Identifying the most significant input parameters for predicting global solar radiation using an ANFIS selection procedure

Mohammadi, Kasra; Shamshirband, Shahaboddin; Kamsin, Amirrudin; Lai, P. C.; Mansor, Zulkefli

doi:10.1016/j.rser.2016.05.065

Cited by 79 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, machine-learning methods have been successfully applied to the estimation of meteorological and hydrological variables, such as air temperature (Cobaner, Citakoglu, Kisi, & Haktanir, 2014;Kisi & Shiri, 2014;Kisi & Sanikhani, 2015a;), solar radiation (Mohammadi, Shamshirband, Kamsin, Lai, & Mansor, 2016), dew point temperature (Kisi, Kim, & Shiri, 2013), soil temperature (Hadi, Deo, Mundher, Okan, & Ozgur, 2018;Kim & Singh, 2014), precipitation (Kisi & Sanikhani, 2015b), and evapotranspiration (Feng, Cui, Zhao, Hu, & Gong, 2016;Gavili, Sanikhani, Kisi, & Mahmoudi, 2017;Sanikhani, Kisi, Maroufpoor, & Yaseen, 2018). A few studies have aimed to predict SM using machine-learning methods.…”

Section: Introductionmentioning

confidence: 99%

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Pan

Shangguan

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

Soil moisture (SM) is a key variable of land surface‐atmosphere interactions. Data‐driven methods have been used to predict SM, but the predictability of SM has not been well evaluated. This study investigated what variables and methods can be used to better predict SM for leading times of 7 days or longer with a global coverage of FLUXNET site data for the first time. Three machine‐learning models, that is, Bayesian linear regression, random forest, and gradient boosting regression tree, are used for the prediction. Variables including atmospheric forcing, surface soil temperature, time variables (year, day of year, and hour), the Fourier transformation of time variables, and lagged SM (7‐ to 14‐day lagged) were sequentially added into models. A framework with five experiments is designed for factorial exploration of SM predictability. A stepwise method was used to build the best models for each site. The performance of regression models became better when adding more explaining variables in most cases. The results showed that from 50 to 95% of variation of the best models can be explained. The important explaining variables are lagged surface SM, followed by day of year, year, soil temperature, and atmospheric forcing. The predictability of SM depends highly on SM memory characteristics and the persistence of seasonality. The effect of SM memory characteristics on SM prediction as an initial condition question has been widely discussed in this paper. Our results also provide an insight that mechanisms of seasonality effects on SM should be also paid more attention to.

show abstract

Section: Introductionmentioning

confidence: 99%

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Pan

Shangguan

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…The mean absolute error (MAE) indicates the average quantity of total absolute bias error between estimated and actual values. The coefficient of correlation (R) determines the linear relationship of the predicted data with the measured data [46]. Knowledge of these criteria is relevant to evaluate whether the prediction is sub-estimated or over-estimated with respect to real data.…”

Section: Anfis Pv Module Modelingmentioning

confidence: 99%

Temperature Estimation for Photovoltaic Array Using an Adaptive Neuro Fuzzy Inference System

et al. 2017

View full text Add to dashboard Cite

Abstract:Module temperature is an important parameter of photovoltaic energy systems since their performance is affected by its variation. Several cooling controllers require a precise estimation of module temperature to reduce excessive heating and power losses. In this work, an adaptive neuro fuzzy inference system technique is developed for temperature estimation of photovoltaic systems. For the learning process, experimental measurements comprising six environmental variables (temperature, irradiance, wind velocity, wind direction, relative humidity, and atmospheric pressure) and one operational variable (photovoltaic power output) were used as training parameters. The proposed predictive model comprises a zero-order Sugeno neuro fuzzy system with two generalized bell-shaped membership functions per input and 128 fuzzy rules. The model is validated with experimental information from an instrumented photovoltaic system with a fitness correlation parameter of R = 95%. The obtained results indicate that the proposed methodology provides a reliable tool for estimation of modules temperature based on environmental variables. The developed algorithm can be implemented as part of a cooling control system of photovoltaic modules to reduce the efficiency losses.

show abstract

“…As an alternative to places where there are no data records of solar radiation, estimated values can be obtained with the use of alternative mathematical models to quantify solar radiation (Mohammadi et al, 2016). These models differ from each other, by the degree of complexity and by input variables (Mostafa et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Performance of solar radiation models for obtaining reference evapotranspiration to Santa Maria-RS, Brazil

Boscaini

Robaina

Peiter

et al. 2020

Agraria

View full text Add to dashboard Cite

In the absence of observed data from Solar radiation (Sr), it is possible to estimate it using mathematical models. In general, the models vary in degree of complexity and the adjustment coefficients, and these must be calibrated to the place of interest to obtain the best performance. In this regard, the present work aims to evaluate the performance of simplified models of solar radiation in obtaining reference evapotranspiration. The data were obtained from the automatic meteorological station of the National Meteorological Institute (Inmet), located in Santa Maria -RS, Brazil. In the estimates of global solar radiation and its influence on reference evapotranspiration, ten models were evaluated, five models with the coefficients calibrated and five models, with the coefficients determined by the authors. It was observed that all the models studied presented performance index above 0.82, indicating "optimal" performance. Thus, both calibration and non-calibration models to obtain Sr do not interfere with ETo estimation. Therefore, given the impossibility of obtaining Sr data in meteorological stations, it is possible to use any of the models analyzed.Desempenho de modelos de radiação solar para obtenção da evapotranspiração de referência para Santa Maria-RS, Brasil RESUMO: Na ausência de dados observados de Radiação Solar (Rs) é possível estimá-la mediante a utilização de modelos matemáticos. Em geral, os modelos variam em grau de complexidade e nos coeficientes de ajuste, e esses devem ser calibrados para o local de interesse para obtenção do melhor desempenho. Neste sentido, o presente trabalho tem como finalidade avaliar o desempenho de modelos simplificados de radiação solar na obtenção da evapotranspiração de referência. Os dados foram adquiridos junto a estação meteorológica automática do Instituto Nacional de Meteorologia (Inmet), localizada na cidade de Santa Maria -RS. Nas estimativas de radiação solar global e sua influência na evapotranspiração de referência, foram avaliados dez modelos, sendo cinco modelos com os coeficientes calibrados e cinco modelos, com os coeficientes determinados pelos autores. Observou-se que, todos os modelos estudados, apresentaram índice de desempenho acima de 0,82, indicando "ótimo" desempenho. Dessa forma, tanto os modelos com calibração quanto os sem calibração para a obtenção da Rs, não interferem na estimativa da ETo. Sendo assim, dada a impossibilidade de se obter os dados de Rs nas estações meteorológicas, é possível utilizar qualquer um dos modelos analisados. Palavras-chave: temperatura do ar; demanda evaporativa; Penman-Monteith; necessidade hídricaPerformance of solar radiation models for obtaining reference evapotranspiration to Santa Maria-RS, Brazil Rev. Bras. Cienc. Agrar., Recife, v.15, n.1, e7661, 2020 2/8

show abstract

Identifying the most significant input parameters for predicting global solar radiation using an ANFIS selection procedure

Cited by 79 publications

References 51 publications

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site data

Temperature Estimation for Photovoltaic Array Using an Adaptive Neuro Fuzzy Inference System

Performance of solar radiation models for obtaining reference evapotranspiration to Santa Maria-RS, Brazil

Contact Info

Product

Resources

About