Soil moisture inversion method and system based on microwave scattering mechanism and DNN model

Abstract

The invention relates to the field of artificial intelligence, and provides a soil moisture inversion method and system based on a microwave scattering mechanism and a DNN model, and the method comprises the steps: obtaining field related data of a to-be-planted region, carrying out the preprocessing of the field related data, extracting a dual-polarization crop index, querying corresponding surface crop parameters to determine the growth periods of different plants, and carrying out the calculation of the growth periods. The method comprises the following steps: performing growth period back scattering simulation based on a preset coupling microwave scattering model to obtain back scattering simulation parameters and calculate an actual observation value, querying a time observation sequence therein, constructing a multi-source time sequence characteristic data set in combination with a preset DNN model, extracting multi-source characteristic data, analyzing plant position information, and inverting soil moisture content. And identifying content distribution characteristics, and finally generating an inversion report of the soil moisture of the to-be-planted area. According to the invention, the soil moisture inversion effect can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a soil moisture inversion method and system based on microwave scattering mechanism and DNN model. Background Art

[0002] In today's global ecological environment and agricultural development facing many challenges, accurate measurement of soil moisture content has become a key factor in ensuring ecological balance and promoting sustainable agricultural development. With the rapid advancement of science and technology, especially in the context of the continuous development of microwave remote sensing technology and artificial intelligence technology, there are higher requirements for the accuracy and efficiency of soil moisture inversion.

[0003] At present, traditional soil moisture inversion methods mainly rely on field sampling and laboratory analysis. This method is not only time-consuming and labor-intensive, but also difficult to achieve real-time monitoring over a large area. In addition, although some inversion methods based on microwave radiation transmission models are theoretically feasible, the uncertainty and complexity of model parameters affect the effectiveness in practical applications. Therefore, a soil moisture inversion method based on microwave scattering mechanism and DNN model is needed to improve the effect of soil moisture inversion. Summary of the invention

[0004] The present invention provides a soil moisture inversion method and system based on microwave scattering mechanism and DNN model, the main purpose of which is to improve the effect of soil moisture inversion.

[0005] Acquire field-related data corresponding to the area to be planted, wherein the field-related data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data, and field observation data;

[0006] Performing data preprocessing on the field-related data to obtain preprocessed field data, extracting a dual-polarization crop index from the preprocessed field data, querying a surface crop parameter corresponding to the dual-polarization crop index, and determining growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameter;

[0007] Based on a preset microwave scattering mechanism model, backscattering simulation is performed on the growth periods corresponding to different types of plants in the to-be-planted area to obtain backscattering simulation parameters, and actual observation values ​​corresponding to the backscattering simulation parameters are calculated;

[0008] Querying the time observation sequence in the actual observation value, combining the preset DNN model with the time observation sequence, constructing a multi-source time series feature data set corresponding to the to-be-planted area, and extracting multi-source feature data in the multi-source time series feature data set;

[0009] Based on the multi-source feature data, the location information of the plants in the area to be planted is analyzed, and based on the location information, the soil moisture content corresponding to the area to be planted is inverted, the content distribution characteristics corresponding to the soil moisture content are identified, and based on the content distribution characteristics, an inversion report of the soil moisture in the area to be planted is generated.

[0010] Optionally, extracting the dual-polarization crop index from the pre-processed field data includes:

[0011] Performing data unit segmentation on the pre-processed field data to obtain data segmentation units;

[0012] Extracting horizontal polarization data and vertical polarization data in the data segmentation unit;

[0013] Performing filtering processing on the horizontal polarization data and the vertical polarization data to obtain horizontal polarization filtered data and vertical polarization filtered data;

[0014] Calculating a dual polarization ratio corresponding to the preprocessed field data based on the horizontal polarization filter data and the vertical polarization filter data;

[0015] Based on the dual-polarization ratio, a dual-polarization crop index in the pre-processed field data is determined.

[0016] Optionally, the calculating, based on the horizontal polarization filter data and the vertical polarization filter data, a dual polarization ratio corresponding to the preprocessed field data includes:

[0017] The dual polarization ratio corresponding to the preprocessed field data is calculated.

[0018] Optionally, determining the growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameters includes:

[0019] Performing parameter screening on the surface crop parameters to obtain crop screening parameters;

[0020] Identifying the crop characteristics corresponding to the crop screening parameters, and querying the crop characteristic index corresponding to the crop characteristics;

[0021] Based on the crop characteristic index, analyzing the cycle stage corresponding to the surface crop parameter;

[0022] Based on the cycle stage, the growth periods corresponding to different types of plants in the area to be planted are determined.

[0023] Optionally, the backscattering simulation is performed on the growth periods corresponding to different types of plants in the to-be-planted area based on a preset microwave scattering mechanism model to obtain backscattering simulation parameters, including:

[0024] Collecting detailed parameters of the growth periods corresponding to different types of plants in the area to be planted;

[0025] Based on the detailed parameters, setting parameters of a preset microwave scattering mechanism model;

[0026] And using the coupled microwave scattering model with set parameters, the crop framework corresponding to the area to be planted is constructed;

[0027] identifying crop frame parameters corresponding to the crop frame;

[0028] Backscattering simulation is performed on the crop frame parameters to obtain backscattering simulation parameters.

[0029] Optionally, querying the time observation sequence in the actual observation value includes:

[0030] Collecting a complete data set corresponding to the actual observation value, and extracting the observation fields in the complete data set;

[0031] Standardizing the observed field to obtain a standardized field;

[0032] Mark the field index corresponding to the standardized field, and set the time interval corresponding to the field index;

[0033] Based on the time interval, a time observation sequence in the actual observation value is queried.

[0034] Optionally, combining the preset DNN model with the time observation sequence to construct a multi-source time series feature data set corresponding to the area to be planted includes:

[0035] Identify the appropriate format for data in the preset DNN model;

[0036] Based on the adaptation format, adjusting the sequence observation data corresponding to the time observation sequence;

[0037] Extracting multi-source sequence features from the sequence observation data;

[0038] Performing vector conversion on the multi-source sequence features to obtain a multi-source feature vector;

[0039] The multi-source feature vectors are processed in time series using a preset DNN model to obtain a multi-source time series feature data set corresponding to the area to be planted.

[0040] Optionally, inverting the soil moisture content corresponding to the to-be-planted area based on the location information includes:

[0041] Querying the geographic coordinates in the location information;

[0042] Based on the geographic coordinates, analyzing the land use type corresponding to the to-be-planted area;

[0043] Based on the land use type, determining the coverage area corresponding to the to-be-planted area;

[0044] Based on the coverage, analyzing the soil moisture content in the to-be-planted area;

[0045] Based on the soil moisture ratio, the soil moisture content corresponding to the area to be planted is inverted.

[0046] In order to solve the above problems, the present invention also provides a soil moisture inversion system based on microwave scattering mechanism and DNN model, the system comprising:

[0047] A field data module is used to obtain field-related data corresponding to the area to be planted, wherein the field-related data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data and field observation data;

[0048] A crop parameter module, used to perform data preprocessing on the field-related data to obtain preprocessed field data, extract a dual-polarization crop index in the preprocessed field data, query a surface crop parameter corresponding to the dual-polarization crop index, and determine the growth period corresponding to different plants in the to-be-planted area based on the surface crop parameter;

[0049] An observation value calculation module is used to perform backscattering simulation on the growth periods corresponding to different types of plants in the to-be-planted area based on a preset microwave scattering mechanism model, obtain backscattering simulation parameters, and calculate actual observation values ​​corresponding to the backscattering simulation parameters;

[0050] A feature extraction module is used to query the time observation sequence in the actual observation value, combine the preset DNN model with the time observation sequence, construct a multi-source time series feature data set corresponding to the to-be-planted area, and extract multi-source feature data in the multi-source time series feature data set;

[0051] A report generation module is used to analyze the location information of the plants in the area to be planted based on the multi-source feature data, invert the soil moisture content corresponding to the area to be planted based on the location information, identify the content distribution characteristics corresponding to the soil moisture content, and generate an inversion report of the soil moisture in the area to be planted based on the content distribution characteristics.

[0052] First of all, by acquiring the field-related data corresponding to the area to be planted, the present invention can fully and accurately understand the actual conditions of the area to be planted, provide rich and reliable basic information for soil moisture inversion, and provide a basis for subsequent analysis of the relationship between soil moisture and vegetation growth, thereby improving the accuracy of the inversion result. At the same time, by performing data preprocessing on the field-related data to obtain preprocessed field data, the present invention can remove noise and outliers in the data, improve the quality and accuracy of the data, and can unify and standardize data from different sources and in different formats to facilitate data integration and comprehensive utilization. Based on a preset microwave scattering mechanism model, the present invention performs backscattering simulation on the growth periods corresponding to different types of plants in the area to be planted to obtain backscattering simulation parameters, which is helpful to deeply understand the electromagnetic scattering characteristics of crops at different growth stages. , it is possible to predict in advance the scattering law of microwaves by plants in different growth periods, and provide a theoretical basis for subsequent remote sensing monitoring and data analysis, so as to more accurately interpret the information in remote sensing images and improve the accuracy of crop monitoring. The present invention helps to deeply explore the influence mechanism of environmental factors and plant growth stages on backscattering by querying the time observation sequence in the actual observation value, and reveal the laws related to the plant growth cycle, meteorological cycle or other periodic phenomena, and provide a strong basis for prediction and model optimization. Furthermore, the present invention analyzes the position information of the plants to be planted in the area to be planted based on the multi-source feature data, and can realize the precise planning of the planting area, understand the location distribution of the plants, and arrange the planting layout more reasonably to avoid excessive crowding or sparseness between plants, thereby optimizing land use efficiency and increasing the yield per unit area. Therefore, the soil moisture inversion method and system based on microwave scattering mechanism and DNN model proposed in the present invention can improve the effect of soil moisture inversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic flow chart of a soil moisture inversion method based on microwave scattering mechanism and DNN model provided in one embodiment of the present invention;

[0054] Figure 2 A module schematic diagram of a soil moisture inversion system based on microwave scattering mechanism and DNN model provided by an embodiment of the present invention.

[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0057] The embodiment of the present application provides a soil moisture inversion method based on a microwave scattering mechanism and a DNN model. The execution subject of the soil moisture inversion method based on the microwave scattering mechanism and the DNN model includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the soil moisture inversion method based on the microwave scattering mechanism and the DNN model can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0058] Reference Figure 1 FIG. 1 is a flow chart of a soil moisture inversion method based on microwave scattering mechanism and DNN model provided by an embodiment of the present invention. In this embodiment, the soil moisture inversion method based on microwave scattering mechanism and DNN model includes:

[0059] S1. Acquire relevant field data corresponding to the area to be planted, wherein the relevant field data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data and field observation data.

[0060] By acquiring relevant field data corresponding to the area to be planted, the present invention can fully and accurately understand the actual conditions of the area to be planted, provide rich and reliable basic information for soil moisture inversion, and provide a basis for subsequent analysis of the relationship between soil moisture and vegetation growth, thereby improving the accuracy of the inversion results.

[0061] Among them, the field-related data refers to a series of data obtained from the area to be planted that are closely related to the actual situation of the area, specifically including dual-polarization satellite-borne SAR data, which can reflect the characteristics of the soil surface; multi-spectral satellite remote sensing data, which can obtain relevant information such as vegetation; and field observation data, which are real and reliable data obtained directly on-site through actual measurement, observation, etc. in the area to be planted. Optionally, the acquisition of field-related data corresponding to the area to be planted can be achieved through satellite remote sensing technology, such as: the Sentinel series of satellites can provide high-quality SAR data and multi-spectral data.

[0062] In detail, the field-related data include: dual-polarization satellite-borne SAR data, multi-spectral satellite remote sensing data and field observation data, wherein the dual-polarization satellite-borne SAR data refers to the data obtained by observing the earth's surface in two polarization modes, horizontal polarization (H) and vertical polarization (V), using a satellite-borne synthetic aperture radar (SAR) system; the multi-spectral satellite remote sensing data refers to the data obtained by imaging the earth's surface in multiple different spectral bands through a multi-spectral sensor carried on a satellite. Different spectral bands can reflect the reflection and radiation characteristics of the ground objects in different wavelength ranges, so that different types of ground objects, such as vegetation, water bodies, soil, etc., can be distinguished, and information such as vegetation growth conditions and land use conditions can be obtained; the field observation data refers to data directly obtained through field measurement, sampling, investigation, etc. at the site of the planting area, and these data include but are not limited to soil texture, soil temperature, soil moisture, vegetation height, vegetation density, crop growth stage, etc. Field observation data are characterized by high precision and high reliability, and can provide a direct reference for soil moisture inversion. They can also be used to verify and calibrate the results of other remote sensing data and models.

[0063] S2. Preprocess the field-related data to obtain preprocessed field data, extract the bipolar crop index in the preprocessed field data, query the surface crop parameters corresponding to the bipolar crop index, and determine the growth periods corresponding to different types of plants in the area to be planted based on the surface crop parameters.

[0064] The present invention obtains preprocessed field data by performing data preprocessing on the field-related data, thereby removing noise and outliers in the data, improving the quality and accuracy of the data, and unifying and standardizing data from different sources and in different formats, thereby facilitating data integration and comprehensive utilization.

[0065] The pre-processed field data refers to data obtained after a series of processing operations are performed on the acquired field-related data. These processing operations may include but are not limited to data cleaning (removing noise, outliers, etc.), data calibration (correcting sensor errors, etc.), data format conversion (unifying the format to facilitate subsequent processing), data fusion (integrating data from different sources), data dimension reduction (reducing data dimensions to improve processing efficiency), etc. Optionally, the data pre-processing of the field-related data can be achieved through data pre-processing tools, such as Sci kit-l earn, Pandas and other tools.

[0066] Furthermore, by extracting the bipolar crop index from the preprocessed field data, the present invention can gain an in-depth understanding of the growth conditions of crops, such as the health of the crops, moisture conditions, and changes in growth stages, etc., which helps farmers and agricultural managers to take corresponding measures in a timely manner, such as precision irrigation, fertilization, and pest and disease control, thereby improving the yield and quality of crops.

[0067] Among them, the bipolar crop index refers to an index used to describe crop characteristics determined based on the bipolar ratio and other relevant information. It can comprehensively reflect the growth status, moisture content, vegetation coverage and other information of the crop, and is of great significance for agricultural production management, ecological environment monitoring, etc.

[0068] As an embodiment of the present invention, the extracting the dual-polarization crop index in the preprocessed field data includes: performing data unit segmentation on the preprocessed field data to obtain a data segmentation unit; extracting horizontal polarization data and vertical polarization data in the data segmentation unit; performing filtering processing on the horizontal polarization data and the vertical polarization data to obtain horizontal polarization filtered data and vertical polarization filtered data; calculating a dual polarization ratio corresponding to the preprocessed field data based on the horizontal polarization filtered data and the vertical polarization filtered data; and determining the dual polarization crop index in the preprocessed field data based on the dual polarization ratio.

[0069] Among them, the data segmentation unit refers to the smaller data sets divided into by the pre-processed field data according to certain rules (such as time intervals and geographic coordinates), and each data segmentation unit contains data in a specific time period and a specific area, so as to analyze and process the data more carefully; the horizontal polarization data refers to the field observation data corresponding to the vibration of the electric field vector in the horizontal direction during the propagation of electromagnetic waves, which reflects the scattering, reflection and other characteristics of electromagnetic waves by the ground objects under the horizontal polarization mode; the vertical polarization data refers to the field observation data corresponding to the vibration of the electric field vector in the vertical direction. Similar to the horizontal polarization data, the vertical polarization data also contains the electromagnetic characteristic information of the ground objects under the vertical polarization mode. Information; the horizontal polarization filtering data refers to the data obtained after filtering the horizontal polarization data, and the purpose of filtering is to remove irrelevant information such as noise and interference in the horizontal polarization data, and retain or highlight the useful signal related to the dual-polarization crop index, so as to improve the quality and reliability of the data; the vertical polarization filtering data refers to the data obtained after filtering the vertical polarization data, and is used to remove noise and interference in the vertical polarization data, so as to provide more accurate information for subsequent calculations; the dual polarization ratio refers to a ratio calculated from the horizontal polarization filtering data and the vertical polarization filtering data, which characterizes certain characteristics of the ground object by comparing the data differences under the horizontal polarization and vertical polarization modes.

[0070] Further, the data unit segmentation of the pre-processed field data can be achieved by dividing based on time intervals and geographic grids, such as: the data can be divided into different time units according to fixed time intervals (such as every day, every week, etc.), and the study area can be divided into regular grids according to geographic coordinates, and each grid is used as a geographic unit, so that a data segmentation unit determined by time and geographic location can be obtained; the extraction of horizontal polarization data and vertical polarization data in the data segmentation unit can be achieved through the ENVI tool, such as: the pre-processed field data file can be read through the ENVI tool, and the corresponding horizontal polarization and vertical polarization band data can be extracted through a specific band selection function; the filtering of the horizontal polarization data and the vertical polarization data can be achieved through a filtering algorithm, such as median filtering, mean filtering, Gaussian filtering and other algorithms; the calculation of the dual polarization ratio corresponding to the pre-processed field data can be achieved through the following calculation formula; the determination of the dual polarization crop index in the pre-processed field data can be achieved through a machine learning algorithm, such as support vector machine, random forest and other algorithms.

[0071] As an embodiment of the present invention, the calculating the dual polarization ratio corresponding to the preprocessed field data based on the horizontal polarization filter data and the vertical polarization filter data includes:

[0072] The dual polarization ratio corresponding to the preprocessed field data is calculated using the following formula:

[0073]

[0074] Wherein, DPR represents the dual polarization ratio corresponding to the preprocessed field data, H filtered represents the data value corresponding to the horizontal polarization filter data, Ha represents the weight coefficient corresponding to the horizontal polarization filter data, Hb represents the offset corresponding to the horizontal polarization filter data, Hc represents the constant term corresponding to the horizontal polarization filter data, V filtered represents the data value corresponding to the vertical polarization filter data, Vd represents the weight coefficient corresponding to the vertical polarization filter data, Ve represents the offset corresponding to the vertical polarization filter data, and Vf represents the constant term corresponding to the vertical polarization filter data.

[0075] In detail, the weight coefficient corresponding to the horizontal polarization filter data refers to the relative importance of the horizontal polarization filter data in the process of calculating the dual polarization ratio, which determines the influence of the horizontal polarization filter data on the final result; the offset corresponding to the horizontal polarization filter data refers to the fact that in order to avoid invalid or unstable results in the logarithmic operation, there may be some data points close to zero or negative values ​​in the actual horizontal polarization filter data. If the logarithmic operation is directly performed on these data, the calculation result will be meaningless or a large error will occur. By adding an appropriate offset, all data values ​​can be adjusted to a positive range, thereby ensuring the feasibility of the logarithmic operation; the constant term corresponding to the horizontal polarization filter data refers to the role of fine-tuning in the formula, which can The horizontal polarization filter data after logarithmic transformation and weight adjustment are further corrected so that the calculated dual polarization ratio is more in line with the actual situation or expected results; the weight coefficient corresponding to the vertical polarization filter data is similar to the weight coefficient of the horizontal polarization filter data, and the weight coefficient Vd corresponding to the vertical polarization filter data is used to determine the relative importance of the vertical polarization filter data in calculating the dual polarization ratio; the role of the offset corresponding to the vertical polarization filter data is the same as the offset of the horizontal polarization filter data, both of which are to ensure that the input value is a positive number in the logarithmic operation; the function of the constant term corresponding to the vertical polarization filter data is also similar to the constant term of the horizontal polarization filter data, and is used to perform final fine adjustment on the vertical polarization filter data after logarithmic transformation and weight adjustment.

[0076] The present invention can provide key information for precision agriculture by querying the surface crop parameters corresponding to the dual-polarization crop index, which is helpful for in-depth research on crop growth laws and soil-crop interaction mechanisms, and can reveal the physiological responses and adaptability of crops under different growth conditions.

[0077] Among them, the surface crop parameters refer to a series of quantitative indicators used to describe the characteristics and status of surface crops, including: crop type, growth stage, vegetation coverage, etc. Optionally, the query of the surface crop parameters corresponding to the dual-polarization crop index can be achieved through a regression model, such as: linear regression, polynomial regression, nonlinear regression and other models.

[0078] The present invention determines the growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameters, which helps to accurately grasp the key stages of crop growth, and can reasonably arrange the time and amount of irrigation and fertilization, avoid waste of resources and negative impacts on the environment caused by excessive fertilization, while ensuring that crops obtain sufficient nutrient supply during key growth stages, promote healthy growth of crops, and improve yield and quality.

[0079] Among them, the growth period refers to the entire time period from crop sowing or seedling emergence, through a series of growth and development stages, until the crops mature and are harvested. This time period is subdivided into multiple different growth periods, such as sowing period, seedling period, tillering period, heading period, filling period, maturity period, etc. Each period has specific growth tasks and specific requirements for external environmental conditions.

[0080] As an embodiment of the present invention, determining the growth periods corresponding to different types of plants in the area to be planted based on the surface crop parameters includes: performing parameter screening on the surface crop parameters to obtain crop screening parameters; identifying crop characteristics corresponding to the crop screening parameters; querying the crop characteristic index corresponding to the crop characteristics; based on the crop characteristic index, analyzing the cycle stage corresponding to the surface crop parameters; and determining the growth periods corresponding to different types of plants in the area to be planted based on the cycle stage.

[0081] Among them, the crop screening parameters refer to those key parameters that are closely related to the crop growth period and have a significant indicative effect, which are selected from a large number of surface crop parameters after scientific analysis and judgment. For example, among the many parameters, the leaf area growth rate, the range of change in stem thickness, the chlorophyll content, etc. may be selected as key crop screening parameters; the crop characteristics refer to the unique and observable properties and characteristics exhibited by the crop during the growth process. It can be morphological, such as the shape of the plant, the color and texture of the leaves; it can also be physiological, such as photosynthesis efficiency, respiration intensity, etc.; the crop characteristic index refers to a standardized numerical indicator set to more accurately describe and quantify crop characteristics, such as an index indicating the degree of leaf aging and an index indicating root vitality calculated by a specific formula; the cycle stage refers to a specific time period in the growth process of the crop. During this time period, the growth and development of the crop present relatively stable and regular characteristics, such as the vigorous period of vegetative growth and the critical period of reproductive organ formation.

[0082] Furthermore, the parameter screening of the surface crop parameters can be achieved through parameter screening methods, such as correlation analysis, principal component analysis and other methods; the identification of the crop characteristics corresponding to the crop screening parameters can be achieved through Python's scipy earn library, such as using the clustering algorithm in Python's scipy earn library for analysis; the query of the crop characteristic index corresponding to the crop characteristics can be achieved through R language, such as using R language for statistical analysis and calculating the crop characteristic index; the analysis of the cycle stage corresponding to the surface crop parameters can be achieved through a stage analysis method, such as comparative analysis, fuzzy logic reasoning and other methods; the determination of the growth periods corresponding to different types of plants in the area to be planted can be achieved through a reasoning determination method, such as comparative analysis, fuzzy logic reasoning and other methods.

[0083] S3. Based on the preset microwave scattering mechanism model, backscattering simulation is performed on the growth periods corresponding to different types of plants in the to-be-planted area to obtain backscattering simulation parameters, and actual observation values ​​corresponding to the backscattering simulation parameters are calculated.

[0084] The present invention is based on a preset microwave scattering mechanism model, and performs backscattering simulation on the growth stages corresponding to different types of plants in the to-be-planted area to obtain backscattering simulation parameters, which helps to deeply understand the electromagnetic scattering characteristics of crops at different growth stages, and can predict in advance the scattering laws of microwaves by plants at different growth stages, providing a theoretical basis for subsequent remote sensing monitoring and data analysis, thereby more accurately interpreting the information in remote sensing images and improving the accuracy of crop monitoring.

[0085] Among them, the preset microwave scattering mechanism model refers to a mathematical model established in advance for describing and calculating the scattering conditions during the interaction between electromagnetic waves and plants and the surrounding environment; the backscattering simulation parameters refer to the result parameters obtained by performing backscattering simulation calculations on the constructed crop framework. These parameters quantitatively describe the intensity, frequency characteristics, polarization characteristics and other information of the backscattering of electromagnetic waves after interacting with crops, and are used to analyze and evaluate the growth status, structural characteristics and interaction of crops with electromagnetic waves.

[0086] As an embodiment of the present invention, the backscattering simulation is performed on the growth periods corresponding to different types of plants in the area to be planted based on a preset microwave scattering mechanism model to obtain backscattering simulation parameters, including: collecting detailed parameters of the growth periods corresponding to different types of plants in the area to be planted; based on the detailed parameters, setting parameters of the preset microwave scattering mechanism model; and using the coupled microwave scattering model with the set parameters to construct a crop frame corresponding to the area to be planted; identifying crop frame parameters corresponding to the crop frame; and performing backscattering simulation on the crop frame parameters to obtain backscattering simulation parameters.

[0087] Among them, the detailed parameters refer to the data of various specific characteristics and attributes of different types of plants in the area to be planted during their corresponding growth periods, including but not limited to plant height, stem thickness, leaf area, leaf shape, water content, plant density, etc., as well as soil humidity, roughness and other related information; the crop frame refers to a virtual model that can represent the growth conditions and structural characteristics of plants in the area to be planted, which is constructed in a preset microwave scattering mechanism model based on the collected detailed parameters, and contains information such as the morphology, structure and relationship of the plant with the surrounding environment; the crop frame parameters refer to various specific quantitative indicators that describe the crop frame, such as the geometric dimensions of the frame, the proportion and distribution of its components, material properties (such as dielectric constant, etc.), etc. These parameters are used to accurately characterize the characteristics of the crop frame.

[0088] Furthermore, the collection of detailed parameters of the growth periods corresponding to different types of plants in the area to be planted can be achieved through remote sensing tools, such as ENVI and other tools; the parameter setting of the preset microwave scattering mechanism model can be achieved through parameter import tools, such as ETL, Web and other tools; the construction of the crop framework corresponding to the area to be planted can be achieved by using a coupled microwave scattering model with parameters set; the identification of the crop framework parameters corresponding to the crop framework can be achieved through parameter identification tools, such as SolidWorks and other tools; the backscattering simulation of the crop framework parameters can be achieved through simulation methods, such as numerical simulation, Monte Carlo simulation and other methods.

[0089] By calculating the actual observation values ​​corresponding to the backscatter simulation parameters, the present invention can accurately monitor the growth status, health status and yield prediction of crops, provide a scientific basis for decision-making in agricultural production, and achieve efficient utilization and precise management of agricultural resources.

[0090] The actual observation value refers to the real data about backscattering obtained through actual measurement, monitoring or observation means, which reflects the actual backscattering situation generated after the interaction between electromagnetic waves and objects in a real environment.

[0091] As an embodiment of the present invention, the calculating the actual observed value corresponding to the backscattering simulation parameter includes:

[0092]

[0093] Wherein, Obv represents the actual observed value corresponding to the backscattering simulation parameter, N represents the number of observations corresponding to the backscattering simulation parameter, i represents the observation index corresponding to the backscattering simulation parameter, and f min Indicates the lower frequency limit, f max Indicates the upper frequency limit, S sim (f,θ i ,φ i ) represents the frequency f, incident angle θ i 、Azimuth φ i The simulated backscatter value under obs (f,θ i ,φ i ) represents the frequency f, the incident angle θ i 、Azimuth φ i The corresponding actual observed backscatter value, λ represents the environmental impact weight coefficient in the backscatter simulation parameters, M env (i) represents the environmental parameter matrix at the i-th observation.

[0094] In detail, the lower frequency limit and the upper frequency limit refer to the minimum values ​​of the frequency range considered, while the upper frequency limit is the maximum value; the backscattering simulation value refers to the scattering value of electromagnetic waves in the backward direction predicted by theoretical models and calculation methods; the actually observed backscattering value refers to the scattering data of electromagnetic waves in the backward direction directly measured in actual scenes using special instruments and equipment; the environmental impact weight coefficient refers to a value used to quantify the degree of influence of environmental factors on backscattering, which determines the proportion of environmental parameters in calculating actual observation values. A larger weight coefficient means that the environmental factors have a greater impact on the result, and vice versa; the environmental parameter matrix refers to a multidimensional array or data table used to describe environmental characteristics, which may contain quantified values ​​of various environmental factors such as soil moisture, temperature, wind speed, and atmospheric conditions.

[0095] S4. Query the time observation sequence in the actual observation value, combine the preset DNN model with the time observation sequence, construct a multi-source time series feature data set corresponding to the area to be planted, and extract multi-source feature data in the multi-source time series feature data set.

[0096] By querying the time observation sequence in the actual observation values, the present invention helps to deeply explore the influence mechanism of environmental factors and plant growth stages on backscattering, reveal the laws related to plant growth cycles, meteorological cycles or other periodic phenomena, and provide a strong basis for prediction and model optimization.

[0097] The time observation sequence refers to a series of observation values ​​arranged in chronological order, which reflects the state or characteristic changes of the observed object at different time points.

[0098] As an embodiment of the present invention, the query of the time observation sequence in the actual observation value includes: collecting a complete data set corresponding to the actual observation value; extracting the observation fields in the complete data set; standardizing the observation fields to obtain standardized fields; marking the field index corresponding to the standardized field; setting the time interval corresponding to the field index; and querying the time observation sequence in the actual observation value based on the time interval.

[0099] Among them, the complete data set refers to a set of original data related to all actual observations, covering various observation conditions, environmental factors, measurement parameters and other information; the observation field refers to a specific data column or data area in the complete data set that is specifically used to record observation results or measurement values; the standardized field refers to an observation field that has undergone a series of standardized processing and conversions to make its format, unit, accuracy, etc. meet unified and standardized requirements; the field index refers to a unique identifier or number assigned to each field in the data set (including standardized fields); the time interval refers to a fixed time period set on the time axis, which is used to group, aggregate or analyze data, such as hourly, daily, weekly, etc.

[0100] Furthermore, the collection of the complete data set corresponding to the actual observation values ​​can be achieved through database management tools, such as MySQL and other tools; the extraction of observation fields in the complete data set can be achieved through field extraction methods, such as data screening, field selection and other methods; the standardization of the observation fields can be achieved through standardization tools, such as using functions in the NumPy library to standardize data; the marking of field indexes corresponding to the standardized fields can be achieved through index marking tools, such as MySQL, Python and other tools; the setting of time intervals corresponding to the field indexes can be achieved through SPSS tools, such as using SPSS to analyze the periodicity of data to determine the interval; the querying of the time observation sequence in the actual observation values ​​can be achieved through sequence query methods, such as time sorting query, sliding window query and other methods.

[0101] The present invention combines a preset DNN model with the time observation sequence to construct a multi-source time series feature data set corresponding to the area to be planted, which can mine the complex patterns and potential relationships hidden in the time observation sequence, thereby more accurately characterizing the characteristic changes of the area to be planted.

[0102] Among them, the preset DNN model refers to a deep neural network model designed and trained in advance according to specific tasks and data characteristics, with specific structure and parameters, and is used to process and analyze input data to obtain useful information or make predictions; the multi-source time series feature data set refers to a set composed of processed and extracted multi-source time series features, organized according to certain structures and rules, for subsequent analysis and application.

[0103] As an embodiment of the present invention, the preset DNN model is combined with the time observation sequence to construct a multi-source time series feature data set corresponding to the area to be planted, including: identifying the adaptation format of the data in the preset DNN model; adjusting the sequence observation data corresponding to the time observation sequence based on the adaptation format; extracting multi-source sequence features in the sequence observation data; performing vector conversion on the multi-source sequence features to obtain a multi-source feature vector; and performing time series processing on the multi-source feature vector using the preset DNN model to obtain a multi-source time series feature data set corresponding to the area to be planted.

[0104] Among them, the adaptation format refers to the specific organizational form, data type, dimension and arrangement method of the data that the preset DNN model can accept and process; the sequence observation data refers to data composed of observation values ​​recorded in chronological order, reflecting the state or characteristics of the observed object at different time points; the multi-source sequence feature refers to the significant characteristics or patterns extracted from the sequence observation data from multiple different sources (such as meteorology, soil, crops themselves, etc.) and with time series properties; the multi-source feature vector refers to the mathematical vector obtained by digitizing and vectorizing the extracted multi-source sequence features.

[0105] Furthermore, the identification of the adaptation format of the data in the preset DNN model can be achieved through model analysis software, such as tools such as Netron; the adjustment of the sequence observation data corresponding to the time observation sequence can be achieved through data adjustment methods, such as data resampling, data scaling and other methods; the extraction of multi-source sequence features in the sequence observation data can be achieved through feature extraction methods, such as sliding window analysis, Fourier transform and other methods; the vector conversion of the multi-source sequence features can be achieved through vector conversion methods, such as One-Hot encoding, numerical vector and other methods.

[0106] S5. Based on the multi-source feature data, analyze the location information of the plants in the area to be planted, invert the soil moisture content corresponding to the area to be planted based on the location information, identify the content distribution characteristics corresponding to the soil moisture content, and generate an inversion report of the soil moisture in the area to be planted based on the content distribution characteristics.

[0107] The present invention analyzes the position information of the plants in the area to be planted based on the multi-source feature data, can achieve accurate planning of the planting area, understand the position distribution of the plants, and arrange the planting layout more reasonably to avoid excessive crowding or sparseness between plants, thereby optimizing land use efficiency and increasing the yield per unit area.

[0108] Among them, the location information refers to the specific spatial coordinates or relative position description of the plants in the area to be planted in the area, which may include the row and column positions of the plants in the field, or the precise geographical location represented by geographic coordinates (such as longitude and latitude), or it may be information such as the direction and distance relative to specific reference objects (such as ridges, irrigation facilities, etc.). Optionally, the analysis of the location information of the plants in the area to be planted can be achieved by what methods, tools or algorithms, such as: (and examples of the methods, tools or algorithms that can be implemented therein are given).

[0109] Based on the location information, the present invention inverts the soil moisture content corresponding to the area to be planted, and can carry out targeted irrigation to avoid water resource waste and soil salinization caused by excessive irrigation, and also prevent insufficient irrigation from affecting crop growth, thereby improving water resource utilization efficiency and crop yield.

[0110] The soil moisture content refers to the amount of water contained in a unit volume or unit mass of soil. Commonly used expressions include weight moisture content, volume moisture content, etc., which are used to describe the wetness of the soil.

[0111] As an embodiment of the present invention, inverting the soil moisture content corresponding to the area to be planted based on the location information includes: querying the geographic coordinates in the location information; analyzing the land use type corresponding to the area to be planted based on the geographic coordinates; determining the coverage range corresponding to the area to be planted based on the land use type; analyzing the soil moisture ratio in the area to be planted based on the coverage range; and inverting the soil moisture content corresponding to the area to be planted based on the soil moisture ratio.

[0112] Among them, the geographic coordinates refer to a set of numerical values ​​that use longitude and latitude to represent the position of a certain point on the area to be planted, which consists of two values: longitude and latitude; the land use type refers to the way and purpose of land use, such as cultivated land, forest land, grassland, construction land, water area, etc., which reflects the main function and use of the land in the area to be planted; the coverage area refers to the geographical area occupied by the area to be planted, including its boundaries and area size; the soil moisture content refers to the ratio of the amount of water contained in the soil to the total volume or total mass of the soil.

[0113] Furthermore, the query of the geographic coordinates in the location information can be implemented through GIS tools, such as ArcGIS, QG IS and other tools; the analysis of the land use type corresponding to the area to be planted can be implemented through remote sensing processing tools, such as ENVI, ERDAS and other tools; the determination of the coverage range corresponding to the area to be planted can be implemented through online map tools, such as the developer interface of Baidu Map and Amap; the analysis of the soil moisture content in the area to be planted can be implemented through TDR tools, such as using TDR equipment to measure the dielectric constant of the soil on-site to infer the moisture content; the inversion of the soil moisture content corresponding to the area to be planted can be implemented through a machine learning framework, such as TensorFlow, Scikit-learn and other tools.

[0114] By identifying the content distribution characteristics corresponding to the soil moisture content, the present invention can understand the distribution of soil moisture in different areas, and can formulate irrigation plans in a targeted manner to ensure that crops in each area can receive an appropriate amount of water supply, avoid over-irrigation or under-irrigation, and thus improve crop yield and quality.

[0115] Among them, the content distribution characteristics refer to the changing rules and characteristics of soil moisture content within the spatial range of the area to be planted, including the difference in soil moisture content at different locations, the uniformity of distribution, whether there are areas with concentrated high or low moisture, the trend of moisture content change with depth, and specific distribution patterns in different terrains, soil types and crop planting areas, etc. Optionally, the identification of the content distribution characteristics corresponding to the soil moisture content can be achieved through an interpolation algorithm, such as: Kriging interpolation algorithm, inverse distance weighted interpolation algorithm, etc.

[0116] Furthermore, based on the content distribution characteristics, the present invention generates an inversion report of soil moisture in the area to be planted, which can clearly understand the moisture distribution details of each area in the entire area to be planted, so as to accurately formulate irrigation plans, avoid waste of water resources and increased costs caused by blind watering, and ensure that crops receive sufficient and appropriate water supply during the critical growth period, thereby promoting good growth and high yield of crops.

[0117] Among them, the inversion report refers to a comprehensive written or electronic document formed based on the analysis and calculation of the soil moisture content distribution characteristics, which contains detailed information about the soil moisture conditions in the area to be planted, such as the specific moisture content values ​​in different regions, description and analysis of the distribution pattern, comparison with historical data or standard values, discussion of factors that may affect moisture distribution, and conclusions and suggestions based on these analyses, etc. Optionally, the inversion report of the soil moisture in the area to be planted based on the content distribution characteristics can be generated through a report generation tool, such as: Power BI, Tableau and other tools.

[0118] First of all, by acquiring the field-related data corresponding to the area to be planted, the present invention can fully and accurately understand the actual conditions of the area to be planted, provide rich and reliable basic information for soil moisture inversion, and provide a basis for subsequent analysis of the relationship between soil moisture and vegetation growth, thereby improving the accuracy of the inversion result. At the same time, by performing data preprocessing on the field-related data to obtain preprocessed field data, the present invention can remove noise and outliers in the data, improve the quality and accuracy of the data, and can unify and standardize data from different sources and in different formats to facilitate data integration and comprehensive utilization. Based on a preset microwave scattering mechanism model, the present invention performs backscattering simulation on the growth periods corresponding to different types of plants in the area to be planted to obtain backscattering simulation parameters, which is helpful to deeply understand the electromagnetic scattering characteristics of crops at different growth stages. , it is possible to predict in advance the scattering law of microwaves by plants in different growth periods, and provide a theoretical basis for subsequent remote sensing monitoring and data analysis, so as to more accurately interpret the information in remote sensing images and improve the accuracy of crop monitoring. The present invention helps to deeply explore the influence mechanism of environmental factors and plant growth stages on backscattering by querying the time observation sequence in the actual observation value, and reveal the laws related to the plant growth cycle, meteorological cycle or other periodic phenomena, and provide a strong basis for prediction and model optimization. Furthermore, the present invention analyzes the position information of the plants to be planted in the area to be planted based on the multi-source feature data, and can realize the precise planning of the planting area, understand the location distribution of the plants, and arrange the planting layout more reasonably to avoid excessive crowding or sparseness between plants, thereby optimizing land use efficiency and increasing the yield per unit area. Therefore, the soil moisture inversion method and system based on microwave scattering mechanism and DNN model proposed in the present invention can improve the effect of soil moisture inversion.

[0119] like Figure 2 , which is a functional module diagram of a soil moisture inversion system based on microwave scattering mechanism and DNN model provided by an embodiment of the present invention.

[0120] The soil moisture inversion system 200 based on microwave scattering mechanism and DNN model of the present invention can be installed in an electronic device. According to the functions implemented, the soil moisture inversion system 200 based on microwave scattering mechanism and DNN model can include a field data module 201, a crop parameter module 202, an observation value calculation module 203, a feature extraction module 204 and a report generation module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0121] In this embodiment, the functions of each module / unit are as follows:

[0122] A field data module 201 is used to obtain field-related data corresponding to the area to be planted, wherein the field-related data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data and field observation data;

[0123] The crop parameter module 202 is used to perform data preprocessing on the field-related data to obtain preprocessed field data, extract the dual-polarization crop index in the preprocessed field data, query the surface crop parameters corresponding to the dual-polarization crop index, and determine the growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameters;

[0124] The observation value calculation module 203 is used to perform backscattering simulation on the growth periods corresponding to different types of plants in the to-be-planted area based on a preset microwave scattering mechanism model, obtain backscattering simulation parameters, and calculate actual observation values ​​corresponding to the backscattering simulation parameters;

[0125] The feature extraction module 204 is used to query the time observation sequence in the actual observation value, combine the preset DNN model with the time observation sequence, construct a multi-source time series feature data set corresponding to the to-be-planted area, and extract multi-source feature data in the multi-source time series feature data set;

[0126] The report generation module 205 is used to analyze the location information of the plants in the area to be planted based on the multi-source feature data, invert the soil moisture content corresponding to the area to be planted based on the location information, identify the content distribution characteristics corresponding to the soil moisture content, and generate an inversion report of the soil moisture in the area to be planted based on the content distribution characteristics.

[0127] In detail, the modules described in the soil moisture inversion system 200 based on microwave scattering mechanism and DNN model described in the embodiment of the present invention adopt the same technical means as the soil moisture inversion method based on microwave scattering mechanism and DNN model described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0128] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. The soil moisture inversion method based on microwave scattering mechanism and DNN model is characterized by: The method comprises: Acquire field-related data corresponding to the area to be planted, wherein the field-related data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data, and field observation data; Performing data preprocessing on the field-related data to obtain preprocessed field data, extracting a dual-polarization crop index from the preprocessed field data, querying a surface crop parameter corresponding to the dual-polarization crop index, and determining growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameter; Based on a preset microwave scattering mechanism model, backscattering simulation is performed on the growth periods corresponding to different types of plants in the to-be-planted area to obtain backscattering simulation parameters, and actual observation values ​​corresponding to the backscattering simulation parameters are calculated; Querying the time observation sequence in the actual observation value, combining the preset DNN model with the time observation sequence, constructing a multi-source time series feature data set corresponding to the to-be-planted area, and extracting multi-source feature data in the multi-source time series feature data set; Based on the multi-source feature data, the location information of the plants in the area to be planted is analyzed, and based on the location information, the soil moisture content corresponding to the area to be planted is inverted, the content distribution characteristics corresponding to the soil moisture content are identified, and based on the content distribution characteristics, an inversion report of the soil moisture in the area to be planted is generated.

2. The soil moisture inversion method based on microwave scattering mechanism and DNN model as claimed in claim 1 is characterized in that: The step of extracting the bipolar crop index from the preprocessed field data comprises: Performing data unit segmentation on the pre-processed field data to obtain data segmentation units; Extracting horizontal polarization data and vertical polarization data in the data segmentation unit; Performing filtering processing on the horizontal polarization data and the vertical polarization data to obtain horizontal polarization filtered data and vertical polarization filtered data; Calculating a dual polarization ratio corresponding to the preprocessed field data based on the horizontal polarization filter data and the vertical polarization filter data; Based on the dual-polarization ratio, a dual-polarization crop index in the pre-processed field data is determined.

3. The soil moisture inversion method based on microwave scattering mechanism and DNN model as claimed in claim 2 is characterized in that: The calculating, based on the horizontal polarization filter data and the vertical polarization filter data, a dual polarization ratio corresponding to the pre-processed field data comprises: The dual polarization ratio corresponding to the preprocessed field data is calculated.

4. The soil moisture inversion method based on microwave scattering mechanism and DNN model according to claim 1 is characterized in that: The step of determining the growth periods corresponding to different types of plants in the to-be-planted area based on the surface crop parameters includes: Performing parameter screening on the surface crop parameters to obtain crop screening parameters; Identifying the crop characteristics corresponding to the crop screening parameters, and querying the crop characteristic index corresponding to the crop characteristics; Based on the crop characteristic index, analyzing the cycle stage corresponding to the surface crop parameter; Based on the cycle stage, the growth periods corresponding to different types of plants in the area to be planted are determined.

5. The soil moisture inversion method based on microwave scattering mechanism and DNN model according to claim 1 is characterized in that: The backscattering simulation is performed on the growth periods of different plants in the to-be-planted area based on the preset microwave scattering mechanism model to obtain backscattering simulation parameters, including: Collecting detailed parameters of the growth periods corresponding to different types of plants in the area to be planted; Based on the detailed parameters, setting parameters of a preset microwave scattering mechanism model; And using the coupled microwave scattering model with set parameters, the crop framework corresponding to the area to be planted is constructed; identifying crop frame parameters corresponding to the crop frame; Backscattering simulation is performed on the crop frame parameters to obtain backscattering simulation parameters.

6. The soil moisture inversion method based on microwave scattering mechanism and DNN model according to claim 1 is characterized in that: The querying of the time observation sequence in the actual observation value comprises: Collecting a complete data set corresponding to the actual observation value, and extracting the observation fields in the complete data set; Standardizing the observed field to obtain a standardized field; Mark the field index corresponding to the standardized field, and set the time interval corresponding to the field index; Based on the time interval, a time observation sequence in the actual observation value is queried.

7. The soil moisture inversion method based on microwave scattering mechanism and DNN model according to claim 1 is characterized in that: The method combines the preset DNN model with the time observation sequence to construct a multi-source time series feature data set corresponding to the area to be planted, including: Identify the appropriate format for data in the preset DNN model; Based on the adaptation format, adjusting the sequence observation data corresponding to the time observation sequence; Extracting multi-source sequence features from the sequence observation data; Performing vector conversion on the multi-source sequence features to obtain a multi-source feature vector; The multi-source feature vectors are processed in time series using a preset DNN model to obtain a multi-source time series feature data set corresponding to the area to be planted.

8. The soil moisture inversion method based on microwave scattering mechanism and DNN model according to claim 1 is characterized in that: The inverting of the soil moisture content corresponding to the to-be-planted area based on the location information includes: Querying the geographic coordinates in the location information; Based on the geographic coordinates, analyzing the land use type corresponding to the to-be-planted area; Based on the land use type, determining the coverage area corresponding to the to-be-planted area; Based on the coverage, analyzing the soil moisture content in the to-be-planted area; Based on the soil moisture ratio, the soil moisture content corresponding to the area to be planted is inverted.

9. The soil moisture inversion system based on microwave scattering mechanism and DNN model is characterized by: The system is used to perform the soil moisture inversion method based on microwave scattering mechanism and DNN model as described in any one of claims 1 to 8, and the system comprises: A field data module is used to obtain field-related data corresponding to the area to be planted, wherein the field-related data includes: dual-polarization spaceborne SAR data, multi-spectral satellite remote sensing data and field observation data; A crop parameter module, used to perform data preprocessing on the field-related data to obtain preprocessed field data, extract a dual-polarization crop index in the preprocessed field data, query a surface crop parameter corresponding to the dual-polarization crop index, and determine the growth period corresponding to different plants in the to-be-planted area based on the surface crop parameter; An observation value calculation module is used to perform backscattering simulation on the growth periods corresponding to different types of plants in the to-be-planted area based on a preset microwave scattering mechanism model, obtain backscattering simulation parameters, and calculate actual observation values ​​corresponding to the backscattering simulation parameters; A feature extraction module is used to query the time observation sequence in the actual observation value, combine the preset DNN model with the time observation sequence, construct a multi-source time series feature data set corresponding to the to-be-planted area, and extract multi-source feature data in the multi-source time series feature data set; A report generation module is used to analyze the location information of the plants in the area to be planted based on the multi-source feature data, invert the soil moisture content corresponding to the area to be planted based on the location information, identify the content distribution characteristics corresponding to the soil moisture content, and generate an inversion report of the soil moisture in the area to be planted based on the content distribution characteristics.

Images