Methane (CH4) is one of the main greenhouse gases, whose retrieval is easily affected by atmospheric water (H2O) and surface albedo. In this letter, based on a radiative transfer model, the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) radiance with different H2O and surface albedo is simulated as training data. Back propagation (BP) feed-forward neural network algorithm in machine learning is used to train the CH4 retrieval model, which is applied to quantify the atmospheric CH4 concentration. This method can effectively decrease the impact of atmospheric H2O and surface albedo on CH4 retrieval. Moreover, this machine learning-based approach separates the processes of model training and prediction. This enables rapid characterization of CH4 emission point sources in images as the matched filter (MF) method, while also obtaining the column-averaged concentration of CH4, similar to the optimal estimation (OE) method. The research results indicate that the mean absolute percentage error (MAPE) of the optimal BP model is as low as 0.33%. If necessary, further increases in training data can improve the resolution and applicability of the model.

中文翻译：

---

基于反向传播神经网络和模拟AVIRIS-NG数据的大气甲烷反演

甲烷（CH4）是主要温室气体之一，其回收易受大气水（H2O）和地表反照率的影响。在这封信中，基于辐射传输模型，模拟了具有不同水和表面反照率的下一代机载可见光/红外成像光谱仪（AVIRIS-NG）辐射率作为训练数据。采用机器学习中的反向传播（BP）前馈神经网络算法来训练CH4反演模型，用于量化大气CH4浓度。该方法可以有效降低大气H2O和地表反照率对CH4反演的影响。此外，这种基于机器学习的方法将模型训练和预测的过程分开。这使得能够像匹配滤波器 (MF) 方法一样快速表征图像中的 CH4 排放点源，同时还获得 CH4 的列平均浓度，类似于最佳估计 (OE) 方法。研究结果表明，最优BP模型的平均绝对百分比误差（MAPE）低至0.33%。如有必要，进一步增加训练数据可以提高模型的分辨率和适用性。