A method, device, computer equipment and readable storage medium for predicting carbon emissions from inland waterways

Abstract

The present invention discloses a method, device, computer equipment and readable storage medium for predicting carbon emissions of inland waterways, including: first, obtaining the inland waterway information of the current year and the predicted year in the target area, and calculating the carbon emissions of the construction period, operation period and maintenance period in the current year respectively. Based on this, combined with relevant information, the carbon emissions of each stage in the predicted year are calculated to determine the carbon emissions of the inland waterway throughout its life cycle in the predicted year. Finally, based on the above data and the population and GDP data of the target area, XGBoost is used to construct an inland waterway mileage and carbon emission prediction model to provide an effective reference for inland waterway planning and management.

Description

Technical Field

[0001] The present invention relates to the field of environmental governance technology, and in particular to a method, device, computer equipment and readable storage medium for predicting carbon emissions from inland waterways. Background Art

[0002] With the development of inland waterway transportation, its carbon emission problem has received increasing attention.

[0003] Accurate prediction of carbon emissions from inland waterways is crucial for rational planning, energy conservation and emission reduction.

[0004] However, existing prediction methods are often not comprehensive and systematic enough, and it is difficult to comprehensively consider various factors such as the various stages of the inland waterway life cycle and different levels of waterways. Summary of the invention

[0005] The object of the present invention is to provide a method, device, computer equipment and readable storage medium for predicting carbon emissions from inland waterways.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting carbon emissions in an inland waterway, comprising: Obtain the current inland waterway information of the target area in the current year and the predicted inland waterway information in the predicted year; The carbon emissions of the current annual river waterway in the entire life cycle are calculated separately, including the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions; According to the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions corresponding to the predicted inland river waterway are calculated; Determine the predicted annual carbon emissions for the entire life cycle of the inland waterway based on the predicted annual carbon emissions during the construction period, the predicted annual carbon emissions during the operation period, and the predicted annual carbon emissions during the maintenance period; According to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area, a prediction model of inland waterway mileage and carbon emissions corresponding to the target area is constructed based on XGBoost.

[0007] In a second aspect, an embodiment of the present invention provides an inland waterway carbon emission prediction device, comprising: An acquisition module is used to obtain the current annual river waterway information of the target area in the current year and the predicted annual river waterway information in the predicted year; respectively calculate the carbon emissions of the current annual river waterway in the whole life cycle, including the carbon emissions of the current annual construction period, the current annual operation period and the current annual maintenance period; according to the carbon emissions of the current annual construction period, the current annual operation period and the current annual maintenance period, in combination with the current annual river waterway information and the predicted annual river waterway information, calculate the predicted annual construction period carbon emissions, predicted annual operation period carbon emissions and predicted annual maintenance period carbon emissions corresponding to the predicted annual river waterway; according to the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions, determine the predicted annual annual river waterway carbon emissions in the whole life cycle; The prediction module is used to construct an inland waterway mileage and carbon emission prediction model corresponding to the target area based on XGBoost according to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor and a non-volatile memory storing computer instructions, wherein when the computer instructions are executed by the processor, the computer device executes the method described in the first aspect.

[0009] In a fourth aspect, an embodiment of the present invention provides a readable storage medium, wherein the readable storage medium includes a computer program, and when the computer program is executed, the computer device where the readable storage medium is located is controlled to execute the method described in the first aspect.

[0010] Compared with the prior art, the beneficial effects provided by the present invention include: adopting an inland waterway carbon emission prediction method, device, computer equipment and readable storage medium disclosed in the present invention, by obtaining the current year and predicted year inland waterway information of the target area, the carbon emissions during the construction period, operation period and maintenance period of the current year are calculated respectively.

[0011] Based on this and combined with relevant information, the carbon emissions at each stage of the forecast year are calculated to determine the carbon emissions of the river waterway over its entire life cycle within the forecast year.

[0012] Finally, based on the above data and the population and GDP data of the target area, XGBoost was used to build an inland waterway mileage and carbon emission prediction model to provide an effective reference for inland waterway planning and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below.

[0014] It should be understood that the following drawings depict only certain embodiments of the present invention and therefore should not be viewed as limiting the scope.

[0015] For ordinary technicians in this field, other related drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A schematic diagram of the steps of a method for predicting carbon emissions from inland waterways provided in an embodiment of the present invention; Figure 2 A schematic block diagram of the structure of an inland waterway carbon emission prediction device provided by an embodiment of the present invention; Figure 3 A schematic block diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0018] Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

[0020] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In order to solve the technical problems in the aforementioned background technology, Figure 1 This is a flow chart of the inland waterway carbon emission prediction method provided in an embodiment of the present disclosure. The inland waterway carbon emission prediction method is introduced in detail below.

[0022] Step S201, obtaining the current inland waterway information of the target area in the current year and the predicted inland waterway information of the predicted year; Step S202, respectively calculating the carbon emissions of the current annual inland waterway during the entire life cycle, including the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions; Step S203, according to the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, calculate the predicted annual construction period carbon emissions, predicted annual operation period carbon emissions and predicted annual maintenance period carbon emissions corresponding to the predicted inland river waterway; Step S204, determining the predicted annual carbon emissions of the inland waterway throughout its life cycle based on the predicted annual carbon emissions during the construction period, the predicted annual carbon emissions during the operation period, and the predicted annual carbon emissions during the maintenance period; Step S205, based on the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area, a prediction model of inland waterway mileage and carbon emissions corresponding to the target area is constructed based on XGBoost.

[0023] In the embodiment of the present invention, illustratively, after receiving the task instruction for carbon emission prediction of inland waterways in XX Province, the server first specifies that the target area for this prediction is XX Province.

[0024] The current status year is determined to be 2022, and the forecast year is set to 2030 based on the XX Province Trunk Waterway Network Plan (2023-2035).

[0025] The server collects information on inland waterway mileage and mileage of waterways of different levels in XX Province in 2022 from relevant databases and materials.

[0026] Assume that the collected data is as follows: Inland waterway mileage WH = 2400km. Mileage of waterways of different levels: First-class waterway WH i (i=1): 1200km. Secondary channel WH i (i=2): 600km. Third-level waterway WH i (i=3): 600km.

[0027] At the same time, the server also needs to collect data related to energy consumption of waterways of various levels during the construction, operation and maintenance periods in order to subsequently calculate carbon emissions.

[0028] The server continues to obtain the inland waterway information for 2030 from the XX Province Trunk Waterway Network Planning (2023-2035) and other relevant planning documents. Assume that the obtained data is as follows: Channel mileage WF = 3000km. Channel mileage of different levels: First-level channel WF i (i=1): 1500km. Secondary channel WF i(i=2): 800km. Third-level waterway WF i (i=3):700km.

[0029] The server calculates the carbon emissions during the construction period of each level of waterways in XX Province in 2022.

[0030] Taking the first-class waterway as an example, assuming that the construction mileage of a first-class waterway in XX Province in 2022 is 100km (this is just an example of the construction of one section of the first-class waterway, and there may actually be multiple construction projects with different situations), the energy consumption process includes construction machinery, construction technology (such as blasting, dredging, etc.), construction personnel, etc., a total of 200 tons of diesel, 20 tons of gasoline, 100 tons of fuel oil, and 1 million kWh of electricity are consumed.

[0031] According to the formula , where j is the fuel type, Y aj is the consumption of the jth fuel during the current waterway construction period, EM j is the emission factor of the jth fuel.

[0032] The carbon emission factors for diesel, gasoline, fuel oil and electricity are 3.159tCO2 / t, 2.985tCO2 / t, 3.235tCO2 / t and 0.5366kgCO2 / kWh respectively.

[0033] The carbon emissions during the construction period of this first-level waterway are: E a1 =200×3.159+20×2.985+100×3.235+100×0.5366×10 4 ×10 -3 =1551.6 tons.

[0034] Assuming that there are no construction projects on the secondary and tertiary waterways in XX Province in 2022, then in the subsequent calculations involving the carbon emissions during the construction period of these two levels of waterways, the corresponding change coefficient can be multiplied according to the specific circumstances (for example, in some overall calculations, the carbon emissions during the construction period of these two levels of waterways can be regarded as 0, and the specific processing method is determined according to the actual model and analysis requirements).

[0035] The server begins to calculate the carbon emissions of various levels of waterways in XX Province during the operation period in 2022.

[0036] For the first-class waterway, it is assumed that there will be 30,000 ships sailing on the first-class waterway in XX Province in 2022, of which 29,000 are fuel-powered ships and 1,000 are electric ships. The average diesel consumption of each fuel-powered ship is 300 tons, and the electricity consumption of each electric ship is 1 million kWh.

[0037] For the secondary waterway, it is assumed that there will be 6,000 ships sailing on the secondary waterway in XX Province in 2022, of which 4,000 are fuel-powered ships and 2,000 are electric ships. The average diesel consumption of each fuel-powered ship is 260 tons, and the electricity consumption of each electric ship is 800,000 kWh.

[0038] For the third-level waterway, it is assumed that there will be a total of 5,000 ships sailing on the third-level waterway in XX Province in 2022, of which 3,000 are fuel-powered ships and 2,000 are electric ships. The average diesel consumption of each fuel-powered ship is 220 tons, and the electricity consumption of each electric ship is 600,000 kWh.

[0039] According to the formula , where i is the waterway grade, N i,j is the number of ships sailing on the i-th class channel during the j-th fuel operation period in the current year, P bi,bj It is the current annual average consumption of the jth type of fuel for each ship in the i-level waterway during the operation period.

[0040] The carbon emissions during the operation period of the first-level waterway are: E b1 =(29000×300×3.159+1000×100×0.5366×10 4 ×10 -3 )=(29000×300×3.159+1000×100×0.5366×10)=28019900 tons.

[0041] Carbon emissions during the operation period of the secondary waterway are: E b2 =(4000×260×3.159+2000×80×0.5366×10 4 ×10 -3 )=(4000×260×3.159+2000×80×0.5366×10)=4143920 tons.

[0042] Carbon emissions during the operation period of the third-level waterway are: E b3 =(3000×220×3.159+2000×60×0.5366×10 4 ×10 -3 )=(3000×220×3.159+2000×60×0.5366×10)=2728860 tons.

[0043] Therefore, the carbon emissions of all waterways in XX Province during the operation period in 2022 are b =E b1 +E b2 +E b3 = 28019900+4143920+2728860=34892690 tons Assuming that the total length of all inland waterways in XX Province will be 2,400 km in 2022, the energy consumption process includes waterway inspection, navigation mark maintenance, waterway dredging, waterway facility maintenance, etc., consuming a total of 2,400 tons of diesel, 300 tons of fuel oil, and 6 million kWh of electricity.

[0044] According to the formula , where j is the fuel type, Y cj is the consumption of the jth fuel during the current channel maintenance period, EM j is the emission factor of the jth fuel.

[0045] Then the carbon emissions of all inland waterways in XX Province during the maintenance period in 2022 are: E c =2400×3.159+300×3.235+600×0.5366×10 4 ×10 -3 =11771.7 tons.

[0046] In summary, the carbon emissions of the inland waterways in XX Province in 2022 are E=E a +E b +E c =1551.6 (assuming that the construction of the first-level waterway represents the overall construction period, the carbon emissions during the construction period of the second-level and third-level waterways are handled as special cases) + 34892690+11771.7=34906003.3 tons.

[0047] First, the carbon emission intensity (ES i ), taking the first-class waterway as an example, according to the formula ES i =E a / L i , L i is the mileage of the first-class waterway constructed in the current year. It is known that the construction mileage of the first-class waterway is 100 km, and its carbon emissions during the construction period are E a1 =1551.6 tons, so the carbon emission intensity during the first-level waterway construction period ES1=1551.6 / 100=15.516tCO2 / km.

[0048] Then calculate the predicted annual construction period carbon emissions according to the formula , k1 is the coefficient of change of carbon emission intensity per unit mileage due to technological progress or energy efficiency improvement compared with the current year. It is assumed that k1=0.98 is obtained through field and literature research.

[0049] For first-class waterways, WF i (First-class waterway mileage in 2030) = 1500km, WH i (First-class waterway mileage in 2022) = 1200km. The predicted annual carbon emissions of the first-class waterway during the construction period EFa1 =15.516×(1500-1200)×0.98=15.516×300×0.98=4561.704 tons.

[0050] The same method can be used to calculate the predicted annual carbon emissions of secondary and tertiary waterways during the construction period (assuming that the relevant basic data for the construction period of secondary and tertiary waterways have also been collected and completed as required, such as the current annual construction mileage and predicted annual construction mileage of secondary waterways. The detailed assumed data and calculation process are omitted here, and the conditions of each level of waterways must be fully considered in actual operations).

[0051] Predicting NF i,j (The fuel types are the same as in step 2: diesel and electricity). The server collects information on population, GDP, freight volume, etc. in 2022 and 2030 in XX Province. Based on Ni,j in step 2 (the number of ships sailing in different fuel operation periods in each grade of waterway in 2022) and WF in step 1 i , WH i (The mileage of each level of waterway in 2030 and 2022), the prediction model is established using the random forest regression algorithm to predict the NF of ships using different fuel types during the operation period of each level of waterway in 2030 i,j .

[0052] It is assumed that the forecast shows that in 2030, the number of fuel-powered ships on first-level waterways will be 32,000, and the number of electric ships will be 1,200; the number of fuel-powered ships on second-level waterways will be 4,500, and the number of electric ships will be 2,200; the number of fuel-powered ships on third-level waterways will be 3,300, and the number of electric ships will be 2,300.

[0053] Determine the additional fuel and related data in the forecast year (assuming that methanol inland ships will be put into operation in 2030), and the number of ships with additional fuel in the research scope in the forecast year NF i,j , based on the predicted number of new fuel-intensive ships in the country in that year × (inland waterway mileage within the research scope / inland waterway mileage nationwide).

[0054] Assuming that through relevant surveys, we know that the number of new methanol ships in the country will be 10,000 in 2030, the national inland waterway mileage is 50,000 km, and the inland waterway mileage of XX Province is 3,000 km (forecast value in 2030), then the number of new methanol ships in XX Province in 2030 = 10,000 × (3,000 / 50,000) = 600.

[0055] The predicted annual average consumption of newly added fuel Pi,j takes the annual average consumption of newly added fuel ships of different tonnages. It is assumed that through on-site investigation, it is known that the annual average consumption of 3,000-ton methanol ships is 200 tons (the first-level waterway can accommodate 3,000-ton ships), the annual average consumption of 2,000-ton methanol ships is 150 tons (the second-level waterway can accommodate 2,000-ton ships), and the annual average consumption of 1,000-ton methanol ships is 100 tons (the third-level waterway can accommodate 1,000-ton ships).

[0056] Calculate the predicted annual operating carbon emissions according to the formula , k2 is the coefficient of change of the average annual fuel consumption reduced due to technological progress or energy efficiency improvement compared with the current year. Assume that k2=0.95.

[0057] For diesel fuel, take the first-class waterway as an example: PF i,j (diesel, first-class waterway) = 300 tons (assuming the average diesel consumption of each fuel ship is similar to that in 2022, which can be adjusted according to actual conditions), EF b1 (diesel, first-class waterway) = (32000×300×3.159×0.95) = 28810080 tons.

[0058] For the power consumption of electric boats, take the first-class waterway as an example: PF i,j (Electricity, first-class waterway) = 1 million kWh (assuming that the electricity consumption of each electric ship is similar to that in 2022, which can be adjusted according to actual conditions), EF b1 (electricity, first-class waterway) = (1200 × 100 × 0.5366 × 10 4 ×10 -3 ×0.95)=611724 tons.

[0059] For the newly added methanol fuel, take the first-class waterway as an example: PF i,j (Methanol, first-class waterway) = 200 tons (annual average consumption of 3,000-ton methanol ships), EF b1 (Methanol, first-level waterway) = (600 × 200 × (assuming methanol emission factor is 2.5tCO2 / t) × 0.95) = 285,000 tons.

[0060] The predicted annual carbon emissions of the first-class waterway during operation period EF b1 =EF b1 (diesel, first class channel) + EF b1 (Electrical, first-class channel) + EF b1 (Methanol, first-level waterway) = 28810080 + 611724 + 285000 = 29706804 tons.

[0061] The same method can be used to calculate the predicted annual operating carbon emissions of secondary and tertiary waterways (the detailed calculation process is omitted).

[0062] According to the formula: , k3 is the coefficient of change of inland waterway maintenance fuel consumption due to technological progress or energy efficiency improvement compared with the current year. It is assumed that k3=0.96 is obtained through field and literature research.

[0063] Known E c (Carbon emissions during the maintenance period of all inland waterways in XX Province in 2022) = 11,771.7 tons, WF (inland waterway mileage in XX Province in 2030) = 3,000 km, WH (inland waterway mileage in XX Province in 2022) = 2,400 km.

[0064] Then EF c =11771.7×3000 / 2400×0.96=11771.7×1.25×0.96=14126.04 tons.

[0065] Predict the carbon emissions of the annual life cycle of the river channel EF = EF a +EF b +EF c .

[0066] Assume that EF a (Forecasted annual carbon emissions during construction period) = 4561.704 tons (calculation example for first-class waterways, actual calculation needs to be summarized for waterways of all levels), EF b (Forecasted annual carbon emissions during operation) = 29678.15 tons (calculation example for first-class waterways, actual calculation needs to be summarized for waterways of all levels), EF c (Predicted annual carbon emissions during the maintenance period) = 14126.04 tons.

[0067] Then EF=4561.704+29706804+14126.04=29725491.74 tons (this is just an example result, the actual calculation needs to fully consider the conditions of each level of waterway) The server takes the inland waterway mileage, carbon emission data, population, GDP and other information of XX Province in 2022 (current year) and 2030 (forecast year) as input, and establishes an inland waterway mileage and carbon emission prediction model based on the decision tree ensemble learning algorithm XGBoost.

[0068] Specifically, the server first organizes and preprocesses the input data, such as standardizing population and GDP data, to ensure that data of different magnitudes have appropriate weights during the model training process.

[0069] Then, divide the sorted data into training set and test set according to a certain ratio, for example, 70% of the data is used as training set and 30% of the data is used as test set.

[0070] Next, the server uses the XGBoost algorithm to train the training set, and continuously adjusts the model parameters, such as learning rate, tree depth, etc., to make the model achieve a better fitting effect on the training set.

[0071] During the training process, the server monitors the model's loss function value, such as the mean square error (MSE). When the loss function value reaches a certain convergence standard, the model training is considered to be basically completed.

[0072] Finally, the server uses the test set to verify the trained model and evaluate the prediction accuracy of the model.

[0073] If the error between the model's prediction results on the test set and the actual data is within an acceptable range, then the model can be considered effective and can be used to infer the data on inland waterway mileage under a certain carbon emission level in a long time series, providing data reference for the future inland waterway development plan of XX Province.

[0074] For example, when a certain expected carbon emission level is input, the model can output the possible mileage of the inland waterways in XX Province under that carbon emission level. This is of great significance for the rational planning of waterway construction, operation and maintenance activities to achieve a balance between inland waterway development and environmental protection.

[0075] In the embodiment of the present invention, the acquisition of the current intra-annual river waterway information of the target area in the current year and the predicted intra-annual river waterway information in the predicted year may be implemented through the following examples.

[0076] Acquire the current inland river waterway mileage of the target area and at least two different levels of waterway mileages included in the current inland river waterway mileage; Obtaining the predicted inland river waterway mileage of the target area and at least two different levels of waterway mileages included in the predicted inland river waterway mileage; The current intra-river waterway mileage, the at least two different levels of waterway mileages included in the current intra-river waterway mileage, the predicted intra-river waterway mileage, and the at least two different levels of waterway mileages included in the predicted intra-river waterway mileage are correspondingly used as the current intra-river waterway information of the target area in the current year and the predicted intra-river waterway information in the predicted year.

[0077] In the embodiment of the present invention, exemplarily, after receiving the task instruction for obtaining the relevant information of the inland waterway of XX Province, the server starts to carry out the data collection work.

[0078] The server first queries the total mileage information of inland waterways in XX Province in 2022 (the current year) from the waterway management database of the transportation department of XX Province.

[0079] After inquiry, it was learned that the inland waterway mileage WH of XX Province in 2022 is 2400km.

[0080] Then, the server further extracts detailed mileage data of waterways of different levels from the database.

[0081] According to the classification of waterway levels, the mileage of first-class waterways in 2022 is WH i (i=1) is 1200km; the mileage of the secondary waterway is WH i (i=2) is 600km; the mileage of the third-level waterway is WH i (i=3) is 600km.

[0082] The server will organize and store the acquired inland waterway mileage of XX Province in 2022, which is 2,400 km, including 1,200 km of first-level waterways, 600 km of second-level waterways, and 600 km of third-level waterways, as partial inland waterway information of the target area (XX Province) in the current year.

[0083] After completing the collection of information for the current year, the server continues to obtain relevant data for the forecast year.

[0084] Based on the planning document "XX Province Trunk Waterway Network Planning (2023-2035)", the server extracts the planned inland waterway mileage information of XX Province in 2030 (forecast year).

[0085] It is learned through extraction that the inland waterway mileage WF of XX Province will be 3000km in 2030.

[0086] Also based on the above-mentioned planning documents, the server further sorted out the mileage data of different levels of waterways in 2030.

[0087] Among them, the mileage of the first-class waterway in 2030 is WF i (i=1) is 1500km; the mileage of the secondary waterway is WF i (i=2) is 800km; the mileage of the third-level waterway is WF i (i=3) is 700km.

[0088] Finally, the server will obtain the inland waterway mileage of XX Province in 2030 (3,000 km), including 1,500 km of first-level waterways, 800 km of second-level waterways, and 700 km of third-level waterways, and match them with the previously sorted data on the current year, as the current inland waterway information of the target area (XX Province) in the current year and the predicted inland waterway information in the predicted year, so as to facilitate subsequent related analysis work such as inland waterway carbon emission prediction.

[0089] In an embodiment of the present invention, the calculation of the current annual carbon emissions of the entire life cycle of the inland waterway, including the current annual carbon emissions during the construction period, the current annual carbon emissions during the operation period, and the current annual carbon emissions during the maintenance period, can be implemented through the following examples.

[0090] By formula: , calculate the current annual construction period carbon emissions, where E a is the current annual carbon emission during the construction period, j is the fuel type; Y aj is the consumption of the jth fuel during the current waterway construction period; EM j is the emission factor of the jth fuel; By formula: , calculate the carbon emissions of the current annual operation period, where E b is the current annual carbon emissions during operation, i is the waterway grade, N i,j is the number of ships sailing on the i-th class channel during the j-th fuel operation period in the current year, P bi,bj The current annual average consumption of the jth type of fuel for each ship in the i-level waterway during the operation period; By formula: , calculate the carbon emissions of the current situation during the annual maintenance period, where E c is the carbon emission of the current situation during the annual maintenance period, Y cj is the consumption of the jth type of fuel during the current annual channel maintenance period, in tons; EM j is the emission factor of the jth fuel.

[0091] In an embodiment of the present invention, exemplarily, after obtaining the relevant energy consumption data of the inland waterway construction period in XX Province in 2022 (the current year), the server starts to calculate the carbon emissions during the construction period in the current year.

[0092] For a certain first-level waterway construction project in XX Province in 2022, the server found from the project record database that its construction mileage is 100km, and the energy consumption is as follows: a total of 200 tons of diesel, 20 tons of gasoline, 100 tons of fuel oil, and 1 million kWh of electricity were consumed during the construction process.

[0093] It is known that the emission factors EMj of diesel, gasoline, fuel oil and electricity are 3.159tCO2 / t, 2.985tCO2 / t, 3.235tCO2 / t and 0.5366kgCO2 / kWh respectively.

[0094] According to the formula , j is the fuel type, Y aj is the consumption of the j-th type of fuel during the current waterway construction period.

[0095] The carbon emissions during the construction period of the first-level waterway are calculated as follows: For diesel: 200 tons × 3.159tCO2 / t = 631.8 tons CO2; for gasoline: 20 tons × 2.985tCO2 / t = 59.7 tons CO2; for fuel oil: 100 tons × 3.235tCO2 / t = 323.5 tons CO2; for electricity: 1 million kWh × 0.5366kgCO2 / kWh × 10 -3 (Converted to tons) = 536.6 tons of CO2.

[0096] Adding up the carbon emissions generated by each fuel, we can get the carbon emissions during the construction period of the first-level waterway, E a =631.8+59.7+323.5+536.6=1551.6 tons.

[0097] The server then processes the carbon emissions calculations for the operation period of each level of waterways in Province XX in 2022.

[0098] Taking the first-class waterway as an example, the server obtains from the ship navigation data records that there are 30,000 ships sailing on the first-class waterway in 2022, including 29,000 fuel ships and 1,000 electric ships. And the average diesel consumption of each fuel ship is P i,j (here j is diesel and i is first-class waterway) is 300 tons, and the electricity consumption of each electric ship is 1 million kWh.

[0099] According to the formula , i is the waterway grade, N i,j is the number of ships sailing on the i-th class channel during the j-th fuel operation period in the current year, P bi,bj It is the current annual average consumption of the jth type of fuel for each ship in the i-level waterway during the operation period.

[0100] Carbon emissions from fuel-burning ships: 29,000 ships × 300 tons / ship × 3.159tCO2 / t = 27,483,300 tons of CO2; Regarding carbon emissions from electric boats: 1000 ships × 1 million kWh / ship × 0.5366 kgCO2 / kWh × 10 -3(converted to tons) = 536,600 tons of CO2; The carbon emissions during the operation period of the first-level waterway are E b (First-level waterway) = 27,483,300 + 536,600 = 28,019,900 tons.

[0101] In the same way, the server calculates the carbon emissions during the operation period of the second-level and third-level waterways (the data acquisition and calculation process are similar, and the detailed steps are omitted here). Finally, the carbon emissions during the operation period of each level of waterway are added together to obtain the carbon emissions E of all waterways in XX Province during the operation period in 2022. b .

[0102] The server obtains the energy consumption of all inland waterways (with a mileage of 2,400 km) in XX Province in 2022 from the waterway maintenance work record database.

[0103] The maintenance work consumed a total of 2,400 tons of diesel, 300 tons of fuel oil, and 6 million kWh of electricity.

[0104] Knowing the emission factors of each fuel, according to the formula , Y cj is the consumption of the jth fuel during the current channel maintenance period, EM j is the emission factor of the jth fuel.

[0105] For diesel: 2400 tons × 3.159tCO2 / t = 7581.6 tons CO2; for fuel oil: 300 tons × 3.235tCO2 / t = 970.5 tons CO2; for electricity: 6 million kWh × 0.5366kgCO2 / kWh × 10 -3 (Converted to tons) = 3219.6 tons of CO2.

[0106] By adding up the carbon emissions from each fuel, we can get the carbon emissions E of all inland waterways in XX Province during the maintenance period in 2022. c =7581.6+970.5+3219.6=11771.7 tons.

[0107] Through the above detailed calculations, the server successfully obtained the carbon emissions of the current construction period, operation period and maintenance period of the inland waterway in XX Province in the entire life cycle in 2022.

[0108] In an embodiment of the present invention, based on the current annual construction period carbon emissions, combined with the current annual river waterway information and the predicted annual river waterway information, the predicted annual construction period carbon emissions corresponding to the predicted annual river waterway are calculated, which can be implemented through the following examples.

[0109] By formula: , calculate the carbon emissions during the construction period of the forecast year, where EFa To predict the annual carbon emissions during the construction period, ES i =E a / L i , E.S. i is the carbon emission intensity during the current intra-annual river channel construction period, L i is the waterway mileage of the i-th level waterway in the current year, WF i The annual waterway mileage predicted for the i-th level waterway, WH i is the current year waterway mileage of the i-th level waterway, and k1 is the coefficient of change of carbon emission intensity per unit mileage determined between the forecast year and the current year.

[0110] In an embodiment of the present invention, exemplarily, after completing the calculation and collection of relevant data such as carbon emissions during the inland waterway construction period in XX Province in 2022 (current year), and obtaining the inland waterway mileage information in 2030 (forecast year), the server begins to calculate the carbon emissions during the construction period in the forecast year.

[0111] First, take the first-class waterway in XX Province in 2022 as an example. The server knows from the previous calculation results that the construction mileage L of a certain first-class waterway in that year i The carbon emissions during the construction period are E a It is 1551.6 tons.

[0112] According to the formula , the carbon emission intensity ES1 during the first-level waterway construction period can be calculated.

[0113] That is, ES1=1551.6 tons / 100km=15.516tCO2 / km.

[0114] In the same way, the server will calculate the carbon emission intensity for other levels of waterways (if they are under construction and the relevant data are complete). Here we will take the first-level waterway as an example to continue with the subsequent steps.

[0115] The server has clearly obtained the following parameter values: Current status of first-class waterway Annual waterway mileage WH i (i=1): From the current annual waterway information collected previously, it is known that it is 1200km.

[0116] Predicted annual waterway mileage of first-class waterway WF i (i=1): According to the trunk waterway network planning of XX Province (2030), its value is 1500km.

[0117] Coefficient of variation of carbon emission intensity per unit mileage k1: Through on-site investigation and analysis and evaluation of relevant technology development, energy efficiency improvement, etc., the value of k1 was determined to be 0.98 (this value is obtained from actual investigation and evaluation, not assumption).

[0118] According to the formula , calculation is performed for the first-level waterway.

[0119] Substituting the above determined parameter values ​​into the formula, we can get: EF a1 =ES1×(WF i —WH i )×k1=15.516tCO2 / km×(1500km-1200km)×0.98=15.516tCO2 / km×300km×0.98=4561.704 tons. This is the predicted annual carbon emissions of the first-class waterway in XX Province in 2030 during the construction period.

[0120] If there are other levels of waterways and they are under construction, the server will follow the same process to calculate the predicted annual construction period carbon emissions of each level of waterways, and finally summarize them to obtain the predicted annual construction period carbon emissions corresponding to the inland waterways in XX Province in 2030.

[0121] Through the above rigorous and detailed steps, the server accurately calculated the carbon emissions of the predicted year construction period of the river waterway based on the relevant data of the current year and the waterway information of the predicted year.

[0122] In an embodiment of the present invention, based on the current annual operating carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, the predicted annual operating carbon emissions corresponding to the predicted inland river waterway are calculated, which can be implemented through the following examples.

[0123] By formula: , calculate the predicted annual carbon emissions during the operation period, where EF b To predict the annual carbon emissions during operation, NF i,j To predict the number of ships using the jth fuel in the i-th class waterway operation period in a year, PF i,j is the average fuel consumption of each ship of the jth fuel in the i-th class waterway during the operation period in the predicted year, and k2 is the coefficient of change of the average annual fuel consumption determined between the predicted year and the current year.

[0124] In an embodiment of the present invention, exemplarily, before starting to calculate the carbon emissions of the inland waterway operation period in XX Province in 2030 (forecast year), the server has completed the calculation of the carbon emissions of the inland waterway operation period in XX Province in 2022 (current year) and the collection of inland waterway information in the current year and the forecast year.

[0125] In previous calculations, the server has clarified the relevant data on different fuels during the operation period of each level of waterways in 2022, such as the number of ships sailing in the first-level waterways, the average consumption of different fuels for each ship, and other information.

[0126] These data provide a basic reference for calculations in subsequent forecast years.

[0127] The server integrates and analyzes data from multiple channels, such as the traffic flow monitoring system and ship registration management system in XX Province, to obtain the number of ships sailing during the operation period of each level of waterways in 2030.

[0128] Taking the first-level waterway as an example, statistics show that in 2030, the number of fuel-powered ships on the first-level waterway will be 32,000, and the number of electric ships will be 1,200.

[0129] Similarly, the server also obtained the corresponding ship number information of the secondary and tertiary waterways in 2030 (the detailed data listing is omitted here, the principle is the same).

[0130] For different fuel types, the server determined the average fuel consumption of each ship during the operation period of each level of waterway in 2030 based on the ship operation plans reported by each shipping company, ship equipment upgrades, and field research visits.

[0131] Taking the first-class waterway as an example, assuming that for diesel fuel, the average diesel consumption of each fuel ship in 2030 is PF i,j (here j is diesel and i is first-class waterway) is 300 tons (obtained from actual survey, not assumed value); the electricity consumption for electric ships is 1 million kWh.

[0132] For new fuel types (if any), for example, assuming that methanol ships are put into operation in some waterways in 2030, the server has determined the average annual consumption of methanol ships of different tonnages through research on relevant pilot projects, technical parameters of new ships, etc. For example, the average annual consumption of 3,000-ton methanol ships is 200 tons (3,000-ton ships can be navigated in the first-level waterway).

[0133] The server determined the coefficient of change k2 of the average annual fuel consumption between the forecast year and the current year through in-depth analysis of shipping industry technology development reports, research related to ship energy efficiency improvement, and on-site inspections of ship operations.

[0134] After comprehensive evaluation, the value of k2 was determined to be 0.95 (obtained from actual survey and evaluation, not assumption).

[0135] Taking the first-class waterway as an example, according to the formula Perform calculations.

[0136] For diesel fuel: NF i,j (diesel, first class channel) = 32000, PF i,j (diesel, first class channel) = 300 tons, EM j(diesel) = 3.159tCO2 / t, k2 = 0.95. So the carbon emission is: 32000×300×3.159×0.95=28810080 tons.

[0137] For electric boats, electricity consumption: NF i,j (electricity, first-class channel) = 1200, PF i,j (Electricity, first-class waterway) = 1 million kWh, EM j (electricity) = 0.5366kgCO2 / kWh, k2 = 0.95. The carbon emission is: 1200×100×0.5366×10 4 ×10 -3 ×0.95=611724 tons.

[0138] If there are new fuel types (such as methanol), the calculation is also performed according to the above formula and corresponding parameters (the calculation example of methanol fuel is omitted here, the principle is the same).

[0139] Finally, the carbon emissions corresponding to each fuel type are added together to obtain the predicted annual carbon emissions EF of the first-level waterway during operation. b (First-class waterway).

[0140] Using the same method, the server will calculate the secondary and tertiary waterways separately, and finally summarize the predicted annual operating carbon emissions corresponding to the inland waterways in XX Province in 2030.

[0141] In an embodiment of the present invention, based on the current annual maintenance period carbon emissions, combined with the current annual river waterway information and the predicted annual river waterway information, the predicted annual maintenance period carbon emissions corresponding to the predicted annual river waterway are calculated, which can be implemented through the following examples.

[0142] By formula: , where EF c is the predicted annual carbon emissions during the maintenance period, WF is the predicted annual inland waterway mileage, WH is the current annual inland waterway mileage, and k3 is the coefficient of change of inland waterway maintenance fuel consumption determined between the predicted year and the current year.

[0143] In the embodiment of the present invention, for example, before calculating the carbon emissions during the maintenance period in the forecast year, the server has completed the carbon emissions during the maintenance period of the inland waterway in XX Province in 2022 (the current year) (E c ) and the collection of inland waterway mileage information for the current year (2022) and the forecast year (2030).

[0144] The server has determined from previously collected data that the inland waterway mileage WH of XX Province in 2022 is 2400km. This data is accurate information obtained by querying authoritative data sources such as the waterway management database of the transportation department.

[0145] According to the XX Province Trunk Waterway Network Plan (2023-2035), the server extracts the value of the inland waterway mileage WF of XX Province in 2030 as 3000km.

[0146] This planning document provides the basis for determining the predicted annual waterway mileage.

[0147] The server conducted a detailed analysis of the maintenance work records of the inland waterway maintenance departments of XX Province, the maintenance equipment upgrades, and related technical improvement measures over the years, combined with the actual changes in maintenance operations learned from field surveys and visits, and determined the coefficient of change k3 of inland waterway maintenance fuel consumption between the forecast year and the current year.

[0148] After rigorous evaluation, the value of k3 was determined to be 0.96 (this is the true value obtained from actual research and analysis).

[0149] The server has previously calculated the carbon emissions of all inland waterways in XX Province during the maintenance period in 2022. c .

[0150] For example, by querying the waterway maintenance work record database, it is known that the energy consumption involved in the maintenance work in 2022 is 2,400 tons of diesel, 300 tons of fuel oil, and 6 million kWh of electricity. According to the emission factors corresponding to each fuel (diesel emission factor, fuel oil emission factor, electricity emission factor), according to the formula Calculate E c The value is 11771.7 tons.

[0151] According to the formula: , the server substitutes the above-determined parameter values ​​into the formula for calculation.

[0152] Taking the case of XX province as an example, WH=2400km, WF=3000km, E c =11771.7 tons, k3=0.96 Substituting into the formula, we get: EF c =11771.7×(3000 / 2400)×0.96=11771.7×1.25×0.96=14126.04 tons.

[0153] This is the predicted annual maintenance period carbon emissions corresponding to the inland waterway in XX Province in 2030.

[0154] Through such a detailed calculation process based on actual data, the server accurately derives the predicted carbon emissions during the annual maintenance period, providing important data support for subsequent related work such as carbon emissions analysis over the entire life cycle of inland waterways.

[0155] In an embodiment of the present invention, based on the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area, an inland waterway mileage and carbon emission prediction model corresponding to the target area is constructed based on XGBoost, which can be implemented through the following examples.

[0156] Standardize the current inland river waterway information, the predicted inland river waterway information, the current inland river waterway life cycle carbon emissions, the predicted inland river waterway life cycle carbon emissions, the target area population data, and the GDP data; From the standardized data, feature data related to inland waterway mileage and carbon emissions are selected as input features; After dividing the input features into a training set and a test set, model training is performed based on XGBoost to obtain the inland waterway mileage and carbon emission prediction model corresponding to the target area, and the inland waterway mileage and carbon emission prediction curve graph corresponding to the demand time range is output based on the inland waterway mileage and carbon emission prediction model.

[0157] In an embodiment of the present invention, illustratively, after completing the information related to the current and predicted years of the inland waterways in XX Province and the calculation of the carbon emissions over the entire life cycle, the server begins to build a prediction model. First, the collected inland waterway information of XX Province in 2022 (current year), inland waterway information in 2030 (prediction year), the current inland waterway carbon emissions over the entire life cycle, the predicted inland waterway carbon emissions over the entire life cycle, and the population data and GDP data of XX Province are sorted out.

[0158] In order to make data of different magnitudes play a better role in subsequent model training, the server standardizes these data. For example, the mileage data of inland waterways may range from thousands of kilometers, while the carbon emissions data may range from a few tons to tens of thousands of tons. The population data and GDP data are even more different in magnitude.

[0159] Through standardization, these data are converted into standard distribution data with a mean of 0 and a standard deviation of 1 according to certain rules, so that each data feature is at the same scale, which is convenient for subsequent analysis and model training.

[0160] After standardization, the server selects characteristic data related to inland waterway mileage and carbon emissions from these data as input features. For example, the mileage changes of different levels of waterways in the current year and the predicted year (such as the current year mileage and predicted year mileage of first-level waterways), the changes in carbon emissions in each stage (construction period, operation period, maintenance period) in the current year and the predicted year are selected as key input features.

[0161] These characteristics can directly reflect the development status of inland waterways and the carbon emissions associated with them, and are crucial for building accurate prediction models.

[0162] The server divides the filtered input feature data into training sets and test sets according to a certain ratio.

[0163] Usually, about 70% of the data is used as a training set to train the model so that it can learn the patterns in the data; the remaining 30% of the data is used as a test set to verify the accuracy of the model after the model training is completed.

[0164] For example, assuming there are 1,000 valid data records after screening, 700 of them will be selected as the training set and 300 as the test set.

[0165] The server uses the XGBoost algorithm to perform model training on the divided training sets.

[0166] During the training process, the XGBoost algorithm will continuously adjust the model parameters (such as learning rate, tree depth, etc.) according to the relationship between the inland waterway mileage, carbon emissions, and related population, GDP and other factors in the input feature data, so that the model can achieve a better fitting effect on the training set.

[0167] The server will continuously monitor the training status of the model and determine whether the model has converged by observing the loss function value (such as mean square error) of the model on the training set.

[0168] When the loss function value reaches a relatively stable small value, it means that the model has learned the effective rules in the data and the training is basically completed.

[0169] After the model training is completed, the server outputs the corresponding inland waterway mileage and carbon emission prediction curve based on the trained inland waterway mileage and carbon emission prediction model and the input conditions given within the required time range (such as a specific year, a specific population growth trend, a GDP growth trend, etc.).

[0170] For example, if you want to understand the changing trends of inland waterway mileage and carbon emissions in XX Province in the next five years, the server will take the relevant time series data and the corresponding population, GDP and other forecast data as input, calculate through the model and output a curve chart showing the changes in inland waterway mileage and carbon emissions in XX Province in the next five years, providing intuitive data reference for the planning and management of inland waterways.

[0171] In order to more clearly express the solution provided by the embodiment of the present invention, a relatively complete implementation method is provided below.

[0172] 1. Determine the forecast year and forecast range and collect basic information.

[0173] Based on the target area (XX province), determine the prediction range.

[0174] Collect the current year (2022) inland waterway mileage WH (e.g. 2400km) and different levels of waterway mileage WH within the research scope i (For example: the first-class waterway is 1200km, the second-class waterway is 600km, and the third-class waterway is 600km). i is the waterway grade, and takes 1, 2, and 3, representing the first-class, second-class, and third-class waterways respectively.

[0175] Collect the river channel planning within the forecast range (for example: XX Province Trunk Channel Network Planning (2023-2035)), obtain the planning year (for example: 2030), channel mileage WF (for example: 3000km), and different levels of channel mileage WF i (For example: first-level waterway is 1,500 km, second-level waterway is 800 km, and third-level waterway is 700 km).

[0176] Among them, the planning year is the forecast year.

[0177] 2. Divide the entire life cycle of inland waterways into construction period, operation period and maintenance period, and calculate the carbon emissions of the existing inland waterway construction period, operation period and maintenance period respectively.

[0178] E=E a +E b +E c .

[0179] E a It is the carbon emission during the construction period of a certain waterway within the study scope in the current year.

[0180] E b It is the carbon emissions of all waterways in operation within the study scope in the current year.

[0181] E c It is the carbon emission during the maintenance period of all waterways within the study scope in the current year.

[0182] .

[0183] Where, j is the fuel type; Y aj is the consumption of the jth fuel during the current waterway construction period, in tons; EM j E is the emission factor of the jth fuel, in tons CO2 / ton. c The calculation method is similar.

[0184] .

[0185] Where, j is the fuel type; Y cj is the consumption of the jth type of fuel during the current annual channel maintenance period, in tons; EM j is the emission factor of the jth fuel, in tons CO2 / ton.

[0186] The carbon emission factors for diesel, gasoline, fuel oil and electricity are 3.159tCO2 / t, 2.985tCO2 / t, 3.235tCO2 / t and 0.5366kgCO2 / kWh respectively.

[0187] Example of construction period: In 2022, the construction mileage of a first-level waterway in XX Province is 100 km. The energy consumption process includes construction machinery, construction technology (such as blasting, dredging, etc.), construction personnel, etc., consuming a total of 200 tons of diesel, 20 tons of gasoline, 100 tons of fuel oil, and 1 million kWh of electricity. According to the above formula, its carbon emissions are E a =200×3.159+20×2.985+100×3.235+100×0.5366×10 4 ×10 -3 = 1551.6 tons. [No more examples for the second and third level waterways. If there is no second and third level waterway construction in the current year, the predicted part can be multiplied by the coefficient of variation].

[0188] Example of maintenance period: In 2022, all inland waterways in XX Province will be 2,400 km. The energy consumption process includes waterway inspection, navigation mark maintenance, waterway dredging, waterway facility maintenance, etc., consuming a total of 2,400 tons of diesel, 300 tons of fuel oil, and 6 million kWh of electricity.

[0189] According to the above formula, its carbon emission is E c =2400×3.159+300×3.235+600×0.5366×10 4 ×10 -3 =11771.7 tons.

[0190] .

[0191] Where i is the waterway grade, N i,jis the number of ships sailing on the i-th class channel during the j-th fuel operation period in the current year, P bi,bj It is the current annual average consumption of the jth type of fuel for each ship in the i-level waterway during the operation period.

[0192] Example during the operation period: In 2022, the number of ships sailing on the first-level waterways in Province XX will total 30,000, of which 29,000 are fuel-powered ships and 1,000 are electric ships. The average diesel consumption of each fuel-powered ship is 300 tons, and the electricity consumption of each electric ship is 1 million kWh.

[0193] In 2022, the number of ships sailing on the secondary waterways in XX Province totaled 6,000, including 4,000 fuel-powered ships and 2,000 electric ships. The average diesel consumption of each fuel-powered ship was 260 tons, and the electricity consumption of each electric ship was 800,000 kWh.

[0194] In 2022, the number of ships sailing on the third-level waterways in XX Province will total 5,000, including 3,000 fuel-powered ships and 2,000 electric ships. The average diesel consumption of each fuel-powered ship is 220 tons, and the electricity consumption of each electric ship is 600,000 kWh.

[0195] According to the above formula, its carbon emission is E b =(29000×300×3.159+1000×100×0.5366×10 4 ×10 -3 )+(4000×260×3.159+2000×80×0.5366×10 4 ×10 -3 )+(3000×220×3.159+2000×60×0.5366×10 4 ×10 -3 )=34892680 tons.

[0196] 3. Based on the current status of carbon emissions during the inland waterway construction period, calculate the predicted annual carbon emissions during the inland waterway construction period.

[0197] 1) Based on the calculation results of the construction period in step 2, calculate the carbon emission intensity of the current inland waterway construction period (unit: tCO2 / km).

[0198] .

[0199] Taking the first-class waterway as an example, ES1=1551.6 / 100=15.516tCO2 / km, L i The waterway mileage constructed in the current year of the i-th level waterway.

[0200] 2) Based on the current and predicted inland waterway mileage in step 1, calculate the predicted annual carbon emissions during the inland waterway construction period.

[0201] .

[0202] k1 is the coefficient of change of carbon emission intensity per mileage due to technological progress or energy efficiency improvement compared with the current year, which can be obtained through on-site or literature research; if not involved, it can be set to 1.

[0203] Taking the first-class waterway as an example, EF a1 =15.516×(1500-1200)×0.98=4561.704 tons.

[0204] 4. Based on the current carbon emissions during the inland waterway operation period, calculate the predicted annual carbon emissions during the inland waterway operation period.

[0205] NF i,j To predict the number of ships using the jth fuel in the i-th class waterway operation period in a year, PF i,j It is the predicted annual average fuel consumption of each ship for the jth type of fuel in the i-level waterway during the operation period.

[0206] k2 is the coefficient of change of the average annual fuel consumption reduced due to technological progress or energy efficiency improvement compared with the current year. It can be obtained through on-site or literature research. If not involved, it can be set to 1.

[0207] 1) Predicting NF i,j (The fuel types are the same as in the current year in step 2: diesel and electricity): Collect information on the study area population, GDP, freight volume, etc. for the current year and the forecast year, based on the N in step 2 i,j and WF from step 1 i , WH i , using the random forest regression algorithm to establish a prediction model and predict NF i,j .

[0208] 2) Compared with the fuel types in step 2, additional fuel types, such as methanol inland vessels may be put into operation in 2030.

[0209] Forecast year: Number of ships using new fuels within the study scope NF i,j , based on the predicted number of new fuel-intensive ships in the country in that year × (inland waterway mileage within the research scope / inland waterway mileage nationwide).

[0210] The predicted annual average consumption of new fuel Pi,j is the annual average consumption of new fuel ships of different tonnages, which can be obtained through on-site or literature research.

[0211] 5. Based on the current status of carbon emissions during the inland waterway maintenance period, calculate the predicted annual carbon emissions during the inland waterway maintenance period.

[0212] .

[0213] Note: Formula and EF a different.

[0214] k3 is the coefficient of change of fuel consumption for inland waterway maintenance due to technological progress or energy efficiency improvement compared with the current year, which can be obtained through on-site or literature research; if not involved, it can be set to 1.

[0215] 6. Based on the prediction results of steps 3, 4, and 5, calculate and predict the carbon emissions of the river waterway over its entire life cycle.

[0216] EF=EF a +EF b +EF c .

[0217] 7. Taking the inland waterway mileage, carbon emission data, population, GDP and other information in the current year and the predicted year as input, an inland waterway mileage and carbon emission prediction model is established based on the decision tree ensemble learning algorithm XGBoost. The inland waterway mileage data under a certain carbon emission level in a long time series can be inferred, providing data reference for the formulation of inland waterway development plans within the scope of future research.

[0218] Please refer to Figure 2 , Figure 2 An inland waterway carbon emission prediction device 110 provided in an embodiment of the present invention includes: The acquisition module 1101 is used to obtain the current annual river waterway information of the target area in the current year and the predicted annual river waterway information in the predicted year; respectively calculate the carbon emissions of the current annual river waterway in the whole life cycle, including the carbon emissions of the current annual construction period, the current annual operation period and the current annual maintenance period; according to the carbon emissions of the current annual construction period, the current annual operation period and the current annual maintenance period, in combination with the current annual river waterway information and the predicted annual river waterway information, calculate the predicted annual construction period carbon emissions, predicted annual operation period carbon emissions and predicted annual maintenance period carbon emissions corresponding to the predicted annual river waterway; according to the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions, determine the predicted annual annual river waterway carbon emissions in the whole life cycle; The prediction module 1102 is used to construct an inland waterway mileage and carbon emission prediction model corresponding to the target area based on XGBoost according to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area.

[0219] It should be noted that the implementation principle of the aforementioned inland waterway carbon emission prediction device 110 can refer to the implementation principle of the aforementioned inland waterway carbon emission prediction method, which will not be repeated here. It should be understood that the division of the various modules of the above device is only a division of logical functions, and in actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated.

[0220] And these modules can all be implemented in the form of software calling through processing elements; or all be implemented in the form of hardware; or some modules can be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware.

[0221] For example, the inland waterway carbon emission prediction device 110 can be a separately established processing element, or it can be integrated in one of the chips of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and called and executed by one of the processing elements of the above-mentioned device. The functions of the above-mentioned inland waterway carbon emission prediction device 110.

[0222] The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.

[0223] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more microprocessors (digital signal processors, DSPs), or, one or more field programmable gate arrays (FPGAs), etc.

[0224] For another example, when a certain module above is implemented in the form of a processing element scheduling a program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program codes.

[0225] For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0226] An embodiment of the present invention provides a computer device 100, which includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device 100 executes the aforementioned inland waterway carbon emission prediction device 110.

[0227] like Figure 3 As shown, Figure 3 A structural block diagram of a computer device 100 provided in an embodiment of the present invention.

[0228] The computer device 100 includes an inland waterway carbon emission prediction device 110 , a memory 111 , a processor 112 and a communication unit 113 .

[0229] To achieve data transmission or interaction, the memory 111 , the processor 112 , and the communication unit 113 are electrically connected to each other directly or indirectly.

[0230] For example, these components may be electrically connected to each other via one or more communication buses or signal lines.

[0231] The inland waterway carbon emission prediction device 110 includes at least one software function module that can be stored in the memory 111 in the form of software or firmware or fixed in the operating system (OS) of the computer device 100 .

[0232] The processor 112 is used to execute the inland waterway carbon emission prediction device 110 stored in the memory 111, such as the software function modules and computer programs included in the inland waterway carbon emission prediction device 110.

[0233] An embodiment of the present invention provides a readable storage medium, which includes a computer program. When the computer program is running, it controls the computer device where the readable storage medium is located to execute the aforementioned inland waterway carbon emission prediction device 110.

[0234] For purposes of illustration, the foregoing description has been made with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed.

[0235] Numerous modifications and variations are possible in light of the above teaching.

[0236] The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical application, to thereby enable others skilled in the art to best utilize the disclosure and utilize various embodiments with various modifications as are suited to the particular use contemplated.

Claims

1. A method for predicting carbon emissions from inland waterways, characterized in that: include: Obtain the current inland waterway information of the target area in the current year and the predicted inland waterway information in the predicted year; The carbon emissions of the current annual river waterway in the entire life cycle are calculated separately, including the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions; According to the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions corresponding to the predicted inland river waterway are calculated; Determine the predicted annual carbon emissions for the entire life cycle of the inland waterway based on the predicted annual carbon emissions during the construction period, the predicted annual carbon emissions during the operation period, and the predicted annual carbon emissions during the maintenance period; According to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area, a prediction model of inland waterway mileage and carbon emissions corresponding to the target area is constructed based on XGBoost.

2. The method according to claim 1, characterized in that The obtaining of the current inland waterway information of the target area in the current year and the predicted inland waterway information in the predicted year includes: Acquire the current inland river waterway mileage of the target area and at least two different levels of waterway mileages included in the current inland river waterway mileage; Obtaining the predicted inland river waterway mileage of the target area and at least two different levels of waterway mileages included in the predicted inland river waterway mileage; The current intra-river waterway mileage, the at least two different levels of waterway mileages included in the current intra-river waterway mileage, the predicted intra-river waterway mileage, and the at least two different levels of waterway mileages included in the predicted intra-river waterway mileage are correspondingly used as the current intra-river waterway information of the target area in the current year and the predicted intra-river waterway information in the predicted year.

3. The method according to claim 2, characterized in that The carbon emissions of the current annual river waterway during the entire life cycle are calculated separately, including the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions, including: By formula: , calculate the current annual construction period carbon emissions, where E a is the current annual carbon emission during the construction period, j is the fuel type; Y aj is the consumption of the jth fuel during the current waterway construction period; EM j is the emission factor of the jth fuel; By formula: , calculate the carbon emissions of the current annual operation period, where E b is the current annual carbon emissions during operation, i is the waterway grade, N i,j is the number of ships sailing on the i-th class channel during the j-th fuel operation period in the current year, P bi,bj The current annual average consumption of the jth type of fuel for each ship in the i-level waterway during the operation period; By formula: , calculate the carbon emissions of the current situation during the annual maintenance period, where E c is the carbon emission during the current maintenance period, Y cj is the consumption of the jth type of fuel during the current annual waterway maintenance period.

4. The method according to claim 3, characterized in that: According to the current annual construction period carbon emissions, combined with the current annual river waterway information and the predicted annual river waterway information, the predicted annual construction period carbon emissions corresponding to the predicted annual river waterway are calculated, including: By formula: , calculate the carbon emissions during the construction period of the forecast year, where EF a To predict the annual carbon emissions during the construction period, ES i =E a / L i , E.S. i is the carbon emission intensity during the current intra-annual river channel construction period, L i is the waterway mileage of the i-th level waterway in the current year, WF i The annual waterway mileage predicted for the i-th level waterway, WH i is the current year waterway mileage of the i-th level waterway, and k1 is the coefficient of change of carbon emission intensity per unit mileage determined between the forecast year and the current year.

5. The method according to claim 3, characterized in that: According to the current annual operation period carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, the predicted annual operation period carbon emissions corresponding to the predicted inland river waterway are calculated, including: By formula: , calculate the predicted annual carbon emissions during the operation period, where EF b To predict the annual carbon emissions during operation, NF i,j To predict the number of ships using the jth fuel in the i-th class waterway operation period in a year, PF i,j is the average fuel consumption of each ship of the jth type of fuel in the i-th class waterway during the operation period in the predicted year, and k2 is the coefficient of change of the average annual fuel consumption determined between the predicted year and the current year.

6. The method according to claim 3, characterized in that According to the current annual maintenance period carbon emissions, combined with the current inland river waterway information and the predicted inland river waterway information, the predicted annual maintenance period carbon emissions corresponding to the predicted inland river waterway are calculated, including: By formula: , where EF c is the predicted annual carbon emissions during the maintenance period, WF is the predicted annual inland waterway mileage, WH is the current annual inland waterway mileage, and k3 is the coefficient of change of inland waterway maintenance fuel consumption determined between the predicted year and the current year.

7. The method according to claim 1, characterized in that According to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over the entire life cycle, the predicted inland waterway carbon emissions over the entire life cycle, and the population data and GDP data of the target area, a prediction model of inland waterway mileage and carbon emissions corresponding to the target area is constructed based on XGBoost, including: Standardize the current inland river waterway information, the predicted inland river waterway information, the current inland river waterway life cycle carbon emissions, the predicted inland river waterway life cycle carbon emissions, the target area population data, and the GDP data; From the standardized data, feature data related to inland waterway mileage and carbon emissions are selected as input features; After dividing the input features into a training set and a test set, model training is performed based on XGBoost to obtain the inland waterway mileage and carbon emission prediction model corresponding to the target area, and the inland waterway mileage and carbon emission prediction curve graph corresponding to the demand time range is output based on the inland waterway mileage and carbon emission prediction model.

8. An inland waterway carbon emission prediction device, characterized in that: include: An acquisition module is used to obtain the current river waterway information of the target area in the current year and the predicted river waterway information in the predicted year; Calculate the carbon emissions of the current annual construction period, the current annual operation period and the current annual maintenance period respectively; calculate the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions corresponding to the predicted annual waterway according to the current annual construction period carbon emissions, the current annual operation period carbon emissions and the current annual maintenance period carbon emissions, combined with the current annual waterway information and the predicted annual waterway information; determine the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions according to the predicted annual construction period carbon emissions, the predicted annual operation period carbon emissions and the predicted annual maintenance period carbon emissions; The prediction module is used to construct an inland waterway mileage and carbon emission prediction model corresponding to the target area based on XGBoost according to the current inland waterway information, the predicted inland waterway information, the current inland waterway carbon emissions over its entire life cycle, the predicted inland waterway carbon emissions over its entire life cycle, and the population data and GDP data of the target area.

9. A computer device, characterized in that: The computer device comprises a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device executes the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium includes a computer program, and when the computer program is executed, the computer device where the readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images