# US 12,602,659 B1 · Intelligent maritime emission reporting and compliance system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,659 B1 - Document ID: US12602659B1 - Status: Granted - Kind: B1 - Application number: 18/988,419 - Filed: 2024-12-19 - Granted: 2026-04-14 - Earliest claimed: 2023-10-26 - Assignees: Abu Dhabi Maritime Academy SOLE PROPRIETORSHIP LLC - Applicants: Abu Dhabi Maritime Academy SOLE PROPRIETORSHIP LLC - Inventors: Yasser Alwahedi; Dmitry Mikhaylov; Muhammad Saeed; Mohamed Alhosani - Web page: https://patentgrep.com/patent/US12602659B1 ## CPC - G06Q 10/10: Office automation; Time management - G06F 17/11: for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06Q 50/40: Business processes related to the transportation industry (shipping G06Q10/083) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The present invention relates to a sophisticated maritime emission reporting and compliance system utilizing advanced Long Short-Term Memory (LSTM) neural networks. This innovative system seamlessly integrates with shipboard systems, ensuring accurate data collection and processing. It harnesses data from Intrusion Detection Systems (IDS), on-board sensors, navigation systems, Automatic Identification System (AIS), and remote sensing devices. The collected data undergoes rigorous analysis, producing comprehensive reports aligning with EU Emission Trading System guidelines, obligatory for ships operating within the EU from 2024. This invention guarantees meticulous compliance and streamlined reporting for maritime emissions. ## Claims ### Claim 1 A maritime emission reporting and compliance system, comprising: an Intrusion Detection System (IDS) for ship security monitoring, connected to Operational Technology (OT) systems via secure protocols, incorporating Test Access Point (TAP) and Switched Port Analyzer (SPAN) functionalities for real-time data exchange, wherein the IDS is configured to provide: video feeds configured to visually monitor ship compartments, audio recordings configured for auditory surveillance of ship activities, and network activity logs facilitating digital security analysis and anomaly detection; an Automatic Identification System (AIS); on-board sensors; navigation systems; remote sensing devices, including: Light Detection and Ranging (LIDAR) sensors configured to measure particulate matter, ozone, and nitrogen dioxide levels in the atmosphere, and Sound Navigation and Ranging (SONAR) sensors configured to assess water temperature, salinity, and depth in the sea; and Long Short-Term Memory (LSTM) neural networks configured to process diverse data variables from the IDS, the on-board sensors, the navigation systems, the AIS, and the remote sensing devices; wherein the AIS is configured to generate data tracking ship location, speed, and course, utilizing radio and satellite communication technologies, the data being indicative of ship location coordinates for real-time position tracking, ship speed data for velocity analysis, and course information for directional monitoring; wherein the navigation systems are configured to utilize ship route, speed, and environmental parameters, the navigation systems integrating Global Positioning System (GPS) sensors for precise location tracking in all weather conditions, and gyroscopic sensors for generating accurate ship orientation data during movements; wherein the on-board sensors are configured to deliver real-time data on engine performance, fuel consumption, and emissions, the on-board sensors including: temperature sensors configured to measure engine heat levels with precision, pressure sensors configured to detect changes in engine pressure accurately, gas analyzers configured to record levels of CO2, NOx, and SOx emissions reliably, and particulate matter sensors configured to analyze fine pollutants in emissions comprehensively; and wherein at least one of the LTSM neural networks is configured to utilize the following emission calculation formula for precise CO2 emission calculations: CO 2 ⁢ Emissions = ∑ i = 1 n ⁢ Fuel ⁢ Consumption i × Emission ⁢ Factor i Where Fuel Consumption represents engine fuel consumption, and Emission Factor represents the engine CO2 emission factor. ### Claim 2 (depends on 1) The maritime emission reporting and compliance system as claimed in claim 1, wherein the Long Short-Term Memory (LSTM) neural networks are configured to proactively predict emissions trends and provide early warnings for potential non-compliance with regulatory thresholds, thereby assisting ship operators in taking preventive measures to maintain emissions within permissible limits. ### Claim 3 (depends on 1) The maritime emission reporting and compliance system as claimed in claim 1, wherein the Long Short-Term Memory (LSTM) neural networks employ advanced machine learning techniques to continuously optimize emission factor adjustments, resulting in improved emissions accuracy and cost-effective compliance with regulatory standards. ### Claim 4 (depends on 1) The maritime emission reporting and compliance system as claimed in claim 1, wherein the Long Short-Term Memory (LSTM) neural networks utilize historical emissions data, weather forecasts, and ship performance data to generate predictive emission models, enabling ship operators to make informed decisions regarding voyage routes, fuel selection, and emission reduction strategies to minimize environmental impact and operational costs. ### Claim 5 (depends on 1) The maritime emission reporting and compliance system as claimed in claim 1, wherein the Long Short-Term Memory (LSTM) neural networks facilitate data-driven decision-making by providing ship operators with actionable insights and recommendations based on real-time emissions data, contributing to improved operational efficiency and sustainability in maritime transportation. ### Claim 6 (depends on 1) The maritime emission reporting and compliance system as claimed in claim 1, wherein the Long Short-Term Memory (LSTM) neural networks incorporate self-learning mechanisms, continuously refining their emission prediction models based on historical emissions data and operational performance, thereby enhancing the system's ability to achieve emissions reduction targets and minimize environmental impact. ### Claim 7 A method for calculating CO2 emissions in maritime vessels, the method comprising: collecting maritime emission reporting and compliance system related data using a maritime emission reporting and compliance system, the maritime emission reporting and compliance system comprising: an Intrusion Detection System (IDS) for ship security monitoring, connected to Operational Technology (OT) systems via secure protocols, incorporating Test Access Point (TAP) and Switched Port Analyzer (SPAN) functionalities for real-time data exchange, wherein the IDS is configured to provide: video feeds configured to visually monitor ship compartments, audio recordings configured for auditory surveillance of ship activities, and network activity logs facilitating digital security analysis and anomaly detection; an Automatic Identification System (AIS); on-board sensors; navigation systems; remote sensing devices, including: Light Detection and Ranging (LIDAR) sensors configured to measure particulate matter, ozone, and nitrogen dioxide levels in the atmosphere, and Sound Navigation and Ranging (SONAR) sensors configured to assess water temperature, salinity, and depth in the sea; and Long Short-Term Memory (LSTM) neural networks configured to process diverse data variables from the IDS, the on-board sensors, the navigation systems, the AIS, and the remote sensing devices; the AIS being configured to generate data tracking ship location, speed, and course, utilizing radio and satellite communication technologies, the data being indicative of ship location coordinates for real-time position tracking, ship speed data for velocity analysis, and course information for directional monitoring; the navigation systems being configured to utilize ship route, speed, and environmental parameters, the navigation systems integrating Global Positioning System (GPS) sensors for precise location tracking in all weather conditions, and gyroscopic sensors for generating accurate ship orientation data during movements; the on-board sensors being configured to deliver real-time data on engine performance, fuel consumption, and emissions, the on-board sensors including: temperature sensors configured to measure engine heat levels with precision, pressure sensors configured to detect changes in engine pressure accurately, gas analyzers configured to record levels of CO2, NOx, and SOx emissions reliable, and particulate matter sensors configured to analyze fine pollutants in emissions comprehensively; and at least one of the LTSM neural networks being configured to utilize the following emission calculation formula for precise CO2 emission calculations: CO 2 ⁢ Emissions = ∑ i = 1 n ⁢ Fuel ⁢ Consumption i × Emission ⁢ Factor i Where Fuel Consumption represents engine fuel consumption, and Emission Factor represents the engine CO2 emission factor; and optimizing emission calculations based on ship type, load, and environmental conditions. ### Claim 8 (depends on 7) The method as claimed in claim 7, further comprising utilizing the Long Short-Term Memory (LSTM) neural networks for real-time adjustment of emission factors. ### Claim 9 (depends on 8) The method as claimed in claim 8, wherein the factors include engine load, fuel type, atmospheric pressure, humidity level, sea temperature, ship speed, and/or geographic location. ### Claim 10 (depends on 7) The method as claimed in claim 7, further comprising proactively predicting emissions trends and providing early warnings for potential non-compliance with regulatory thresholds, thereby assisting ship operators in taking preventive measures to maintain emissions within permissible limits. ### Claim 11 (depends on 7) The method as claimed in claim 7, further comprising employing advanced machine learning techniques to continuously optimize emission factor adjustments, so as to improve emissions accuracy and comply with regulatory standards. ### Claim 12 (depends on 7) The method as claimed in claim 7, further comprising utilizing historical emissions data, weather forecasts, and ship performance data to generate predictive emission models, enabling ship operators to make informed decisions regarding voyage routes, fuel selection, and emission reduction strategies to minimize environmental impact and operational costs. ### Claim 13 (depends on 7) The method as claimed in claim 7, further comprising facilitating data-driven decision-making by providing ship operators with actionable insights and recommendations based on real-time emissions data, contributing to improved operational efficiency and sustainability in maritime transportation. ### Claim 14 (depends on 7) The method as claimed in claim 7, wherein the Long Short-Term Memory (LSTM) neural networks incorporate self-learning mechanisms, continuously refining their emission prediction models based on historical emissions data and operational performance, thereby enhancing the system's ability to achieve emissions reduction targets and minimize environmental impact. ### Claim 15 A non-transitory computer-readable storage medium containing instructions that, when executed, cause a computer to perform operations comprising: receiving maritime emission reporting and compliance system related data from a maritime emission reporting and compliance system comprising: an Intrusion Detection System (IDS) for ship security monitoring, connected to Operational Technology (OT) systems via secure protocols, incorporating Test Access Point (TAP) and Switched Port Analyzer (SPAN) functionalities for real-time data exchange, wherein the IDS is configured to provide: video feeds configured to visually monitor ship compartments, audio recordings configured for auditory surveillance of ship activities, and network activity logs facilitating digital security analysis and anomaly detection; an Automatic Identification System (AIS); on-board sensors; navigation systems; remote sensing devices, including: Light Detection and Ranging (LIDAR) sensors configured to measure particulate matter, ozone, and nitrogen dioxide levels in the atmosphere, and Sound Navigation and Ranging (SONAR) sensors configured to assess water temperature, salinity, and depth in the sea; and Long Short-Term Memory (LSTM) neural networks configured to process diverse data variables from the IDS, the on-board sensors, the navigation systems, the AIS, and the remote sensing devices; the AIS being configured to generate data tracking ship location, speed, and course, utilizing radio and satellite communication technologies, the data being indicative of ship location coordinates for real-time position tracking, ship speed data for velocity analysis, and course information for directional monitoring; the navigation systems being configured to utilize ship route, speed, and environmental parameters, the navigation systems integrating Global Positioning System (GPS) sensors for precise location tracking in all weather conditions, and gyroscopic sensors for generating accurate ship orientation data during movements; the on-board sensors being configured to deliver real-time data on engine performance, fuel consumption, and emissions, the on-board sensors including: temperature sensors configured to measure engine heat levels with precision, pressure sensors configured to detect changes in engine pressure accurately, gas analyzers configured to record levels of CO2, NOx, and SOx emissions reliable, and particulate matter sensors configured to analyze fine pollutants in emissions comprehensively; and at least one of the LTSM neural networks being configured to utilize the following emission calculation formula for precise CO2 emission calculations: CO 2 ⁢ Emissions = ∑ i = 1 n ⁢ Fuel ⁢ Consumption i × Emission ⁢ Factor i Where Fuel Consumption represents engine fuel consumption, and Emission Factor represents the engine CO2 emission factor; and generating reports for maritime emission compliance following at least one predetermined guideline, based on the received maritime emission reporting and compliance system related data. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium as claimed in claim 15, wherein the Long Short-Term Memory (LSTM) neural networks are used for real-time adjustment of emission factors. ### Claim 17 (depends on 15) The non-transitory computer-readable storage medium as claimed in claim 15, wherein the operations further comprise proactively predicting emissions trends and providing early warnings for potential non-compliance with regulatory thresholds, thereby assisting ship operators in taking preventive measures to maintain emissions within permissible limits. ### Claim 18 (depends on 15) The non-transitory computer-readable storage medium as claimed in claim 15, wherein the operations further comprise employing advanced machine learning techniques to continuously optimize emission factor adjustments, so as to improve emissions accuracy and comply with regulatory standards. ### Claim 19 (depends on 15) The non-transitory computer-readable storage medium as claimed in claim 15, wherein the operations further comprise utilizing historical emissions data, weather forecasts, and ship performance data to generate predictive emission models, enabling ship operators to make informed decisions regarding voyage routes, fuel selection, and emission reduction strategies to minimize environmental impact and operational costs. ### Claim 20 (depends on 15) The non-transitory computer-readable storage medium as claimed in claim 15, wherein the Long Short-Term Memory (LSTM) neural networks incorporate self-learning mechanisms, continuously refining their emission prediction models based on historical emissions data and operational performance, thereby enhancing the system's ability to achieve emissions reduction targets and minimize environmental impact.