Intelligent space simulation and measurement method and system for low-carbon urban renewal

Abstract

The application discloses a low-carbon city updating-oriented intelligent space simulation and measurement method and system, and relates to the technical field of big data processing.The low-carbon city updating-oriented intelligent space simulation and measurement method and system comprises the following steps: S1, acquiring construction carbon source data, and performing time axis repositioning, space object binding, signal drift correction and normalization processing; S2, identifying construction carbon disturbance candidate segments and performing carbon source demixing, and constructing construction carbon disturbance atoms; S3, constructing counterfactual operation baseline, and executing carbon debt working condition reenactment; S4, identifying the carbon recovery state of space objects, and generating carbon measurement evidence chains.The application effectively improves the fusion processing capability among construction phase carbon source data, operation phase energy consumption data, space object data and environmental response data, and solves the problem that it is difficult to unify data modeling of construction carbon input, post-updating operation emission reduction and space object state.

Description

Technical Field

[0001] This invention relates to the field of big data processing technology, specifically to a method and system for intelligent spatial simulation and measurement for low-carbon urban renewal. Background Technology

[0002] With the development of existing building renovation, rooftop energy facility integration, road cross-section adjustment, public space renewal, and greening replanting, data on construction machinery operation, temporary energy consumption, vehicle trajectory, material consumption, video recognition, environmental monitoring, building energy consumption, energy output, road traffic, and thermal environment response are continuously increasing. Existing systems mostly use project-wide or single data tables for statistics, lacking spatial object-oriented data calibration, data attribution, data unmixing, data replay, and data traceability mechanisms. This makes it difficult to form a verifiable data chain between carbon data during the construction phase and emission reduction data during the operation phase.

[0003] For example, the invention patent with announcement number CN118798450B discloses a method for simulating and predicting the spatial pattern of land use based on collaborative spatial planning and carbon reduction control. This method includes: collecting data, preprocessing the collected data, and establishing a basic database for optimizing low-carbon land use; calculating annual land use carbon emissions using energy carbon emissions and spatial mapping technology, and predicting the land use carbon emission coefficient for the target year using the GM(1,1) model; predicting and optimizing the quantitative structure of low-carbon land use based on Markov and linear programming models, combined with natural development trends and land use planning requirements; simulating and predicting land use patterns under different scenarios using the PLUS model; evaluating the carbon reduction benefits of the low-carbon land use optimization method based on collaborative spatial planning, and proposing multi-scale low-carbon decision-making and optimization suggestions.

[0004] For example, the invention patent with announcement number CN114037199B discloses a method for quantitatively measuring the resilience of urban street networks, including: collecting spatial vector data of urban street networks in the target urban area based on open-source network map data; determining the semantic model of "points" and "edges" of the street network, mapping the actual space into network topology data composed of "points" and "edges"; designing random removal and ordered removal experiments for dynamic deduction and iterative simulation; plotting the relationship curve between changes in urban street network performance indicators and removal ratios, and determining the structural change threshold point of the street network and the street network's ability to withstand disturbances.

[0005] In existing technologies, existing systems typically store and calculate carbon emission data during the construction phase, updated operational emission reduction data, and spatial object data separately, lacking a unified time axis relocation mechanism, spatial object baseline chain, construction carbon source unmixing mechanism, counterfactual operational baseline reconstruction mechanism, and carbon measurement evidence chain generation mechanism.

[0006] Therefore, in order to address the above issues, there is an urgent need for intelligent spatial simulation and measurement methods and systems for low-carbon urban renewal. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides an intelligent spatial simulation and measurement method and system for low-carbon urban renewal, which solves the problem of difficulty in unifying data modeling of construction carbon input, post-renewal operation emission reduction, and spatial object status.

[0009] Technical solution

[0010] To achieve the above objectives, this invention provides the following technical solution: a smart spatial simulation and measurement method for low-carbon urban renewal, comprising: S1, acquiring construction carbon source data and performing time axis relocation, spatial object binding, signal drift correction, and normalization processing to obtain a perturbation spatial benchmark dataset; S2, based on the perturbation spatial benchmark dataset, identifying candidate segments of construction carbon perturbation and performing carbon source unmixing, constructing construction carbon perturbation atoms, and generating a set of construction carbon perturbation atoms; S3, based on the set of construction carbon perturbation atoms, constructing a counterfactual operating baseline, performing carbon debt reenactment, and generating a spatial carbon repayment chain; S4, based on the set of construction carbon perturbation atoms and the spatial carbon repayment chain, evaluating the critical migration of carbon recovery, identifying the carbon recovery status of spatial objects, and generating a carbon measurement evidence chain.

[0011] Further, the specific process of acquiring construction carbon source data and performing time axis relocation, spatial object binding, signal drift correction, and normalization to obtain the disturbance spatial reference dataset is as follows: The construction carbon source data includes equipment acquisition timestamps, edge reception timestamps, measurement timestamps, platform writing timestamps, current measurement time, work surface activation start time, machinery start / stop time, vehicle dwell start time, material weight change time, spatial adjacency relationships, work surface activation status, construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, work surface activation signals, video spatial recognition signals, environmental disturbance signals, construction machinery positions, material consumption positions, and vehicle dwell positions. The system includes the location of temporary energy consumption, the location of the work surface activation, the location of video recognition hotspots, the association of work surface activation, the association of equipment operation, the association of vehicle parking, the association of material consumption, the association of time overlap, and the spatial object number. A time-tracking relocation method based on equipment acquisition timescales, edge reception timescales, and platform writing timescales is used to relocate the construction carbon source data along the time axis. A spatial object hierarchy mapping method is used to establish parent-child relationships among building component layers, construction surface layers, building layers, road section layers, public space layers, and street grid layers. A signal drift correction method based on spatial adjacency relationships and work surface activation states is used to correct misbinding of spatial objects. The construction carbon source data undergoes amplitude normalization processing to output a perturbation spatial reference dataset.

[0012] Furthermore, based on the perturbation spatial reference dataset, the specific process of identifying candidate segments of construction carbon disturbance and performing carbon source unmixing is as follows: Based on the perturbation spatial reference dataset, using the calibration timescale obtained from time axis relocation as the time axis, and using the start time of work surface activation, the start and stop times of machinery, the start time of vehicle dwell, and the time of material weight change as window boundaries, a synchronization window is segmented. State change points that fall into the same synchronization window and are spatially adjacent are aggregated to form candidate segments of construction carbon disturbance; spatial consistency judgment is performed on the candidate segments of construction carbon disturbance, and the spatial reference calibration matching method is used to determine whether the candidate segments fall into the same spatial reference object; based on the carbon source signal unmixing method of constraint graph decomposition, the candidate segments of construction carbon disturbance are used as graph nodes, and the work surface activation association, equipment operation, etc. are used as the graph nodes. Correlation, vehicle dwelling correlation, material consumption correlation, spatial adjacency, and temporal overlap correlation are used as graph edges to construct a carbon source unmixing constraint graph. Carbon source unmixing, also known as carbon source signal unmixing, refers to the data processing process of allocating mixed carbon source signals to corresponding construction carbon disturbance candidate segments according to temporal overlap ratio, spatial overlap ratio, and numbering consistency when construction machinery operation signals, temporary energy consumption signals, and vehicle dwelling signals all point to two or more spatial objects within the same measurement time window. Based on the temporal overlap ratio, spatial overlap ratio, and numbering consistency of each candidate segment with respect to machinery signals, energy consumption signals, transportation signals, and material signals, the allocation ratio of each candidate segment to the mixed carbon source signal is calculated, and the mixed carbon source signal is decomposed into the corresponding construction carbon disturbance candidate segments according to the allocation ratio.

[0013] Furthermore, the specific process of constructing construction carbon perturbation atoms and generating a set of construction carbon perturbation atoms is as follows: Candidate fragments of construction carbon perturbation are atomized using a perturbation kernel locking method. The activation record of the work surface within the candidate fragment is used as a spatial anchor point. Construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, work surface activation signals, video spatial recognition signals, and environmental perturbation signals are used as perturbation evidence to determine the perturbation core region. Within the perturbation core region, a work-dominant fingerprint is constructed using a work evidence co-directional encoding method. When the work-dominant fingerprint is within the perturbation core region... If the fingerprints remain consistent, the perturbation core region is determined as a construction carbon perturbation atom. A construction carbon perturbation atom refers to the smallest construction carbon source data unit formed under the same perturbation core region and the same operation-dominant fingerprint. The construction carbon perturbation atom includes an atom number, a primary home space object number, a shared space object number, a perturbation start time, a perturbation end time, and an operation-dominant fingerprint. When the operation-dominant fingerprint switches within the perturbation core region, the perturbation core region is divided into sub-regions with the fingerprint switching point as the boundary, and construction carbon perturbation atoms are determined for each sub-region, generating a set of construction carbon perturbation atoms.

[0014] Furthermore, based on the construction carbon perturbation atom set, the specific process of constructing the counterfactual operating baseline is as follows: the state fields changed by the update action are extracted from the updated object state, and the state is backfilled using the operating records of the space object before the update, generating candidate operating states when the current update action is not implemented; environmental consistency correction is performed on the candidate operating states using the matching method of similar environmental segments; the response relationship of the space object to the external environment in the state before the update is established respectively, and the environmental conditions of the current measurement time slice are superimposed with the residual correction results of similar environmental segments to obtain the counterfactual operating baseline when the current update action is not implemented; the counterfactual emission reduction difference is extracted using the difference component decomposition method, and the counterfactual emission reduction difference is corrected using the emission reduction effectiveness screening method.

[0015] Furthermore, the specific process of performing carbon debt reenactment and generating a space carbon repayment chain is as follows: First, the primary spatial object, operational fingerprint, spatial impact range, and corresponding update actions of the carbon disturbance atoms during construction are read and converted into reenactment objects. Second, operational segments before the current update action is implemented are extracted from the counterfactual operational baseline, and measured operational segments under the same spatial object, the same measurement time slice, and the same environmental conditions are extracted from the updated operational state to form a set of reenactment comparison segments. Third, for different types of reenactment objects, the pre-defined relationship between the update action type and the carbon disturbance response rules is established. The system uses a mapping relationship to perform morphological comparisons on a set of reenactment control segments, generating a space carbon repayment chain. The relationship between construction carbon debt and operational emission reductions is confirmed through a repayment chain closure verification method. If the counterfactual operational baseline predicts that a certain update action should produce a low-carbon response, but the measured operational segment after the update does not show the predefined low-carbon response pattern, the operational condition reenactment is deemed a failure. When the operational condition reenactment fails, the corresponding counterfactual emission reduction difference is no longer directly included in the effective repayment; the corresponding construction carbon perturbation atom is marked as a carbon debt to be verified, and the repayment chain is frozen. When the operational condition reenactment is successful, a space carbon repayment simulation set is generated.

[0016] Furthermore, based on the construction carbon perturbation atom set and the space carbon repayment chain, the specific process for assessing the critical migration for carbon recovery is as follows: The starting time when a space object transitions from the construction state to the operational state is obtained through the construction completion marker and the operation start marker; the intermediate measurement time is obtained from the measurement time axis from the operation start time to the current measurement time; the counterfactual operational baseline before the current update action is implemented is compared with the updated operational state under the same space object, the same time slice, and the same environmental conditions to obtain the counterfactual emission reduction difference; the difference between the updated operational measured state and the counterfactual carbon repayment simulation results is compared to obtain the model drift penalty term; the basic carbon perturbation amount is obtained by converting the mechanical operation carbon component, temporary energy consumption carbon component, transportation perturbation carbon component, and material implicit carbon component in the construction carbon perturbation atom using the same carbon measurement caliber; and the spatial carbon perturbation amount is obtained by calculating the probability distribution of the construction carbon perturbation atom belonging to different candidate space objects. Inter-attribution entropy; extract the counterfactual emission reduction difference for each discrete moment corresponding to each measurement cycle from the start of operation to the current measurement moment, multiply it by the spatial coupling compensation coefficient to obtain the emission reduction; take the negative of the model drift penalty term and perform exponential operation to obtain the drift attenuation factor; multiply the emission reduction by the drift attenuation factor to obtain the effective emission reduction; accumulate the effective emission reductions obtained at all discrete moments in chronological order and add 1 to obtain the effective carbon compensation; multiply the basic carbon perturbation by the sum of the carbon source aliasing amplification factor and the constant 1 to obtain the aliasing corrected carbon perturbation; multiply the aliasing corrected carbon perturbation by the exponent of the spatial attribution entropy to obtain the corrected carbon perturbation; sum the corrected carbon perturbation of all construction carbon perturbation atoms and add 1 to obtain the corrected carbon debt; divide the effective carbon compensation by the corrected carbon debt to obtain the carbon compensation coverage; take the logarithm of the carbon compensation coverage and perform sigmoid compression to obtain the critical migration value for carbon recovery.

[0017] Furthermore, the specific process for identifying the carbon recovery status of spatial objects is as follows: when the carbon recovery critical migration value is less than the carbon recovery status threshold, the target spatial object is determined to still be in a state of residual carbon debt; when the carbon recovery critical migration value reaches the carbon recovery status threshold, the target spatial object is determined to have entered the carbon recovery completed state; when the carbon recovery critical migration value rises within M measurement periods but has not yet reached the carbon recovery status threshold, the target spatial object is marked as a carbon recovery migration object; when the carbon recovery critical migration value falls back, the target spatial object is marked as a carbon recovery unstable object; for spatial objects in the building component layer, construction surface layer, building layer, road section layer, public space layer, and street grid layer, the hierarchical state back-writing and parent-child object transmission verification method is used to write back upwards along the parent-child affiliation relationship. When the condition replay fails, the completion state transmission stops, the carbon recovery status is calculated, the carbon recovery status of adjacent spatial objects is analyzed spatially, and the carbon recovery critical surface dataset is output.

[0018] Furthermore, the specific process of generating the carbon measurement evidence chain is as follows: when a building facade, rooftop work surface, road excavation section, greening replanting area, or public space unit still experiences new construction carbon disturbance atoms generated by construction re-intervention events after entering the operation phase, and the corresponding spatial carbon repayment chain operation condition reenactment fails, it is identified as an abnormal accumulation of construction carbon debt; the identified abnormal carbon recovery status is written into the carbon measurement evidence chain, and a traceable chain evidence report is formed by using the spatial object number as the main index and the carbon recovery critical migration value as the status index.

[0019] Furthermore, the second aspect of this invention provides an intelligent spatial simulation and measurement system for low-carbon urban renewal, applied to an intelligent spatial simulation and measurement method for low-carbon urban renewal, comprising: a spatial spectrum calibration module, used to acquire construction carbon source data and perform time axis relocation, spatial object binding, signal drift correction and normalization processing to obtain a perturbation spatial benchmark dataset; a carbon perturbation atom identification module, used to identify construction carbon perturbation candidate segments and perform carbon source unmixing based on the perturbation spatial benchmark dataset, construct construction carbon perturbation atoms, and generate a construction carbon perturbation atom set; a counterfactual carbon repayment simulation module, used to construct a counterfactual operating baseline based on the construction carbon perturbation atom set, perform carbon debt condition reenactment, and generate a spatial carbon repayment chain; and a critical migration measurement module, used to evaluate the critical migration of carbon recovery based on the construction carbon perturbation atom set and the spatial carbon repayment chain, identify the carbon recovery status of spatial objects, and generate a carbon measurement evidence chain.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) In this invention, the construction carbon source data is relocated by multiple time scales through equipment acquisition time scale, edge reception time scale and platform writing time scale, and the construction machinery operation signal, temporary energy consumption signal, vehicle trajectory signal, material weight change signal, work surface activation signal, video space recognition signal and environmental disturbance signal are written into the disturbance space benchmark dataset, so that data from different sources, different sampling frequencies and different spatial granularities can be processed under a unified time axis and a unified spatial object number, thereby improving the consistency and computability of the low-carbon urban renewal data base.

[0023] (2) This invention uses a carbon source unmixing constraint diagram to decompose mixed carbon source signals generated by shared work surfaces, shared road sections, shared material storage areas, or shared temporary energy meters within the same time window, and assigns mechanical energy signals, temporary energy signals, transportation disturbance signals, and material-implied carbon signals to corresponding construction carbon disturbance candidate segments. This processing can solve the problem of unclear data attribution when multiple construction objects share a data source, and improve the accuracy of multi-source construction data at the spatial object level.

[0024] (3) In this invention, by perturbation kernel locking and unidirectional encoding of operational evidence, candidate fragments of construction carbon perturbation are further transformed into construction carbon perturbation atoms, and mechanical motion fingerprints, energy consumption waveform fingerprints, vehicle service fingerprints, material flow fingerprints, work surface location fingerprints, and environmental response fingerprints are generated. This processing can compress continuous, mixed, and heterogeneous construction data into construction carbon perturbation atoms with fixed fields, clear sources, and stable spatial attribution, reducing the data complexity of subsequent counterfactual modeling and carbon recovery calculations.

[0025] (4) This invention, through carbon debt reenactment, incorporates construction carbon perturbation atoms, counterfactual operation segments, updated measured operation segments, and operation response patterns into the space carbon repayment simulation result set, and generates a space carbon repayment chain through spatial closure, mechanistic closure, and temporal closure verification. This process can organize construction phase data and operation phase data into a traceable data chain, rather than only storing total results, thereby improving the data correlation capability between construction carbon debt and operation emission reduction.

[0026] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0027] Figure 1 This is a flowchart of the intelligent space simulation and measurement method for low-carbon urban renewal according to the present invention.

[0028] Figure 2 This is a diagram of the intelligent space simulation and measurement system architecture for low-carbon urban renewal according to the present invention.

[0029] Figure 3 This is a normalized variation diagram of multi-source signals in the perturbation spatial reference dataset of this invention;

[0030] Figure 4 This is a diagram showing the composition of carbon source components in the carbon perturbation atoms during construction according to the present invention.

[0031] Figure 5 This is a trend chart of the critical migration value for carbon recovery in this invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Please see Figures 1-5This invention provides a technical solution: a smart spatial simulation and measurement method for low-carbon urban renewal, comprising: S1, acquiring construction carbon source data and performing time axis relocation, spatial object binding, signal drift correction and normalization processing to obtain a perturbation spatial benchmark dataset; S2, based on the perturbation spatial benchmark dataset, identifying candidate fragments of construction carbon perturbation and performing carbon source unmixing, constructing construction carbon perturbation atoms, and generating a set of construction carbon perturbation atoms; S3, based on the set of construction carbon perturbation atoms, constructing a counterfactual operating baseline, performing carbon debt reenactment, and generating a spatial carbon repayment chain; S4, based on the set of construction carbon perturbation atoms and the spatial carbon repayment chain, evaluating the critical migration of carbon recovery, identifying the carbon recovery status of spatial objects, and generating a carbon measurement evidence chain.

[0034] Specifically, the process of acquiring construction carbon source data and performing time-axis relocation, spatial object binding, signal drift correction, and normalization to obtain the perturbation spatial reference dataset is as follows:

[0035] Construction carbon source data is read from construction machinery controllers, temporary energy meters, vehicle positioning records, material batch records, video recognition results, and environmental monitoring records. The construction carbon source data includes equipment acquisition timestamps, edge reception timestamps, measurement timestamps, platform writing timestamps, current measurement time, work surface activation start time, machinery start / stop time, vehicle dwell start time, material weight change time, spatial adjacency relationships, work surface activation status, construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, work surface activation signals, video spatial recognition signals, environmental disturbance signals, construction machinery location, material consumption location, vehicle dwell location, temporary energy consumption attribution location, work surface activation location, video recognition hotspot location, work surface activation association, equipment operation association, vehicle dwell association, material consumption association, temporal overlap association, and spatial object number. The equipment acquisition time stamp is derived from the local clock of the construction machinery controller and vehicle positioning recording terminal; the edge reception time stamp is derived from the reception time of the edge gateway; the platform writing time stamp is derived from the data entry timestamp of the central platform; and the measurement timestamp is explicitly defined as the sensor sampling time, replacing the original current measurement time and maintaining consistency with the measurement time axis. All three types of time stamps use NTP synchronization, with an allowable deviation of no more than 100 milliseconds. Abnormal time stamps, such as those missing or exceeding a reasonable range, are filled using linear interpolation or the previous valid value.

[0036] The time-stamp relocation method, based on device acquisition timescales, edge reception timescales, and platform write timescales, uses the device acquisition timescale as the baseline. If the difference between the edge reception timescale and the device acquisition timescale exceeds the allowable deviation of 100 milliseconds, the median or weighted average of the three timescales is used to calculate the calibration timescale, with weights of 0.5, 0.3, and 0.2, respectively. For misalignments caused by network latency, a latency compensation algorithm is used to dynamically adjust the timescale based on the difference between the edge reception timescale and the platform write timescale. In case of conflict, the device acquisition timescale is used first.

[0037] This system addresses time discrepancies in construction machinery start-up and shutdown, vehicle entry and exit, material batch arrival, and temporary energy consumption fluctuations across different data acquisition links; it also relocates construction carbon source data along a time axis; and establishes parent-child relationships among building component layers, construction surface layers, building layers, road section layers, public space layers, and street grid layers using a spatial object hierarchy mapping method. Furthermore, it employs a signal drift correction method based on spatial adjacency relationships and the activation state of work surfaces. The drift criterion is the deviation of the spatial object binding relationship from the spatial adjacency matrix within a continuous time window, with a trigger threshold of a deviation exceeding 0.3 (i.e., an adjacency probability below 70%). The correction rule is: when the activation state of a work surface changes abruptly without a change in spatial location, the spatial object is rebound to the work surface with the highest adjacency. After correction, consistency checks are performed using five measurement periods before and after the correction. If contradictions still exist, the data is marked for manual review to correct misbinding of spatial objects. Amplitude normalization is applied to the construction carbon source data. The normalization benchmark is the statistical mean of each signal type under historical undisturbed conditions. The normalization formula is: the normalized amplitude equals the original amplitude minus the minimum value, divided by the difference between the maximum and minimum values, with a value range of 0 to 1. After normalization, inverse normalization verification is performed, comparing the energy spectrum distribution and peak characteristics of the signals before and after normalization. If the deviation exceeds 5%, the normalization parameters are recalibrated. A perturbation spatial benchmark dataset is output.

[0038] like Figure 3 The figure shows the normalized variation of multi-source signals from the disturbance spatial reference dataset. The graph uses the measurement period as the horizontal axis and the normalized value as the vertical axis, displaying the changes in construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, video spatial recognition signals, and environmental disturbance signals over a continuous measurement period. Figure 3It is evident that various construction carbon source signals gradually increase from low values ​​in the early stages, reaching a peak near the middle measurement period, and then gradually decline, consistent with the process of construction disturbances from initiation, enhancement, concentrated operation, to weakening at the end. Construction machinery operation signals, temporary energy consumption signals, and video spatial recognition signals exhibit high synchronicity within the peak range, indicating a high degree of activation at the work site and a clear correspondence between machinery operation, temporary energy consumption, and on-site construction activities. Vehicle trajectory signals and material weight change signals also synchronously enhance near their peaks, indicating that vehicle entry and exit, material consumption, and work site activities overlap within the same measurement range, serving as important evidence for identifying candidate segments of construction carbon disturbances and demixing carbon sources.

[0039] This implementation scheme corrects signal drift by using spatial adjacency relationships and the activation status of the work surface, reducing misbinding of spatial objects caused by vehicle positioning drift, video hotspot offset, material consumption location offset, and temporary energy consumption attribution offset. Through amplitude normalization and inverse normalization verification, construction carbon source signals of different dimensions and sampling sources can be compared at the same scale. This results in a perturbation spatial benchmark dataset with unified time scale, clearly defined spatial objects, traceable drift records, and consistent signal scale, providing a stable data foundation for subsequent identification of construction carbon perturbation candidate segments, carbon source demixing, construction carbon perturbation atom construction, and calculation of critical migration values ​​for carbon recovery.

[0040] Specifically, based on the perturbation space benchmark dataset, the process of identifying candidate segments of construction carbon perturbation and performing carbon source unmixing is as follows:

[0041] Based on the perturbation spatial reference dataset, the calibration timescale obtained by time axis relocation is used as the time axis. The synchronization window is segmented using the start time of work surface activation, the start and stop time of machinery, the start time of vehicle dwelling, and the time of material weight change as window boundaries. State abrupt change points that fall within the same synchronization window and are spatially adjacent are aggregated to form candidate segments of construction carbon perturbation. First-order difference calculations are performed on signals such as the start and stop time of machinery, the start time of vehicle dwelling, the time of material weight change, and the start time of work surface activation. Abrupt change points are identified when the difference value exceeds three times the root mean square of the historical signal. At the same time, multi-source consistency verification is adopted. When two adjacent signal sources change simultaneously within a 50-millisecond time window and the direction of change is consistent, the confidence of the abrupt change point is enhanced.

[0042] Spatial consistency is assessed for candidate segments of construction carbon disturbance by using a spatial benchmark calibration and matching method to determine whether the candidate segments fall into the same spatial benchmark object. The locations of construction machinery, materials consumption, vehicles, temporary energy consumption, work surface activation, and video recognition hotspots in the candidate segments are mapped to building component layers, construction surface layers, building layers, road segment layers, public space layers, and street grid layers, respectively, forming multiple candidate spatial objects. Based on spatial inclusion relationships, adjacent topological relationships, work surface activation relationships, and object parent-child affiliation relationships, the candidate spatial objects are chained together. If the aforementioned candidate spatial objects can be traced back to the same parent-child affiliation path to the same higher-level spatial object, and the machinery operation signal, vehicle stop signal, material consumption signal, temporary energy consumption signal, and video recognition hotspot location all fall into the object set corresponding to the path, then the candidate segment of construction carbon disturbance is determined to meet the single-object affiliation condition.

[0043] If the mechanical operation location, vehicle stopping location, material consumption location, temporary energy consumption location, and video recognition hotspot location in the candidate segment fall into adjacent spatial objects, and there are boundary overlaps, adjacent construction surfaces, road segment connections, shared material storage, or shared temporary energy consumption relationships between the above spatial objects, then the object perturbation overlap identification method determines that the current candidate segment has carbon source aliasing, and enters the mixed carbon source demixing process; the object perturbation overlap identification method is used to identify the common occupation status of the same carbon source signal by different construction behaviors within the same time window, avoiding the direct attribution of carbon source signals jointly generated by multiple spatial objects to a single spatial object.

[0044] The carbon source signal unmixing method based on constraint graph decomposition uses candidate segments of construction carbon disturbance as graph nodes and work surface activation association, equipment operation association, vehicle dwelling association, material consumption association, spatial adjacency relationship, and temporal overlap association as graph edges to construct a carbon source unmixing constraint graph. Carbon source unmixing, or carbon source signal unmixing, refers to the data processing process of allocating mixed carbon source signals to corresponding candidate segments of construction carbon disturbance according to temporal overlap ratio, spatial overlap ratio, and numbering consistency when construction machinery operation signals, temporary energy consumption signals, and vehicle dwelling signals all point to two or more spatial objects within the same measurement time window. Based on the temporal overlap ratio, spatial overlap ratio, and numbering consistency of each candidate segment with respect to machinery signals, energy consumption signals, transportation signals, and material signals, the allocation ratio of each candidate segment to the mixed carbon source signal is calculated. The formula for calculating the temporal overlap ratio is the temporal overlap length divided by the total duration of the candidate segment, and the formula for calculating the spatial overlap ratio is the spatial overlap area divided by the total area covered by the candidate segment. Numbering consistency is calculated using normalized mutual information and has a value range of 0 to 1. The weights for each indicator are: temporal overlap ratio (0.4), spatial overlap ratio (0.3), and numbering consistency (0.3). These are weighted and summed to obtain the unnormalized allocation ratio. The unnormalized allocation ratios of all candidate segments are normalized so that the sum of the allocation ratios for each segment equals 1. When outliers occur, such as ratios less than 0 or greater than 1, truncation is performed, setting values ​​less than 0 to 0 and values ​​greater than 1 to 1. Then, normalization is performed again, and the mixed carbon source signal is decomposed into the corresponding construction carbon disturbance candidate segments according to the allocation ratio.

[0045] In this implementation scheme, the allocation ratio is calculated through constraint graph decomposition, temporal overlap ratio, spatial overlap ratio, and numbering consistency. Abnormal ratios are truncated and re-normalized, enabling the mixed carbon source signal to be decomposed into corresponding construction carbon disturbance candidate segments according to reproducible rules. This transforms continuous, mixed, and heterogeneous construction carbon source data into construction carbon disturbance candidate segments with clear boundaries, well-defined spatial attribution, and traceable carbon source allocation, providing reliable input for the construction carbon disturbance atom construction, basic carbon disturbance quantity calculation, and carbon recovery critical migration value calculation.

[0046] Specifically, the process of constructing construction carbon perturbation atoms and generating a set of construction carbon perturbation atoms is as follows:

[0047] The candidate segments of construction carbon disturbance are atomized using the perturbation kernel locking method. The activation record of the work surface within the candidate segment is used as the spatial anchor point. The perturbation core interval is determined by using construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, work surface activation signals, video spatial recognition signals, and environmental disturbance signals as perturbation evidence. At least three types of perturbation evidence must change synchronously within a time window of 100 milliseconds, and the spatial distance between the spatial anchor point and the work surface activation position within the candidate segment must be less than 0.5 meters, with a duration of not less than 500 milliseconds and a confidence score of more than 0.8.

[0048] Within the core disturbance region, a work-dominant fingerprint is constructed using a work evidence co-directional coding method. Equipment start-stop status, effective operating duration, load fluctuation pattern, and no-load deviation status are extracted from construction machinery operation signals to form a mechanical action fingerprint. Power rise segment, stable energy consumption segment, power fall segment, standby tailwave segment, and synchronization relationship with the work surface activation time are extracted from temporary energy consumption signals to form an energy consumption waveform fingerprint. Vehicle entry direction, stopping position, stopping duration, loading / unloading status, and departure direction are extracted from vehicle trajectory signals to form a vehicle service fingerprint. Material batch number, material reduction time, material reduction magnitude, material transfer direction, and final material consumption location are extracted from material weight change signals. The following steps are taken to form a fingerprint for the material flow direction: First, the overlap between the construction equipment identification frame, personnel activity area, material movement area, occlusion change area, and spatial object boundary is extracted from the video spatial recognition signal to form a fingerprint for the work surface location. Second, changes in dust, noise, vibration, or local thermal disturbance are extracted from the environmental disturbance signal and correlated with the operating time of construction machinery and the loading / unloading time of vehicles to form an environmental response fingerprint. Third, the mechanical action fingerprint, energy consumption waveform fingerprint, vehicle service fingerprint, material flow fingerprint, work surface location fingerprint, and environmental response fingerprint are sequentially aligned. When these fingerprints all point to the same work surface, the same construction object, and the same work type, they are synthesized into the work-dominant fingerprint of the disturbance core area. At least four of the mechanical action fingerprint, energy consumption waveform fingerprint, vehicle service fingerprint, material flow fingerprint, work surface location fingerprint, and environmental response fingerprint have a similarity greater than 0.85 to the standard template fingerprint of the same work surface, the same construction object, and the same work type.

[0049] The primary fingerprint for a work operation consists of fixed-length coded fields, including a four-digit work surface code, a two-digit construction object type code, a two-digit work type code, a four-digit machinery motion code, a four-digit energy consumption waveform code, a four-digit vehicle service code, a four-digit material flow code, and a four-digit environmental response code. The encoding rule is to encode typical states of each fingerprint type using binary or integer encoding, and the generation rule is to concatenate each field sequentially into a 64-bit binary string. The fingerprint comparison rule uses Hamming distance; fingerprints with a distance less than or equal to 3 are considered identical.

[0050] When the dominant fingerprint of an operation remains consistent within the perturbation core interval, the dominant fingerprint is calculated every 100 milliseconds in adjacent time windows. If the Hamming distance of the fingerprints in five consecutive windows does not exceed 3, they are considered consistent. The perturbation core interval is then defined as a construction carbon perturbation atom. A construction carbon perturbation atom is the smallest construction carbon source data unit formed under the same perturbation core interval and the same dominant fingerprint. When the dominant fingerprint of an operation switches within the perturbation core interval, the Hamming distance of the fingerprints in three consecutive windows is greater than 3, and the difference between the new fingerprint and the previous fingerprint exceeds a threshold of 6. Simultaneously, at least two types of perturbation evidence confirm the emergence of a new operation type. A single window fluctuation does not trigger a switch; the switch point is confirmed only after the fingerprints of the two windows before and after the switch point stabilize. Using the fingerprint switch point as the boundary, the perturbation core interval is divided into sub-intervals, and construction carbon perturbation atoms are determined for each sub-interval. The atom number, primary spatial object number, shared spatial object number, perturbation start time, perturbation end time, and dominant fingerprint of each construction carbon perturbation atom are structurally bound to generate a set of construction carbon perturbation atoms.

[0051] like Figure 4 The diagram shows the composition of carbon source components in construction carbon perturbation atoms. The graph uses different construction carbon perturbation atoms as the horizontal axis and the amount of carbon perturbation as the vertical axis, employing a stacked columnar structure to illustrate the compositional relationships of mechanical operation carbon, temporary energy consumption carbon, transport perturbation carbon, and material-embedded carbon within each construction carbon perturbation atom. Figure 4 It is evident that the carbon source composition of different construction carbon disturbance atoms varies significantly. Atom 3 has the highest total carbon disturbance, with high levels of carbon from mechanical operation, transportation disturbance, and materials. This indicates that the construction behavior corresponding to this atom is simultaneously affected by mechanical operations, vehicle transportation, and material consumption, making it suitable as a multi-source-dominated construction carbon disturbance atom. Atoms 1, 2, 5, 6, and 7 have a large proportion of materials-induced carbon disturbance. In atom 4, the combined value of carbon from mechanical operation and transportation disturbance is higher than that of materials-induced carbon disturbance, indicating that construction carbon debt mainly originates from material inputs. Future carbon recovery verification should focus on the building energy conservation repayment chain or rooftop energy repayment chain of the corresponding spatial object. Atom 6 has the lowest total carbon disturbance, with both mechanical operation carbon and materials-induced carbon lower than other atoms, indicating a relatively small initial construction carbon debt for the corresponding construction behavior. However, it is still necessary to combine this with the greening carbon sink repayment chain or thermal environment repayment chain to determine whether effective repayment has been achieved.

[0052] This implementation scheme, through fixed-length encoding, Hamming distance comparison, continuous window stability determination, and fingerprint switching confirmation rules, can accurately distinguish between continuous occurrences of the same operation, operation type switching, and short-term signal jitter, thereby improving the stability of the atomic boundary delineation of construction carbon disturbances. It can transform mixed, continuous, and heterogeneous construction carbon source data into the smallest numberable, locatable, traceable, and usable data unit for carbon debt calculation, providing reliable input for basic carbon disturbance decomposition, construction carbon debt correction, spatial carbon repayment chain establishment, and carbon recovery critical migration value calculation.

[0053] Specifically, the process of constructing a counterfactual operating baseline based on the set of carbon perturbation atoms during construction is as follows:

[0054] The state fields changed by the update action are separated from the updated object state. The mapping relationship between the update action and the state fields is determined based on the action event type and state field change lookup table. The causal determination rule is: within a 30-second time window before and after the update action, if the correlation coefficient between the change in the state field and the action target parameter is greater than 0.7, and no other interfering actions occur simultaneously, then the change is determined to be caused by the current update action. The event association window is centered on the execution time of the update action, extending 5 measurement periods before and after it.

[0055] The status is backfilled using the operational records before the spatial object update. The backfill data comes from continuous operational records for at least 7 calendar days before the update, and the matching conditions are the same spatial object number and the same measurement time type. When there are missing values ​​in the records before the update, linear interpolation of 3 measurement periods before and after the same time period is used to fill them in. The backfilling priority is based on time proximity, and the median is used when there are multiple records at the same time point. Candidate operational states are generated when the current update action has not been implemented. The candidate operational states are corrected for environmental consistency by matching similar fragments in the same environment. The environmental variables include five fields: outdoor temperature, humidity, wind speed, solar radiation intensity, and air quality index. The similarity function uses weighted Euclidean distance, with weights of 0.3 for temperature, 0.2 for humidity, 0.1 for wind speed, 0.3 for solar radiation, and 0.1 for air quality. The matching threshold is set to a similarity greater than 0.85. Candidate fragments are derived from all historical operational fragments of the same spatial object as the current candidate operational state within at least 30 days before the update. If there is no matching fragment, the weighted average of the three nearest neighbor fragments is used as a substitute.

[0056] The response relationships of spatial objects to the external environment were established under their pre-update states: for building spatial objects, the response relationships between outdoor temperature, usage intensity, and historical energy consumption were extracted; for rooftop spatial objects, the response relationships between lighting conditions, roof shading status, and external electricity demand were extracted; for road spatial objects, the response relationships between road traffic background, vehicle speed, parking, and traffic carbon emissions were extracted; and for public space objects, the response relationships between green coverage, surface thermal environment, residential activities, and cooling load of surrounding buildings were extracted. All response relationships were modeled using multiple linear regression, with input parameters being the environmental and operational variables corresponding to each object, and the output being the target response value. Model fitting used data from at least 30 days prior to the update, trained using a daily sliding window, and parameters were updated every 24 hours.

[0057] The environmental conditions of the current measurement time slice are input into the above response relationship, and the residual correction results of similar segments in the same environment are superimposed to obtain the counterfactual operating baseline when the current update action has not been implemented; the updated target spatial object is read and reconstructed according to the spatial object number and the unified measurement time slice; through the triple registration method of spatial object, measurement time slice and environmental state, the counterfactual operating baseline and the updated operating state are aligned with the same spatial object, same time slice and same environmental conditions, the comparison segments with mismatched environmental conditions are eliminated, and the comparable counterfactual operating segments and updated operating segments are retained.

[0058] The counterfactual emission reduction difference is extracted using the difference component decomposition method. The decomposed components include a baseline load component, a behavior adjustment component, a technical efficiency component, and an external disturbance component. The calculation methods for each component are as follows: the baseline load component is taken as the value corresponding to the counterfactual operating baseline; the behavior adjustment component is the counterfactual operating baseline minus the standard operating value; the technical efficiency component is the updated actual operating value minus the average value of similar spatial objects under the same conditions; and the external disturbance component is the deviation value caused by actual environmental disturbances. The counterfactual emission reduction difference equals the baseline load component minus the technical efficiency component, and then minus the behavior adjustment component and the external disturbance component.

[0059] For building spaces, the predicted energy consumption in the counterfactual operating baseline is compared with the actual operating energy consumption after renovation to obtain the difference in building energy conservation and emission reduction. For rooftop energy spaces, the purchased electricity demand in the counterfactual operating baseline is compared with the local consumption of rooftop energy after renovation to obtain the difference in energy substitution and emission reduction. For road spaces, the carbon emissions from road traffic in the counterfactual operating baseline are compared with the carbon emissions from road traffic after renovation to obtain the difference in traffic operation emission reduction. For public spaces, the impact of thermal environment cooling load in the counterfactual operating baseline is compared with the impact of thermal environment cooling load after renovation to obtain the difference in thermal environment emission reduction. For green spaces, the original carbon sink capacity in the counterfactual operating baseline is compared with the carbon sink capacity of green spaces after renovation to obtain the difference in green space carbon sink increment.

[0060] The counterfactual emission reduction differences were corrected using an emission reduction effectiveness screening method. This method decomposes the differences into components of system efficiency improvement, operational mode change, external environmental fluctuations, and measurement error. The criteria for determining effective emission reduction differences are that the updated operating state, relative to the counterfactual operating baseline, demonstrates reduced energy consumption, reduced purchased electricity, decreased traffic carbon emissions, reduced cooling load, or enhanced carbon sinks, and the absolute value of the difference is greater than twice the comprehensive sensor accuracy error. The exclusion criteria for invalid emission reduction differences include: the absolute value of the difference is less than the comprehensive sensor accuracy error, the contribution of the external environmental fluctuation component exceeds 50%, and the confidence interval of the measurement error component includes zero.

[0061] When the updated operating status, relative to the counterfactual operating baseline, shows reduced energy consumption, reduced externally purchased electricity, decreased traffic carbon, reduced cooling load, or enhanced carbon sink, the corresponding difference will be marked as an effective emission reduction difference. When the updated operating status shows an increase in energy consumption, increased vehicle detours, extended parking time, insufficient rooftop energy absorption, or insufficient greening response, the corresponding difference will be marked as a carbon rebound difference and included in the carbon payback simulation as a negative emission reduction result.

[0062] This implementation plan identifies energy consumption reduction, reduced external electricity purchases, decreased transportation carbon emissions, reduced cooling load, and enhanced carbon sinks. It also marks energy consumption rebound, increased vehicle detours, prolonged parking, insufficient rooftop energy utilization, and insufficient greening response as carbon rebound differences. This ensures that counterfactual emission reduction differences reflect both positive emission reduction contributions and negative operational impacts. It generates counterfactual emission reduction differences with clearly defined sources, comparable environments, decomposable components, and screenable errors, providing a reliable operational data foundation for carbon debt reenactment, spatial carbon repayment chain closure verification, and calculation of critical migration values ​​for carbon recovery.

[0063] Specifically, the process of reenacting carbon debt scenarios and generating spatial carbon repayment chains is as follows:

[0064] The system reads the primary spatial object, operation-dominant fingerprint, spatial influence range, and corresponding update action of the construction carbon perturbation atoms. The field structure of the construction carbon perturbation atoms includes atom number, primary spatial object number, shared spatial object number, perturbation start time, perturbation end time, operation-dominant fingerprint, spatial influence range, and corresponding update action. The spatial influence range is determined by combining parent-child affiliation and spatial adjacency relationships in the spatial object hierarchy mapping method. The corresponding update action is obtained by matching the operation-dominant fingerprint with the update action type mapping table within the perturbation core interval.

[0065] Convert to working condition replay objects; facade renovation, door and window replacement and building envelope renewal correspond to building thermal response replay objects; roof energy facility installation corresponds to roof electricity substitution replay objects; road renovation, road cross-section adjustment and slow-moving space renewal correspond to traffic operation replay objects; public space paving renewal, shading facility installation and open space renovation correspond to thermal environment conduction replay objects; greening replanting corresponds to vegetation growth and cooling replay objects.

[0066] Operational segments before the current update action were extracted from the counterfactual operational baseline. Measured operational segments under the same spatial object, measurement time slice, and environmental conditions were extracted from the updated operational state. The spatial object numbers must be identical, the measurement time slice length deviation must not exceed one measurement cycle, and the environmental conditions must match: outdoor temperature deviation not exceeding 2 degrees Celsius, humidity deviation not exceeding 10%, wind speed deviation not exceeding 1 meter per second, and solar radiation intensity deviation not exceeding 50 watts per square meter. This forms a set of reenactment control segments. For different types of operational condition reenactment objects, based on the predefined mapping relationship between update action type and carbon disturbance response rules, the set of reenactment control segments is morphologically compared to generate a spatial carbon repayment chain. For each set of reenactment control segments, waveform features of the counterfactual and measured operational segments are extracted. Feature dimensions include peak value, trough value, mean, standard deviation, rise time, fall time, and steady-state duration. The similarity between the two curves is calculated using dynamic time warping, with a similarity threshold set to 0.8. The pass criteria for comparison are: the measured operating segment shows a predefined favorable change in the target emission reduction dimension compared with the counterfactual operating segment, such as the peak reduction of building heating and cooling load by more than 5%, the duration of the reduction gap in purchased electricity by more than 30 minutes, and the reduction of vehicle low-speed dwell time by more than 10%.

[0067] For building thermal response reenactment objects, the system determines whether the peak value of building heating and cooling loads, temperature sensitivity, and floor zoning energy consumption response decrease accordingly relative to the counterfactual energy consumption curve after the building envelope is updated; for rooftop electricity substitution reenactment objects, the system determines whether rooftop energy output forms a gap in purchased electricity within the same time window, and whether this is explained by the local load absorption process; for traffic operation reenactment objects, the system determines whether the low-speed parking, parking search, detour paths, and short-distance travel structures of vehicles after road updates result in a carbon reduction response, and whether carbon load is transferred to adjacent roads; for thermal environment conduction reenactment objects, the system determines whether surface thermal disturbance shrinks after public space updates, and whether it is conducted to the cooling load of adjacent buildings or changes in the thermal environment of the living space; for vegetation growth and cooling reenactment objects, the system determines whether vegetation cover growth, vegetation activity enhancement, carbon sink growth, or cooling response occurs after greening replanting. If the aforementioned changes in operational patterns are consistent with the low-carbon mechanisms, spatial object locations, and temporal relationships of the corresponding renewal actions, then corresponding building energy conservation repayment chains, rooftop energy repayment chains, road traffic repayment chains, public space thermal environment repayment chains, or greening carbon sink repayment chains will be generated. If only the total amount changes, but non-renewal factors such as changes in usage intensity, equipment shutdown, load transfer, temporary traffic disturbances, spillover from adjacent roads, or no actual improvement in greening status cannot be ruled out, then an effective repayment chain will not be confirmed, and the corresponding construction carbon disturbance atoms will be retained as carbon debt to be verified.

[0068] The relationship between construction carbon debt and operational emission reduction is confirmed through a repayment chain closure verification method. Repayment chain closure requires the simultaneous fulfillment of three closure conditions: First, spatial closure: the primary spatial object number of the construction carbon disturbance atom must completely match the spatial object number of the operational response in spatial benchmark calibration, or their spatial adjacency must confirm that they belong to the same work surface activating the associated path, with a spatial distance not exceeding 0.5 meters. Second, mechanistic closure: the operational response pattern must conform to at least one pattern in a predefined low-carbon response pattern library. This library includes five patterns: building cooling load reduction, external power purchase deficit formation, transportation carbon emission reduction, thermal environment cooling load impact reduction, and green carbon sink enhancement. Each pattern corresponds to specific waveform characteristic judgment conditions; for example, the building cooling load reduction pattern requires a peak cooling load reduction of greater than 5% and a temperature sensitivity coefficient reduction of more than 0.1. Third, temporal closure: the start time of the operational response must not be earlier than the completion time of the construction disturbance, and there must be at least three continuously traceable measurement time slices. The response pattern must remain stable within each cycle, with allowable fluctuations between cycles not exceeding 15% of the average. Only when the above closure conditions are met simultaneously, and the confidence score is not lower than 0.9, can the carbon disturbance atoms during construction be bound to the corresponding operational emission reduction response as an effective spatial carbon repayment chain.

[0069] If the counterfactual operating baseline predicts that a certain update action should produce a low-carbon response, but the measured operating segment after the update does not show the predefined low-carbon response pattern, then the operating condition reenactment is judged to have failed. For example, if there is no decrease in temperature sensitivity after the building envelope is updated, no decrease in purchased electricity gap after rooftop energy access, detours between adjacent road sections after road updates, no contraction of thermal disturbance after public space updates, and no increase in vegetation activity or cooling response after greening replanting, then the corresponding repayment chain reenactment is judged to have failed.

[0070] When a scenario reenactment fails, the corresponding counterfactual emission reduction difference is no longer directly included in the effective repayment. Instead, the corresponding construction carbon disturbance atom is marked as a carbon debt to be verified, and the repayment chain is frozen. When an operational response pattern matching the scenario reenactment object reappears in the measurement time slice, the repayment chain closure verification is re-executed. If no closure can be formed in any measurement time slice, the construction carbon disturbance atom is marked as a carbon debt residue object. When a scenario reenactment succeeds, the construction carbon disturbance atom, the scenario reenactment object, the counterfactual operational segment, the updated measured operational segment, the operational response pattern, and the repayment chain closure result are structurally bound to generate a space carbon repayment simulation set. The space carbon repayment simulation set includes the space object number, the construction carbon disturbance atom number, the scenario reenactment object, the counterfactual operational segment, the updated measured operational segment, the operational response pattern, the repayment chain type, the closure status, the reenactment failure identifier, the traffic carbon rebound chain identifier, and the carbon debt residue identifier, and is used for calculating the critical migration value for carbon recovery.

[0071] This implementation plan can improve the accuracy of the correspondence between carbon debt during the construction phase and emission reduction during the operation phase, enhance the data reliability of the calculation of the critical migration value of carbon recovery, and provide a traceable spatial carbon repayment data basis for identifying carbon recovery completed objects, carbon recovery migration objects, carbon debt residual objects, and carbon recovery unstable objects.

[0072] Specifically, the process of assessing the critical migration for carbon recovery based on the construction carbon perturbation atom set and the spatial carbon repayment chain is as follows:

[0073] The start time of the transition from construction to operation of a spatial object is obtained through the construction completion marker and the operation start marker. The construction completion marker is derived from the status field of the construction progress management system, the sensor signal of the work surface being turned off, or manual confirmation and entry. The trigger condition is that the work surface is active for more than 300 seconds with a value of 0 and no new batch of materials entering the site. The operation start marker is derived from the first normal operation data of the building energy management system or vehicle detection system. The trigger condition is that the mechanical operation signal or temporary energy consumption signal recovers to more than 90% of the baseline level before construction. When the two markers conflict, the later one is taken as the start time, and the source of the marker and the conflict mark are recorded.

[0074] The intermediate measurement time is obtained from the measurement timeline from the start of operation to the current measurement time; the counterfactual operating baseline before the current update action is implemented is compared with the updated operating state under the same spatial object, the same time slice, and the same environmental conditions to obtain the counterfactual emission reduction difference; the model drift penalty term is obtained by comparing the difference between the updated measured operating state and the counterfactual carbon payback simulation results; the model drift penalty term is calculated as the root mean square of the relative error between the updated measured operating state and the counterfactual carbon payback simulation results in all measurement cycles, with the dimensionless percentage and a value range of 0 to 1, and is derived from the cycle-by-cycle residual statistics of the comparison output results. The basic carbon disturbance amount is obtained by converting the mechanical operation carbon component, temporary energy consumption carbon component, transportation disturbance carbon component, and material-implied carbon component in the construction carbon disturbance atom using the same carbon measurement caliber. The mechanical operation carbon component adopts the carbon emission factor of fuel or electricity; the temporary energy consumption carbon component adopts the grid average emission factor; the transportation disturbance carbon component is the emission factor combining vehicle transportation distance and load; and the material-implied carbon component adopts the default value in the building material carbon emission factor library or the value declared by a third-party environmental product. The time boundaries of all components are consistent with the disturbance start time to disturbance end time of the construction carbon disturbance atom.

[0075] The spatial attribution entropy is calculated by the probability distribution of carbon perturbation atoms belonging to different candidate spatial objects. The formula for calculating the spatial attribution entropy is: a negative summation sign multiplied by the attribution probability multiplied by the logarithm of the attribution probability, with base 2. The attribution probability is derived from the normalized result of the matching confidence of candidate fragments and each spatial object in the spatial benchmark calibration matching method. The sum of the probabilities is 1. The entropy ranges from 0 to log2(N), where N is the number of candidate spatial objects.

[0076] The counterfactual emission reduction difference for each discrete moment corresponding to each measurement cycle from the start of operation to the current measurement moment is extracted and multiplied by the spatial coupling compensation coefficient to obtain the emission reduction. The model drift penalty term is inversely inverted and then exponentially calculated to obtain the drift attenuation factor. The specific form of the exponential calculation is an exponential function with the natural constant e as the base, i.e., exp(-model drift penalty term). Since the model drift penalty term is dimensionless and its value ranges from 0 to 1, the result of the exponential calculation is between 0.3679 and 1. The emission reduction is multiplied by the drift attenuation factor to obtain the effective emission reduction. The effective emission reductions obtained from all discrete moments are accumulated sequentially over time and then 1 is added to obtain the effective carbon compensation. The addition of 1 serves as a smoothing term to avoid the calculation anomaly caused by the effective carbon compensation being zero in subsequent divisions. At the same time, it provides a baseline value of 1 for the initial carbon compensation, representing the initial state where the construction disturbance has not yet produced any compensation. The aliasing-corrected carbon perturbation is obtained by multiplying the base carbon perturbation by the sum of the carbon source aliasing amplification factor and a constant of 1. This corrected carbon perturbation is then multiplied by the exponent of the spatial attribution entropy to obtain the corrected carbon perturbation. Here, the exponent of the spatial attribution entropy is explicitly defined as the exponential function exp(spatial attribution entropy) with the natural constant e as the base, i.e., the aliasing-corrected carbon perturbation multiplied by exp(H), where H is the spatial attribution entropy. The corrected carbon perturbation amounts of all construction carbon perturbation atoms are summed and then increased by 1 to obtain the corrected carbon debt. The effective carbon repayment amount is divided by the corrected carbon debt to obtain the carbon repayment coverage. The logarithm of the carbon repayment coverage is then sigmoid-compressed to obtain the critical migration value for carbon recovery. The logarithm base is the natural logarithm. The input carbon repayment coverage is guaranteed to be greater than 0 by ensuring that both the effective carbon repayment amount and the corrected carbon debt are positive, requiring no further processing. The sigmoid function takes the form of the standard logistic function f(x) = 1 / (1 + exp(-x)), where x is the natural logarithm of carbon repayment coverage. It has no slope or translation parameter adjustment and its output range is 0 to 1.

[0077] The specific formula for calculating the critical migration value for carbon recovery is as follows:

[0078] ;

[0079] In the formula, The value represents the critical migration value for carbon recovery of spatial object i at time t, used to determine the degree to which the spatial object has migrated from the carbon debt state under construction to the carbon recovery completed state; i represents the spatial object number, used to determine the specific spatial object corresponding to the carbon recovery measurement; t represents the current measurement time, used to determine the current calculation endpoint for the critical migration value for carbon recovery. It indicates the starting time when a spatial object transitions from the construction state to the operation state. It is obtained through the construction end marker and the operation start marker and is used to determine the cumulative starting point of the effective carbon repayment capacity during the operation phase. This represents an intermediate measurement moment in the cumulative calculation process during the runtime phase, used to read the counterfactual emission reduction difference, spatial coupling compensation coefficient, and model drift penalty term at each time step during the integration process; Represents the spatial object i at time i The counterfactual emission reduction difference is used to characterize the effective emission reduction contribution of the spatial object relative to the unupdated state during the operational phase. Represents the spatial object i at time i The spatial coupling repayment coefficient is obtained through the adjacency relationship, energy consumption relationship, thermal environment impact relationship, road traffic transmission relationship and repayment chain closure state between spatial objects. It is used to characterize the degree of effective transfer of carbon repayment capacity of adjacent or related spatial objects to the target spatial object. Represents the spatial object i at time i The model drift penalty term is used to mitigate unreliable emission reduction contributions caused by deviations between the actual operating conditions and the simulated emission reduction conditions. This represents the set of construction carbon perturbation atoms belonging to space object i, used to determine the sources of all carbon debt formed during the construction phase of the space object. This represents any construction carbon perturbation atom in the set of construction carbon perturbation atoms, used to calculate the carbon perturbation contribution of a space object during the construction phase one by one. The basic carbon perturbation amount represents the amount of carbon perturbation in construction carbon, which is used to characterize the basic construction carbon debt formed by the construction carbon perturbation atom. The carbon source aliasing amplification factor representing carbon perturbation atoms during construction is obtained by statistically analyzing the temporal and spatial overlap of mechanical operation signals, vehicle stationing signals, material change signals, and temporary energy consumption signals within the same spatial object in the same time slice. It is used to amplify the uncertainty of construction carbon debt when the carbon source boundary is unclear and the carbon source signal is difficult to completely separate. The spatial assignment entropy of construction carbon perturbation atoms is used to characterize the degree of uncertainty in the assignment of construction carbon perturbation atoms among multiple spatial objects.

[0080] Table 1 shows the quantitative assessment table of carbon recovery status for six spatial objects. A comprehensive assessment of carbon migration thresholds, recovery status, anomaly characteristics, and spatial connectivity was conducted on these six spatial objects: Object 1 is the north facade area 1, with a carbon recovery threshold of 0.84, a carbon recovery status of completed carbon recovery, evidence chain record 1, no anomalies, and a critical surface relationship of completed connectivity; Object 2 is the rooftop photovoltaic area 1, with a carbon recovery threshold of 0.82, a carbon recovery status of completed carbon recovery, evidence chain record 2, no anomalies, and a critical surface relationship of completed connectivity; Object 3 is a section of road excavation, with a carbon recovery threshold of 0.68, a carbon recovery status of carbon migration, and evidence chain record 2. The evidence chain record is evidence chain 3, with no abnormal state, and the critical surface relationship is a migration connectivity region; the spatial object of sequence number 4 is road node 2, with a carbon recovery critical migration value of 0.39, a carbon recovery status of carbon debt residue, evidence chain record is evidence chain 4, there is a traffic carbon rebound anomaly, and the critical surface relationship is a residue connectivity region; the spatial object of sequence number 5 is the public space paved area, with a carbon recovery critical migration value of 0.76, a carbon recovery status of carbon recovery completed, evidence chain record is evidence chain 5, with no abnormal state, and the critical surface relationship is a completed connectivity region; the spatial object of sequence number 6 is greening replanting area 1, with a carbon recovery critical migration value of 0.52, a carbon recovery status of carbon recovery unstable, evidence chain record is evidence chain 6, there is a carbon sink insufficiency anomaly, and the critical surface relationship is a critical boundary.

[0081] Table 1. Quantitative Assessment Table of Carbon Recovery Status of Space Objects

[0082]

[0083] like Figure 5 The graph shows the trend of carbon recovery critical migration values. The graph uses the measurement period as the horizontal axis and the carbon recovery critical migration value as the vertical axis, displaying the changes in carbon recovery status of Area 1 (exterior facade), Area 1 (rooftop photovoltaic), Section 1 (road excavation), Section 2 (road node), paved public space, and Area 1 (green space replanting) within a continuous measurement period. The dashed lines in the graph represent carbon recovery status thresholds, used to distinguish whether spatial objects have met the criteria for carbon recovery completion. Figure 5As can be seen, the carbon recovery critical migration values ​​of the facade area 1 and the rooftop photovoltaic area 1 continuously increased over the measurement period, reaching or exceeding the carbon recovery status threshold in the later stages. This indicates that the construction carbon debt of the corresponding spatial objects has been effectively covered by the building energy-saving response and rooftop energy substitution response during the operation phase, and they can be identified as carbon recovery completed objects. The paved area of ​​the public space approached and reached the threshold in the later stages, indicating that its thermal environment conduction response gradually formed a stable repayment effect. Although the road excavation section maintained an upward trend, it did not reach the carbon recovery status threshold, indicating that it is still in the carbon recovery migration state. The road node 2 and the greening replanting area 1 showed a phased decline or fluctuation, indicating that the traffic repayment chain or greening carbon sink repayment chain of the corresponding spatial objects has not yet been stably closed, and they need to continue to be regarded as unstable carbon recovery objects or carbon debt objects to be verified.

[0084] In this implementation plan, the carbon recovery critical migration value is calculated by using the nonlinear ratio between effective carbon repayment and corrected carbon debt. This allows spatial objects to be categorized into carbon recovery completed, carbon recovery migration, carbon debt residue, and carbon recovery unstable states. It integrates carbon input during construction, emission reduction response during operation, carbon source uncertainty, and spatial object status into a single measurement process, providing a reliable basis for generating the carbon recovery critical surface, identifying anomalous spatial objects, and forming a carbon measurement evidence chain.

[0085] Specifically, the process for identifying the carbon recovery status of space objects is as follows:

[0086] When the carbon recovery critical migration value is less than the carbon recovery state threshold, the target spatial object is determined to still be in a state of residual carbon debt. When the carbon recovery critical migration value reaches the carbon recovery state threshold, the target spatial object is determined to have entered the carbon recovery completed state. When the carbon recovery critical migration value rises within M measurement periods of a positive integer value of 5 but has not yet reached the carbon recovery state threshold, M is determined based on the typical carbon response time constant of the spatial object type: M is 3 for building component layers and construction surface layers, M is 5 for building layers and road section layers, and M is 7 for public space layers and street grid layers. The target spatial object is marked as a carbon recovery migration object. When the carbon recovery critical migration value declines, if the month-on-month decrease of the critical migration value exceeds 2% within three consecutive measurement periods, and there are at least two periods before the decline that show an upward or stable trend, a median filter window length of 3 is used for smoothing to filter out single-period noise. The target spatial object is marked as a carbon recovery unstable object.

[0087] For spatial objects in the building component layer, construction surface layer, building layer, road section layer, public space layer, and street grid layer, a layered state write-back and parent-child object propagation verification method is used to write back upwards along the parent-child affiliation relationship. State propagation stops when a condition replay fails. Carbon recovery status is calculated, and spatial connectivity analysis is performed on the carbon recovery status of adjacent spatial objects. The adjacency matrix of the spatial connectivity analysis is constructed based on the parent-child affiliation relationship and spatial adjacency relationship in the spatial object genealogy mapping method. A matrix element value of 1 indicates that spatial objects are adjacent or belong to the same parent object, and a value of 0 indicates that they are not adjacent. The connectivity threshold is set so that spatial objects with a carbon recovery critical migration value greater than 0.6 constitute a connected component. Cross-level connectivity is allowed, but the parent-child affiliation path length does not exceed 3. The output format includes the connected component number, a list of spatial objects within the component, the coordinates of the component boundary polygon, and the connectivity strength value. A carbon recovery critical surface dataset is output. The carbon recovery critical surface dataset includes the spatial object number, carbon recovery critical migration value, carbon recovery status, carbon debt residual status, coupling repayment relationship, critical surface connectivity relationship, and state update time.

[0088] This implementation scheme enables the carbon recovery critical surface to have a locationable, traceable, and updatable data representation. It can extend the carbon recovery critical migration value of a single spatial object to the carbon recovery critical surface of a continuous spatial region, providing a stable basis for identifying abnormal carbon recovery states, generating carbon measurement evidence chains, and outputting spatial simulation results for low-carbon urban renewal.

[0089] Specifically, the process of generating the carbon measurement evidence chain is as follows:

[0090] If, after a building facade, rooftop work surface, road excavation section, greening replanting area, or public space unit has entered the operation phase, new construction carbon disturbance atoms generated by construction re-intervention events still occur, and the corresponding spatial carbon repayment chain operation condition fails to be reenacted, it is identified as an abnormal accumulation of construction carbon debt. If, after the facade renovation, window and door replacement, or building envelope renewal is completed, the energy consumption curve of the updated building still fluctuates synchronously with the changes in outdoor temperature, the peak of cooling and heating loads has not been weakened, or the energy consumption reduction is only caused by the shortening of usage time, equipment shutdown, or reduced occupancy intensity, without the formation of an improvement in the thermal response of the building envelope, it is identified as insufficient emission reduction during building operation.

[0091] Once the rooftop energy facilities are installed, although the rooftop energy output has appeared, if the building's external power purchase curve does not form a corresponding downward gap within the same time window, or if the rooftop energy output is offset by abnormal charging and discharging of energy storage, load transfer, or abandonment, and no local consumption substitution effect is formed, then the rooftop energy repayment is identified as ineffective.

[0092] When road renovation, road cross-section adjustment, or slow-traffic space update is completed, although the target road segment may show local traffic improvement, if adjacent road segments experience detours, longer parking search times, increased low-speed stops, or traffic spillover, resulting in a failure of traffic carbon to actually decrease in the spatial network, it is identified as an abnormal rebound in traffic carbon.

[0093] If, after the renovation of public space paving, the installation of shading facilities, or the transformation of open space is completed, the surface thermal disturbance in the renovated area does not shrink, the shading effect does not form a stable cooling zone, or the cooling load of adjacent buildings and the thermal environment of the living space do not show corresponding improvement, then it is identified as a lack of thermal environment compensation.

[0094] If, after the replanting of greenery is completed, there are only changes in the green area or planting records, but the vegetation cover, vegetation activity, carbon sink growth, or surface cooling response are not verified by the operational data within the continuous measurement period, or if the replanted greenery shows insufficient survival, cover breaks, or discontinuous thermal environment response, it is identified as insufficient carbon sink repayment.

[0095] If the mechanical operation location, vehicle parking location, material consumption location, temporary energy meter binding location, and video work surface identification location of a certain construction carbon disturbance atom fall into multiple adjacent spatial objects, and cannot be stably traced back to the same construction surface, the same building, the same road section, or the same public space unit in subsequent measurements, it is identified as an anomaly of uncertain carbon source attribution.

[0096] When the carbon recovery critical surface repeatedly retreats towards the completed area within adjacent measurement periods, and the retreat locations are concentrated at the same building facade, the same road node, the same rooftop energy node, or the same public space boundary, it is identified as an abnormal carbon recovery critical surface oscillation. This anomaly indicates that the construction carbon debt and operational repayment chain of the corresponding spatial object has not yet formed a stable closure, and it needs to be retained as a carbon debt object to be verified. The identified abnormal carbon recovery status is written into the carbon measurement evidence chain. The data structure of the carbon measurement evidence chain includes chain node number, spatial object number, carbon recovery critical migration value, abnormal status type, original data index, evidence source field, and evidence generation timestamp. A traceable chain-like evidence report is formed using the spatial object number as the primary index and the carbon recovery critical migration value as the status index. The chain node numbers are in ascending sequence, and the abnormal state types include abnormal accumulation of construction carbon debt, insufficient emission reduction in building operation, failure of rooftop energy repayment, abnormal rebound of transportation carbon, lack of repayment of thermal environment carbon, insufficient repayment of green carbon sink, abnormal uncertainty of carbon source attribution, and abnormal oscillation of carbon recovery critical surface. The original data index points to the construction carbon disturbance atom number, counterfactual operation segment number, or spatial carbon repayment simulation set number. The evidence source fields include construction machinery controllers, temporary energy meters, vehicle positioning records, material batch records, video recognition results, environmental monitoring records, or carbon recovery critical surface datasets.

[0097] This implementation plan enables rapid tracing of the location of anomalies, the corresponding sources of carbon debt during construction, operational response segments, and the closure of the repayment chain. It improves the reproducibility and anomaly location capabilities of low-carbon urban renewal measurement results, providing evidentiary support for carbon debt residue verification, carbon recovery threshold updates, and the output of spatial object-level low-carbon measurement results.

[0098] Specifically, the second aspect of this invention provides an intelligent spatial simulation and measurement system for low-carbon urban renewal, applied to an intelligent spatial simulation and measurement method for low-carbon urban renewal, including: a spatial spectrum calibration module, used to acquire construction carbon source data and perform time axis relocation based on three-timescale median weighting, parent-child attribution binding based on spatial adjacency matrix, signal drift correction based on deviation threshold, and amplitude normalization to the 0-1 interval to obtain a perturbation spatial reference dataset; a carbon perturbation atom identification module, used to identify construction carbon perturbation candidate segments and perform carbon source unmixing based on the perturbation spatial reference dataset through state mutation point aggregation and constraint graph decomposition. The perturbation core region is segmented based on the consistency of the operation-dominant fingerprint, and construction carbon perturbation atoms are constructed and a set of construction carbon perturbation atoms is generated. The counterfactual carbon repayment simulation module is used to construct a counterfactual operating baseline based on the set of construction carbon perturbation atoms, using the response relationship of multiple linear regression and the residual correction of similar segments in the same environment. It performs carbon debt operation condition reenactment based on morphological comparison and repayment chain closure verification, and generates a spatial carbon repayment chain. The critical migration measurement module is used to calculate the spatial attribution entropy, model drift penalty term and carbon recovery critical migration value based on the set of construction carbon perturbation atoms and the spatial carbon repayment chain. It evaluates the carbon recovery status through hierarchical state write-back and spatial connectivity analysis, and generates a carbon measurement evidence chain.

[0099] This implementation plan can unify multi-source carbon data during the construction phase, counterfactual baseline data during the operation phase, spatial object status data, and carbon recovery result data into the same calculation chain; it can achieve continuous processing from construction carbon source collection, carbon perturbation atom construction, counterfactual emission reduction verification to carbon recovery status identification, thereby improving the accuracy, traceability, and reproducibility of low-carbon urban renewal spatial simulation and carbon recovery measurement.

[0100] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0101] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart spatial simulation and measurement method for low-carbon urban renewal, characterized in that, Includes the following steps: S1. Acquire construction carbon source data and perform time axis relocation, spatial object binding, signal drift correction and normalization to obtain the perturbation spatial reference dataset. S2, based on the perturbation space benchmark dataset, identifies candidate fragments of construction carbon perturbation and performs carbon source unmixing, constructs construction carbon perturbation atoms, and generates a set of construction carbon perturbation atoms; S3, based on the set of carbon perturbation atoms during construction, constructs a counterfactual operating baseline, performs carbon debt reenactment, and generates a spatial carbon repayment chain; S4 assesses the critical migration of carbon recovery for construction carbon disturbance atom set and space carbon repayment chain, identifies the carbon recovery status of space objects, and generates carbon measurement evidence chain. The specific process of constructing the counterfactual operating baseline based on the construction carbon perturbation atom set is as follows: The state fields that have changed due to the update action are extracted from the updated object state, and the state is backfilled using the running records of the spatial object before the update, generating candidate running states when the current update action is not implemented; the candidate running states are corrected for environmental consistency by matching similar fragments in the same environment; the response relationship of the spatial object to the external environment in the state before the update is established, and the environmental conditions of the current measurement time slice are superimposed with the residual correction results of similar fragments in the same environment to obtain the counterfactual running baseline when the current update action is not implemented; Counterfactual emission reduction differences are extracted using the difference component decomposition method, and then corrected using an emission reduction effectiveness screening method. The specific process of reenacting the carbon debt operating conditions and generating a spatial carbon repayment chain is as follows: The system reads the primary spatial object, operational fingerprint, spatial impact range, and corresponding update action of carbon disturbance atoms during construction, and converts them into operational condition replay objects. It extracts operational segments from the counterfactual operational baseline when the current update action has not been implemented, and extracts measured operational segments from the updated operational state under the same spatial object, the same measurement time slice, and the same environmental conditions to form a set of replay comparison segments. For different types of operational condition replay objects, the system performs morphological comparison on the set of replay comparison segments according to the predefined mapping relationship between update action type and carbon disturbance response rules to generate a spatial carbon repayment chain. The relationship between construction carbon debt and operational emission reduction is confirmed through a repayment chain closure verification method. If the counterfactual operational baseline predicts that a certain update action should produce a low-carbon response, but the measured operational segment after the update does not show the predefined low-carbon response pattern, the operational condition reenactment is deemed to have failed. When the operational condition reenactment fails, the corresponding counterfactual emission reduction difference is no longer directly included in the effective repayment, the corresponding construction carbon perturbation atom is marked as carbon debt to be verified, and the repayment chain is frozen. When the operational condition reenactment is successful, a space carbon repayment simulation set is generated.

2. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process of acquiring construction carbon source data and performing time axis relocation, spatial object binding, signal drift correction, and normalization to obtain the perturbation spatial reference dataset is as follows: Read construction carbon source data, which includes equipment acquisition timestamp, edge reception timestamp, measurement timestamp, platform writing timestamp, current measurement time, start time of work surface activation, start and stop time of machinery, start time of vehicle dwell time, material weight change time, spatial adjacency relationship, work surface activation status, construction machinery operation signal, temporary energy consumption signal, vehicle trajectory signal, material weight change signal, work surface activation signal, video spatial recognition signal, environmental disturbance signal, construction machinery location, material consumption location, vehicle dwell location, temporary energy consumption location, work surface activation location, video recognition hotspot location, work surface activation association, equipment operation association, vehicle dwell association, material consumption association, temporal overlap association, and spatial object number; A time-tracking relocation method based on device acquisition time-tracking, edge reception time-tracking, and platform writing time-tracking is used to relocate construction carbon source data along the time axis. A spatial object hierarchy mapping method is used to establish parent-child relationships among building component layers, construction surface layers, building layers, road section layers, public space layers, and street grid layers. A signal drift correction method based on spatial adjacency relationships and the activation state of the work surface is used to correct misbinding of spatial objects. The amplitude of the construction carbon source data is normalized to output a perturbation spatial reference dataset.

3. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process of identifying candidate fragments of construction carbon disturbance and performing carbon source unmixing based on the perturbation space benchmark dataset is as follows: Based on the perturbation spatial reference dataset, the calibration timescale obtained by time axis relocation is used as the time axis. The window boundaries are used as the start time of work surface activation, the start and stop time of machinery, the start time of vehicle stay, and the time of material weight change to divide the synchronous window. State change points that fall into the same synchronous window and are spatially adjacent are aggregated to form construction carbon perturbation candidate segments. The spatial consistency of the construction carbon perturbation candidate segments is judged, and the spatial reference calibration matching method is used to determine whether the candidate segments fall into the same spatial reference object. The carbon source signal demixing method based on constraint graph decomposition uses construction carbon disturbance candidate segments as graph nodes and work surface activation association, equipment operation association, vehicle dwelling association, material consumption association, spatial adjacency relationship, and temporal overlap association as graph edges to construct a carbon source demixing constraint graph. Carbon source demixing, or carbon source signal demixing, refers to the data processing process where, when construction machinery operation signals, temporary energy consumption signals, and vehicle dwelling signals all point to two or more spatial objects within the same measurement time window, the mixed carbon source signals are allocated to the corresponding construction carbon disturbance candidate segments according to the temporal overlap ratio, spatial overlap ratio, and numbering consistency. Based on the temporal overlap ratio, spatial overlap ratio, and numbering consistency of each candidate segment with respect to machinery signals, energy consumption signals, transportation signals, and material signals, the allocation ratio of each candidate segment to the mixed carbon source signal is calculated, and the mixed carbon source signal is decomposed into the corresponding construction carbon disturbance candidate segments according to the allocation ratio.

4. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process of constructing construction carbon perturbation atoms and generating a set of construction carbon perturbation atoms is as follows: The candidate fragments of construction carbon disturbance are atomized using a perturbation kernel locking method. The activation record of the work surface within the candidate fragment is used as a spatial anchor point. Construction machinery operation signals, temporary energy consumption signals, vehicle trajectory signals, material weight change signals, work surface activation signals, video spatial recognition signals, and environmental disturbance signals are used as disturbance evidence to determine the core disturbance region. Within the core disturbance region, a work-dominant fingerprint is constructed using a work evidence co-directional encoding method. When the work-dominant fingerprints within the core disturbance region remain consistent, the core disturbance region is defined as a construction carbon disturbance atom. The construction carbon disturbance atom refers to the smallest construction carbon source data unit formed under the same core disturbance region and the same work-dominant fingerprint. The construction carbon disturbance atom includes an atom number, a primary spatial object number, a shared spatial object number, a disturbance start time, a disturbance end time, and a work-dominant fingerprint. When the work-dominant fingerprint switches within the core disturbance region, the core disturbance region is divided into sub-regions using the fingerprint switching point as the boundary, and construction carbon disturbance atoms are determined for each sub-region, generating a set of construction carbon disturbance atoms.

5. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process for assessing the critical migration for carbon recovery of the construction carbon perturbation atom set and the space carbon repayment chain is as follows: The starting time when a spatial object transitions from the construction state to the operation state is obtained by identifying the construction end marker and the operation start marker; the intermediate measurement time is obtained by measuring the time axis from the operation start time to the current measurement time; the counterfactual operation baseline before the current update action is implemented is compared with the updated operation state under the same spatial object, the same time slice, and the same environmental conditions to obtain the counterfactual emission reduction difference; The model drift penalty term is obtained by comparing the difference between the updated measured running state and the counterfactual carbon repayment simulation results; the basic carbon perturbation amount is obtained by converting the mechanical operation carbon component, temporary energy consumption carbon component, transportation perturbation carbon component and material implicit carbon component in the construction carbon perturbation atom using the same carbon measurement caliber; the spatial attribution entropy is obtained by calculating the attribution probability distribution of construction carbon perturbation atom to different candidate spatial objects. The counterfactual emission reduction difference for each discrete moment corresponding to each measurement cycle from the start of operation to the current measurement moment is extracted and multiplied by the spatial coupling compensation coefficient to obtain the emission reduction amount; the model drift penalty term is inversely calculated and then exponentially calculated to obtain the drift attenuation factor; the emission reduction amount is multiplied by the drift attenuation factor to obtain the effective emission reduction amount; the effective emission reduction amounts obtained from all discrete moments are accumulated in chronological order and then 1 is added to obtain the effective carbon compensation amount; the basic carbon perturbation amount is multiplied by the sum of the carbon source aliasing amplification factor and the constant 1 to obtain the aliasing corrected carbon perturbation amount; the aliasing corrected carbon perturbation amount is multiplied by the exponent of the spatial attribution entropy to obtain the corrected carbon perturbation amount; the corrected carbon perturbation amounts of all construction carbon perturbation atoms are added together and then 1 is added to obtain the corrected carbon debt; the effective carbon compensation amount is divided by the corrected carbon debt to obtain the carbon compensation coverage; the carbon compensation coverage is logarithmically calculated and then sigmoid compression is performed to obtain the carbon recovery critical migration value.

6. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process for identifying the carbon recovery status of spatial objects is as follows: When the carbon recovery critical migration value is less than the carbon recovery state threshold, the target space object is determined to still be in a state of residual carbon debt; when the carbon recovery critical migration value reaches the carbon recovery state threshold, the target space object is determined to have entered the carbon recovery completed state; when the carbon recovery critical migration value rises within M measurement periods but has not yet reached the carbon recovery state threshold, the target space object is marked as a carbon recovery migration object; when the carbon recovery critical migration value falls back, the target space object is marked as a carbon recovery unstable object. For spatial objects in the building component layer, construction surface layer, building layer, road section layer, public space layer, and street grid layer, the state is written back upwards along the parent-child relationship through the layered state write-back and parent-child object transmission verification method. When the working condition replay fails, the state transmission is stopped, the carbon recovery state is calculated, the carbon recovery state of adjacent spatial objects is analyzed spatially, and the carbon recovery critical surface dataset is output.

7. The intelligent spatial simulation and measurement method for low-carbon urban renewal according to claim 1, characterized in that: The specific process for generating the carbon measurement evidence chain is as follows: If, after a building facade, rooftop work surface, road excavation section, greening replanting area, or public space unit has entered the operation phase, new construction carbon disturbance atoms generated by construction re-intervention events still occur, and the corresponding spatial carbon repayment chain condition reenactment fails, it is identified as an abnormal accumulation of construction carbon debt. The identified abnormal carbon recovery status is written into the carbon measurement evidence chain, and a traceable chain evidence report is formed with the spatial object number as the main index and the carbon recovery critical migration value as the status index.

8. A smart spatial simulation and measurement system for low-carbon urban renewal, employing the smart spatial simulation and measurement method for low-carbon urban renewal as described in any one of claims 1-7, characterized in that, include: The spatial spectrum calibration module is used to acquire construction carbon source data and perform time axis relocation, spatial object binding, signal drift correction and normalization to obtain a perturbation spatial reference dataset. The carbon perturbation atom identification module is used to identify candidate fragments of construction carbon perturbation based on the perturbation space benchmark dataset, perform carbon source unmixing, construct construction carbon perturbation atoms, and generate a set of construction carbon perturbation atoms. The counterfactual carbon repayment simulation module is used to construct a counterfactual operating baseline based on the set of carbon perturbation atoms during construction, perform carbon debt reenactment, and generate a spatial carbon repayment chain. The critical migration measurement module is used to assess the critical migration of carbon recovery for construction carbon perturbation atom sets and space carbon repayment chains, identify the carbon recovery status of space objects, and generate a carbon measurement evidence chain.

Images