Prediction of diffuse photosynthetically active radiation using different soft computing techniques

Wang, Lunche; Hu, Bo; Kisi, Özgür; Zounemat‐Kermani, Mohammad; Gong, Wei

doi:10.1002/qj.3081

Cited by 23 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measurements of diffuse PAR at latitudes similar to that of Lampedusa were reported by Dye (2004) and Wang et al (2017). Dye et al (2004) and in different terrestrial environments (woody savannas and grassland, respectively).…”

Section: Mean Annual Cyclessupporting

confidence: 62%

A long-term time series of global and diffuse photosynthetically active radiation in the Mediterranean: interannual variability and cloud effects

Trisolino¹,

Sarra²,

Anello³

et al. 2018

Atmos. Chem. Phys.

View full text Add to dashboard Cite

Abstract. Measurements of global and diffuse photosynthetically active radiation (PAR) have been carried out on the island of Lampedusa, in the central Mediterranean Sea, since 2002. PAR is derived from observations made with multi-filter rotating shadowband radiometers (MFRSRs) by comparison with a freshly calibrated PAR sensor and by relying on the on-site Langley plots. In this way, a long-term calibrated record covering the period 2002–2016 is obtained and is presented in this work. The monthly mean global PAR peaks in June, with about 160 W m−2, while the diffuse PAR reaches 60 W m−2 in spring or summer. The global PAR displays a clear annual cycle with a semi amplitude of about 52 W m−2. The diffuse PAR annual cycle has a semi amplitude of about 12 W m−2. A simple method to retrieve the cloud-free PAR global and diffuse irradiances in days characterized by partly cloudy conditions has been implemented and applied to the dataset. This method allows retrieval of the cloud-free evolution of PAR and calculation of the cloud radiative effect, CRE, for downwelling PAR. The cloud-free monthly mean global PAR reaches 175 W m−2 in summer, while the diffuse PAR peaks at about 40 W m−2. The cloud radiative effect, CRE, on global and diffuse PAR is calculated as the difference between all-sky and cloud-free measurements. The annual average CRE is about −14.7 W m−2 for the global PAR and +8.1 W m−2 for the diffuse PAR. The smallest CRE is observed in July, due to the high cloud-free condition frequency. Maxima (negative for the global, and positive for the diffuse component) occur in March–April and in October, due to the combination of elevated PAR irradiances and high occurrence of cloudy conditions. Summer clouds appear to be characterized by a low frequency of occurrence, low altitude, and low optical thickness, possibly linked to the peculiar marine boundary layer structure. These properties also contribute to produce small radiative effects on PAR in summer. The cloud radiative effect has been deseasonalized to remove the influence of annual irradiance variations. The monthly mean normalized CRE for global PAR can be well represented by a multi-linear regression with respect to monthly cloud fraction, cloud top pressure, and cloud optical thickness, as determined from satellite MODIS observations. The behaviour of the normalized CRE for diffuse PAR can not be satisfactorily described by a simple multi-linear model with respect to the cloud properties, due to its non-linear dependency, in particular on the cloud optical depth. The analysis suggests that about 77 % of the global PAR interannual variability may be ascribed to cloud variability in winter.

show abstract

Section: Mean Annual Cyclessupporting

confidence: 62%

A long-term time series of global and diffuse photosynthetically active radiation in the Mediterranean: interannual variability and cloud effects

Trisolino¹,

Sarra²,

Anello³

et al. 2018

Atmos. Chem. Phys.

View full text Add to dashboard Cite

show abstract

“…The important parameters are fraction of sunshine hours, latitude, altitude, precipitation, air temperature, and relative humidity, etc. Therefore, many empirical 3–8 and machine learning 9–13 techniques are in vogue. One of the popular machine learning technique is the artificial neural network (ANN).…”

Section: Introductionmentioning

confidence: 99%

“…18 These reported parameters were found to be very helpful in estimating the solar radiation by using soft-computing methodologies such as ANN, adaptive neuro-fuzzy inference systems (ANFIS), Yang's hybrid model (YHM), Bristow–Campbell model (BCM), and M5 model tree (M5Tree) and remote sensing. 12,13,19,20 Feng et al. 2 have applied 15 typical empirical models for estimating diffuse radiation in China.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient solar radiation estimation using cohesive artificial neural network technique with optimal synaptic weights

Kumar

Kaur

2019

Proceedings of the Institution of Mechanical Engineers, Part A:

View full text Add to dashboard Cite

Estimation of solar potential is vital for renewable energy applications. In several studies, artificial neural networks have been employed to model solar radiation using various meteorological parameters. The collection and availability of the most appropriate input parameters is important for getting an accurate artificial neural network model. The present study aims to estimate the global solar radiation using different meteorological parameters and identify the significant parameters based on the analysis of synaptic weights in an artificial neural network model using the connection weight approach. Initially, artificial neural network and empirical models is applied to estimate the solar radiation in Chamba region. The artificial neural network architecture 5-48-15-1 resulted in minimum mean absolute percentage error of 12.15%. The mean absolute percentage error values for linear models are found to be 18.95%, 15.39%, and 21.62%, respectively. Thereafter, connection weight approach is applied to find significant parameters. The efficacy of the approach has been shown through a case study related to estimation of solar radiations in the Hamirpur region situated in the state of Himachal Pradesh (India). Five input parameters, namely temperature (T), relative humidity (RH), clearness index (KT), precipitation (PT), and pressure (P), have been considered to estimate solar radiations using a feed-forward neural network. The proposed approach infers that temperature is the most significant parameter followed by humidity and pressure. The clearness index and precipitation has been found to have the least effect on the estimation of solar radiations. Results also indicate that artificial neural network based technique is more accurate compared to empirical model.

show abstract

“…Therefore, using remote sensing data to model climate data is a convenient and economical way. In recent years, the artificial intelligence approaches such as Coactive Neuro-Fuzzy Inference System (CANFIS), Adaptive Neuro-Fuzzy Inference System (ANFIS) which is hybrid of Artificial Neural Networks (ANN) and Fuzzy Inference System (FIS), Fuzzy-Logic (FL) [2], Radial Basis Neural Network (RBNN) which is a type of ANN, Support Vector Machines (SVM), Generalized Regression Neural Network (GRNN) which is a type of ANN, Genetic Algorithm (GA), Wavelet Transformation (WT) and Multi-Layer Perceptron Neural Network (MLPNN) have been significantly utilized in diverse fields such as modelling climate indicators [3][4][5][6][7][8][9][10][11][12][13][14][15]. In order to model the target data, researchers used terrestrial station data as inputs, which have many limitations.…”

Section: Introductionmentioning

confidence: 99%

Evaluating machine learning methods and satellite images to estimate combined climatic indices

Norouzi

Behzadi

2019

NMCE

View full text Add to dashboard Cite

The reflections recorded on satellite images have been affected by various environmental factors. In these images, some of these factors are combined with other environmental factors that cannot be distinguished. Therefore, it seems wise to model these environmental phenomena in the form of hybrid indicators. In this regard, satellite imagery and machine learning methods can play a unique role in modeling and data mining of climatic phenomena as a result of their significant advantages, including their availability and analysis. Therefore, addressing the improvement and expansion of machine learning methods and modeling algorithms using remote sensing data is inevitable. In this study, 7 well-known machine learning algorithms are applied with different initial data to show that satellite images are able to estimate the combined indices more accurately. A new index (HT) is also defined by combining the quantities of relative humidity and temperature. Then, machine learning algorithms are trained for each of these three quantities. For each of the temperature and relative humidity quantities, four optimal bands were selected using the PCA method, then a combination of these optimal bands was determined for the HT index. Two criteria are used to validate the results: Root Mean Square Error (RMSE) statistic and comparing the map of the interpolation method with the result of this study. RMSE values show that satellite imagery could have a high ability to model and estimate composite indices. Classification-KNN-Coarse and Ensemble-Bagged Trees with accuracy of 79.8626 % and 84.9281% are identified as the best machine learning methods for temperature and relative humidity, while the best accuracy to estimate the HT index is 92.8792% for Matern 5/2 GPR. Therefore, it can be said that by changing the methods of database preparation, the modeling results can be changed effectively in order to train models.

show abstract

Prediction of diffuse photosynthetically active radiation using different soft computing techniques

Cited by 23 publications

References 50 publications

A long-term time series of global and diffuse photosynthetically active radiation in the Mediterranean: interannual variability and cloud effects

A long-term time series of global and diffuse photosynthetically active radiation in the Mediterranean: interannual variability and cloud effects

Efficient solar radiation estimation using cohesive artificial neural network technique with optimal synaptic weights

Evaluating machine learning methods and satellite images to estimate combined climatic indices

Contact Info

Product

Resources

About