A method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area.

Abstract

This invention provides a method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area, relating to the field of infrastructure planning technology. The method includes: S1, analyzing and predicting historical demand data for four scenario types based on historical demand data of the target area; S2, using Monte Carlo simulation for parameter calibration and improving the prediction accuracy of the modified exponential growth model and logistic growth model through Bayesian estimation; S3, determining the demand for low-altitude passenger take-off and landing facilities and the demand for low-altitude cargo take-off and landing facilities, and optimizing the total demand for low-altitude take-off and landing stations in the target area; S4, planning the low-altitude infrastructure in the target area to achieve spatial matching between low-altitude take-off and landing facility nodes and demand hotspots. This invention integrates multiple dynamic technological progress models and multi-scenario analysis mechanisms to improve the accuracy and scientific nature of data prediction; it introduces a station reuse coefficient to achieve efficient sharing of passenger and freight facilities and optimize the planning and layout of low-altitude take-off and landing facilities.

Description

Technical Field

[0001] This invention relates to the field of infrastructure planning technology, and more specifically to a method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area. Background Technology

[0002] As capital-intensive public service facilities, the scientific decision-making regarding the scale of initial investment and the construction sequence of low-altitude infrastructure has a decisive impact on the project's life-cycle benefits. Currently, research on demand forecasting for low-altitude take-off and landing facilities is still in the exploratory stage, and existing methods generally suffer from insufficient spatial dimension refinement. Because low-altitude transportation networks exhibit significant system network effects, their service efficiency highly depends on the spatially coordinated layout of facility nodes; therefore, demand forecasting must be organically integrated with spatial location analysis.

[0003] However, in terms of data support, the existing statistical system still has structural deficiencies in its coverage depth at the township-level administrative divisions. Taking traffic demand forecasting as an example, the OD matrix data required by the traditional four-stage method is generally lacking at the county level and below, and the available effective data dimensions, such as population and GDP, are relatively limited. This data sparsity significantly increases the difficulty of predicting the spatial distribution of demand. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention aims to provide a method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area. By integrating multiple dynamic technological advancement models and multi-scenario analysis mechanisms, it flexibly addresses market and technological uncertainties, fully considers predictive flexibility, and improves the accuracy and scientific rigor of predictions. It efficiently utilizes limited data, enabling relatively accurate demand forecasting even with limited data types. By introducing a station reuse coefficient, it achieves efficient sharing of passenger and freight facilities, reduces redundant construction, optimizes the planning and layout of low-altitude take-off and landing facilities, and, based on spatial-level distribution prediction, matches node layout with demand hotspots.

[0005] Specifically, the present invention provides a method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area, which includes the following steps:

[0006] S1: Obtain historical demand data for the target area, analyze and predict historical demand data for four scenario types, and obtain demand prediction results for passenger commuting scenarios. Demand forecast results for passenger transport and tourism scenarios Demand forecast results for last-mile logistics scenarios Demand forecast results for product and cargo transportation scenarios Set the saturation permeability of the target area. The market impact coefficient in the modified exponential growth model growth rate in the logistic growth model The revised results of passenger commuter demand were determined using a modified exponential growth model. Correction results for demand in product and cargo transportation scenarios The revised demand results for passenger tourism scenarios were determined using the logistic growth model. Correction results for demand in last-mile logistics scenarios ;

[0007] S2: Using Monte Carlo simulation to determine the saturated permeability of the target area in step S1. Market impact coefficient of the modified exponential growth model The growth rate of the logistic growth model Parameter calibration was performed, and the robustness of the modified exponential growth model and logistic growth model was improved through Bayesian estimation to output the total demand for low-altitude commuting flights. Low-altitude tourism demand flights Last-mile logistics demand and total number of cargo flights ;

[0008] S3: Determine the demand for low-altitude passenger take-off and landing facilities based on the output of step S2. Demand for low-altitude cargo take-off and landing facilities Use space utilization factor and time reuse factor The total demand for low-altitude take-off and landing stations in the target area, obtained through collaborative optimization, is:

[0009] ;

[0010] in, The total demand for low-altitude take-off and landing stations in the target area; To find the minimum value of the function; Demand for low-altitude passenger transport take-off and landing facilities; Demand for low-altitude cargo take-off and landing facilities; Space utilization coefficient; This is the time reuse factor;

[0011] S4: Obtain the total demand for low-altitude takeoff and landing stations in the target area based on step S3. This is used for low-altitude infrastructure planning in target areas, enabling spatial matching of low-altitude take-off and landing facility nodes with demand hotspots.

[0012] Preferably, the demand for low-altitude passenger take-off and landing facilities in step S3 is... The method for obtaining it is as follows:

[0013] Based on the total demand for low-altitude commuting flights and low-altitude tourism demand The demand for low-altitude passenger take-off and landing facilities is calculated as follows:

[0014] ;

[0015] in, This represents the total demand for low-altitude passenger transport. The number of suitable flight days per year; Average daily working hours; This represents the maximum takeoff and landing capacity of a single facility. Total number of flights required for low-altitude commuting; To meet the demand for low-altitude tourism.

[0016] Preferably, the demand for low-altitude cargo take-off and landing facilities in step S3 is... The method for obtaining it is as follows:

[0017] Based on last-mile logistics demand and total number of cargo flights The required quantity of low-altitude cargo take-off and landing facilities is calculated as follows:

[0018] ;

[0019] in, To meet the demand for low-altitude cargo transport; For last-mile logistics demand; This represents the total number of cargo flights.

[0020] Preferably, the maximum takeoff and landing capacity per facility in step S3 is... The method for obtaining it is as follows:

[0021] ;

[0022] in, The total usable area of ​​the take-off and landing facilities; The minimum circle diameter for the horizontal projection of the aircraft; To meet the minimum safe distance for eddy current interference critical distance; This is the parameter for pi.

[0023] Preferably, step S1 specifically includes:

[0024] S11: Collect historical demand data for four scenarios in the target area: passenger commuting, passenger tourism, last-mile logistics delivery, and product cargo transportation;

[0025] S12: Based on the historical demand data of four scenario types, predictive analysis is performed using regression analysis, consumption coefficient method and exponential smoothing method respectively. The average value is taken to obtain the demand prediction results of the four scenario types in the target area.

[0026] S13: Determine the revised results of passenger commuter demand using the modified exponential growth model. Correction results for demand in product and cargo transportation scenarios The revised demand results for passenger tourism scenarios were determined using the logistic growth model. Correction results for demand in last-mile logistics scenarios .

[0027] Preferably, the passenger commuter demand correction result in step S13 The method for obtaining it is as follows:

[0028] ;

[0029] in, Corrected results for passenger commuter demand; Demand forecast results for passenger commuting scenarios; To correct the output of the exponential growth model, based on the saturation penetration rate and market influence coefficient Sure; For time parameters; The ratio of the distance from the target area to the city center; This is for data delivery on a single commuter flight.

[0030] Preferably, the correction result of passenger tourism scenario demand in step S13 The method for obtaining it is as follows:

[0031] ;

[0032] in, The results were corrected for demand in passenger transport and tourism scenarios. Demand forecast results for passenger transport and tourism scenarios; For the dynamic demand correction function in passenger transport and tourism scenarios, based on the saturation penetration rate... and growth rate Sure; This is data for a single tourist transport flight.

[0033] Preferably, the result of the demand correction for the last-mile logistics scenario in step S13 is... The method for obtaining it is as follows:

[0034] ;

[0035] in, Corrected results for demand in last-mile logistics scenarios; Demand forecast results for last-mile logistics scenarios; For the dynamic demand correction function in the last-mile logistics scenario, based on the saturation penetration rate and growth rate Sure; This refers to the delivery volume per single flight.

[0036] Preferably, the product cargo transportation scenario demand correction result in step S13 The method for obtaining it is as follows:

[0037] ;

[0038] in, The result is a correction for the demand in the product and cargo transportation scenario. Demand forecast results for product and cargo transportation scenarios; This is a dynamic demand correction function for product and cargo transportation scenarios, based on the saturation penetration rate. and market influence coefficient Sure; This refers to the load capacity per flight.

[0039] Preferably, step S2 specifically includes:

[0040] S21: Set the initial saturation permeability of the target area Market Influence Coefficient and growth rate The parameter range;

[0041] S22: Perform Monte Carlo simulations to generate multiple sets of parameter combinations, and calculate the demand forecast results for each parameter combination by modifying the exponential growth model and the logistic growth model;

[0042] S23: Compare the demand forecast results from step S22 with the actual observed values ​​and calculate the root mean square error index.

[0043] S24: Perform Bayesian posterior update and select the optimal parameter combination to apply to the modified exponential growth model and logistic growth model;

[0044] S25: Update the demand for four scenario types based on the modified exponential growth model and the logistic growth model.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] (1) This invention can make efficient use of limited data and transform macroeconomic indicators into micro-space demand by introducing multi-source auxiliary parameters, effectively addressing the problem of data scarcity and enabling relatively accurate demand forecasting even with limited data types.

[0047] (2) By integrating multiple dynamic technological progress models and multi-scenario analysis mechanisms, this invention can flexibly respond to market and technological uncertainties, fully consider forecasting flexibility, and improve the accuracy and scientific nature of data forecasting.

[0048] (3) This invention introduces a station reuse coefficient to achieve efficient sharing of passenger and freight facilities, reduce redundant construction, optimize facility planning and layout, and at the same time, based on spatial distribution prediction, make the node layout match the demand hotspots.

[0049] (4) Based on the predicted total demand for passenger low-altitude scenarios and the number of low-altitude product cargo flights, this invention can guide operators to purchase appropriate types and quantities of aircraft, help operators to rationally allocate resources, and improve the utilization efficiency of low-altitude take-off and landing facilities. Attached Figure Description

[0050] Figure 1 This is a flowchart of the method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area according to the present invention.

[0051] Figure 2 This is a detailed flowchart illustrating the spatial forecasting of low-altitude take-off and landing facility demand in a specific township area, as per an embodiment of the present invention.

[0052] Figure 3 This is a graph showing the predicted low-altitude commuting demand in various township markets in the tenth year according to an embodiment of the present invention.

[0053] Figure 4 This is a graph showing the predicted low-altitude air traffic demand for key tourist towns in the tenth year according to an embodiment of the present invention.

[0054] Figure 5 This is a graph showing the consumer-side results of the tenth-year forecast of low-altitude last-mile logistics demand in townships / streets according to an embodiment of the present invention.

[0055] Figure 6 This is a production-side chart showing the predicted flight counts for low-altitude freight transport in major towns / streets in the tenth year according to an embodiment of the present invention.

[0056] Figure 7 The number of low-altitude landing facilities to be constructed in townships is the embodiment of the present invention. Detailed Implementation

[0057] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0058] This invention proposes a method for predicting the spatial distribution of demand for low-altitude take-off and landing facilities in a target area, such as... Figure 1 As shown, based on historical demand data analysis of the target area, historical demand data for four scenario types are predicted; Monte Carlo simulation is used for parameter calibration, and Bayesian estimation is used to improve the prediction accuracy of the modified exponential growth model and the logistic growth model; the demand for low-altitude passenger take-off and landing facilities and the demand for low-altitude cargo take-off and landing facilities are determined, and the total demand for low-altitude take-off and landing stations in the target area is optimized; the low-altitude infrastructure in the target area is planned to ensure spatial matching between low-altitude take-off and landing facility nodes and demand hotspots; specifically, the following steps are included:

[0059] Step S1: Obtain historical demand data for towns and villages in the target area, and analyze and process it to obtain the total low-altitude demand for towns and villages in the target area across multiple scenarios.

[0060] Step S11: In this embodiment of the invention, the target area is based on a township as the basic spatial unit, collecting data on tourism and long-distance commuter passenger volume; for example... Figure 2 This is a detailed flowchart of the spatial forecasting of the demand for low-altitude take-off and landing facilities in a certain township area according to an embodiment of the present invention. In this embodiment, buses are the main means of transportation. The historical demand data table is composed of relevant data such as the output / external transportation volume of fresh products or other time-sensitive products in the area, as well as the last-mile logistics delivery volume. It is specifically divided into four scenario types: passenger commuting, passenger tourism, last-mile logistics delivery, and product cargo transportation.

[0061] Table 1 Historical Demand Data

[0062]

[0063] Step S12: Based on the scenario type analysis in Table 1, passenger tourism and passenger commuting scenarios are used for passenger demand forecasting in the target area's towns and villages; product cargo transportation and last-mile logistics delivery scenarios are used for freight demand forecasting in the target area's towns and villages. For the passenger tourism scenario, based on historical data on ticket purchases at various tourist attractions, regression analysis, consumption coefficient method, and exponential smoothing method are used to calculate the average value to obtain the predicted number of tourist ticket purchases in towns and villages for the next five to ten years. The same forecasting method is used for passenger commuting, product cargo transportation, and last-mile logistics delivery scenarios to obtain the corresponding demand forecast results. for:

[0064] ;

[0065] in, This is the demand forecast result; The demand forecast results from the regression analysis model; The demand forecast results are from the consumption coefficient method; The demand forecast results are from the growth curve model.

[0066] Demand forecasting results were established using multiple linear regression. The relationship between demand forecasting and regional development level and time variables was used to obtain the demand forecasting results from the regression analysis model. for:

[0067] ;

[0068] in, The first regression coefficient, The second regression coefficient, The third regression coefficient, The fourth regression coefficient is estimated using the least squares method; t represents the year, which is a time parameter variable. For GDP parameters; For population indicator parameters; The residual term follows a normal distribution.

[0069] Demand forecast results using the consumption coefficient method for:

[0070] ;

[0071] in, To consume the basic demand; This is the consumption elasticity coefficient, with a value ranging from 0.5 to 1.2, adjusted according to industry characteristics; For future consumption demand; This represents the current consumption demand. It is the natural logarithm function.

[0072] The Gompertz curve was used to fit the nonlinear growth trend, and the demand forecast results of the growth curve model were obtained. for:

[0073] ;

[0074] in, The theoretical maximum demand was determined through expert interviews and extrapolation from historical data; exp is the natural exponential function. These are the first fitting parameters for the growth curve model; These are the second fitting parameters for the growth curve model; and All were estimated using the nonlinear least squares method.

[0075] Based on the above steps, the four scenario types in step S11 are analyzed to obtain the demand forecast results for passenger commuting scenarios. Demand forecast results for passenger transport and tourism scenarios Demand forecast results for last-mile logistics scenarios Demand forecast results for product and cargo transportation scenarios .

[0076] Step S13: Obtain the four demand forecast results for the target area towns obtained in Step S12. Based on the weather conditions required for scenario operation, the peak and off-peak season patterns, and local climate characteristics, determine the actual number of operating days for the passenger tourism scenario. Using the four demand forecast results from Step S12 as a basis, and combining the aircraft seating capacity of the planned low-altitude take-off and landing facilities, calculate the average daily number of flights required for low-altitude take-off and landing facilities under pessimistic, mesoscopic, and optimistic scenarios. For passenger commuting, product and cargo transportation, and last-mile logistics delivery scenarios, use the same forecasting process to obtain the demand forecast results for their respective average daily number of flights.

[0077] Passenger commuting and freight transportation primarily serve the overall national situation and will exhibit an S-shaped growth curve. Initial growth will be slow, followed by a period of rapid growth before gradually approaching saturation. Therefore, a modified exponential growth model is more appropriate for analysis in this context. Passenger tourism and last-mile logistics delivery are determined by local transportation data and productivity. Consequently, their initial growth rate will be relatively stable, gradually approaching a certain saturation point. The growth curve will be relatively flat and uniformly approaching saturation, reflecting a more stable, rigid growth process driven by fundamental factors. A logistic growth model can effectively fit this change process.

[0078] Step S131: The demand for passenger commuting in the target area's towns and villages is adjusted using a modified exponential growth model, resulting in the following adjusted demand:

[0079] ;

[0080] in, The result is a correction for demand in passenger commuting scenarios; Demand forecast results for passenger commuting scenarios; To correct the output of the exponential growth model and simulate the trend of "exponential growth in the early stage and approaching saturation in the later stage," but because saturation occurs quickly in commuting scenarios, it is simplified to an exponential growth form. ; The saturation permeability is taken as 5%-20% of the peak value at maturity; This is the market impact coefficient, reflecting the level of technological maturity and the strength of policy support. ∈[0.05,0.2]; For time parameters; The ratio of the distance from the target area to the city center. =Actual distance / Straight-line distance; For single-flight commuting data delivery, technological advancements will lead to... Round up to the nearest whole number to increase; This is the initial data for a single commuter transport flight, with an initial value of 2 people. These are the parameters for the first scenario analysis. The value is determined based on the scenario analysis: Pessimism = 0.01 Mesoscopic = 0.02 Meso-level = 0.03, and by substituting technological advancements under different scenarios, the corrected passenger commuting demand is calculated. The result.

[0081] Step S132: The demand for passenger transport and tourism in the target area's towns and villages is adjusted using the logistic growth model, resulting in the adjusted demand for passenger transport and tourism:

[0082] ;

[0083] in, The results were corrected for demand in passenger transport and tourism scenarios. Demand forecast results for passenger transport and tourism scenarios; This is a dynamic demand correction function for passenger transport and tourism scenarios, and it represents the technology penetration rate function result of the logistic curve growth model. ; The growth rate is defined in the example, and its value range is [value range missing]. ∈[0.1,0.3]; The inflection point time is typically set to the 5th year in the future in the embodiments; For single-flight tourist transport data, technological advancements will be used to... ], rounded up to the nearest whole number; This is the initial single-flight tourist transport data, with a value of 2 people. For the second scenario analysis parameters, The value is determined based on the scenario analysis: Pessimism = 0.01 Mesoscopic = 0.02 Meso-level = 0.03, and by substituting technological advancements under different scenarios, the corrected demand for passenger transport and tourism scenarios is calculated. The result.

[0084] Step S133: The logistic growth model is used to adjust the demand for last-mile logistics in the target area's towns and villages, resulting in the following adjusted demand:

[0085] ;

[0086] in, Corrected results for demand in last-mile logistics scenarios; Demand forecast results for last-mile logistics scenarios; This is a dynamic demand correction function for last-mile logistics scenarios, and it represents the technology penetration rate function result of the logistic curve growth model. ; This refers to the delivery volume per flight, the initial value in the example. It is 2 units, and after technological advancements, it will be based on... increase; For the third scenario analysis parameters, The value is determined based on the scenario analysis: Pessimism = 0.03 Mesoscopic = 0.04 Meso-level = 0.05, and by substituting technological advancements under different scenarios, the corrected demand for last-mile logistics scenarios is calculated. The result.

[0087] Step S134: The demand for product and goods transportation in the target area's townships is adjusted using a modified exponential growth model, resulting in the following adjusted demand:

[0088] ;

[0089] in, The result is a correction for the demand in the product and cargo transportation scenario. Demand forecast results for product and cargo transportation scenarios; This is a dynamic demand correction function for product and cargo transportation scenarios, representing the result of a technology penetration rate function that modifies the exponential growth model. ; For single-flight load, the initial value in the example is... It is 50kg, and after technological advancements, it will be based on... increase; For the fourth scenario analysis parameters, The value is determined based on the scenario analysis: Pessimism = 0.02 Mesoscopic = 0.03 Meso-level = 0.04, and by substituting technological advancements under different scenarios, the corrected demand for product and goods transportation scenarios is calculated. The result.

[0090] Step S2: Use Monte Carlo simulation to determine the saturation permeability of the target area townships in Step S13. Market impact coefficient of the modified exponential growth model The growth rate of the logistic growth model Parameter calibration was performed, and the robustness of the modified exponential growth model and logistic growth model was improved through Bayesian estimation. The prediction accuracy of the modified exponential growth model and logistic growth model was verified by backtesting with existing historical demand data from townships in the target area.

[0091] Step S21: Set the initial saturation permeability of the target area towns Market Influence Coefficient and growth rate The parameter range. Saturated permeability. Typically set based on market research or expert model evaluation; in the example, in the passenger commuting scenario, the value may range from 5% to 20% of the peak value at maturity. Market Impact Coefficient Reflecting technological maturity and policy support, this value is typically set between [0.05, 0.2] in modified exponential growth models. Growth rate The parameters used in the logistic growth model are typically set between [0.1, 0.3].

[0092] Step S22: Perform Monte Carlo simulation; based on the parameter range set in step S21, use a programming language to perform a large number of random samples to generate multiple sets of parameter combinations, and calculate the demand forecast results under each parameter combination by modifying the exponential growth model and the logistic growth model.

[0093] Step S23: Evaluate the demand forecast results based on the modified exponential growth model and the logistic growth model. For each set of saturation penetration rates generated in step S22... Market Influence Coefficient and growth rate The parameters are combined and substituted to calculate the future demand forecast results, which are then compared with the actual observed values ​​to calculate evaluation indicators such as the root mean square error (RMSE).

[0094] Step S24: Based on the root mean square error (RMSE) calculated in step S23, perform a Bayesian posterior update of the saturated permeability. Market Influence Coefficient and growth rate By weighting the various parameter combinations, the optimal saturation permeability is selected. Market Influence Coefficient and growth rate The parameter combination is applied to the modified exponential growth model and logistic growth model in step S13 to predict the demand in historical periods. A certain historical period of the target area township is selected. In this example, historical demand data from 2018 to 2022 is used. The low-altitude demand in this period is predicted by the parameter combination before calibration and the parameter combination after calibration, respectively. The difference between the predicted value and the actual value is compared, the root mean square error (RMSE) is calculated, and it is determined whether it is less than or equal to 15%.

[0095] Step S25: Update the saturated permeability from step S24 Market Influence Coefficient and growth rate Substituting the modified exponential growth model and logistic growth model from step S13, the modified demand results for passenger commuting scenarios are obtained. Updated to total demand for low-altitude commuting flights ;like Figure 3 The figure shown is a graph of the predicted low-altitude commuting demand in various townships in the tenth year of this embodiment of the invention. The graph shows the predicted flight numbers under different scenarios of township commuting demand in the embodiment, under optimistic, pessimistic and meso-level conditions.

[0096] Corrected results for demand in passenger transport and tourism scenarios Updated to meet low-altitude tourism demand. ;like Figure 4 The figure shown is a forecast of low-altitude demand in key tourist towns in the tenth year according to an embodiment of the present invention. The forecast results of demand flights under different scenarios of tourism demand in towns in the embodiment are shown in optimistic, pessimistic and meso-level conditions.

[0097] Corrected results for demand in last-mile logistics scenarios Updated to last-mile logistics demand flights ; Figure 5 This is a graph showing the consumer-side results of the tenth-year forecast of low-altitude last-mile logistics demand in townships / streets according to an embodiment of the present invention. The graph shows the demand flight prediction results under different scenarios of township last-mile logistics demand in the embodiment, under optimistic, pessimistic, and meso-level conditions.

[0098] Corrected results for product cargo transportation scenario demand Updated to total cargo demand flights ; Figure 6 This is a production-side result diagram showing the predicted flight count for low-altitude freight transport in major towns / streets in the tenth year of this invention. The tenth year represents the time when the local market is saturated. The diagram shows the predicted flight count under different scenarios of low-altitude freight transport demand in towns in this embodiment, under optimistic, pessimistic, and meso-level conditions.

[0099] Step S3: Based on step S2, determine the demand for low-altitude passenger take-off and landing facilities and the demand for low-altitude cargo take-off and landing facilities, and obtain the total demand for low-altitude take-off and landing stations in the target area's towns and villages.

[0100] Step S31: Obtain the total number of low-altitude commuter flights obtained in step S25. and low-altitude tourism demand The demand for low-altitude passenger take-off and landing facilities is calculated as follows:

[0101] ;

[0102] in, Demand for low-altitude passenger transport take-off and landing facilities; This represents the total demand for low-altitude passenger transport. The number of suitable flight days per year, ranging from 200 to 300 days, is based on meteorological data. T = 365 - the annual average number of days with strong winds and heavy rain. The values ​​represent the average daily working hours, and in this example, the range is 8-12 hours, taking into account day and night constraints and maintenance time. The maximum takeoff and landing capacity per facility is determined based on the aircraft size and site area. Total number of flights required for low-altitude commuting; To meet the demand for low-altitude tourism.

[0103] Maximum takeoff and landing capacity per facility The method for obtaining it is as follows:

[0104] ;

[0105] in, The total usable area of ​​the take-off and landing facilities; The minimum circle diameter for the horizontal projection of the aircraft; To meet the minimum safe distance for eddy current interference critical distance; The parameter is pi; the maximum takeoff and landing capacity of a single facility. To find the numerator in the formula The effective net usable area after edge buffer correction, denominator The area is for the safe use of a single aircraft.

[0106] Step S32: Obtain the last-mile logistics demand flight numbers obtained in step S25. and total number of cargo flights The required quantity of low-altitude cargo take-off and landing facilities is calculated as follows:

[0107] ;

[0108] in, Demand for low-altitude cargo take-off and landing facilities; To meet the demand for low-altitude cargo transport; For last-mile logistics demand; This represents the total number of cargo flights.

[0109] Step S33: Since the low-altitude take-off and landing fields in the target area's towns and villages have both passenger and freight transport functions, there is potential for site reuse. The reuse can be done in two ways: spatial partitioning or time-segmented reuse. Therefore, a space utilization coefficient is introduced. and time reuse factor The total demand for low-altitude take-off and landing stations in the target area's towns and villages, obtained through collaborative optimization, is as follows:

[0110] ;

[0111] in, The total demand for low-altitude take-off and landing stations in the target area's towns and villages; To find the minimum value of the function; The space utilization coefficient, taken as 0.8-0.9 in this example, is used to reflect the efficiency of facility sharing. =0.5 × Number of reusable equipment types 复 Number of device types 总 +0.5 × overlapping area of ​​passenger / cargo facility functional spaces, such as shared helipads and loading / unloading areas, S overlap / Total facility footprint S total ; This is the time reuse factor. : The overlap between peak passenger demand and peak freight demand; The average daily working hours.

[0112] In the above formula Ensure 100% service capacity for the primary needs of townships in the target area, and avoid service quality degradation caused by reuse; The secondary needs of towns and villages in the target area are met by reusing parts, and rounding down ensures the integrity and safety of low-altitude take-off and landing facilities.

[0113] Step S4: Obtain the total demand for low-altitude take-off and landing stations in the target area's towns and villages through the above step S3. This information is directly used in the planning and development of low-altitude infrastructure at the city and county levels, ensuring spatial matching between low-altitude take-off and landing facility nodes in target areas and demand hotspots, thus avoiding resource misallocation. Simultaneously, based on the total demand for passenger low-altitude scenarios obtained in step S31... The number of low-altitude product freight flights obtained in step S32 This provides guidance to operators on the type and quantity of aircraft they should procure, which has significant practical implications. For example... Figure 7 The figure shows the final number of low-altitude take-off and landing facilities to be constructed in townships according to an embodiment of the present invention. The total demand forecast for low-altitude facilities in townships in the embodiment is under optimistic, pessimistic and meso-level scenarios. The final number of facilities is determined by the contractor or operator within this range.

[0114] The beneficial effects of this invention are as follows: The embodiments of this invention can efficiently utilize limited data. By introducing multi-source auxiliary parameters, it achieves the transformation from macroeconomic indicators to micro-level spatial demands, effectively addressing the problem of data scarcity. This enables relatively accurate demand forecasting even with limited data types, solving the deficiencies in township-level data coverage in existing statistical systems. By integrating multiple dynamic technological advancement models and multi-scenario analysis mechanisms, it flexibly responds to market and technological uncertainties, improving the accuracy and scientific rigor of forecasts. The embodiments of this invention can introduce a station reuse coefficient to achieve efficient sharing of passenger and freight facilities, reducing redundant construction and optimizing facility planning and layout. Simultaneously, based on township-level spatial distribution forecasts, it ensures that node layout matches demand hotspots. Based on the predicted total demand for low-altitude passenger scenarios and the number of low-altitude freight flights, it can guide operators to procure appropriate types and quantities of aircraft, helping them to rationally allocate resources.

[0115] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area, characterized in that: It comprises: S1: Obtain historical demand data of the target area, analyze and predict the historical demand data of four scene types, and obtain demand prediction results of passenger commuting scenes , demand prediction results of passenger tourism scenes , demand prediction results of end logistics scenes , and demand prediction results of product and goods transportation scenes ; Set the saturation penetration rate of the target area , the market influence coefficient of the corrected exponential growth model , and the growth rate of the logistic growth model , use the corrected exponential growth model to determine the demand correction results of passenger commuting scenes and product and goods transportation scenes ; use the logistic growth model to determine the demand correction results of passenger tourism scenes and end logistics scenes ; S2: Using Monte Carlo simulation to determine the saturated permeability of the target area in step S1. Market impact coefficient of the modified exponential growth model The growth rate of the logistic growth model Parameter calibration was performed, and the robustness of the modified exponential growth model and logistic growth model was improved through Bayesian estimation to output the total demand for low-altitude commuting flights. Low-altitude tourism demand flights Last-mile logistics demand and total number of cargo flights ; S3: Output the result of step S2 to determine the demand for low-altitude passenger transport take-off and landing facilities and the demand for low-altitude cargo transport take-off and landing facilities , use the space utilization coefficient and the time multiplexing coefficient , and cooperatively optimize to obtain the total demand for low-altitude take-off and landing facilities in the target area as: ； wherein, total demand for the target area low-altitude take-off and landing field station; is a minimum value function; is a low-altitude passenger transport take-off and landing facility demand; is a low-altitude cargo transport take-off and landing facility demand; is a space utilization coefficient; is a time multiplexing coefficient; S4: Obtain the total demand of the target area low altitude take-off and landing field station according to step S3 Low altitude infrastructure planning for the target area, so that the low altitude take-off and landing facility node is spatially matched with the demand hotspot.

2. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 1, characterized in that: The low-altitude passenger transport take-off and landing facility demand in step S3 The acquisition method is: According to the total demand of low-altitude commuter and the low-altitude tourism demand , the demand of low-altitude passenger transport landing facilities is calculated as: ； wherein, is the total demand for passenger low-altitude scenarios; is the number of suitable flight days per year; is the average daily working hours; is the maximum take-off and landing capacity of a single facility; is the total demand for low-altitude commuting; is the low-altitude tourism demand.

3. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 2, characterized in that: Low payload air vehicle launch facility demand in step S3 The acquisition method is as follows: According to the end logistics demand sorties and the total freight demand sorties , the low-altitude payload take-off and landing facility demand is calculated as: ； wherein, is the low-altitude product freight demand sorties; is the end logistics demand sorties; is the total freight demand sorties.

4. The method for predicting the spatial distribution of the scale of UAM infrastructure demand for a target area according to claim 2 or 3, characterized in that: The single-facility maximum takeoff and landing sorties capacity in step S3 The acquisition method is as follows: ； wherein, is the total area of the landing facility; is the minimum circle diameter of the horizontal projection of the aircraft; is the minimum safety distance to meet the critical distance of vortex interference; is the parameter of the circle constant.

5. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 1, characterized in that: Step S1 is specifically: S11: Collect historical demand data of four scene types of passenger commuting, passenger tourism, terminal logistics distribution and product cargo transportation in the target area; S12: According to the historical demand data of the four scene types, respectively use regression analysis method, consumption coefficient method and exponential smoothing method for prediction analysis, take the average value, respectively obtain the demand prediction results of the four scene types in the target area; S13: Determine the demand volume correction result of the passenger commuting scenario using the revised exponential growth model and the demand volume correction result of the product cargo transportation scenario ; The corrected result of the demand of the passenger transportation tourism scene is determined using a logistic growth model and the corrected result of the demand of the terminal logistics scene .

6. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 5, characterized in that: The passenger commuting scenario demand quantity correction result in step S13 The acquisition method is as follows: ； wherein, is the demand correction result for passenger commuting scenarios; is the demand prediction result for passenger commuting scenarios; is the modified exponential growth model output result, determined according to the saturated penetration rate and the market influence coefficient ; is the time parameter; is the target area to city center distance ratio; is the single-trip commuting transport data.

7. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 5, characterized in that: The demand quantity of the passenger travel scene in step S13 is corrected The acquisition method is as follows: ； wherein, is the demand correction result for the passenger tourism scenario; is the demand prediction result for the passenger tourism scenario; is the dynamic demand correction function for the passenger tourism scenario, determined according to the saturation penetration rate and the growth rate ; is the single-trip tourism transport data.

8. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 5, characterized in that: The end stream scene demand quantity correction result in step S13 The acquisition method is as follows: ； wherein, is the demand quantity correction result for the end logistics scenario; is the demand quantity prediction result for the end logistics scenario; is the dynamic demand correction function for the end logistics scenario, determined according to the saturated permeability and the growth rate ; is the single-trip distribution quantity.

9. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 5, characterized in that: The product cargo transportation scene demand quantity correction result in step S13 The acquisition method is: ； wherein, is the product goods transportation scenario demand correction result; is the product goods transportation scenario demand prediction result; is the product goods transportation scenario dynamic demand correction function determined according to the saturated penetration rate and the market influence coefficient ; is the single flight load.

10. The method for predicting the spatial distribution of the scale of low-altitude take-off and landing facility demand for a target area according to claim 1, characterized in that: Step S2 is specifically: S21: set the initial saturation permeability of the target region , market influence coefficient and growth rate parameter range; S22: Perform Monte Carlo simulation to generate multiple sets of parameter combinations, and calculate the demand prediction results under each parameter combination by using the modified exponential growth model and the logistic growth model; S23: Compare the demand prediction results of step S22 with the actual observation value, and calculate the root mean square error index; S24: Perform Bayesian posterior update, and select the optimal parameter combination to be applied to the modified exponential growth model and the logistic growth model; S25: Update the demand of the four scene types according to the modified exponential growth model and the logistic growth model.

Images