当前位置: X-MOL 学术Agric. For. Meteorol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Modelling Photosynthetic Active Radiation (PAR) through meteorological indices under all sky conditions
Agricultural and Forest Meteorology ( IF 6.2 ) Pub Date : 2021-09-02 , DOI: 10.1016/j.agrformet.2021.108627
A. García-Rodríguez 1 , D. Granados-López 1 , S. García-Rodríguez 1 , M. Díez-Mediavilla 1 , C. Alonso-Tristán 1
Affiliation  

In this study, ten-minute meteorological data-sets recorded at Burgos, Spain, are used to develop models of Photosynthetic Active Radiation (PAR) following two different procedures: multilinear regression and Artificial Neural Networks. Ten Meteorological Indices (MIs) are chosen as inputs to the models: clearness index (kt), diffuse fraction (kd), direct fraction (kb), Perez's clear sky index (ɛ), brightness index (Δ), cloud cover (CC), air temperature (T), pressure (P), solar azimuth cosine (cosZ), and horizontal global irradiation (RaGH). The experimental data are clustered according to the sky conditions, following the CIE standard sky classification. A previous feature selection procedure established the most adequate MIs for modelling PAR in clear, partial and overcast sky conditions. RaGH was the common MI used by all models and for all sky conditions. Additional variables were also included: the geometrical parameter, cosZ, and three variables related to the sky conditions, kt,ε, and Δ. Both modelling methods, multilinear regression and ANN, yielded very high determination coefficients (R2) with very close results in the models for each of the different sky conditions. Slight improvements can be observed in the ANN models. The results underline the equivalence of multilinear regression models and ANN models of PAR following previous feature selection procedures.



中文翻译:

在所有天空条件下通过气象指数模拟光合有效辐射 (PAR)

在这项研究中,在西班牙布尔戈斯记录的 10 分钟气象数据集用于开发光合主动辐射模型(一种电阻) 遵循两种不同的程序:多元线性回归和人工神经网络。选择了 10 个气象指数 (MI) 作为模型的输入:清晰指数 (), 扩散分数 (d), 直接分数 ()、佩雷斯晴空指数(ɛ)、亮度指数(Δ), 云量 (CC), 气温 (), 压力 (), 太阳方位余弦 (CZ) 和水平全局辐照 (电阻一种GH)。实验数据根据天空条件进行聚类,遵循 CIE 标准天空分类。先前的特征选择程序为建模建立了最合适的 MI一种电阻 在晴朗、局部和多云的天空条件下。 电阻一种GH是所有模型和所有天空条件使用的通用 MI。还包括其他变量:几何参数,CZ,以及与天空条件相关的三个变量, ,ε, 和 Δ. 两种建模方法,多元线性回归和人工神经网络,都产生了非常高的决定系数(电阻2) 在每种不同天空条件的模型中都有非常接近的结果。在 ANN 模型中可以观察到轻微的改进。结果强调了PAR的多元线性回归模型和 ANN 模型在先前特征选择程序之后的等效性。

更新日期:2021-09-02
down
wechat
bug