This study introduces a novel deep learning model called CNN-BiLSTM for near-real-time daily wildfire spread prediction. The model integrates Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) modules to capture spatial and temporal patterns. The research uses the Visible Infrared Imaging Radiometer Suite (VIIRS) active fire product and various environmental variables, including topography, land cover, temperature, NDVI, wind information, precipitation, soil moisture, and runoff, to train the model. The evaluation results show that the CNN-BiLSTM model outperforms benchmark models such as LSTM and CNN-LSTM, achieving an F1 Score of 0.58 and 0.73 for validation and training sets, respectively. The study also explores the impact of parameter configurations and environmental variables on the model's performance, highlighting the importance of optimal threshold values and time steps. The findings suggest that the CNN-BiLSTM model is a promising tool for enhancing wildfire management efforts through its capacity for near-real-time prediction.This study introduces a novel deep learning model called CNN-BiLSTM for near-real-time daily wildfire spread prediction. The model integrates Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) modules to capture spatial and temporal patterns. The research uses the Visible Infrared Imaging Radiometer Suite (VIIRS) active fire product and various environmental variables, including topography, land cover, temperature, NDVI, wind information, precipitation, soil moisture, and runoff, to train the model. The evaluation results show that the CNN-BiLSTM model outperforms benchmark models such as LSTM and CNN-LSTM, achieving an F1 Score of 0.58 and 0.73 for validation and training sets, respectively. The study also explores the impact of parameter configurations and environmental variables on the model's performance, highlighting the importance of optimal threshold values and time steps. The findings suggest that the CNN-BiLSTM model is a promising tool for enhancing wildfire management efforts through its capacity for near-real-time prediction.