Although machine learning (ML) techniques are increasingly popular in water resource studies, they are not extensively utilized in modeling snowmelt. In this study, we developed a model based on a deep learning long short-term memory (LSTM) for snowmelt-driven discharge modeling in a Himalayan basin. For comparison, we developed the nonlinear autoregressive exogenous model (NARX), Gaussian process regression (GPR), and support vector regression (SVR) models. The snow area derived from moderate resolution imaging spectroradiometer (MODIS) snow images along with remotely sensed meteorological products were utilized as inputs to the models. The Gamma test was conducted to determine the appropriate input combination for the models. The shallow LSTM model with a hidden layer achieved superior results than the deeper LSTM models with multiple hidden layers. Out of seven optimizers tested, Adamax proved to be the aptest optimizer for this study. The evaluation of the ML models was done by the coefficient of determination (R2), mean absolute error (MAE), modified Kling–Gupta efficiency (KGE’), Nash–Sutcliffe efficiency (NSE), and root-mean-squared error (RMSE). The LSTM model (KGE’ = 0.99) enriched with snow cover input achieved the best results followed by NARX (KGE’ = 0.974), GPR (KGE’ = 0.95), and SVR (KGE’ = 0.949), respectively. The outcome of this study proves the applicability of the ML models, especially the LSTM model, in predicting snowmelt driven discharge in the data-scant mountainous watersheds.

In this study, a Long Short-Term Memory (LSTM) network approach is employed to evaluate the prediction performance of PM_2.5 in the Beijing–Tianjin–Hebei region (BTH). The proposed method is evaluated using the hourly air quality datasets from the China National Environmental Monitoring Center, European Center for Medium-range Weather Forecasts ERA5 (ECMWF-ERA5), and Multi-resolution Emission Inventory for China (MEIC) for the years 2016 and 2017. The predicted PM_2.5 concentrations demonstrate a strong correlation with the observed values (R² = 0.871–0.940) in the air quality dataset. Furthermore, the model exhibited the best performance in situations of heavy pollution (PM_2.5 > 150 μg/m³) and during the winter season, with respective R² values of 0.689 and 0.915. In addition, the influence of ECMWF-ERA5’s hourly meteorological factors was assessed, and the results revealed regional heterogeneity on a large scale. Further evaluation was conducted by analyzing the chemical components of the MEIC inventory on the prediction performance. We concluded that the same temporal profile may not be suitable for addressing emission inventories in a large area with a deep learning method.