Future scene heat island local effect data correction method for providing basis for sustainable building and energy consumption design

Abstract

The invention belongs to the technical field of urban climate big data, and discloses a future scene heat island local effect data correction method for providing a basis for sustainable building and energy consumption design. Obtaining an EPW climate data file; constructing a regression model for predicting heat island effect parameters based on the urban form and remote sensing feature data, obtaining dynamic correction parameters related to air temperature, wind speed and solar radiation, and applying the dynamic correction parameters to hourly correction processing of EPW data; generating a future climate prediction file; and carrying out climate data visual expression. Through combination of influence correction of the urban heat island effect on meteorological data and prediction of future climate change, more accurate and comprehensive climate data support is provided for building design. Compared with the prior art, the method not only considers the correction of the urban heat island effect, but also can provide long-time climate prediction based on future climate change scenes for designers.

Description

Technical Field

[0001] The present invention relates to the field of urban climate big data technology, and in particular to a method for correcting future scenario heat island local effect data that provides a basis for sustainable building and energy consumption design. Background Art

[0002] With the acceleration of global urbanization, urban climate issues, particularly the Urban Heat Island (UHI) effect, are increasingly becoming a significant factor affecting the quality of the urban environment and residents' lives. The UHI refers to the phenomenon in which urban areas experience significantly higher temperatures than surrounding rural areas. This phenomenon is primarily caused by factors such as building density, transportation, and energy consumption. The UHI not only increases a city's energy demand but also affects air quality, reduces residents' thermal comfort, and exacerbates the negative impacts of climate change.

[0003] Currently, many studies in urban meteorology have focused on the impact of the urban heat island effect on local climate. For example, by improving climate data models, the impact of the urban heat island effect on urban temperature, humidity, wind speed and other meteorological factors has been simulated. However, existing research generally has the following shortcomings:

[0004] 1. Lack of accurate weather data correction for the urban heat island effect: Traditional urban meteorological data models often ignore or simplify the impact of the urban heat island effect on meteorological parameters, particularly in terms of building density, green space coverage, and traffic flow. Existing climate data often fails to accurately reflect the climate differences between urban cores and surrounding areas, resulting in a lack of accurate climate data support for building energy efficiency and thermal comfort design.

[0005] 2. Inadequate Integration of Urban Heat Island Effect Correction and Long-Term Climate Prediction: In existing urban climate simulation methods, urban heat island effect correction and long-term climate prediction are often performed separately, lacking research that effectively integrates the two. Most research focuses on short-term (several years) meteorological data corrections, neglecting the accurate prediction of long-term climate change trends. In particular, when addressing future climate change, existing research fails to fully integrate the impact of the urban heat island effect with future climate scenario data, resulting in a failure to provide long-term climate trend support for architectural design.

[0006] 3. Inadequate Accuracy in Urban Microclimate Research: Existing simulation methods for urban microclimate research often rely on historical meteorological data and global climate models. These methods offer relatively low accuracy in simulating localized urban climate change. The diverse environments and complex climatic factors (such as topography, building structure, and wind direction) of cities result in insufficient local precision and responsiveness in traditional models, making them incapable of meeting the precise climate data requirements of urban design.

[0007] In summary, existing technologies lack a method for correcting future scenarios of localized urban heat island effects to support sustainable building and energy design. Therefore, a novel method is urgently needed that can both correct for the impact of the urban heat island effect on meteorological data and provide accurate future climate forecasts, thereby providing more accurate and reliable climate data support for sustainable building design and urban planning. Summary of the Invention

[0008] The purpose of this invention is to provide a method for correcting localized urban heat island effect data based on future scenarios, providing a basis for sustainable building and energy efficiency design. By combining the correction of the impact of the urban heat island effect on meteorological data with predictions of future climate change, this method provides more accurate and comprehensive climate data support for architectural design. Compared with existing technologies, this method not only takes into account the correction of the urban heat island effect, but also provides designers with long-term climate forecasts based on future climate change scenarios.

[0009] In order to achieve the above object, the present invention provides the following technical solutions:

[0010] A method for correcting local heat island effect data in future scenarios, which provides a basis for sustainable building and energy consumption design, comprises the following steps:

[0011] S1: Obtain EPW climate data files and collect urban morphology and remote sensing characteristic data related to the region in a unified space and time;

[0012] S2: Use the Dragonfly tool to improve the EPW climate data. Based on the urban morphology and remote sensing characteristic data, a regression model for predicting urban heat island effect parameters is constructed to obtain dynamic correction parameters related to temperature, wind speed and solar radiation, and apply them to the hourly correction of EPW data.

[0013] S3: Generate future climate prediction files using CCWorldWeatherGen tool;

[0014] S4: Use LadyBug Tools to visualize climate data.

[0015] The EPW climate data file includes dry-bulb temperature, wet-bulb temperature, wind speed, wind direction, global horizontal radiation, and relative humidity.

[0016] The corrected EPW climate data include temperature correction, wind speed correction and global horizontal radiation correction.

[0017] The temperature correction is specifically:

[0018] Based on building density (BD), normalized difference vegetation index (NDVI), sky visibility factor (SVF), land surface temperature (LST), and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point heat island warming parameter (ΔT_UHI(x,y,t)). The base temperature is then corrected according to the following formula:

[0019] T_adj(x,y,t) = T_base(x,y,t) + ΔT_UHI(x,y,t)

[0020] Where: T_adj(x,y,t) is the corrected temperature, T_base(x,y,t) is the base temperature, and ΔT_UHI(x,y,t) is the dynamic warming value caused by the heat island effect.

[0021] The wind speed correction is specifically as follows:

[0022] Based on building density (BD), sky visibility factor (SVF), urban surface roughness, terrain slope, and time variable t, a regression learning model or machine learning model is established to predict the hourly and point-by-point wind speed attenuation parameter α(x, y, t). The basic wind speed is corrected according to the following formula:

[0023] V_adj(x,y,t) = V_base(x,y,t) × (1-α(x,y,t))

[0024] Where: V_adj(x,y,t) is the corrected wind speed, V_base(x,y,t) is the base wind speed, and α(x,y,t) is the wind speed attenuation factor considering the urban heat island effect.

[0025] The solar radiation correction is specifically as follows:

[0026] Based on the sky visibility factor (SVF), surface albedo, building facade reflectivity, green space coverage, and time variable t, a regression learning model or machine learning model is established to predict the hourly and point-by-point radiation correction coefficient η_UHI(x,y,t). The basic global horizontal solar radiation is corrected according to the following formula:

[0027] I_adj(x,y,t) = I_base(x,y,t) × η_UHI(x,y,t)

[0028] Where I_adj(x,y,t) is the corrected global horizontal solar radiation, I_base(x,y,t) is the base global horizontal solar radiation, and η_UHI(x,y,t) is the radiation correction factor under the influence of the urban heat island effect.

[0029] The step S3 includes loading and introducing the climate scenario model data published by IPCC as future climate driving parameters, applying the meteorological change trend under the future typical emission path to the corrected climate data to generate a city microclimate EPW data file with future year characteristics.

[0030] The step S4 generates different types of climate data visualization charts using LadyBug Tools through HourlyPlot, WindRose and PsychrometricChart plugins.

[0031] The present application has the beneficial effect of providing a basis for sustainable building design by accurately analyzing and visualizing city climate big data. Through the technology of the present application, the influence of urban heat island effect in existing climate data can be effectively corrected, and future climate change trends can be predicted, providing more accurate and long-term climate data support for architects. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 A future scenario heat island local effect data correction method flowchart for providing a basis for sustainable building and energy consumption design;

[0033] Figure 2 A model diagram of Zhongshan Square in Dalian City;

[0034] Figure 3-Figure 14 A comparison chart of corrected point temperature and weather station temperature from January to December. DETAILED DESCRIPTION

[0035] S1: Obtain EPW climate data;

[0036] The meteorological input program (Dragonfly Climate Data Input) of the Grasshopper-Dragonfly platform is used to read and process the historical observed meteorological data after city-level observation. This program can receive and analyze EPW format climate data files, which usually include a series of meteorological parameters such as dry bulb temperature, wet bulb temperature, atmospheric pressure, relative humidity, wind speed, wind direction, solar radiation, etc. The heat island effect mainly affects the city microclimate from three aspects: air temperature, wind speed and solar radiation, so step S2 corresponds to the respective correction methods.

[0037] S2: Correction of urban heat island effect

[0038] In step S2, the Dragonfly tool was used to construct a model system for hourly and point-by-point weather correction by inputting parameters related to the urban heat island effect, such as distance from the city center, surface properties, and building density. These inputs played a key role in correcting the urban climate, particularly in reflecting climate differences between different urban areas. The core mechanism of urban heat island correction is as follows:

[0039] 1) Temperature correction:

[0040] Based on input factors such as building density (BD), normalized difference vegetation index (NDVI), sky visibility factor (SVF), land surface temperature (LST), and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point heat island warming parameter ΔT_UHI(x,y,t). The base temperature is corrected according to the following formula:

[0041] T_adj(x,y,t) = T_base(x,y,t) + ΔT_UHI(x,y,t)

[0042] Where: T_adj(x,y,t) is the corrected temperature, T_base(x,y,t) is the base temperature, and ΔT_UHI(x,y,t) is the dynamic temperature increase due to the urban heat island effect. The regression learning model or machine learning model may include, but is not limited to, multiple linear regression, ensemble regression methods, or artificial neural network models. Factors such as building density and hard road surfaces in urban centers can cause temperatures to rise, while green areas can help reduce temperatures.

[0043] 2) Wind speed correction

[0044] Based on input factors such as building density (BD), sky visibility factor (SVF), urban surface roughness, terrain slope, and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point wind speed attenuation parameter α(x, y, t). The basic wind speed is corrected according to the following formula:

[0045] V_adj(x,y,t) = V_base(x,y,t) × (1-α(x,y,t))

[0046] Wherein: V_adj(x,y,t) is the corrected wind speed, V_base(x,y,t) is the base wind speed, and α(x,y,t) is the wind speed attenuation factor that takes into account the urban heat island effect. The regression learning model or machine learning model may include but is not limited to multiple regression, integrated regression method or neural network model. The prediction result reflects the degree of influence of urban building form and spatial structure on wind speed.

[0047] 3) Solar radiation correction

[0048] Based on input factors such as sky visibility factor (SVF), surface albedo, building facade reflectivity, green space coverage, and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point radiation correction coefficient η_UHI(x,y,t). The basic global horizontal solar radiation is corrected according to the following formula:

[0049] I_adj(x,y,t) = I_base(x,y,t) × η_UHI(x,y,t)

[0050] Where I_adj(x,y,t) is the corrected global horizontal solar radiation, I_base(x,y,t) is the base global horizontal solar radiation, and η_UHI(x,y,t) is the radiation correction factor for the urban heat island effect. The regression learning model or machine learning model may include, but is not limited to, multiple regression, ensemble regression methods, or neural network models to simulate the combined regulatory effects of building density, material properties, and greening conditions on solar radiation distribution. Step S2 corrects climate data based on an urban heat island effect algorithm to enhance the data's ability to reflect the urban environment.

[0051] In summary, the method presented here can be widely applied to calibrate meteorological data in other cities or regions. It can correct for errors caused by the urban heat island effect, particularly the discrepancies between meteorological data collection points and simulated measurement points, thereby improving the accuracy and reliability of meteorological data. Whether correcting historical measured data or optimizing future climate scenario forecasts, this algorithm can effectively calibrate and adapt across diverse urban environments.

[0052] S3: Generate future climate prediction data

[0053] Use the CCWorldWeatherGen climate data warping tool to load climate data from the IPCC SRES A2 scenario prediction model and generate weather forecast files for different future scenarios (2050 and 2080). The CCWorldWeatherGen climate data warping tool can predict future climate trends based on future greenhouse gas emissions and socioeconomic development paths. The IPCC SRES A2 scenario prediction model is widely used in the international climate change field. Based on a specific greenhouse gas emissions scenario, it simulates the interaction between future socioeconomic paths, technological progress, and climate change. The IPCC SRES A2 scenario prediction model was chosen because it assumes that greenhouse gas emissions will continue to increase and that countries will implement relatively limited emission reduction measures. This model aligns with reality and most accurately reflects future weather trends.

[0054] S4: Climate Data “Correction + Prediction” Visualization

[0055] Plug-ins such as LadyBug Tools can be used to process distorted climate data files. The HourlyPlot plug-in can be used to generate color maps of climate elements such as temperature, humidity, and radiation; the WindRose plug-in can be used to generate wind rose diagrams of wind speed and direction; and the PsychrometricChart plug-in can be used to generate various climate data visualization charts, such as enthalpy-psychrometric diagrams. These visualizations allow designers to more intuitively understand climate data and facilitate its application in architectural design.

[0056] The following takes a block in Dalian as an example and describes the specific implementation method and working principle of the present invention in further detail in conjunction with the accompanying drawings. It should be understood that the specific implementation method is only used to illustrate the present invention and is not used to limit the scope of the present invention.

[0057] The present invention discloses a method for correcting local heat island effect data in future scenarios, which provides a basis for sustainable building and energy consumption design. This method is based on the Grasshopper visual programming platform in the Rhino software, and combines architectural meteorological analysis plug-ins such as Dragonfly and Ladybug to build a complete set of integrated processes for data acquisition, correction, prediction and visualization. First, the basic prefecture-level EPW meteorological data is imported, and the urban heat island effect is corrected to construct historical climate data that is closer to the actual urban microclimate. Secondly, combined with the global climate model data released by the IPCC, localized meteorological forecast data files under different future scenarios are generated to form EPW files that reflect the changing trends of key climate variables in 2050 and 2080. Afterwards, the system loads the "corrected + predicted" climate data in the Grasshopper environment, and uses the Ladybug tool to perform multi-dimensional graphic visualization processing including solar radiation, wind direction and speed, temperature and humidity time series, etc. Finally, by comparing multiple time sections and multi-model output results, a scientific and intuitive climate basis is provided for architects and urban planners in the sustainable design process. The specific process is as follows: Figure 1 shown.

[0058] The steps include:

[0059] Step S1: Acquire climate data;

[0060] This step obtains basic input data for the Zhongshan Square area in Dalian, including meteorological parameters, geographical location, surrounding building environment, high-density urban characteristics, and information related to sustainable building design.

[0061] Meteorological parameter data includes: longitude and latitude, dry-bulb temperature, wet-bulb temperature, relative humidity, wind speed, wind direction, atmospheric pressure, hourly direct radiation, diffuse radiation, global horizontal radiation, vertical radiation, direct illumination power, point reflectance, diffuse reflectance, and environmental coverage. This data can be provided by the China Meteorological Administration or the local municipal meteorological bureau, obtained through non-confidential channels, and entered into the meteorological database. Alternatively, a micro-meteorological station can be established on-site to collect hourly data on key parameters such as solar radiation intensity and ambient temperature, improving local adaptability.

[0062] Building information includes: building location, elevation, geometry, height, etc. It can be extracted through digital topographic maps, remote sensing data or urban planning information, and input into the 3D modeling environment for modeling.

[0063] Surrounding environment and geographical location information includes: tree coverage, green space ratio, ground albedo, material thickness, thermal conductivity, etc. This information will directly affect the effective reception of solar radiation and serve as an important input for subsequent calculations.

[0064] Zhongshan Square area belongs to the central business district, building information input Figure 2 For the building model within the building, the tree coverage rate of the surrounding environment was set to 0.1, the green space rate was set to 0.2, the ground albedo was set to 0.25, the material thickness was set to 0.2m, and the thermal conductivity was set to 1 W / m·K; the building density was set to 0.65, the average sky visibility factor (SVF) was 0.32, the average NDVI was 0.18, and the average land surface temperature (LST) during the summer noon period was 41.3°C. The model time parameters were input on an hourly basis, and seasonal analysis was performed in combination with monthly variables.

[0065] Step S2: urban heat island effect correction;

[0066] In the Rhino-Grasshopper platform, the Dragonfly plug-in was used to correct the original meteorological data for the urban heat island effect, making the data more accurate to the actual microclimate characteristics of high-density built environments. High-density buildings and hard roads in urban core areas absorb and release more solar radiation, creating a significant heat island effect. This "barrier effect" also inhibits wind flow, requiring adjustments to be made in the EPW climate data.

[0067] Temperature correction: Based on factors such as building density, distance from the city center, surface type, and greening rate, the heat island warming effect is calculated and superimposed on the basic dry-bulb temperature to generate a corrected hourly temperature series.

[0068] Based on input factors such as building density (BD), normalized difference vegetation index (NDVI), sky visibility factor (SVF), land surface temperature (LST), and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point heat island warming parameter ΔT_UHI(x,y,t). The base temperature is corrected according to the following formula:

[0069] T_adj(x,y,t) = T_base(x,y,t) + ΔT_UHI(x,y,t)

[0070] Wherein: T_adj(x,y,t) is the corrected temperature, T_base(x,y,t) is the base temperature, and ΔT_UHI(x,y,t) is the dynamic warming value caused by the heat island effect. The regression learning model or machine learning model may include but is not limited to multiple linear regression, integrated regression method or artificial neural network model.

[0071] Wind speed correction: Combined with the building layout and ventilation corridor distribution, the wind speed attenuation coefficient is set to simulate the wind speed drop in high-density areas and adjust the original wind speed data.

[0072] Based on input factors such as building density (BD), sky visibility factor (SVF), urban surface roughness, terrain slope, and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point wind speed attenuation parameter α(x, y, t). The basic wind speed is corrected according to the following formula:

[0073] V_adj(x,y,t) = V_base(x,y,t) × (1 − α(x,y,t))

[0074] Wherein: V_adj(x,y,t) is the corrected wind speed, V_base(x,y,t) is the base wind speed, and α(x,y,t) is the wind speed attenuation factor that takes into account the urban heat island effect. The regression learning model or machine learning model may include but is not limited to multiple regression, integrated regression method or neural network model. The prediction result reflects the degree of influence of urban building form and spatial structure on wind speed.

[0075] Radiation correction: Analyze building shading and ground reflection characteristics, correct direct and diffuse radiation values, and reflect actual sunlight accessibility and heat load.

[0076] Based on input factors such as sky visibility factor (SVF), surface albedo, building facade reflectivity, green space coverage, and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point radiation correction coefficient η_UHI(x,y,t). The basic global horizontal solar radiation is corrected according to the following formula:

[0077] I_adj(x,y,t) = I_base(x,y,t) × η_UHI(x,y,t)

[0078] Wherein, I_adj(x,y,t) is the corrected global horizontal solar radiation, I_base(x,y,t) is the base global horizontal solar radiation, and η_UHI(x,y,t) is the radiation correction coefficient under the influence of the urban heat island effect; the regression learning model or machine learning model may include but is not limited to multiple regression, integrated regression method or neural network model, which is used to simulate the comprehensive regulatory effect of building density, material properties and greening conditions on solar radiation distribution.

[0079] All correction parameters can be derived from remote sensing images, urban spatial databases or measured data. The entire process is automatically completed in Grasshopper, and the corrected climate EPW file is output.

[0080] At the same time, the output is Figure 3-Figure 14 This example shows the difference between the weather station temperature and the measured point temperature after correction for the urban heat island effect for 12 months. The corrected measured point temperature differs from the weather station temperature by 0-0.3°.

[0081] Step S3: Generate future climate prediction data;

[0082] To assess the adaptability of building design under different climate change contexts, this step constructs future climate datasets at multiple time points to reflect the potential impact of long-term trends and uncertainties on building performance.

[0083] We selected typical emission scenario models published by the IPCC and extracted monthly average meteorological data, including core elements such as temperature, humidity, wind speed, and solar radiation. The model sources were HadCM3, GFDL, or other mainstream climate simulation datasets.

[0084] Data conversion is performed using tools such as CCWorldWeatherGen, interpolating and adjusting the original climate model data into a localized EPW format to meet the input requirements of building thermal environment simulation software. This process includes comparing future climate with historical baseline climate, bias correction, and hourly meteorological reconstruction.

[0085] The generated EPW files cover the years 2050 and 2080, corresponding to near-term, mid-term, and long-term climate projections, respectively. This provides data support for adaptability analysis of buildings at different lifecycle stages. The data simulation considers Dalian's actual geographical location and meteorological characteristics to ensure spatial consistency and comparability.

[0086] All future climate files can be directly imported into the Grasshopper platform for subsequent visualization and multi-objective performance evaluation. By comparing scenarios across different timescales, designers can identify key climate pressure points and optimize building space and construction strategies.

[0087] Climate change prediction data for 2050

[0088]

[0089] Climate change prediction data for 2080

[0090]

[0091] Step S4: Visualization of climate data “correction + prediction”

[0092] In the Rhino-Grasshopper platform, the Ladybug plug-in is called to perform visual analysis on the EPW files generated by correction and prediction, intuitively displaying the changing trends and design impacts of key climate variables.

[0093] The Hourly Plot component displays the temporal distribution of meteorological elements such as dry-bulb temperature, humidity, and radiation intensity throughout the year, identifying key periods of thermal environment change. The Wind Rose component generates wind speed and direction rose diagrams for analyzing ventilation potential. The Radiation Rose component reflects solar radiation intensity at different locations throughout the year, guiding orientation and shading design. The Psychrometric Chart displays the coverage of the hygrothermal comfort zone, assisting in the selection of passive strategies.

[0094] Multiple EPW files for future scenarios can be loaded in parallel to generate comparative climate trend charts for 2050 and 2080. Graphical output can cover the entire year or a specific month, supporting responsiveness assessments of key design stages or functional spaces.

[0095] Visualization results can be exported as images, charts, or parameter reports and integrated into design specifications or proposal presentations, providing a climate-based basis for building layout, construction, energy-saving strategies, and more. Graphical representation enables even non-specialists to understand the impact of climate change on building performance, improving communication efficiency and scientific decision-making.

Claims

1. A method for correcting local heat island effect data in future scenarios to provide a basis for sustainable building and energy consumption design, characterized by: The following steps are involved: S1: Obtain EPW climate data files and collect urban morphology and remote sensing characteristic data related to the region in a unified space and time; S2: Use the Dragonfly tool to improve the EPW climate data. Based on the urban morphology and remote sensing characteristic data, a regression model for predicting urban heat island effect parameters is constructed to obtain dynamic correction parameters related to temperature, wind speed and solar radiation, and apply them to the hourly correction of EPW data. S3: Generate future climate prediction files using CCWorldWeatherGen tool; S4: Use LadyBug Tools to visualize climate data.

2. The method for correcting local heat island effect data in future scenarios that provides a basis for sustainable building and energy consumption design according to claim 1, characterized in that: The EPW climate data file includes dry-bulb temperature, wet-bulb temperature, wind speed, wind direction, global horizontal radiation, and relative humidity.

3. The method for correcting local heat island effect data in future scenarios that provides a basis for sustainable building and energy consumption design according to claim 1, characterized in that: The corrected EPW climate data include temperature correction, wind speed correction and global horizontal radiation correction.

4. The method for correcting future scenario heat island local effect data for providing a basis for sustainable building and energy consumption design according to claim 3, characterized in that: The temperature correction is specifically: Based on building density (BD), normalized difference vegetation index (NDVI), sky visibility factor (SVF), land surface temperature (LST), and time variable (t), a regression learning model or machine learning model is established to predict the hourly and point-by-point heat island warming parameter (ΔT_UHI(x,y,t)). The base temperature is then corrected according to the following formula: T_adj(x,y,t) = T_base(x,y,t) + ΔT_UHI(x,y,t) , Where: T_adj(x,y,t) is the corrected temperature, T_base(x,y,t) is the base temperature, and ΔT_UHI(x,y,t) is the dynamic warming value caused by the heat island effect.

5. The method for correcting local heat island effect data in future scenarios that provides a basis for sustainable building and energy consumption design according to claim 3, characterized in that: The wind speed correction is specifically as follows: Based on building density (BD), sky visibility factor (SVF), urban surface roughness, terrain slope, and time variable t, a regression learning model or machine learning model is established to predict the hourly and point-by-point wind speed attenuation parameter α(x, y, t). The basic wind speed is corrected according to the following formula: V_adj(x,y,t) = V_base(x,y,t) × (1 − α(x,y,t)) , Where: V_adj(x,y,t) is the corrected wind speed, V_base(x,y,t) is the base wind speed, and α(x,y,t) is the wind speed attenuation factor considering the urban heat island effect.

6. The method for correcting future scenario heat island local effect data for providing a basis for sustainable building and energy consumption design according to claim 3, characterized in that: The solar radiation correction is specifically as follows: Based on the sky visibility factor (SVF), surface albedo, building facade reflectivity, green space coverage, and time variable t, a regression learning model or machine learning model is established to predict the hourly and point-by-point radiation correction coefficient η_UHI(x,y,t). The basic global horizontal solar radiation is corrected according to the following formula: I_adj(x,y,t) = I_base(x,y,t) × η_UHI(x,y,t) , Where I_adj(x,y,t) is the corrected global horizontal solar radiation, I_base(x,y,t) is the base global horizontal solar radiation, and η_UHI(x,y,t) is the radiation correction factor under the influence of the urban heat island effect.

7. The method for correcting future scenario heat island local effect data for providing a basis for sustainable building and energy consumption design according to claim 1, characterized in that: The step S3 includes loading and introducing the climate scenario model data released by the IPCC as future climate driving parameters, applying the meteorological change trend under the future typical emission path to the corrected climate data, and generating an urban microclimate EPW data file with future year characteristics.

8. The method for correcting future scenario heat island local effect data for providing a basis for sustainable building and energy consumption design according to claim 1, characterized in that: The step S4 uses LadyBug Tools to generate different types of climate data visualization charts through HourlyPlot, WindRose and PsychrometricChart plug-ins.

Images