E-LM) Index. ANFIS-CM and GP are equivalent for 5-min forecasts, yielding the lowest RMSE (233.45 and 233.01 mu mol m(-2)s(-1)) and MAE (186.59 and 186.23 mu mol m(-2)s(-1)). In contrast, MLR, M5Tree, and RF yields higher RMSE and MAE [(RMSE = 322.25 mu mol m(-2)s(-1), MAE = 275.32 mu mol m(-2)s(-1)), (RMSE = 287.70 mu mol m(-2)s(-1), MAE = 234.78 mu mol m(-2)s(-1)), and (RMSE = 359.91 mu mol m(-2)s(-1), MAE = 324.52 mu mol m(-2)s(-1))]. Based on normalized error, ANFIS-CM is considerably superior (MAE = 17.18% versus 19.78%, 34.37%, 26.39%, and 30.60% for GP, MLR, M5Tree, and RF models, respectively). For hourly forecasts, ANFIS-CM outperforms all other methods (WI = 0.964 vs. 0.942, 0.955, 0.933 & 0.893, and E-LM = 0.741 versus 0.701, 0.728, 0.619 & 0.490 for GP, MLR, M5Tree, and RF, respectively). Descriptive errors support the versatile predictive skills of the ANFIS-CM model and its role in real-time prediction of the photosynthetic-active energy to explore biofuel generation from micro-algae, studying food chains, and supporting agricultural precision.

• 出版日期2019-2
• 单位McGill