Risk prediction method, device and equipment for drainage basin nitrogen loss and medium

Abstract

The invention discloses a risk prediction method, device and equipment for drainage basin nitrogen loss and a medium, and belongs to the field of drainage basin nitrogen loss risk prediction.The method comprises the steps that multi-source driving data and land type raster data of a drainage basin are obtained; configuring an improved Noah-MP-CN model based on land type raster data, and simulating drainage basin nitrogen loss by using the model and multi-source driving data to obtain nitrogen loss amount spatial and temporal distribution data; and carrying out risk early warning analysis according to the data, and generating a visual prediction result containing an annual scale background risk level, an extreme event peak risk and high-risk area information. Therefore, by implementing the method, the problem of low risk prediction accuracy of drainage basin nitrogen loss in the prior art can be solved.

Description

Technical Field

[0001] This invention relates to the field of watershed nitrogen loss risk prediction, and in particular to a method, apparatus, equipment and medium for predicting watershed nitrogen loss risk. Background Technology

[0002] In the risk prediction of nitrogen loss in watersheds, nitrogen loss is affected by multiple factors such as meteorological conditions, soil characteristics, land use type and nitrogen input. The prediction process involves complex coupling of biogeochemical cycles and hydrological processes, with strong spatiotemporal heterogeneity, making risk early warning difficult.

[0003] In existing technologies, risk assessment often employs single-driving-factor models or static empirical threshold methods. However, these methods fail to fully integrate multi-source dynamic data, do not consider the impact of different land types on key nitrogen cycle processes such as biological nitrogen fixation and denitrification, and do not achieve high-resolution simulation of the spatiotemporal dynamics of nitrogen loss or effective identification of extreme events. Consequently, they suffer from limited prediction accuracy, difficulty in accurately reflecting the spatiotemporal distribution characteristics of nitrogen loss within the watershed, and thus cannot provide reliable prediction results for watershed nitrogen loss risks. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for predicting the risk of nitrogen loss in watersheds, which can solve the problem of low accuracy in the risk prediction of nitrogen loss in watersheds in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a risk prediction method for watershed nitrogen loss, including: Acquire multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data; The nitrogen loss in the watershed was simulated based on the multi-source driving data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model was obtained by configuring the initial Noah-MP-CN model based on the land type raster data; Risk warning analysis is performed based on the spatiotemporal distribution data of nitrogen loss to obtain risk information, and risk visualization prediction results are generated based on the risk information; wherein, the risk information includes annual background risk level information, extreme event peak risk information, and high-risk area information.

[0006] This application provides a comprehensive and realistic foundation for watershed nitrogen loss simulation by acquiring multi-source driving data covering meteorology, soil, nitrogen input, and land type raster data. The improved Noah-MP-CN model, optimized based on land type raster data, significantly enhances the accuracy and adaptability of the spatiotemporal distribution data of nitrogen loss. Based on this spatiotemporal distribution data, multi-dimensional risk warning analysis is conducted to comprehensively capture key information such as annual-scale background risk levels, peak risks of extreme events, and high-risk areas. The risk prediction results are presented in a visual format, making various risk characteristics more intuitive and understandable, and achieving comprehensive and multi-dimensional precise control over watershed nitrogen loss risks.

[0007] As a preferred example of the first aspect, the simulation of nitrogen loss in the watershed based on the multi-source driven data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed includes: The meteorological driving data, soil data, and nitrogen input data from the multi-source driving data are used to generate a standardized driving dataset readable by the improved Noah-MP-CN model through a preset standardized data preparation script; The standardized driving dataset is input into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed, resulting in several spatiotemporal four-dimensional data of nitrogen loss with longitude, latitude, soil depth and time as spatiotemporal coordinates. These data are then combined to form the spatiotemporal distribution data of nitrogen loss.

[0008] In this preferred example, the meteorological driving data, soil data, and nitrogen input data are standardized by using a pre-set standardized data preparation script. This standardizes the data format and ensures the compatibility of the generated driving dataset with the improved Noah-MP-CN model. Then, the standardized driving dataset is input into the improved model to simulate watershed nitrogen loss. By leveraging the model's optimization advantages for watershed characteristics and combining the four-dimensional spatiotemporal coordinates composed of longitude, latitude, soil depth, and time, the distribution characteristics of nitrogen loss at different spatial locations, soil depths, and time dimensions can be captured. The resulting spatiotemporal distribution data of nitrogen loss is both complete and accurate.

[0009] As a preferred example of the first aspect, the standardized driving dataset is in the NetCDF file format.

[0010] As a preferred example of the first aspect, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data, including: Based on the land type raster data and the preset parameter lookup table, the biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each raster in the watershed are obtained. The biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each grid in the watershed are input into the configuration file of the initial Noah-MP-CN model to obtain the improved Noah-MP-CN model.

[0011] In this preferred example, the biological nitrogen fixation scaling factor and denitrification soil water factor threshold corresponding to each grid are accurately matched according to the land type raster data and the preset parameter lookup table. This allows the model parameters to fully fit the ecological characteristics and nitrogen cycle patterns of different land types in the watershed, avoiding the problem of insufficient adaptability caused by the use of uniform parameters in the initial model. These targeted parameters are integrated into the configuration file of the initial Noah-MP-CN model to form an improved model, which effectively improves the model's adaptability and accuracy in simulating key nitrogen loss processes under different land types.

[0012] As a preferred example of the first aspect, if the risk information is annual-scale background risk level information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the least squares method was used to perform linear regression fitting to establish regression equations for total annual precipitation and total annual nitrogen loss. Substitute the forecast values ​​corresponding to each day in the annual precipitation forecast of the basin into the regression equation to obtain the level information corresponding to each day, and combine the level information corresponding to each day to form the annual-scale background risk level information.

[0013] In this preferred example, based on the spatiotemporal distribution data of nitrogen loss, the least squares method is used to perform linear regression fitting to establish a regression equation between annual total precipitation and annual total nitrogen loss. This scientifically quantifies the correlation between precipitation and watershed nitrogen loss, accurately characterizing their relationship and ensuring the statistical reliability of the risk assessment model. Substituting the forecast values ​​of each day in the annual precipitation forecast of the watershed into this regression equation to obtain the corresponding level information and form annual-scale background risk level information, enables forward-looking risk prediction based on precipitation forecasts. This refines the time dimension of annual-scale risk assessment, making the presentation of annual-scale background risk more systematic and complete.

[0014] As a preferred example of the first aspect, if the risk information is high-risk area information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the nitrogen loss variation value of each spatial grid in the watershed is calculated, and high-risk area information is generated based on the nitrogen loss variation value of each spatial grid and the land type raster data.

[0015] In this preferred example, the nitrogen loss change value of each spatial grid is calculated based on the spatiotemporal distribution data of nitrogen loss, which can accurately capture the spatial dynamic differences of nitrogen loss and avoid omissions of details in macro analysis; combined with land type raster data to generate high-risk area information, the identification of high-risk areas is more in line with the actual situation and more targeted.

[0016] As a preferred example of the first aspect, generating a risk visualization prediction result based on the risk information includes: Temporal risk information is generated based on the annual-scale background risk level information and the extreme event peak risk information, and spatial risk information is generated based on the high-risk area information; The risk visualization prediction result is generated through a preset visualization interface based on the time risk information and the spatial risk information.

[0017] In this preferred example, by integrating annual-scale background risk levels and extreme event peak risk information to generate temporal risk information, it can comprehensively cover the characteristics of both routine background risks and sudden peak risks of nitrogen loss in the watershed over time, avoiding the limitations of single-time-dimensional analysis. Based on high-risk area information, spatial risk information is generated, clearly defining the spatial distribution pattern of risks and clarifying regional differences. A pre-set visualization interface transforms temporal and spatial risk information into visualized risk prediction results, converting abstract risk data into an intuitive and easy-to-understand presentation, facilitating relevant personnel to quickly grasp the comprehensive spatiotemporal risk situation of nitrogen loss in the watershed.

[0018] Secondly, the present invention provides a risk prediction device for watershed nitrogen loss, comprising: a data acquisition module, a simulation module, and a risk prediction module; The data acquisition module is used to acquire multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data; The simulation module is used to simulate nitrogen loss in the watershed based on the multi-source driving data and the improved Noah-MP-CN model, and obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data; The risk prediction module is used to perform risk warning analysis based on the spatiotemporal distribution data of nitrogen loss, obtain risk information, and generate risk visualization prediction results based on the risk information; wherein, the risk information includes annual-scale background risk level information, extreme event peak risk information, and high-risk area information.

[0019] As a preferred example of the second aspect, the simulation of nitrogen loss in the watershed based on the multi-source driving data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed includes: The meteorological driving data, soil data, and nitrogen input data from the multi-source driving data are used to generate a standardized driving dataset readable by the improved Noah-MP-CN model through a preset standardized data preparation script; The standardized driving dataset is input into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed, resulting in several spatiotemporal four-dimensional data of nitrogen loss with longitude, latitude, soil depth and time as spatiotemporal coordinates. These data are then combined to form the spatiotemporal distribution data of nitrogen loss.

[0020] As a preferred example of the second aspect, the standardized driving dataset is in the NetCDF file format.

[0021] As a preferred example of the second aspect, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data, including: Based on the land type raster data and the preset parameter lookup table, the biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each raster in the watershed are obtained. The biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each grid in the watershed are input into the configuration file of the initial Noah-MP-CN model to obtain the improved Noah-MP-CN model.

[0022] As a preferred example of the second aspect, if the risk information is annual-scale background risk level information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the least squares method was used to perform linear regression fitting to establish regression equations for total annual precipitation and total annual nitrogen loss. Substitute the forecast values ​​corresponding to each day in the annual precipitation forecast of the basin into the regression equation to obtain the level information corresponding to each day, and combine the level information corresponding to each day to form the annual-scale background risk level information.

[0023] As a preferred example of the second aspect, if the risk information is high-risk area information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the nitrogen loss variation value of each spatial grid in the watershed is calculated, and high-risk area information is generated based on the nitrogen loss variation value of each spatial grid and the land type raster data.

[0024] As a preferred example of the second aspect, generating a risk visualization prediction result based on the risk information includes: Temporal risk information is generated based on the annual-scale background risk level information and the extreme event peak risk information, and spatial risk information is generated based on the high-risk area information; The risk visualization prediction result is generated through a preset visualization interface based on the time risk information and the spatial risk information.

[0025] In summary, this application's embodiments provide comprehensive and realistic data support for watershed nitrogen loss simulation by acquiring multi-source driving data covering meteorology, soil, nitrogen input, and land type raster data. The improved Noah-MP-CN model, optimized based on land type raster data, significantly enhances the accuracy and adaptability of the spatiotemporal distribution data of nitrogen loss. Based on this spatiotemporal distribution data, multi-dimensional risk warning analysis is conducted, comprehensively capturing key information such as annual-scale background risk levels, peak risks of extreme events, and high-risk areas. The risk prediction results are presented in a visual format, making various risk characteristics more intuitive and understandable, and achieving comprehensive and multi-dimensional precise control over watershed nitrogen loss risks.

[0026] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the steps of the risk prediction method for watershed nitrogen loss of the present invention.

[0027] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the risk prediction method for watershed nitrogen loss of the present invention. Attached Figure Description

[0028] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating an embodiment of a risk prediction method for watershed nitrogen loss provided by the present invention; Figure 2 A flowchart illustrating an embodiment of a risk prediction method for watershed nitrogen loss provided by the present invention; Figure 3 This is a module structure diagram of one embodiment of a risk prediction device for nitrogen loss in watersheds provided by the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0032] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0033] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0034] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0035] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0036] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0037] Example 1 See Figure 1 To address the problem of low accuracy in predicting nitrogen loss risks in existing technologies, an embodiment of the present invention provides a method for predicting nitrogen loss risks in watersheds, comprising: S1. Obtain multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data.

[0038] For example, the weather driving data can be directly downloaded from the official data product of GLDAS Noah version 3.3. This data has been optimized for the Noah-MP model and can be used as a baseline weather driving force.

[0039] For example, the soil data may be obtained from the raw raster and attribute data of the Harmonized World Soil Database (HWSD) or a national soil dataset.

[0040] For example, the nitrogen input data can be obtained from the Global Nitrogen Fertilizer Application Dataset (GCNFD) and the output of the atmospheric nitrogen deposition model on an annual scale.

[0041] S2. Based on the multi-source driving data and the improved Noah-MP-CN model, the nitrogen loss in the watershed is simulated to obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data.

[0042] It should be noted that the Noah-MP-CN model is an open-source, multi-process coupled mechanistic model developed from the Noah-MP land surface process model by introducing a carbon and nitrogen biogeochemical cycle module. The original Noah-MP model focused on simulating energy, water, and carbon fluxes, providing parameterization schemes for various physical processes through a multi-hypothesis framework. However, its initial version lacked a complete simulation of nitrogen dynamics, only approximating the limitation of nitrogen on plant growth through a constant nitrogen stress factor in the maximum carboxylation rate parameter related to photosynthesis. This clearly failed to reflect the complex nitrogen cycle in nature and its interactions with carbon and water processes. The Noah-MP-CN model was developed precisely to address this deficiency. By integrating a relatively complete nitrogen cycle sub-model, it dynamically couples key processes such as plant nitrogen uptake, soil nitrogen transformation and transport with the model's original photosynthesis, carbon allocation, and hydrological processes, thereby achieving a more accurate simulation of the coupled water-carbon-nitrogen cycle in ecosystems.

[0043] As a preferred embodiment, step S2, simulating nitrogen loss in the watershed based on the multi-source driven data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed, includes: The meteorological driving data, soil data, and nitrogen input data from the multi-source driving data are used to generate a standardized driving dataset readable by the improved Noah-MP-CN model through a preset standardized data preparation script; The standardized driving dataset is input into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed, resulting in several spatiotemporal four-dimensional data of nitrogen loss with longitude, latitude, soil depth and time as spatiotemporal coordinates. These data are then combined to form the spatiotemporal distribution data of nitrogen loss.

[0044] Specifically, the step of generating a standardized driving dataset readable by the improved Noah-MP-CN model from the meteorological driving data, soil data, and nitrogen input data in the multi-source driving data using a preset standardized data preparation script can be implemented in the following preferred manner: Write a unified Python script that uses the xarray, pandas, and netCDF4 libraries to perform the following operations: ① Basic mesh creation: Create a standard space xarray.Dataset based on the target simulation area and resolution.

[0045] ② Meteorological data embedding: Key variables such as precipitation (PRCP) and temperature (T2M) in meteorological data are resampled to the base grid through bilinear interpolation and directly written into the Dataset.

[0046] ③ Soil Data Calculation and Embedding: Parameters such as sand, clay, and organic carbon content are extracted from HWSD data. The script calculates all soil hydraulic parameters required by the Noah-MP model using the algorithm specified in the script. The original attributes and calculated parameters are then aggregated according to the soil layers defined in the model, using a thickness-weighted average in the vertical direction, and finally written into a Dataset.

[0047] ④ Spatiotemporal distribution and embedding of nitrogen input data: Annual-scale nitrogen fertilizer and deposition data are downscaled to monthly or daily data required by the model using a custom time-series assignment function in the script. The spatiotemporally distributed nitrogen input data is then written as a new variable into the Dataset.

[0048] ⑤ Output a unified file (i.e., a standardized driving dataset): Finally, the script generates a NetCDF file containing meteorological, soil, and nitrogen input driving data. The meteorological data is named YYYYMMddtt.LDASIN_DOMAIN1 according to time, the soil data is named Soil_CONUS-regrid.nc, and the nitrogen input data is NANI_US_input-ESMF_conserve.nc.

[0049] Specifically, the process of inputting the standardized driving dataset into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed can be described as follows: The improved Noah-MP-CN model source code and its dependencies were packaged into a Docker image. Then, tasks were submitted using the Slurm job scheduling system on a high-performance computing cluster. The task scripts specified the use of multiple computing nodes. Internally, the model decomposed the entire watershed into multiple subdomains for synchronous computation via the MPI parallel interface, significantly improving the efficiency of large-scale simulations. The model ultimately outputs a NetCDF file containing a spatiotemporal four-dimensional data array (longitude, latitude, soil depth, and time) of nitrogen loss.

[0050] In some preferred embodiments, the standardized driving dataset is in NetCDF file format.

[0051] In a preferred embodiment, step S2, the improved Noah-MP-CN model, is obtained by configuring the initial Noah-MP-CN model based on the land type raster data, including: Based on the land type raster data and the preset parameter lookup table, the biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each raster in the watershed are obtained. The biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each grid in the watershed are input into the configuration file of the initial Noah-MP-CN model to obtain the improved Noah-MP-CN model.

[0052] For example, a preset parameter lookup table may be as follows: Table 1 Preset Parameter Lookup Table Where s represents the biological nitrogen fixation scaling factor, This represents the soil water factor threshold for denitrification, and LULC_Type represents the land type.

[0053] S3. Perform risk warning analysis based on the spatiotemporal distribution data of nitrogen loss to obtain risk information, and generate risk visualization prediction results based on the risk information; wherein, the risk information includes annual-scale background risk level information, extreme event peak risk information, and high-risk area information.

[0054] As a preferred implementation, step S3, if the risk information is annual-scale background risk level information, then the risk warning analysis is performed based on the spatiotemporal distribution data of nitrogen loss, including: Based on the spatiotemporal distribution data of nitrogen loss, the least squares method was used to perform linear regression fitting to establish regression equations for total annual precipitation and total annual nitrogen loss. Substitute the forecast values ​​corresponding to each day in the annual precipitation forecast of the basin into the regression equation to obtain the level information corresponding to each day, and combine the level information corresponding to each day to form the annual-scale background risk level information.

[0055] Specifically, if the risk information is annual-scale background risk level information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss can be implemented through the following preferred methods: Based on multi-year simulation results, with total annual precipitation as the independent variable and total annual nitrogen loss as the dependent variable, a linear regression was performed using the least squares method to obtain the regression equation and coefficient of determination. According to the annual precipitation forecasts issued by the meteorological department, the forecast values ​​were substituted into the regression equation to calculate the predicted losses, which were then classified into three levels of background risk: low, medium, and high, based on their magnitude.

[0056] As a preferred implementation, step S3, if the risk information is high-risk area information, then the risk warning analysis is performed based on the spatiotemporal distribution data of nitrogen loss, including: Based on the spatiotemporal distribution data of nitrogen loss, the nitrogen loss variation value of each spatial grid in the watershed is calculated, and high-risk area information is generated based on the nitrogen loss variation value of each spatial grid and the land type raster data.

[0057] Specifically, if the risk information is high-risk area information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss can be implemented through the following preferred methods: Typical simulation results from wet and dry years were selected, and the difference in nitrogen loss was calculated grid by grid. The difference raster layer was then overlaid with a land use classification map for analysis. Natural breakpoints were classified based on the numerical distribution of the differences and rendered with different colors to generate a spatial sensitivity map. Areas with high differences were identified as high-risk zones.

[0058] As a preferred implementation, step S3, generating a risk visualization prediction result based on the risk information, includes: Temporal risk information is generated based on the annual-scale background risk level information and the extreme event peak risk information, and spatial risk information is generated based on the high-risk area information; The risk visualization prediction result is generated through a preset visualization interface based on the time risk information and the spatial risk information.

[0059] Specifically, to fully explain the above process, such as Figure 2 As shown, the entire process begins with the improved model, configuring dynamic parameters such as the biological nitrogen fixation scaling factor and the soil water factor threshold for denitrification. Next, the model simulation phase begins: meteorological, land use, and agricultural data are collected, processed into driving data that the model can read, and the model is run to output results. These results are then transmitted to the data analysis module, where annual budget analysis, extreme event risk identification, spatial sensitivity analysis, and the quantitative relationships between data points are analyzed, relevant thresholds and increments are calculated, and risk identification and classification are completed. Finally, the reporting and early warning phase generates a comprehensive early warning report and pushes corresponding fertilization recommendations to users in the target area based on this information.

[0060] In summary, this application's embodiments provide comprehensive and realistic data support for watershed nitrogen loss simulation by acquiring multi-source driving data covering meteorology, soil, nitrogen input, and land type raster data. The improved Noah-MP-CN model, optimized based on land type raster data, significantly enhances the accuracy and adaptability of the spatiotemporal distribution data of nitrogen loss. Based on this spatiotemporal distribution data, multi-dimensional risk warning analysis is conducted, comprehensively capturing key information such as annual-scale background risk levels, peak risks of extreme events, and high-risk areas. The risk prediction results are presented in a visual format, making various risk characteristics more intuitive and understandable, and achieving comprehensive and multi-dimensional precise control over watershed nitrogen loss risks.

[0061] Example 2 like Figure 3 As shown, based on the above method embodiments, corresponding device embodiments are provided; One embodiment of the present invention provides a risk prediction device for nitrogen loss in watersheds, including: a data acquisition module 31, a simulation module 32 and a risk prediction module 33; The data acquisition module 31 is used to acquire multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data; The simulation module 32 is used to simulate nitrogen loss in the watershed based on the multi-source driving data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data; The risk prediction module 33 is used to perform risk warning analysis based on the spatiotemporal distribution data of nitrogen loss, obtain risk information, and generate risk visualization prediction results based on the risk information; wherein, the risk information includes annual background risk level information, extreme event peak risk information, and high-risk area information.

[0062] As a preferred embodiment, the step of simulating nitrogen loss in the watershed based on the multi-source driven data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed includes: The meteorological driving data, soil data, and nitrogen input data from the multi-source driving data are used to generate a standardized driving dataset readable by the improved Noah-MP-CN model through a preset standardized data preparation script; The standardized driving dataset is input into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed, resulting in several spatiotemporal four-dimensional data of nitrogen loss with longitude, latitude, soil depth and time as spatiotemporal coordinates. These data are then combined to form the spatiotemporal distribution data of nitrogen loss.

[0063] In a preferred embodiment, the standardized driving dataset is in NetCDF file format.

[0064] In a preferred embodiment, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data, including: Based on the land type raster data and the preset parameter lookup table, the biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each raster in the watershed are obtained. The biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each grid in the watershed are input into the configuration file of the initial Noah-MP-CN model to obtain the improved Noah-MP-CN model.

[0065] As a preferred implementation, if the risk information is annual-scale background risk level information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the least squares method was used to perform linear regression fitting to establish regression equations for total annual precipitation and total annual nitrogen loss. Substitute the forecast values ​​corresponding to each day in the annual precipitation forecast of the basin into the regression equation to obtain the level information corresponding to each day, and combine the level information corresponding to each day to form the annual-scale background risk level information.

[0066] As a preferred implementation, if the risk information is high-risk area information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the nitrogen loss variation value of each spatial grid in the watershed is calculated, and high-risk area information is generated based on the nitrogen loss variation value of each spatial grid and the land type raster data.

[0067] As a preferred embodiment, generating a risk visualization prediction result based on the risk information includes: Temporal risk information is generated based on the annual-scale background risk level information and the extreme event peak risk information, and spatial risk information is generated based on the high-risk area information; The risk visualization prediction result is generated through a preset visualization interface based on the time risk information and the spatial risk information.

[0068] For more detailed steps and working principles of this embodiment, please refer to the relevant description in Embodiment 1, but not limited to these descriptions.

[0069] In summary, this application's embodiments provide comprehensive and realistic data support for watershed nitrogen loss simulation by acquiring multi-source driving data covering meteorology, soil, nitrogen input, and land type raster data. The improved Noah-MP-CN model, optimized based on land type raster data, significantly enhances the accuracy and adaptability of the spatiotemporal distribution data of nitrogen loss. Based on this spatiotemporal distribution data, multi-dimensional risk warning analysis is conducted, comprehensively capturing key information such as annual-scale background risk levels, peak risks of extreme events, and high-risk areas. The risk prediction results are presented in a visual format, making various risk characteristics more intuitive and understandable, and achieving comprehensive and multi-dimensional precise control over watershed nitrogen loss risks.

[0070] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the risk prediction method for watershed nitrogen loss provided by any of the above-described method embodiments of the present invention.

[0071] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0072] Based on the above embodiments of the risk prediction method for watershed nitrogen loss, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the risk prediction method for watershed nitrogen loss of any embodiment of the present invention.

[0073] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0074] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0075] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0076] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the risk prediction method for watershed nitrogen loss described in any of the above-described method embodiments of the present invention.

[0077] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0078] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A risk prediction method for watershed nitrogen loss, characterized in that, include: Acquire multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data; The nitrogen loss in the watershed was simulated based on the multi-source driving data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model was obtained by configuring the initial Noah-MP-CN model based on the land type raster data; Risk warning analysis is performed based on the spatiotemporal distribution data of nitrogen loss to obtain risk information, and risk visualization prediction results are generated based on the risk information; wherein, the risk information includes annual background risk level information, extreme event peak risk information, and high-risk area information.

2. The risk prediction method for watershed nitrogen loss as described in claim 1, characterized in that, The process of simulating nitrogen loss in the watershed based on the multi-source driving data and the improved Noah-MP-CN model to obtain the spatiotemporal distribution data of nitrogen loss in the watershed includes: The meteorological driving data, soil data, and nitrogen input data from the multi-source driving data are used to generate a standardized driving dataset readable by the improved Noah-MP-CN model through a preset standardized data preparation script; The standardized driving dataset is input into the improved Noah-MP-CN model to simulate nitrogen loss in the watershed, resulting in several spatiotemporal four-dimensional data of nitrogen loss with longitude, latitude, soil depth and time as spatiotemporal coordinates. These data are then combined to form the spatiotemporal distribution data of nitrogen loss.

3. The risk prediction method for watershed nitrogen loss as described in claim 2, characterized in that, The standardized driving dataset is in NetCDF file format.

4. The risk prediction method for watershed nitrogen loss as described in claim 1, characterized in that, The improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data, including: Based on the land type raster data and the preset parameter lookup table, the biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each raster in the watershed are obtained. The biological nitrogen fixation scaling factor and the denitrification soil water factor threshold corresponding to each grid in the watershed are input into the configuration file of the initial Noah-MP-CN model to obtain the improved Noah-MP-CN model.

5. The risk prediction method for watershed nitrogen loss as described in claim 1, characterized in that, If the risk information is annual-scale background risk level information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the least squares method was used to perform linear regression fitting to establish regression equations for total annual precipitation and total annual nitrogen loss. Substitute the forecast values ​​corresponding to each day in the annual precipitation forecast of the basin into the regression equation to obtain the level information corresponding to each day, and combine the level information corresponding to each day to form the annual-scale background risk level information.

6. The risk prediction method for watershed nitrogen loss as described in claim 1, characterized in that, If the risk information is high-risk area information, then the risk warning analysis based on the spatiotemporal distribution data of nitrogen loss includes: Based on the spatiotemporal distribution data of nitrogen loss, the nitrogen loss variation value of each spatial grid in the watershed is calculated, and high-risk area information is generated based on the nitrogen loss variation value of each spatial grid and the land type raster data.

7. A risk prediction method for watershed nitrogen loss as described in any one of claims 1-6, characterized in that, The step of generating a risk visualization prediction result based on the risk information includes: Temporal risk information is generated based on the annual-scale background risk level information and the extreme event peak risk information, and spatial risk information is generated based on the high-risk area information; The risk visualization prediction result is generated through a preset visualization interface based on the time risk information and the spatial risk information.

8. A risk prediction device for watershed nitrogen loss, characterized in that, include: Data acquisition module, simulation module, and risk prediction module; The data acquisition module is used to acquire multi-source driving data and land type raster data of the watershed; wherein, the multi-source driving data includes meteorological driving data, soil data and nitrogen input data; The simulation module is used to simulate nitrogen loss in the watershed based on the multi-source driving data and the improved Noah-MP-CN model, and obtain the spatiotemporal distribution data of nitrogen loss in the watershed; wherein, the improved Noah-MP-CN model is obtained by configuring the initial Noah-MP-CN model based on the land type raster data; The risk prediction module is used to perform risk warning analysis based on the spatiotemporal distribution data of nitrogen loss, obtain risk information, and generate risk visualization prediction results based on the risk information; wherein, the risk information includes annual-scale background risk level information, extreme event peak risk information, and high-risk area information.

9. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein, when the processor executes the computer program, it implements the risk prediction method for watershed nitrogen loss as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, the device containing the computer-readable storage medium is controlled to perform the risk prediction method for watershed nitrogen loss as described in any one of claims 1-7.

Images