Though downward longwave radiation (DLR) models curb the paucity of data, they are mostly location dependent. Therefore, there is a need to evaluate their relevance given the increasing use of machine learning techniques. In this study, cloudless DLR estimates from regression models and soft computing models of neural networks (NN), support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS) were compared. Clear days from September 1992 to August 1994 and July 1995 to March 1998 in Ilorin (8.50 °N, 4.55 °E), Nigeria were considered, while the predictors for the models were water vapour pressure, e and air temperature, T. A new regression model in relation to the Boltzmann constant, σ: 1.0141.0×1030×eT13+0.699σT4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left(1.014\left(\frac{1.0\times {10}^{30}\times e}{T^{13}}\right)+0.699\right)\sigma {T}^4 $$\end{document}, was better than other regression models and applicable at another location. Between 1 and 8, the sixth degree was the best polynomial kernel function in SVR models’ estimations of cloudless DLR. Though the new regression model was comparable to expert systems, ANFIS was still the best model due to its consistent high correlations and lowest estimation errors. Experience-based computational procedures that combine enough logics with neural networks respond effectively to other data. Furthermore, the analytical relationship between water vapour pressure and air temperature in DLR’s mechanism should be redefined accordingly, while the sixth polynomial should be used as the default setting in SVR systems.

中文翻译：

---

无云下行长波辐射深度学习与回归建模

虽然向下长波辐射 (DLR) 模型控制了数据的缺乏，但它们主要取决于位置。因此，鉴于机器学习技术的使用越来越多，有必要评估它们的相关性。在这项研究中，比较了来自回归模型和神经网络 (NN)、支持向量回归 (SVR) 和自适应神经模糊推理系统 (ANFIS) 的软计算模型的无云 DLR 估计。考虑了 1992 年 9 月至 1994 年 8 月和 1995 年 7 月至 1998 年 3 月在尼日利亚伊洛林（8.50°N，4.55°E）的晴天，而模型的预测因子是水蒸气压力 e 和气温 T。一个新的与玻尔兹曼常数σ相关的回归模型：1.0141.0×1030×eT13+0。699σT4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin} {-69pt} \begin{document}$$ \left(1.014\left(\frac{1.0\times {10}^{30}\times e}{T^{13}}\right)+0.699\right) \sigma {T}^4 $$\end{document}，优于其他回归模型，适用于其他位置。在 1 到 8 之间，六阶是 SVR 模型对无云 DLR 的估计中最好的多项式核函数。尽管新的回归模型与专家系统相当，但 ANFIS 仍然是最好的模型，因为它具有一致的高相关性和最低的估计误差。基于经验的计算程序将足够的逻辑与神经网络相结合，有效地响应其他数据。此外，