Air temperature forecasting has been a vital climatic factor required for different applications in many areas such as energy, industry, agriculture, health, environment, and meteorology. This study compares the performances of two static neural networks (NNs) used for the prediction of hourly ambient air temperatures in a coastal area of Turkey. Thirteen parameters from Land Surface Diagnostics and Surface Flux Diagnostics Collections from the MERRA-2 reanalysis dataset including pressure, surface specific humidity, wind speed, wind direction, air density at surface, evaporation, planetary boundary layer height, total precipitable water vapor, total precipitation, total cloud area fraction, total column ozone, greenness fraction, and leaf area index were used as input parameters for the models. Feed-Forward Neural Network (FFNN) and Cascade Forward Neural Network (CFNN) models were applied to forecast hourly ambient air temperatures at 2 m height from the surface. The results indicated that the most accurate and reliable predictions were obtained by the CFNN model with 30 neurons, while the lowest prediction performance was obtained by the FFNN model with 5 neurons. The root mean squares error (RMSE), mean absolute error (MAE) and coefficient of determination (R²) values for training (and testing) of the CFNN model with 30 neurons were 0.358 (0.376), 0.273 (0.283), and 0.997 (0.992), respectively, whereas the same parameters were 0.430 (0.447), 0.334 (0.343), and 0.996 (0.989) for the FFNN model with 5 neurons. The CFNN model had a lower RMSE and MAE, and a higher R² than the FFNN model. These results showed that increasing the number of neurons of hidden layers from 5 to 30 provided better model performance.

气温预测一直是能源、工业、农业、健康、环境和气象等许多领域不同应用所需的重要气候因素。本研究比较了用于预测土耳其沿海地区每小时环境气温的两个静态神经网络 (NN) 的性能。来自 MERRA-2 再分析数据集的陆地表面诊断和表面通量诊断集合的 13 个参数，包括压力、地表比湿度、风速、风向、地表空气密度、蒸发、行星边界层高度、可降水总量、总降水量、总云面积分数、总柱状臭氧、绿度分数和叶面积指数用作模型的输入参数。应用前馈神经网络 (FFNN) 和级联前向神经网络 (CFNN) 模型来预测距地表 2 m 高度的每小时环境气温。结果表明，具有 30 个神经元的 CFNN 模型获得的预测最准确和可靠，而具有 5 个神经元的 FFNN 模型获得的预测性能最低。均方根误差 (RMSE)、平均绝对误差 (MAE) 和决定系数 (R ² ) 具有 30 个神经元的 CFNN 模型的训练（和测试）值分别为 0.358 (0.376)、0.273 (0.283) 和 0.997 (0.992)，而相同的参数分别为 0.430 (0.447)、0.3434 (0.334) (0.992)和 0.996 (0.989) 对于具有 5 个神经元的 FFNN 模型。与 FFNN 模型相比，CFNN 模型具有更低的 RMSE 和 MAE，以及更高的R ²。这些结果表明，将隐藏层的神经元数量从 5 增加到 30 可提供更好的模型性能。