Optimalisasi Operasi Kapal Niaga Berbasis Carbon Intensity Indicator (CII): Studi Trade-off Emisi Karbon dan Efisiensi Biaya di Indonesia

Prastowo, Hari (2025) Optimalisasi Operasi Kapal Niaga Berbasis Carbon Intensity Indicator (CII): Studi Trade-off Emisi Karbon dan Efisiensi Biaya di Indonesia. Doctoral thesis, Institut Teknologi Sepuluh Nopember.

Text 04111760010008-Doctoral.pdf - Accepted Version Restricted to Repository staff only Download (15MB) | Request a copy

Abstract

Disertasi ini bertujuan untuk mengoptimalkan operasional kapal niaga di Indonesia dengan memanfaatkan Carbon Intensity Indicator (CII) sebagai alat ukur utama dalam menilai efisiensi energi dan dampak lingkungan dari aktivitas operasional kapal. Penelitian ini juga mengkaji
trade-off antara pengurangan emisi karbon dan efisiensi biaya operasional kapal, yang menjadi tantangan utama dalam memenuhi regulasi internasional terkait emisi gas rumah kaca, khususnya yang ditetapkan oleh IMO. Selain itu, penelitian ini mengevaluasi dampak kebijakan pajak karbon terhadap profitabilitas perusahaan, mengingat implikasi fiskal yang dihadapi oleh industri maritim. Disertasi ini ini membandingkan empat metode estimasi konsumsi bahan
bakar kapal, yaitu metode Trozzi, Jalkanen (STEAM2), Wang, dan Mersin yang diterapkan pada kapal niaga dengan tipe dan rute berbeda. Hasil evaluasi menunjukkan bahwa metode
Wang menghasilkan nilai error terendah secara statistik dengan overall MAE sebesar 18,44%, sedangkan metode STEAM2 memberikan hasil yang lebih relevan secara operasional dengan cakupan kecepatan yang paling sering digunakan, menjadikannya metode utama dalam studi ini. Optimalisasi konsumsi bahan bakar tercapai melalui pengaturan kecepatan kapal, yang mengurangi konsumsi bahan bakar hingga 6,2% pada kapal dengan muatan penuh. Oleh karena itu, optimasi kecepatan kapal perlu diterapkan untuk meningkatkan rating CII dan mengurangi konsumsi bahan bakar, yang berdampak positif pada efisiensi operasional dan pengurangan
emisi. Selain itu, simulasi kebijakan fiskal menunjukkan bahwa penerapan pajak karbon dapat menggerus profitabilitas hingga 15–25% pada skenario pelayaran dengan kecepatan tinggi, khususnya pada kapal dengan rating CII D atau E. Hal ini memperkuat urgensi pengelolaan efisiensi operasi demi menekan beban fiskal akibat emisi. Untuk mendukung proses prediksi operasional secara berkelanjutan, disertasi ini mengembangkan model machine learning berbasis algoritma Random Forest. Model menggunaka perhitungan deterministik berbasis STEAM2. Evaluasi model menunjukkan akurasi prediksi yang baik dengan nilai Mean Absolute Error sebesar 0,14 kg/h dan Root Mean Square Error sebesar 0,52 kg/h, menjadikannya andal untuk memprediksi konsumsi bahan bakar dan emisi gas buang secara prediktif. Dengan menggunakan data operasional yang lebih rinci dan analisis berbasis machine learning, sistem ini diharapkan dapat memberikan kontribusi signifikan terhadap pengurangan emisi karbon di sektor pelayaran dan memastikan pemenuhan regulasi IMO.
=======================================================================================================================================
This dissertation aims to optimize the operational efficiency of commercial ships in Indonesia by utilizing the Carbon Intensity Indicator (CII) as the primary tool for assessing energy efficiency and the environmental impact of ship operations. The study also examines the trade-off between carbon emission reduction and operational cost efficiency, which represents a major challenge in meeting international regulations on greenhouse gas emissions,
particularly those set by the International Maritime Organization (IMO). This dissertation compares four ship fuel consumption estimation methods Trozzi, Jalkanen (STEAM2), Wang, and Mersin where applied to commercial vessels operating across various types and routes.
Evaluation results indicate that the Wang method achieved the lowest statistical error, with an overall MAE of 18.44%. However, the STEAM2 method proved to be more operationally
relevant, particularly within the typical speed ranges encountered in real-world operations, thereby positioning it as the primary method adopted in this study. Fuel consumption optimization was achieved through speed management strategies, leading to a reduction in fuel
consumption of up to 6.2% on fully loaded vessels. Consequently, implementing speed optimization is crucial for improving CII ratings and reducing fuel consumption, which
positively impacts both operational efficiency and emission reductions. Furthermore, fiscal policy simulations reveal that the implementation of a carbon tax could reduce net profitability by 15–25% under high-speed sailing scenarios, especially for vessels with poor CII ratings (D
or E). This finding highlights the urgency of managing operational efficiency to mitigate the fiscal burden associated with carbon emissions. To support sustainable operational prediction, this dissertation develops a machine learning model based on the Random Forest algorithm.
The model incorporates deterministic calculations derived from the STEAM2 approach. Evaluation of the model demonstrates robust predictive accuracy, with a Mean Absolute Error of 0.14 kg/h and a Root Mean Square Error of 0.52 kg/h, confirming its reliability in predicting
main engine fuel consumption and associated exhaust gas emissions. By leveraging detailed operational data and machine learning-based analysis, the predictive emission monitoring system developed in this study is expected to make a significant contribution to reducing carbon
emissions in the maritime sector and ensuring compliance with IMO regulations.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Carbon Intensity Indicator (CII), Carbon Emition, Carbon Tax, Fuel Consumption Estimation, Random Forest.
Subjects:	T Technology > TS Manufactures > TS174 Maintainability (Engineering) . Reliability (Engineering) V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM276.A1 Fuel (Including supplies, costs, etc.) V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM731 Marine Engines
Divisions:	Faculty of Marine Technology (MARTECH) > Ocean Engineering > 38001-(S3) PhD Thesis
Depositing User:	Hari Prastowo
Date Deposited:	08 Aug 2025 05:47
Last Modified:	08 Aug 2025 06:37
URI:	http://repository.its.ac.id/id/eprint/127993

Actions (login required)

View Item