One of the greatest global challenges in meteorology is predicting the daily precipitation total. The agricultural industry in India is highly dependent on precipitation for water supplies and general socio-economic growth, making accurate rainfall predictions essential. Weather patterns are dynamic, making it difficult to anticipate rainfall with enough accuracy and timeliness, a necessity for many industries, including aviation, energy production, and tourism. Over the past two decades, rainfall forecasting has shown a surprising degree of precision because of artificial intelligence approaches, particularly deep learning (DL). These methods are quite good at identifying hidden trends in past meteorological data, which helps to improve rainfall prediction accuracy. To anticipate the daily intensity of rainfall, this study will use machine learning approaches to determine the major atmospheric factors that contribute to rainfall. To estimate daily precipitation, the study explored various configurations of recurrent neural network (RNN)-based deep neural network models, including Long Short-Term Memory (LSTM), Stacked-LSTM, Bi-LSTM, Gated Recurrent Units (GRU) and Bi-GRU. The RNN models comprised 50 hidden layers, ReLU activation at the input layer and linear activation at output layer. Training utilized Adam Optimizer with a fixed learning rate of 0.000001 and a batch size of 32, Epochs of 100. The dataset, primarily focusing on the India Meteorological Department (IMD) Automatic Weather Station (AWS) dataset from the Almora district of Uttarakhand, was split into training and testing sets with portions of 0.8 and 0.2, respectively. To improve data quality, a thorough pretreatment of AWS data was conducted, as this data is prone to anomalies and missing values. The models’ performances are evaluated using appropriate metrics such as RMSE, MSE, MAE and R2. After investigating various RNN models, it was discovered that one predictive GRU model performed better than the other, obtaining noteworthy metrics like a reduced RMSE of 0.00732, MSE of 0.00005, MAE of 0.00284 and a higher R2 of 0.95524.