KR-102963457-B1 - Multi-sensor fusion-based regionally customized carbon emission tracking and prediction system and method

Abstract

The present invention relates to a technology for the precise measurement and verification of greenhouse gas emissions, and in particular to a system and method for precisely tracking and predicting omitted emission sources by fusing image-based object recognition, real-time IoT sensor data, satellite imagery, and spatial information. By providing a multi-sensor fusion-based region-specific carbon emission precision tracking and prediction system and method of the present invention, the limitations of voluntary reporting are overcome to reduce reliance on reporting, real-time monitoring of omitted and atypical emission sources is possible, support is provided for the establishment of national greenhouse gas inventories by the government and local governments, substantial contribution is made to carbon neutrality goal management, and it has the effect of being usable for responding to the global MRV system.

Inventors

• 김형도
• 서일영

Assignees

• 주식회사 아이언닉스

Dates

Publication Date

20260513

Application Date

20250730

Claims (6)

1. It includes a carbon emission precision tracking and prediction server (1) for integrating environmental, spatial, and image data to precisely track carbon emission sources in real time, predict and correct emissions based on artificial intelligence, and provide reliability assessment and policy support. The above carbon emission precision tracking and prediction server (1) A sensor fusion module (100) for collecting data including air quality, temperature, CO₂, and methane in real time from field IoT sensors, collecting video data in real time from drones and collecting video data in real time from CCTVs, and preprocessing the data and detecting emission activities including combustion, exhaust, and transportation through an object recognition algorithm, and A spatial information integration engine (200) for integrating and analyzing spatial information including satellite images and GIS maps to update the emission tracking range of the observation target area in real time and to set dynamic observation zones to minimize observation blind spots, and An AI-based estimation and correction module (300) for fusing data collected in real time from a sensor fusion module (100) with past time series data, precisely estimating emissions based on deep learning, and correcting omissions using AI, and A multi-sensor fusion-based region-specific carbon emission precision tracking and prediction system characterized by including an emission heatmap generation module (400) for visualizing cumulative emission fluctuations based on a time axis, detecting abnormal patterns, and automatically identifying surge intervals.
2. In paragraph 1, The above carbon emission precision tracking and prediction server (1) It includes a verification reliability evaluation module (500) for calculating a reliability index by comparing reported data and estimated data and requesting additional observations in areas of high uncertainty, and A multi-sensor fusion-based region-specific carbon emission precision tracking and prediction system characterized by calculating a reliability index by synthesizing error rate, agreement, and data quality indicators, and systematically requesting additional observations for the placement of additional sensors or drone re-observation in the area to perform automatic detection when the reliability index is below a threshold.
3. delete
4. delete
5. delete
6. delete

Description

Multi-sensor fusion-based regionally customized carbon emission tracking and prediction system and method The present invention relates to a technology for the precise measurement and verification of greenhouse gas emissions, and in particular to a system and method for precisely tracking and predicting omitted emission sources by fusing image-based object recognition, real-time IoT sensor data, satellite imagery, and spatial information. Due to the recent tightening of global environmental regulations and the introduction of international standards such as the Carbon Border Adjustment Mechanism (CBAM) and supply chain due diligence guidelines, the importance of precise measurement and management of greenhouse gas emissions has been significantly highlighted for companies and organizations. Traditionally, greenhouse gas emission calculations have relied on theoretical methods—such as fuel consumption and emission factors—or on intermittent field measurements; however, these methods are fraught with various problems, including data inaccuracy, reporting omissions, and limitations in real-time response. In particular, rapidly collecting, integrating, and analyzing emission data generated not only within a company but also across a complex supply chain is a massive undertaking, and relying on manual methods such as Excel frequently leads to data errors and management inefficiencies. Furthermore, to enhance the reliability of greenhouse gas emission estimates and facilitate their policy application, it is essential to incorporate not only simple bottom-up (theoretical) calculation methods but also real-time monitoring in actual environments and the integration of spatial and temporal data. Recently, the integration of diverse data sources—such as IoT sensors, drones, and satellite imagery—with AI-based analysis technologies has necessitated advanced functions like automatic identification of emission sources, correction of omissions, and detection of anomaly patterns. However, due to complex variables such as atmospheric greenhouse gas concentrations, time-series changes in emission behavior, and the distinction between natural and anthropogenic sources, reliable emission estimation is difficult using existing systems alone. Consequently, the introduction of real-time fused data and AI-based prediction and correction technologies has emerged as a critical task. FIG. 1 is a drawing showing the overall configuration of the present invention. FIG. 2 is a configuration diagram of the sensor fusion module (100) of the present invention. FIG. 3 is a diagram for explaining the operation of the sensor fusion module (100) of the present invention. FIG. 4 is a configuration diagram of the AI-based estimation and correction module (300) of the present invention. FIG. 5 is a drawing relating to an embodiment of the system of the present invention. FIG. 6 is an example showing the operating sequence of the system of the present invention. Throughout the entire specification below, the same reference numerals refer to the same components unless there are special circumstances. Terms with the addition of "part" used below may be implemented in software or hardware, and depending on the embodiment, it is possible for a single "part" to be implemented as a single physical or logical component, for multiple "parts" to be implemented as a single physical or logical component, or for a single "part" to be implemented as multiple physical or logical components. Throughout the specification, when it is stated that a part is connected to another part, this may mean a physical connection between the part and the other part, or an electrical connection. Furthermore, when it is stated that a part includes another part, this does not mean that another part other than the other part is excluded unless specifically stated otherwise, but means that additional parts may be included at the designer's choice. Terms such as "first" or "second" are used to distinguish one part from another part, and unless specifically stated otherwise, they do not imply sequential expressions. Also, singular expressions may include plural expressions unless there is an obvious exception in the context. The present invention relates to a multi-sensor fusion-based region-specific precise carbon emission tracking and prediction system and method, and more specifically, to a system and method for precisely tracking and predicting missing emission sources by fusing image-based object recognition, real-time IoT sensor data, satellite imagery, and spatial information. The carbon emission precision tracking and prediction server (1) is intended to precisely track carbon emission sources in real time by fusing various environmental, spatial, and image data, predict and correct emissions based on artificial intelligence, and provide reliability evaluation and policy support. Referring to FIG. 1, the carbon emission precision tracking and prediction server (1) is configur