• Peketi Shanmuk Sai Manoj
• Pentapalli Deepa Priyanka
• Sabbavarupu Sai Kishore
• Kondareddy Venkata Aravind Reddy
• Singampalli Sriharsha

The” Maritime Emissions Prediction and Berth Scheduling System” addresses key issues in marine logistics and environmental sustainability. Although maritime transportation is essential to world trade, it also has a major negative impact on greenhouse gas emissions and air pollution. Using machine learning approaches for emissions prediction and optimization algorithms for berth scheduling, we present a comprehensive system in this research. To anticipate emissions levels based on ship features and operational factors, the emissions prediction component uses sophisticated machine learning models such as LightGBM, Random Forest, and Feed Forward Neural Network (FNN). In addition, to effectively assign berths while taking into account variables like vessel type, size, and environmental impact, the berth scheduling module uses Mixed-Integer Linear Programming (MILP) optimization. The system’s objectives are to improve maritime transportation’s operational effectiveness, lower emissions, and lessen its negative environmental effects. To ensure the suggested system remains relevant and effective in the changing maritime sector landscape, future additions could involve integrating with port management systems, optimizing for dynamic environmental conditions, and incorporating real-time data streams.

Maritime emissions prediction, Berth scheduling, Machine learning, Optimization, Environmental sustainability.

"Fostering Green Ports Through Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.m669-m675, April-2024, Available :http://www.jetir.org/papers/JETIR2404C86.pdf

"Fostering Green Ports Through Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppm669-m675, April-2024, Available at : http://www.jetir.org/papers/JETIR2404C86.pdf