Tropical cyclones (TCs) also known as typhoons or hurricanes are low-pressure systems that develop over warm ocean waters within the tropical and subtropical region. TCs are one of the most catastrophic weather events in terms of human casualty and property damage. Due to this destructive nature, accurate forecasting of both TC course and intensity is essential for the safety of population reducing financial loss. Efforts made by the meteorologists have caused gradual improvements in TC track and intensity forecasting performance during the last couple of decades. However, this steady performance could be interrupted as a result of irregularities in the synoptic weather patterns. In particular, the known interactions among TC track, TC intensity, and the factors governing them, such as large-scale environmental flow and sea surface temperature, have been observed to be altered under a changing climatic pattern during the recent years. As the factors governing TC track and intensity are becoming increasingly erratic and as the lack of consistent data in the TC formation basins continues to challenge our understanding of these erratic patterns, the operational forecasting models may become less effective in the future. Moreover, spatial resolution of the operational models has been often found insufficient to adequately capture the small-scale interactions between TC and its governing factors, which also reduces the efficiency of the operational TC track and intensity forecasting models. Considering these issues causing ailed prediction performance, a combined TC track and intensity forecasting model was developed using Learning in an Error-driven and Associative, Biologically Realistic Algorithm (Leabra). The model was trained and tested for producing 12- and 24-h forecast using satellite-recorded infrared, sea surface temperature, wind direction, wind speed, and sea level pressure images of all the TCs formed in the Bay of Bengal between the years 2000 and 2022. After training, the model could accurately predict track and intensity levels for more than 98% of the test images. Test images for which the network produced inaccurate track and intensity predictions, the average track prediction error was 29 km for 12 h forecast and 39.5 km for 24 h forecast as well as the average intensity prediction error was 13.25 km/h or 7.15 knots for both 12 and 24 h. This prediction performance specifies the model’s potential for operational deployment as a computationally inexpensive but efficient solution to the TC track and intensity prediction problem.