Water and soil loss prediction evaluation method and system, storage medium and electronic equipment

Abstract

The invention provides a water and soil loss prediction evaluation method and system, a storage medium and electronic equipment. The method comprises the following steps: constructing a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process; constructing a data set containing low-resolution DEM data and DOM data and high-resolution DEM data and DOM data, and constructing a water and soil loss prediction model based on the data set; and performing water and soil loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the water and soil loss prediction model. According to the method, high-resolution data and conventional-resolution data can be compatible for water and soil loss prediction and evaluation, water and soil loss prediction and water and soil conservation effect evaluation work are refined in space, and the overall evaluation efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban pipe network management, and in particular to the technical field of soil and water loss prediction and evaluation methods, systems, storage media and electronic equipment. Background Art

[0002] From large-scale pumped storage, water conservancy and hydropower, wind power and photovoltaic projects to small-scale plant construction, urban road construction, river widening and new construction, in order to protect the local ecological environment and control the hazards of soil and water loss, it is necessary to carry out corresponding soil and water conservation design, construction and monitoring in accordance with the law. Large-scale projects are often located in mountainous areas with complex geographical environments and rugged terrain, with high risks of soil and water loss and greater harm; small-scale projects are small in scope, with high requirements for data accuracy and fine review requirements. In general, scientific soil and water conservation design and monitoring are extremely important for protecting the regional ecological environment and construction production safety. At present, soil and water conservation work for regional soil and water loss prediction and assessment is mostly highly empirical non-indicator judgment or requires a lot of data, and the calculation process is complicated. Some existing soil and water loss dynamic monitoring and assessment systems only focus on the main river basin scale, ignoring the development and application of soil and water loss prediction and assessment systems at the engineering scale. The "Guidelines for Calculating Soil Loss in Production and Construction Projects" covers the entire country and has high applicability and recognition. However, the application process in projects is cumbersome. Pre-processing of data, selection of indicators and calculations require repeated reference to the guidelines. In addition, due to the feasibility of manual calculations, projects are often divided into only a few calculation areas for calculation. Therefore, the spatial resolution of the prediction results is often at the hectare level, and it is difficult to improve the overall performance.

[0003] As conventional satellite images can no longer meet the accuracy requirements at the engineering scale, there is an urgent need for a technical solution that drives soil and water loss prediction and assessment through high-resolution data. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the object of the present invention is to provide a soil and water loss prediction and assessment method, system, storage medium and electronic device for soil and water loss prediction and assessment compatible with high-resolution and conventional resolution data.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a method for predicting and evaluating soil and water loss, comprising: constructing a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process; constructing a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and constructing a soil and water loss prediction model based on the data set; and performing soil and water loss prediction and evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model.

[0006] In one embodiment of the present application, it also includes: extracting soil and water loss factors at different resolutions; fitting the project scale and optimal resolution recommendation curve based on the sensitivity of the soil and water loss factors to the resolution of surface data, so as to provide an optimization basis for the data resolution of various projects in the later stage.

[0007] In one embodiment of the present application, the soil and water loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model includes: obtaining the segmented prediction results based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model; performing any one or more combination operations of statistics, cluster analysis, and grade classification on the segmented prediction results to obtain the soil and water loss prediction evaluation results.

[0008] In one embodiment of the present application, the statistical, cluster analysis, and any one or more combined operations of the segmented prediction results include: soil and water loss grade zoning operations, soil and water loss risk area identification operations, statistical operations on the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period, and soil and water operations in the acceptance stage.

[0009] In one embodiment of the present application, the soil and water loss prediction assessment results include soil and water prediction assessment results, soil and water monitoring assessment results, and soil and water conservation acceptance assessment results; wherein, the soil and water monitoring assessment results include soil and water loss background value calculation assessment results and soil and water loss monitoring assessment results.

[0010] In one embodiment of the present application, the soil and water loss prediction and assessment results are output in the form of images and statistical tables.

[0011] In one embodiment of the present application, the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model use Fortran and Python programming for data processing when performing soil and water loss prediction and evaluation, and use Java language to construct an interactive interface for prediction and evaluation.

[0012] To achieve the above-mentioned purpose and other related purposes, the present application also provides a soil erosion prediction and evaluation system, including: a digital programming module, which constructs a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process; a model construction module, which is used to construct a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and construct a soil erosion prediction model based on the data set; a prediction and evaluation module, which performs soil erosion prediction and evaluation based on the prediction process processing module, the digital prediction parameter database and the soil erosion prediction model.

[0013] To achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer storage medium storing program instructions, which, when executed, implement the steps of the soil and water loss prediction and assessment method as described above.

[0014] To achieve the above-mentioned purpose and other related purposes, the present invention also provides an electronic device, including a memory for storing a computer program; and a processor for running the computer program to implement the steps of the soil and water loss prediction and assessment method as described above.

[0015] As described above, the soil and water loss prediction and assessment method, system, storage medium and electronic device of the present invention have the following beneficial effects:

[0016] This application is compatible with high-resolution and conventional resolution data for soil and water loss prediction and assessment, achieving spatial refinement of soil and water loss prediction and program deployment effect assessment, and can effectively improve the overall assessment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 Shown is a schematic diagram of the overall process of a method for predicting and evaluating soil and water loss in one embodiment of the present application;

[0019] Figure 2 Shown is a flow chart of determining the optimal resolution in a method for predicting and evaluating soil and water loss in one embodiment of the present application;

[0020] Figure 3 Shown is a flow chart of obtaining soil and water loss prediction and assessment results in the process operation guide of the soil and water loss prediction and assessment method in one embodiment of the present application;

[0021] Figure 4 Shown is an example diagram of the soil and water acceptance assessment results in the soil and water loss prediction and assessment method in one embodiment of the present application;

[0022] Figure 5 Shown is an example diagram of the implementation process of the soil and water loss prediction and evaluation method in one embodiment of the present application;

[0023] Figure 6 Shown is a principle block diagram of a soil and water loss prediction and evaluation system in one embodiment of the present application;

[0024] Figure 7It is a principle block diagram of an electronic device in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the implementation of this embodiment through specific examples, and those skilled in the art can easily understand other advantages and effects of this embodiment from the content disclosed in this specification. This embodiment can also be implemented or applied through other different specific implementations, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of this embodiment. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] The main models that can be used to simulate soil and water loss processes at home and abroad include SWAT, USLE, WEPP, InVEST, CSLE, etc.

[0027] (1) SWAT (Soil and Water Assessment Tool) was developed by the Agricultural Research Center of the United States Department of Agriculture (USDA). The original purpose of the model development was to predict the long-term impact of land management on water, sediment and chemicals under the complex and changing soil types, land use patterns and management measures in large watersheds. The overall structure of the model is semi-distributed, and the sediment production module uses an improved soil loss equation.

[0028] (2) USLE (Universal Soil Loss Equation) is an empirical soil loss prediction equation established in the United States based on experimental observation data combined with statistical analysis and generalization of soil erosion influencing factors to quantitatively predict the annual average soil loss on cultivated land or grassland slopes.

[0029] (3) WEEP (Watershed Erosion Prediction Project) is supported by the U.S. Forest Service (Center), the National Soil Erosion Research Laboratory of the USDA Agricultural Research Service, and many universities. It is used and evaluated by the USDA Natural Resources Conservation Service, the USDA Forest Service, the USDA Bureau of Land Management, and other agencies involved in soil and water conservation and environmental planning. The model is applied to small watersheds and hillsides. It can predict soil loss and sediment deposition caused by surface flow on hillsides, soil loss and sediment deposition caused by concentrated flow in small rivers, and sediment in reservoirs.

[0030] (4) InVEST (Integrated Valuation of Ecosystem Services and Trade-offs) was jointly developed by Stanford University, The Nature Conservancy (TNC) and the World Wildlife Fund (WWF) in the United States. It aims to provide a scientific basis for decision makers to weigh the benefits and impacts of human activities by simulating the changes in the quantity and value of ecosystem service systems under different land cover scenarios. The InVEST model, a model system for ecosystem service function evaluation, fills the gap in this field and realizes the spatialization of quantitative evaluation of ecosystem service function value.

[0031] (5) CSLE (Chinese soil loss equation) The Chinese soil loss equation is a soil erosion model that was first used in my country in the 1950s to quantitatively study soil erosion. After the introduction of the United States Universal Soil Loss Equation (USLE) in the 1980s, Professor Liu Baoyuan used the USLE model as a blueprint, referred to the observation data of the runoff plot, and modified the USLE model according to the actual situation of the region, and established a soil erosion prediction model with regional characteristics. It was used in the first national water conservancy census, the soil and water conservation census, and the fourth national soil erosion census.

[0032] It can be seen that understanding the regional soil and water loss situation, spatial differentiation laws and its internal driving factors through model simulation results is of great significance for ecological early warning and soil erosion control.

[0033] The software engineering application of soil and water loss prediction models in my country started late and has a weak foundation. It is still in the exploratory experimental stage. The design consulting system of domestic design institutes is based on a complete design system and standard guidelines, and has the characteristics of being too professional and weak in professional cross-disciplinary. At present, there is no such high-precision soil and water loss prediction and assessment software based on domestic industry standards on the market.

[0034] With the development of "digitalization", it is urgently necessary to promote the development and application of digital software for soil and water loss prediction and assessment based on high-resolution DEM and DOM data in China.

[0035] This embodiment provides a soil and water loss prediction and assessment method, system, storage medium and electronic device for predicting and assessing soil and water loss using compatible high-resolution and conventional resolution data.

[0036] The soil and water loss prediction and assessment method, system, storage medium and electronic device of the embodiment of the present application are based on digital software for soil and water loss prediction and assessment based on high-resolution DEM and DOM data, which improves the original hectare-level prediction accuracy to the highest DEM resolution of 0.1m and DOM 0.02m level processing, and is compatible with the prediction of low-precision data. It can realize multi-scale soil and water loss prediction and assessment of various production and construction projects and is universal.

[0037] The principles and implementation methods of the soil and water loss prediction and evaluation method, system, storage medium and electronic device of this embodiment will be explained in detail below, so that those skilled in the art can understand the soil and water loss prediction and evaluation method, system, storage medium and electronic device of this embodiment without creative work.

[0038] This embodiment provides a method for predicting and evaluating soil erosion. Specifically, Figure 1 As shown, the soil and water loss prediction and assessment method described in this embodiment includes:

[0039] Step S100, constructing a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process;

[0040] Step S200, constructing a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and constructing a soil and water loss prediction model based on the data set;

[0041] Step S300: performing soil and water loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model.

[0042] The above steps S100 to S300 in the soil and water loss prediction and assessment method of this embodiment are described in detail below.

[0043] Step S100: constructing a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process.

[0044] In this embodiment, the preset prediction process used is based on the water conservancy industry standard "Guidelines for Soil Loss Calculation of Production and Construction Projects" (SL 773-2018). The preset prediction process is a method for predicting soil loss in construction projects by dividing soil loss types, specifying soil loss calculation processes and application scopes. According to the guidelines, in this embodiment, the soil loss prediction of production and construction projects is classified into three levels: the first-level classification is based on the dominant factors of erosion external forces in the project area (hydraulic erosion, wind erosion), the second-level classification is based on the engineering disturbance form of the underlying surface in the project area (generally disturbed surface, engineering excavation surface, engineering accumulation body), and the third-level classification is based on the degree of disturbance in the project area, whether there is water coming from above, etc. The first-level and second-level classifications of hydraulic erosion and wind erosion are applicable, and there is no third-level classification for wind erosion. The prediction results are very important for efficient soil loss prediction of production and construction projects, accurate description of key areas of soil and water loss and key periods of soil and water loss, and targeted adoption of corresponding soil and water loss prevention measures.

[0045] Based on the preset prediction process, the corresponding digital prediction process processing module and digital prediction parameter database are constructed to ensure the validity of the core prediction results of the model and provide a solid basis for evaluation.

[0046] In this embodiment, the prediction parameters and processes are carried out in accordance with the standard process to ensure the industry recognition of the prediction results. It is the first in the industry to modularize the prediction process and digitize the national prediction parameter database. This makes the method highly versatile, covering all types of production and construction projects of all sizes, improving the accuracy of prediction and evaluation, significantly reducing the time of internal work, and can solve the blank areas of industry software.

[0047] In this embodiment, a corresponding digital prediction process processing module is constructed based on the preset prediction process, that is, programming is performed based on the preset prediction process, and the prediction process is processed into a digital electronic process. The software module formed by programming is the digital prediction process processing module.

[0048] This embodiment also constructs a digital national prediction parameter database based on a preset prediction process. The digital national prediction parameter database is a system that integrates various prediction models, algorithms and parameters.

[0049] Among them, the digital national prediction parameter database stores basic area tables (including administrative area codes, names and other fields), evaluation configuration tables, evaluation batch information tables (including projects, evaluation configurations, batch evaluation titles, batch evaluation status (0 failed, 1 in progress, 2 successful), batch evaluation total value (yuan), operator ID, operator name, initiation time, end time, algorithm, status (1 normal, 0 deleted), top (1 top, 0 normal) and other fields), evaluation batch algorithm information tables (including evaluation batches, algorithm codes, algorithm evaluation status (0 failed, 1 in progress, 2 successful) algorithm evaluation progress 0-100 and other fields), evaluation ID tables, evaluation tables, dictionary tables, evaluation parameter configuration tables, news carousel tables, log tables, project tables, project file tables, project parameter tables and project personnel tables, etc.

[0050] Step S200, constructing a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and constructing a soil and water loss prediction model based on the data set.

[0051] Combined with the popularization of UAV tilt measurement and airborne LiDAR measurement in recent years, the accuracy and acquisition efficiency of high-resolution terrain and surface basic data have been significantly improved, and the surface process simulation research driven by high-resolution data has gradually increased. The use of high-resolution geographic data for soil and water loss prediction has also become a scientific basis for recent policy management, regional planning, and disaster prevention.

[0052] DEM data refers to Digital Elevation Model, while DOM data stands for Digital Orthophoto Map. DEM data and DOM data each have their own role and importance in the field of spatial information. DEM is mainly used to express the elevation information of the terrain, while DOM is used to provide remote sensing image maps that have been geometrically corrected.

[0053] While providing general precision data calculation, this embodiment also provides high-resolution DEM and DOM data to lead the construction of a soil and water loss prediction model, upgrading the original hectare-level calculation unit to the highest DEM resolution of 0.1m and DOM 0.02m-level processing, thereby achieving spatial refinement of soil and water loss prediction and program deployment effect evaluation work, and solving the difficulty of industry prediction accuracy.

[0054] In this embodiment, high-resolution DEM and DOM data are used to construct a soil erosion prediction model, so as to achieve refinement of soil erosion prediction and scheme deployment effect evaluation work that is not limited to the engineering scale.

[0055] In this embodiment, high-resolution DEM data simulates the terrain surface morphology by recording an ordered numerical array of ground elevations. High-resolution DEM data is used to generate contour lines, slope maps, and stereoscopic perspective maps, so that the soil and water loss prediction model can more accurately evaluate the impact of terrain on soil and water loss. At the same time, high-resolution DEM can also optimize the input parameters of the soil and water loss prediction model by extracting surface morphology information, thereby improving the accuracy and reliability of the model.

[0056] High-resolution DOM data eliminates terrain errors by providing geometrically corrected remote sensing image maps, making the image data visually consistent with the real world. High-resolution DOM data not only has the geometric accuracy of maps, but also retains image features, which is very helpful for accurately depicting surface cover and land use changes. Since DOM data can directly reflect the actual surface conditions, combined with multi-source spatial data, it can provide detailed underlying surface condition information for soil and water loss prediction models, such as vegetation coverage, land use type, etc., which is crucial for the parameter setting of the prediction model.

[0057] In addition, the integration of high-resolution DEM and DOM data can improve the overall performance of the soil erosion prediction model by improving the quality of input data. For example, the method of using convolutional neural network to reconstruct DEM super-resolution can further improve the resolution of DEM data, thereby enhancing the model's ability to capture terrain details. It can not only maintain terrain structure and texture details at different scales, but also make the reconstruction results closer to the actual terrain conditions, which is particularly important for soil erosion prediction under complex terrain conditions.

[0058] This embodiment is compatible with conventional resolution and high-resolution data. Since the high-resolution data grid volume is large, directly reading it completely puts a lot of pressure on the computer memory. Subsequently, an automatic framing processing algorithm can be used to process the block-by-block simulation operation, while creating conditions for future software upgrades and retaining interfaces in parallel.

[0059] The data set of the construction of the soil and water loss prediction model includes not only low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, but also data such as weather, topography, and land use. These data are processed and analyzed by mathematical models, and finally form a model that can predict soil and water loss. The present embodiment adopts soil and water loss prediction models including but not limited to AUSLE, WEPP and RUSLE, wherein the RUSLE model is considered to be one of the most commonly used and effective models due to its effectiveness and wide application.

[0060] In addition, in some embodiments, the data processing in the soil and water loss prediction model can adopt the parallel processing method of the Spark framework, and the parallel processing method based on the Spark framework can improve the computational efficiency of the model.

[0061] Figure 2 Shown is a flow chart for determining the optimal resolution in a method for predicting and evaluating soil and water loss in one embodiment of the present application; Figure 2 As shown, in one implementation of this embodiment, it also includes:

[0062] Step S110, extracting soil and water loss factors at different resolutions;

[0063] Step S120, fitting the project scale and optimal resolution recommendation curve based on the sensitivity of the soil and water loss factor to the surface data resolution, to provide an optimization basis for the data resolution of various projects in the later stage.

[0064] Extracting relevant soil and water loss factors at different resolutions, such as rainfall erosivity, soil erodibility, topographic factors, vegetation cover factors, and soil and water conservation measures factors, is crucial for building an accurate soil and water loss prediction model. These factors together determine the type, intensity, and rate of soil and water loss.

[0065] Among them, rainfall erosivity is the main natural factor leading to soil erosion. It indicates the potential ability of rainfall to erode soil and is related to factors such as rainfall amount, rainfall intensity and rainfall duration. This factor can be obtained by analyzing rainfall data of different periods. Soil erodibility characterizes the ease with which soil is eroded by water and is closely related to the texture, structure, permeability and organic matter content of the soil. Through soil surveys and laboratory analysis, erodibility information of different soil types can be obtained. Topographic factors include slope length, slope, slope direction, etc., which affect the speed and direction of water flow, thereby affecting the erosion process. Using high-resolution DEM data, topographic factors can be accurately extracted. Vegetation coverage factor: Vegetation can effectively slow down the speed of water flow and reduce soil erosion. By processing high-resolution DOM data, vegetation coverage information can be obtained. Soil and water conservation measures factor: It includes various artificial measures to prevent soil erosion, such as terraces, reservoirs, afforestation, etc. This information can be obtained through field surveys.

[0066] Different factors affecting soil erosion have different sensitivities to the resolution of surface data. Topographic factors and vegetation cover factors are particularly sensitive to resolution, while soil erodibility and soil and water conservation measures are relatively less sensitive. By applying high-resolution DEM and DOM data, the measurement and analysis accuracy of sensitive factors can be significantly improved, thereby improving the overall performance and reliability of soil erosion prediction models.

[0067] Specifically, in this embodiment, the soil and water loss factors at different resolutions are automatically resampled and extracted, the sensitivity of the soil and water loss factors to the resolution of the surface data is analyzed, and a preliminary fit is made to the recommended curve of project scale and optimal resolution, so as to provide an optimization basis for the data resolution of various types of projects in the later stage. When this embodiment is applied to the project, the most suitable resolution can be adopted as a whole, and the resolution can be improved in a small range in the analysis and diagnosis of areas with high predicted loss volume for targeted evaluation.

[0068] Step S300: performing soil and water loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model.

[0069] In this embodiment, soil and water loss prediction and evaluation are combined with software engineering to realize data processing, soil and water loss prediction operation and post-evaluation automation. After the software is completed, the soil and water loss prediction process is standardized and automated, which greatly shortens the early data processing, later data sorting, pattern drawing, effect analysis, table statistics and other work. The development of this embodiment focuses on the current blank and difficult digitization areas in the soil and water conservation industry, and develops high-resolution data soil and water loss prediction and evaluation software based on industry standard documents that is not limited to engineering scales. Standardizing and optimizing the professional processes of prediction and evaluation greatly shortens the internal work time of designers.

[0070] Figure 3 It is a flowchart showing the process operation guide for obtaining the soil and water loss prediction and evaluation results in the soil and water loss prediction and evaluation method in one embodiment of the present application; Figure 3 As shown, in one implementation of this embodiment, the soil and water loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model includes:

[0071] Step S310, obtaining a segment prediction result based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model;

[0072] Step S320, performing any one or more combination operations of statistics, cluster analysis, and level classification on the segment prediction results to obtain soil and water loss prediction and evaluation results.

[0073] In the application of soil and water loss prediction models, statistics, cluster analysis and classification of the prediction results are important steps to further process and analyze the model output. These methods help to understand the distribution characteristics of soil and water loss from a macro level, identify key loss areas, and provide a scientific basis for formulating corresponding control measures.

[0074] Among them, the result statistics first need to perform basic statistical analysis on the prediction results, including calculating statistical indicators such as mean value, median, standard deviation, coefficient of variation, etc. These statistical indicators can reflect the overall level and variation of soil and water loss, and help understand the severity and distribution of soil and water loss in different regions. Through cluster analysis, a large number of prediction results can be grouped according to their similarities, so as to identify areas with similar soil and water loss characteristics. The clustering method adopted in this embodiment includes but is not limited to K-means (K-means), hierarchical clustering, etc. These methods can help discover potential soil and water loss patterns, reveal the effects of soil and water conservation measures in different regions and the impact of environmental factors on soil and water loss. This embodiment also divides the study area into different soil and water loss levels according to the severity of the prediction results. For example, it can be divided into four levels of slight, medium, severe and extremely severe according to the size of soil and water loss. This level division helps the government and relevant departments to give priority to and control areas with severe soil and water loss, reasonably allocate resources, and take targeted protection and control measures.

[0075] In one implementation of this embodiment, the statistical, cluster analysis, and any one or more combined operations of the segmented prediction results include: soil and water loss grade zoning operations, soil and water loss risk area identification operations, statistical operations on the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period, and soil and water operations in the acceptance stage.

[0076] In some embodiments, the soil and water loss level zoning operation includes:

[0077] 1) First, relevant geographic and environmental data need to be collected, such as DEM (digital elevation model), rainfall data, soil type, land use, etc. These data are preprocessed, such as format conversion, coordinate matching, clipping, etc., to meet the analysis requirements.

[0078] 2) Calculate soil and water loss factors: Based on the general soil and water loss equation, calculate various influencing factors, including rainfall erosivity, soil erodibility, terrain factors, vegetation cover factors and soil and water conservation measures factors. The calculation of these factors requires specific formulas or models, such as USLE and RUSLE models.

[0079] 3) Generate a soil erosion map: Based on the factors calculated above, the soil erosion prediction model is used to calculate the soil erosion in each area, and the result will generate a map showing different soil erosion amounts.

[0080] 4) Perform grading: Based on the generated soil erosion map, the soil erosion is divided into different levels according to certain standards or thresholds. Common grading includes mild, moderate, severe and very severe. This process can be completed by using the "reclassification" tool in GIS.

[0081] 5) Verification and adjustment: Finally, the generated soil erosion grade zoning is verified and adjusted on the spot to ensure the accuracy and practicality of the zoning results. This may require comparative analysis of ground measured data or historical data.

[0082] Through the above steps, an area can be effectively divided into zones according to the severity of soil erosion.

[0083] In some embodiments, the soil and water loss risk area identification operation includes:

[0084] 1) Data preparation: First, it is necessary to collect relevant geographic and environmental data including DEM (digital elevation model), soil type, land use data, rainfall data, etc. These data provide the basis for analyzing soil erosion risks.

[0085] 2) Calculate influencing factors: Based on soil erosion equations, such as USLE (Universal Soil Loss Equation) or RUSLE (Revised Universal Soil Loss Equation), calculate various factors that affect soil erosion, such as rainfall erosivity, soil erodibility, terrain slope, vegetation cover and land management measures.

[0086] 3) Apply the model for risk assessment: Using the collected data and calculated factors, apply the soil erosion prediction model to estimate the amount of soil erosion or risk value in different areas. This step is usually completed in Geographic Information System (GIS) software, which can generate a spatial distribution map showing different risk levels.

[0087] 4) Risk area identification: Based on the soil and water loss risk values ​​output by the model, the areas are divided into different risk levels, such as low risk, medium risk, high risk and very high risk. This classification can be done based on specific thresholds or standards, which can be set based on historical data, expert opinions or policy requirements.

[0088] 5) Result verification and adjustment: Field verification is carried out on the identified risk areas to check the accuracy and practicality of the model. If necessary, the model can be adjusted based on field observations and other supplementary data to improve its prediction accuracy and applicability.

[0089] The identified soil and water loss risk areas can be used to guide land use planning, optimize agricultural management measures, strengthen vegetation restoration and soil and water conservation projects, etc. These measures are aimed at reducing soil erosion and protecting and improving environmental quality.

[0090] Through these steps, the soil erosion risk area identification algorithm provides important information and tools for governments, environmental protection agencies and land managers to help them manage and protect land resources more effectively and achieve sustainable development goals.

[0091] In some embodiments, the statistical calculation of the spatiotemporal variation of the amount of soil and water loss of the project during the monitoring period includes:

[0092] The statistical calculation of the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period is a calculation process used to analyze and evaluate the impact of a specific project on soil and water loss in time and space. The following are the steps to perform this statistical calculation:

[0093] 1) Data collection: First, collect DEM (digital elevation model), rainfall records, soil type, land use / cover and other data during the monitoring period, which are the basis for assessing soil erosion.

[0094] 2) Calculate the factors affecting soil erosion: Use models such as USLE (Universal Soil Loss Equation) or RUSLE (Revised Universal Soil Loss Equation) to calculate the factors affecting soil erosion at each time point, including rainfall erosivity, soil erodibility, topographic factors, vegetation cover factors and land management measures.

[0095] 3) Spatiotemporal analysis: Apply GIS (Geographic Information System) and remote sensing technology, combined with time series analysis, to assess the amount of soil and water loss at different time points and in different regions. This involves analyzing the changes in various influencing factors at different time points and their impact on the amount of soil and water loss.

[0096] 4) Statistical analysis: Conduct statistical analysis on the calculated soil and water loss to identify trends and patterns in the soil and water loss during the monitoring period, including descriptive statistics (such as mean, median), trend analysis, variability analysis, etc.

[0097] 5) Spatial autocorrelation analysis: Use spatial statistical methods, such as spatial autocorrelation analysis, to evaluate the spatial distribution and aggregation characteristics of soil erosion. This helps identify "hotspots" of soil erosion, that is, areas where soil erosion is particularly severe. Based on the above analysis, explain the temporal and spatial trends of soil erosion and identify possible causes (such as climate change, land use changes, implementation of management measures, etc.). Based on the analysis results, put forward corresponding land management suggestions or adjust the project implementation plan to reduce future soil erosion.

[0098] Through these steps, statistical calculations of the temporal and spatial changes in the amount of soil and water loss in the project during the monitoring period can provide important information to help decision makers and environmental managers understand and respond to soil and water loss problems and achieve optimal results in project management and environmental protection.

[0099] In some embodiments, the soil and water calculation in the acceptance stage includes: using appropriate models and methods, such as USLE (Universal Soil Loss Equation) or RUSLE (Revised Universal Soil Loss Equation), based on the collected data, recalculating the amount of soil and water loss in the project area, comparing the amount of soil and water loss before and after implementation, and evaluating the effectiveness of the project. Performing statistical analysis on the amount of soil and water loss before and after implementation, including descriptive statistics, comparative analysis, etc. Analyzing the impact of project implementation on the amount of soil and water loss, identifying the reduction, and evaluating whether the expected goals of the project have been achieved.

[0100] In one implementation of this embodiment, the soil and water loss prediction assessment results include soil and water loss prediction assessment results, soil and water loss monitoring assessment results, and soil and water conservation acceptance assessment results; wherein, the soil and water loss monitoring assessment results include soil and water loss background value calculation assessment results and soil and water loss monitoring assessment results.

[0101] That is to say, in this embodiment, the prediction results of the individual plots are obtained in the early stage, and then the prediction results are statistically analyzed, clustered, and graded to achieve automatic zoning of soil and water loss levels, identification of key soil and water loss risk areas in each prevention and control zone of the project, statistics on the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period, and automatic calculation of the six major indicators of soil and water conservation in the acceptance stage. Evaluation functions such as automatic zoning of soil and water loss levels, identification of key soil and water loss risk areas in each prevention and control zone of the project, statistics on the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period, and automatic calculation of the six major indicators of soil and water conservation in the acceptance stage are realized.

[0102] In one implementation of this embodiment, the soil erosion prediction assessment results are output in the form of images and statistical tables. The assessment results will be presented and output in the form of images and statistical tables, which greatly shortens the time for subsequent drawing, data statistics and tabulation. Figure 4 Shown is an example diagram of the water and soil acceptance assessment results in the water and soil loss prediction and assessment method in one embodiment of the present application; Figure 4 As shown,

[0103] Figure 5 The diagram shows an example of the implementation process of the soil and water loss prediction and evaluation method in one embodiment of the present application. Figure 5 As shown, the method of this embodiment combines three major branches, namely, high-resolution data acquisition and processing, soil and water loss prediction and evaluation index system, and soil and water loss prevention and control measures and system, in its specific implementation and application, with framework design, software design, and software testing as the main lines to guide the orderly progress of the project.

[0104] The method of this embodiment includes: based on the "Guidelines for Calculating Soil Loss in Production and Construction Projects" (SL 773-2018), it is the first in the industry to modularize the prediction process to realize various process functions, and digitize the national prediction parameter database; evaluate and count the prediction results of the plots, perform statistics of the prediction results of the plots, cluster analysis, grade division and other operations, realize automatic zoning of soil and water loss levels, identification of key soil and water loss risk areas in each prevention and control zone of the project, statistics on the spatiotemporal changes of soil and water loss in the project during the monitoring period, and automatic calculation of the six major indicators of soil and water conservation in the acceptance stage; present and output the prediction results in the form of images and statistical tables, and other operations.

[0105] Among them, in one implementation of this embodiment, the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model use Fortran and Python programming for data processing when performing soil and water loss prediction and evaluation, and use Java language to build an interactive interface for prediction and evaluation.

[0106] Since this method involves mostly matrix-intensive operations, the core code is programmed in Fortran to ensure the operation speed, and Python is used for automated operations such as data processing. The subsequent library packaging integrates this part of the function to increase the convenience of software environment configuration. Java is used for software visualization to reduce the difficulty of software promotion. The interface is designed in a step-by-step guided manner according to standardized prediction and evaluation steps to reduce erroneous operations, and an authorization code module is added, with one machine and one code to prevent software outflow.

[0107] The software modules programmed by the method of this embodiment are compiled into a library, and the interface reservation is improved to prepare for the subsequent server deployment and access to the integrated environmental and water conservation platform.

[0108] The method of this embodiment can not only be used for the whole process consulting services of soil and water conservation plan, monitoring, acceptance and supervision of general development and construction projects, but also can provide leading design and consulting results closely around the soil and water conservation and desertification control topics of large-scale projects such as new energy and pumped storage, scientifically plan and design soil and water conservation measures, conduct dynamic evaluation of later monitoring, enhance the competitiveness of ecological protection "digitalization" planning and design, enhance the technical strength of ecological and environmental protection, and thus play an effective technical support role in a series of subsequent important projects such as the Yellow River protection, large-scale photovoltaic and pumped storage.

[0109] This embodiment also provides a soil erosion prediction and evaluation system. Figure 6 The schematic diagram of the soil and water loss prediction and evaluation system 100 in one embodiment of the present application is shown; Figure 6 As shown, the soil and water loss prediction and evaluation system 100 includes: a digital programming module 110 , a model building module 120 and a prediction and evaluation module 130 .

[0110] In this embodiment, the digital programming module 110 constructs a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process; the model construction module 120 is used to construct a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and construct a soil erosion prediction model based on the data set; the prediction evaluation module 130 performs soil erosion prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil erosion prediction model.

[0111] In this embodiment, the implementation principles of each module of the soil and water loss prediction and evaluation system 100 are the same as the implementation principles of each step of the above-mentioned soil and water loss prediction and evaluation method, and the implementation principles and specific implementation methods of the soil and water loss prediction and evaluation system 100 are not repeated here.

[0112] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is cached. When the computer program is executed by a processor, the soil and water loss prediction and assessment method provided in any embodiment of the present application is implemented.

[0113] In the embodiment of the present application, any combination of one or more storage media can be used. The storage medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or caching a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0114] An embodiment of the present application also provides an electronic device. Figure 7 Shown is a schematic diagram of the structure of the electronic device 10 provided in the embodiment of the present application. In some embodiments, the electronic device 10 can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA) and other terminal devices. In addition, the soil and water loss prediction and evaluation method provided in the present application can also be applied to databases, servers and service response systems based on terminal artificial intelligence. The embodiment of the present application does not impose any restrictions on the specific application scenarios of the soil and water loss prediction and evaluation method.

[0115] like Figure 7 As shown, the electronic device 10 provided in the embodiment of the present application includes a memory 101 and a processor 102 .

[0116] The memory 101 is used to cache computer programs; preferably, the memory 101 includes: ROM, RAM, disk, USB flash drive, cache card or CD, etc., which can cache program codes.

[0117] Specifically, the memory 101 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device 10 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 101 may include at least one program product having a set (e.g., at least one) of program modules, which are configured to perform the functions of the various embodiments of the present application.

[0118] The processor 102 is connected to the memory 101 and is used to execute the computer program cached in the memory 101 so that the electronic device 10 executes the soil and water loss prediction and evaluation method provided in any embodiment of the present application.

[0119] Optionally, the processor 102 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0120] Optionally, the electronic device 10 in this embodiment may further include a display 103. The display 103 is communicatively connected with the memory 101 and the processor 102, and is used to display a GUI interaction interface related to the soil and water loss prediction and evaluation method.

[0121] Furthermore, the electronic device 100 also includes: a firewall, a load balancer, a communication component, a power supply component and other components. Figure 7 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 7 Components shown.

[0122] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0123] In summary, the present application can be compatible with high-resolution and conventional resolution data for soil and water loss prediction and assessment, realize the spatial refinement of soil and water loss prediction and scheme deployment effect assessment work, and can effectively improve the overall assessment efficiency. Therefore, the present embodiment effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0124] The above embodiments are merely illustrative of the principles and effects of the present embodiment, and are not intended to limit the present embodiment. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present embodiment. Therefore, all equivalent modifications or changes made by those of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present embodiment should still be covered by the claims of the present embodiment.

Claims

1. A method for predicting and evaluating soil and water loss, characterized in that: include: Constructing corresponding digital forecasting process processing modules and digital forecasting parameter database based on the preset forecasting process; Constructing a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and constructing a soil and water loss prediction model based on the data set; Soil and water loss prediction assessment is performed based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model.

2. The method for predicting and evaluating soil and water loss according to claim 1, characterized in that: Also includes: Extract soil and water loss factors at different resolutions; Based on the sensitivity of soil and water loss factors to surface data resolution, a curve of project scale and optimal resolution is fitted to provide an optimization basis for data resolution of various projects in the future.

3. The method for predicting and evaluating soil and water loss according to claim 1, characterized in that: The soil and water loss prediction evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model includes: Acquire the prediction results of the sections based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model; Perform any one or more combination operations of statistics, cluster analysis, and level classification on the segmented prediction results to obtain soil and water loss prediction and assessment results.

4. The method for predicting and evaluating soil and water loss according to claim 3, characterized in that: The statistical, cluster analysis, and grade division of the prediction results include one or more combined operations: soil and water loss grade zoning operation, soil and water loss risk area identification operation, statistical operation on the spatiotemporal changes in the amount of soil and water loss in the project during the monitoring period, and soil and water operation in the acceptance stage.

5. The method for predicting and evaluating soil and water loss according to claim 1, characterized in that: The soil and water loss prediction assessment results include soil and water loss prediction assessment results, soil and water loss monitoring assessment results, and soil and water conservation acceptance assessment results; wherein, the soil and water loss monitoring assessment results include soil and water loss background value calculation assessment results and soil and water loss monitoring assessment results.

6. The method for predicting and evaluating soil and water loss according to any one of claims 3 to 5, characterized in that: The soil and water loss prediction and assessment results are output in the form of images and statistical tables.

7. The method for predicting and evaluating soil and water loss according to claim 1, characterized in that: The prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model use Fortran and Python programming to process data when performing soil and water loss prediction and evaluation, and use Java language to build an interactive interface for prediction and evaluation.

8. A soil and water loss prediction and assessment system, characterized by: include: A digital programming module builds a corresponding digital prediction process processing module and a digital prediction parameter database based on a preset prediction process; A model building module is used to build a data set including low-resolution DEM data, DOM data and high-resolution DEM data, DOM data, and to build a soil and water loss prediction model based on the data set; The prediction and evaluation module performs soil and water loss prediction and evaluation based on the prediction process processing module, the digital prediction parameter database and the soil and water loss prediction model.

9. An electronic device, characterized in that: include: comprising a memory for storing a computer program; A processor is used to run the computer program to implement the steps of the soil and water loss prediction and assessment method as described in any one of claims 1 to 7.

10. A computer storage medium storing program instructions, characterized in that: When the program instructions are executed, the steps of the soil and water loss prediction and evaluation method as described in any one of claims 1 to 7 are implemented.

Images