Spectrum-based rice ammonia phosphorus and potassium deficiency and yield estimation method and system

Abstract

The invention relates to the technical field of rice planting, and particularly discloses a spectrum-based rice ammonia phosphorus and potassium deficiency and yield estimation method and system, and the method comprises the steps: obtaining the spectrum data of a rice field block; performing correction processing on the spectral data to obtain reflectivity data of the rice canopy; extracting spectral characteristic parameters about ammonia, phosphorus and potassium nutrient states according to the reflectivity data of the rice canopy; performing spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters about the paddy field blocks; analyzing and acquiring a nutrient loss diagnosis result by combining the numerical value of the spectral characteristic parameter and the spatial distribution characteristic information; estimating the yield of the paddy field blocks according to the nutrient deficiency diagnosis result; according to the method, the problem of inaccurate diagnosis caused by easy confusion of spectral information in the prior art is solved, the accuracy of nutrient deficiency diagnosis is improved, and then the precision of rice yield estimation is improved.

Description

Technical Field

[0001] The present application relates to the field of rice planting technology, and in particular to a spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method and system. Background Art

[0002] As a vital food crop, rice growth monitoring technology is developing in a non-contact, non-destructive manner. Remote sensing spectroscopy, by acquiring reflectance data from the rice canopy, can calculate vegetation indices and spectral characteristic parameters. These parameters are closely correlated with plant physiological and biochemical parameters and can be used to diagnose nutrient deficiencies such as ammonia, phosphorus, and potassium, as well as to estimate yield.

[0003] However, in real farmland environments, rice growth is influenced by multiple factors. In addition to nutrient status, biotic and abiotic stressors such as disease, insect pests, and drought are also prevalent. These stressors can also cause changes in the physiological and biochemical state of rice plants, leading to alterations in the canopy's spectral response. The problem is that different types of stressors can exhibit similar spectral signatures, resulting in spectral information confusion. This spectral confusion makes it difficult for nutrient deficiency diagnosis models based solely on spectral data to accurately distinguish true nutrient problems from anomalies caused by other stresses. Models may mistakenly interpret spectral anomalies caused by non-nutrient stress as nutrient deficiency, leading to incorrect diagnostic results and inappropriate fertilization recommendations. Conversely, when multiple stresses coexist, the spectral responses of interfering factors such as disease can mask the signatures of nutrient deficiency, resulting in missed diagnoses and difficulties in accurate yield prediction, ultimately adversely affecting rice health and yield potential.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a spectral-based rice ammonia, phosphorus and potassium deficiency and yield prediction method and system to solve the problem that spectral information is easily confused and leads to inaccurate diagnosis, improve the accuracy of nutrient deficiency diagnosis, and thus improve the accuracy of rice yield estimation.

[0006] In a first aspect, the present application provides a spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method for estimating the yield of rice fields, the method comprising the following steps: S1, obtain spectral data of rice fields; S2. performing correction processing on the spectral data to obtain reflectance data of the rice canopy; S3. extracting spectral characteristic parameters related to the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy; S4. performing spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters with respect to the rice field; S5. Determine whether nutrient deficiency occurs in the rice field based on the numerical value of the spectral characteristic parameter and the spatial distribution characteristic information, and obtain a nutrient deficiency diagnosis result by analyzing if nutrient deficiency occurs; S6. Estimating the yield of the rice field according to the nutrient deficiency diagnosis result.

[0007] The spectral-based rice ammonia, phosphorus and potassium deficiency and yield estimation method of the present application determines whether there is nutrient deficiency in the rice field by combining the numerical information of spectral characteristic parameters with the spatial distribution characteristic information obtained by spatial analysis, thereby effectively distinguishing anomalies caused by nutrient deficiency from spectral anomalies caused by other stress factors. It solves the problem in the existing technology that spectral information is easily confused and leads to inaccurate diagnosis, improves the accuracy of nutrient deficiency diagnosis, and thus improves the accuracy of rice yield estimation, providing a scientific basis for precise fertilization and management of rice.

[0008] The spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, wherein the correction process includes radiation calibration and geometric correction; step S2 includes: S21, performing radiometric calibration and geometric correction on the spectral data to obtain preliminary reflectivity data and corresponding position information; S22. Filter the preliminary reflectivity data based on the reflectivity characteristics of pixels of different ground object types to obtain reflectivity data on rice canopy pixels.

[0009] The method of the present application eliminates the errors caused by sensors and observation geometry by performing radiometric calibration and geometric correction on the original spectral data; further, by screening based on the reflectance characteristics of pixels of different land object types, the interference information of non-rice canopy objects such as water bodies and soil is effectively removed, and pure rice canopy reflectance data is obtained, thereby improving data quality and providing accurate and reliable basic data for subsequent nutrient diagnosis and yield estimation.

[0010] The spectral-based rice ammonia, phosphorus, potassium deficiency and yield estimation method, wherein the correction process also includes atmospheric correction, step S2 further includes: S23. Performing atmospheric correction on the reflectance data of the rice canopy pixels.

[0011] The spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, wherein step S2 further comprises: S24, obtaining observation geometry information corresponding to the spectral data; S25. Perform bidirectional reflection distribution characteristic correction based on the observation geometry information and the reflectivity data after atmospheric correction to obtain reflectivity data of the rice canopy under standard observation geometry.

[0012] The spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, wherein step S3 comprises: S31, obtaining a range or combination of target bands related to the ammonia, phosphorus, and potassium nutrient status of the rice based on the rice growth period information and / or variety information of the rice field; S32. Obtain spectral characteristic parameters regarding the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy and the band range or band combination, wherein the spectral characteristic parameters include a vegetation index, a reflectance combination value of a target band, and an absorption peak characteristic value.

[0013] The spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, wherein step S31 comprises: S311, obtaining current growth period information and / or variety information of the rice field; S312. According to the current growth period information and / or variety information, search for a range or combination of target bands related to the ammonia, phosphorus, and potassium nutrient status from preset corresponding relationship data.

[0014] The spectral-based rice ammonia, phosphorus, potassium deficiency and yield estimation method, wherein step S4 comprises: S41, obtaining spatial position information corresponding to the spectral characteristic parameters; S42, calculating a global spatial autocorrelation index and a local spatial autocorrelation index of the spectral characteristic parameter according to the spectral characteristic parameter value and the spatial position information; S43. Acquire spatial distribution characteristic information of the spectral characteristic parameters according to the global spatial autocorrelation index and the local spatial autocorrelation index, where the spatial distribution characteristic information includes overall spatial aggregation characteristics and local significant areas of the spectral characteristic parameters.

[0015] The spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, wherein step S43 comprises: S431, judging the type of the overall spatial aggregation characteristics of the spectral feature parameters according to the value of the global spatial autocorrelation index and its statistical significance; S432: Identify a local significant region of the spectral characteristic parameter according to the value of the local spatial autocorrelation index and its statistical significance.

[0016] In the spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method, the nutrient deficiency diagnosis result includes the deficiency type, deficiency area, and deficiency severity. Step S6 includes: S61, obtaining the expected yield of the rice field in the absence of nutrient deficiency; S62. Based on a preset rule or prediction model, according to the type of deficiency and the severity of deficiency, predict the deficiency yield for the corresponding deficiency area to obtain a yield loss value; S63. Calculate and obtain the predicted yield of the rice field based on the yield loss value and the expected yield.

[0017] In a second aspect, the present application also provides a spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation system for estimating yield of rice fields, the system comprising: Acquisition module, used to obtain spectral data of rice fields; a correction module, configured to perform correction processing on the spectral data to obtain reflectance data of the rice canopy; a feature extraction module for extracting spectral feature parameters related to the nutrient status of ammonia, phosphorus and potassium based on the reflectance data of the rice canopy; A spatial analysis module, configured to perform spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters on rice fields; a diagnosis module for determining whether nutrient deficiency occurs in the rice paddy field based on the numerical value of the spectral characteristic parameter and the spatial distribution characteristic information, and analyzing and obtaining a nutrient deficiency diagnosis result if nutrient deficiency occurs; An estimation module is used to estimate the yield of the rice field according to the nutrient deficiency diagnosis result.

[0018] The spectral-based rice ammonia, phosphorus and potassium deficiency and yield estimation system of the present application determines whether there is nutrient deficiency in rice fields by combining the numerical information of spectral characteristic parameters with the spatial distribution characteristic information obtained by spatial analysis, thereby effectively distinguishing anomalies caused by nutrient deficiency from spectral anomalies caused by other stress factors, thereby improving the accuracy of rice yield estimation.

[0019] From the above, it can be seen that the present application provides a spectral-based rice ammonia, phosphorus and potassium deficiency and yield estimation method and system, wherein the spectral-based rice ammonia, phosphorus and potassium deficiency and yield estimation method of the present application determines whether there is nutrient deficiency in the rice field by combining the numerical information of spectral characteristic parameters with the spatial distribution characteristic information obtained by spatial analysis, thereby effectively distinguishing the anomalies caused by nutrient deficiency from the spectral anomalies caused by other stress factors, solving the problem in the prior art that spectral information is easily confused and leads to inaccurate diagnosis, improving the accuracy of nutrient deficiency diagnosis, and thus improving the accuracy of rice yield estimation, providing a scientific basis for precise fertilization and management of rice. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the spectral-based rice ammonia, phosphorus, potassium deficiency and yield estimation method provided in an embodiment of the present application.

[0021] Figure 2 Schematic diagram of the structure of the spectral-based rice ammonia, phosphorus and potassium deficiency and yield prediction system provided in the embodiments of the present application.

[0022] Reference numerals: 201, acquisition module; 202, correction module; 203, feature extraction module; 204, spatial analysis module; 205, diagnosis module; 206, estimation module. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0025] First, please refer to Figure 1 Some embodiments of the present application provide a spectral-based rice ammonia, phosphorus, and potassium deficiency and yield estimation method for estimating the yield of a rice field. The method comprises the following steps: S1, obtain spectral data of rice fields; S2. Correcting the spectral data to obtain reflectance data of the rice canopy; S3. Extracting spectral characteristic parameters related to the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy; S4. performing spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters on the rice fields; S5. Determine whether nutrient deficiency occurs in the rice field by combining the numerical value and spatial distribution characteristic information of the spectral characteristic parameters, and obtain nutrient deficiency diagnosis results by analysis if nutrient deficiency occurs; S6. Estimate the yield of rice fields based on the nutrient deficiency diagnosis results.

[0026] Specifically, spectral data refers to electromagnetic spectrum information acquired by sensors. This data can be acquired in a variety of ways, such as using spectral sensors mounted on drones, satellites, or ground platforms. It provides raw spectral response information of the rice canopy. Correction processing involves preprocessing the raw spectral data to eliminate or mitigate the effects of external factors (such as the atmosphere, sensor characteristics, and observation geometry) on the spectral information. This is used to obtain reflectance data that accurately reflects the characteristics of the rice canopy. Rice canopy reflectance data refers to the corrected reflectance values of the rice canopy at different wavelengths. This is a physical quantity directly related to the physiological and biochemical state of rice and serves as the basis for extracting spectral characteristic parameters. Spectral characteristic parameters are indicators related to the nutrient status of rice extracted from rice canopy reflectance data. These can take the form of vegetation indices (such as NDVI and EVI), reflectance combinations in specific bands, or characteristic absorption peak values. They are primarily used to quantify the nutrient status of rice. Spatial analysis involves analyzing the spatial distribution of spectral characteristic parameters within rice fields using tools such as geographic information systems. Methods such as spatial autocorrelation analysis, cluster analysis, and hotspot analysis can be employed. It primarily aims to reveal patterns and patterns in the spatial variation of spectral characteristic parameters. Spatial distribution information refers to the spatial distribution characteristics of spectral characteristic parameters obtained through spatial analysis. This includes overall spatial aggregation characteristics (e.g., clustered, dispersed, or random) as well as localized areas of significant significance (e.g., clusters of high or low values). It primarily provides spatial clues to possible nutrient deficiencies. Combining the numerical values of spectral characteristic parameters with spatial distribution information for diagnosis considers both whether the spectral characteristic parameter values are abnormal and whether the abnormal areas exhibit specific spatial distribution patterns. This approach primarily distinguishes anomalies caused by nutrient deficiency from those due to other localized stresses, improving diagnostic accuracy. Nutrient deficiency diagnostic results refer to the data associated with determining the presence of nutrient deficiency in a rice field, providing detailed information for subsequent yield estimation and precision management. Yield estimation refers to the diagnosis of nutrient deficiency, which can adopt a calculation method based on loss value or a regression method based on a prediction model. It is mainly used to guide agricultural production decisions.

[0027] Specifically, the method of the present application first acquires raw spectral data from a rice paddy. This data contains reflectance information from the rice canopy at different wavelengths. Next, the raw spectral data is corrected as necessary to eliminate the effects of the external environment and the sensor itself, resulting in reflectance data that truly reflects the characteristics of the rice canopy. Based on this reflectance data, spectral characteristic parameters related to the ammonia, phosphorus, and potassium nutrient status of the rice are extracted. These parameters are sensitive indicators of the rice's nutrient level. Subsequently, spatial analysis is performed on the extracted spectral characteristic parameters to obtain information on the spatial distribution characteristics of these parameters within the entire rice paddy, revealing their spatial aggregation or dispersion patterns. When determining nutrient deficiency, the method no longer relies solely on whether the spectral characteristic parameter values are below a threshold. Instead, the parameter values are combined with the spatial distribution characteristics obtained through spatial analysis. For example, a diagnosis of nutrient deficiency is more likely only when areas with low values exhibit a specific spatial aggregation pattern. This combined judgment method can effectively eliminate random or localized spectral anomalies caused by non-nutrient stresses such as sporadic pests and diseases and localized drought, thereby more accurately identifying the true area, type, and severity of nutrient deficiency. Ultimately, the yield of rice fields is estimated based on accurate nutrient deficiency diagnosis results, and more reliable yield predictions are obtained by taking into account the impact of nutrient deficiency on yield.

[0028] The spectral-based rice ammonia, phosphorus and potassium deficiency and yield estimation method of the present application determines whether there is nutrient deficiency in the rice field by combining the numerical information of spectral characteristic parameters with the spatial distribution characteristic information obtained by spatial analysis, thereby effectively distinguishing anomalies caused by nutrient deficiency from spectral anomalies caused by other stress factors. It solves the problem in the existing technology that spectral information is easily confused and leads to inaccurate diagnosis, improves the accuracy of nutrient deficiency diagnosis, and thus improves the accuracy of rice yield estimation, providing a scientific basis for precise fertilization and management of rice.

[0029] In some preferred embodiments, the correction process includes radiometric calibration and geometric correction; step S2 includes: S21, performing radiometric calibration and geometric correction on the spectral data to obtain preliminary reflectivity data and corresponding position information; S22. Preliminary reflectance data are screened based on the reflectance characteristics of pixels of different ground object types to obtain reflectance data of rice canopy pixels.

[0030] Specifically, different ground object types include rice canopy pixels, water pixels, and soil pixels. Rice canopy pixels refer to ground pixels primarily covered by the canopy of rice plants. Water pixels refer to ground pixels primarily covered by water. Soil pixels refer to ground pixels primarily covered by soil.

[0031] More specifically, radiometric calibration converts the raw digital signals received by the sensor into physically meaningful radiance or reflectance values. Geometric correction corrects the spatial distortion of the image so that points on the image accurately correspond to their actual locations on the ground. This can be achieved using methods based on ground control points or sensor trajectory and attitude parameters.

[0032] More specifically, the reflectance characteristics of pixels of different land object types refer to the differences in spectral reflectance of different land objects (such as rice canopy, water bodies, and soil) in different bands, which can be characterized by analyzing the spectral curves of typical land objects or calculating the spectral index.

[0033] Specifically, this solution refines and improves the correction processing steps for obtaining rice canopy reflectance data. First, radiometric calibration processes the raw digital signals received by the sensor, converting them into physically meaningful radiance or reflectance values. This eliminates the impact of sensor response variations and ensures data comparability. Geometric correction corrects spatial image distortion, ensuring that points on the image accurately correspond to their actual locations on the ground, laying the foundation for subsequent spatial analysis. Furthermore, step S22 further filters the preliminary reflectance data by analyzing the differences in spectral reflectance characteristics of different ground features (such as rice canopies, water bodies, and soil). This effectively removes background interference and ensures that the final reflectance data is derived solely from the rice canopy itself. This precise screening of rice canopy pixels improves the purity and accuracy of the reflectance data, providing more reliable foundational data for the subsequent extraction of spectral characteristic parameters related to rice nutrient status, thereby improving the accuracy of nutrient deficiency diagnosis and yield estimation.

[0034] Through the above scheme, the method of the present application eliminates the errors caused by sensors and observation geometry by performing radiometric calibration and geometric correction on the original spectral data; further, by screening based on the reflectance characteristics of pixels of different land object types, the interference information of non-rice canopy objects such as water bodies and soil is effectively removed, and pure rice canopy reflectance data is obtained, which improves the data quality and provides accurate and reliable basic data for subsequent nutrient diagnosis and yield estimation.

[0035] In some preferred embodiments, the correction process further includes atmospheric correction, and step S2 further includes: S23. Perform atmospheric correction on the reflectance data of rice canopy pixels.

[0036] Specifically, atmospheric correction eliminates or mitigates the atmospheric influence on the electromagnetic wave signals received by remote sensing sensors, converting the apparent reflectance data received by the sensors into the true reflectance data of the ground objects. Atmospheric correction can be implemented using a variety of models or algorithms, such as those based on radiation transfer models (such as MODTRAN and the 6S model), methods based on image information (such as the dark target method and histogram matching), or methods based on synchronous ground measurement data. The specific execution logic is not detailed here.

[0037] Specifically, this solution adds an atmospheric correction step to step S22. By performing atmospheric correction on the selected rice canopy pixel reflectance data, the effects of atmospheric absorption and scattering are removed, converting the apparent reflectance data into data closer to the true reflectance of the rice canopy. This improves the accuracy of subsequent spectral feature parameter extraction, thereby enhancing the accuracy of nutrient deficiency diagnosis and yield estimation, and resolving the issue of spectral data inaccuracy caused by atmospheric influences.

[0038] In some preferred embodiments, step S2 further includes: S24, obtaining observation geometry information corresponding to the spectral data; S25. Perform bidirectional reflection distribution characteristic correction based on the observation geometry information and the reflectance data after atmospheric correction to obtain reflectance data of the rice canopy under standard observation geometry.

[0039] Specifically, observation geometry information refers to the relative positional relationship between the sensor, target object, and the sun when the remote sensing sensor acquires an image. It can be described by parameters such as the solar zenith angle, solar azimuth angle, sensor zenith angle, sensor azimuth angle, and relative azimuth angle. Bidirectional reflectance distribution characteristic correction refers to eliminating or reducing the influence of observation geometry on the reflectance measurement of the object based on the bidirectional reflectance distribution characteristic model or empirical method of the object, and normalizing the reflectance data obtained under different observation geometries to a preset standard observation geometry. Standard observation geometry refers to the reference observation angle used to normalize the reflectance data. For example, it can be set to the observation conditions when the sensor zenith angle is 0 degrees (nadir observation) and the solar zenith angle is a fixed angle.

[0040] Specifically, remote sensing images usually contain the observation geometry parameters at the time of acquisition in their metadata. These parameters can be used to quantify the impact of different observation angles on reflectivity. Step S25 performs bidirectional reflectance distribution characteristic correction based on the acquired observation geometry information and the rice canopy reflectivity data that has been atmospherically corrected. This correction process applies a bidirectional reflectance distribution characteristic model or algorithm to adjust the reflectivity values measured at different observation angles to equivalent reflectivity values under a preset standard observation geometry. For example, all data can be corrected to the reflectivity under nadir observation conditions. In this way, the reflectivity changes introduced by differences in observation angles are eliminated, making the rice canopy reflectivity data acquired at different times, different sensors or different observation angles more comparable. The rice canopy reflectivity data under standard observation geometry obtained after bidirectional reflectance distribution characteristic correction provides a more stable and reliable input for the subsequent extraction of spectral characteristic parameters related to nutrient status.

[0041] Step S25, combined with pre-processing steps such as radiometric calibration, geometric correction, object screening, and atmospheric correction, operates on the raw spectral data, progressively eliminating external interference factors and gradually extracting information from the raw signal that better reflects the true reflectance characteristics of the rice canopy. Radiometric calibration and geometric correction provide basic spatial and radiometric accuracy; object screening ensures that only the rice area is analyzed; atmospheric correction eliminates the effects of atmospheric scattering and absorption; and bidirectional reflectance distribution correction further eliminates the influence of observation angle. This comprehensive correction process results in purer and more accurate reflectance data, significantly improving the reliability of rice nutrient diagnosis and yield estimation based on these data.

[0042] In some preferred embodiments, the spectral characteristic parameters include: a vegetation index, a red edge parameter, a narrow band spectral index, a reflectance combination value of a vegetation pigment related band, and an absorption peak characteristic value.

[0043] Specifically, the vegetation index reflects vegetation biomass and chlorophyll content. The vegetation index is a commonly used parameter to reflect vegetation growth status and pigment content. By extracting the vegetation index, we can understand the overall growth and chlorophyll level of the plant, which is closely related to the nutrient status. The vegetation index includes the normalized difference vegetation index calculated based on the reflectance of the red light band and the near-infrared band, and specifically points out the commonly used normalized difference vegetation index (NDVI). NDVI is calculated based on the reflectance of the red light and near-infrared bands and is sensitive to vegetation cover and chlorophyll content. Calculating NDVI based on the reflectance of the red light and near-infrared bands utilizes the typical characteristics of these two bands in the vegetation spectrum. It can reflect the health status and biomass of vegetation and provide basic information for nutrient diagnosis.

[0044] More specifically, the red edge parameter reflects the health and ammonia status of vegetation. The red edge is a rapidly rising area of the vegetation spectrum between the red and near-infrared bands, and its position and slope are very sensitive to the physiological state of vegetation. Extracting the red edge parameters can more finely capture the changes in vegetation in this key band, provide supplementary information for judging vegetation health and ammonia status, and help distinguish ammonia deficiency from other stresses. Changes in the red edge position are related to chlorophyll content and ammonia levels, and the red edge slope reflects the rate of change of chlorophyll content. Calculating the red edge position and red edge slope based on reflectance data takes advantage of the sensitivity of the red edge area to the physiological state of vegetation, and can provide more subtle physiological information than simple vegetation indices, enhancing the ability to judge ammonia status and health.

[0045] More specifically, narrowband spectral indices reflect the status of specific nutrients. These indices are calculated based on the reflectance of specific narrow bands, which may be associated with the absorption or reflectance characteristics of specific nutrients. Extracting narrowband spectral indices can capture targeted spectral information related to specific nutrients such as phosphorus and potassium, complementing the lack of vegetation indices and red edge parameters, which primarily focus on ammonia and biomass, thereby providing a more comprehensive basis for nutrient diagnosis.

[0046] More specifically, the reflectance combination values and absorption peak characteristic values of vegetation pigment-related bands also provide spectral information related to the physiological and biochemical components of vegetation, further enriching the feature set used for diagnosis.

[0047] More specifically, the extraction of these multiple spectral characteristic parameters, combined with the acquisition of rice canopy reflectance data and subsequent spatial analysis, nutrient deficiency judgment and yield estimation steps, provides richer and more discriminatory information, which helps to improve the accuracy of nutrient deficiency diagnosis and overcome the problem that single or general spectral parameters are easily interfered with by other stress factors, thereby improving the robustness and accuracy of the entire diagnosis and estimation method.

[0048] In some preferred embodiments, step S3 includes: S31. Obtaining a range or combination of target bands related to the ammonia, phosphorus, and potassium nutrient status of the rice based on the rice growth period information and / or variety information of the rice field; S32. Obtain spectral characteristic parameters regarding the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy and the band range or band combination. The spectral characteristic parameters include a vegetation index, a reflectance combination value of a target band, and an absorption peak characteristic value.

[0049] Specifically, step S31 can be implemented by consulting a pre-established correspondence table, using a machine learning model for prediction, or dynamically determining through spectral analysis. Its introduction is intended to enable the subsequently extracted spectral characteristic parameters to more centrally reflect nutrient information and reduce interference from non-nutrient factors.

[0050] More specifically, step S32 is used to calculate or extract spectral indicators that can characterize the nutrient status of rice, with the purpose of converting the original spectral reflectance data into quantitative indicators that are more closely related to the nutrient status.

[0051] Specifically, when extracting spectral characteristic parameters of nutrient status from rice canopy reflectance data, the method of the present application first obtains the growth period information and / or variety information of the current rice field. This is because the physiological and biochemical characteristics of rice are different in different growth periods, and there are also differences between different varieties. These differences lead to different canopy spectral responses and sensitive bands to nutrient deficiency. Based on these specific growth period and / or variety information, the method of the present application determines the target band range or combination that is more closely related to the current ammonia, phosphorus, and potassium nutrient status of the rice. This means that fixed bands or band combinations are no longer used, but spectral information that best reflects the nutrient status is selected according to the specific situation of the rice. Subsequently, the calibrated rice canopy reflectance data is used, and combined with the determined target band range or combination, the spectral characteristic parameters of the ammonia, phosphorus, and potassium nutrient status are calculated and obtained. These parameters can be vegetation indices, reflectance combination values of target bands, or absorption peak characteristic values. By extracting characteristic parameters within a selected target band or using a selected band combination, spectral signals related to the ammonia, phosphorus, and potassium nutrient status of rice can be more accurately captured, reducing the influence of irrelevant spectral information or interfering signals. This dynamic band selection and feature extraction method based on growth period and / or variety information improves the correlation between the extracted characteristic parameters and nutrient status, providing a more reliable data foundation for subsequent nutrient deficiency diagnosis and yield estimation.

[0052] Through the above scheme, the method of the present application can select spectral bands or combinations that are more closely related to the nutrient status to extract characteristic parameters according to the specific growth period and variety of rice, so that the extracted spectral characteristic parameters can more accurately reflect the true nutrient status of rice, reduce the interference of other non-nutrient factors on the diagnostic results, and improve the reliability of nutrient deficiency diagnosis and yield estimation.

[0053] In some preferred embodiments, step S31 includes: S311, obtaining current growth period information and / or variety information of the rice field; S312. According to the current growth period information and / or variety information, search for a range or combination of target bands related to the nutrient status of ammonia, phosphorus, and potassium from preset corresponding relationship data.

[0054] Specifically, growth period information refers to the growth and development stages of rice from sowing to maturity, such as the greening stage, tillering stage, jointing stage, heading stage, grain filling stage, and maturity stage. Variety information refers to the specific rice variety type. Different varieties vary in genetic characteristics, morphological features, and growth habits. This information can be obtained through farmer records, field identification, and variety database queries.

[0055] More specifically, the preset correspondence data refers to a pre-established data set that stores the spectral band ranges or combinations associated with different rice growth periods and / or varieties and specific nutrient (ammonia, phosphorus, potassium) status, which can be stored in the form of tables, databases, lookup tables, etc.

[0056] Through the above-mentioned processing, the method of the present application can dynamically select the spectral band or combination that is most suitable for reflecting the nutrient status according to the specific growth period and / or variety information of rice, thereby improving the correlation between the extracted spectral characteristic parameters and the actual nutrient status, reducing the interference of other non-nutrient stress factors, and making subsequent nutrient deficiency diagnosis and yield estimation more accurate and reliable.

[0057] In some preferred embodiments, step S4 includes: S41, obtaining spatial position information corresponding to the spectral characteristic parameters; S42, calculating the global spatial autocorrelation index and the local spatial autocorrelation index of the spectral characteristic parameter according to the spectral characteristic parameter value and the spatial position information; S43. Obtain spatial distribution characteristic information of the spectral characteristic parameters according to the global spatial autocorrelation index and the local spatial autocorrelation index. The spatial distribution characteristic information includes the overall spatial aggregation characteristics of the spectral characteristic parameters and the local significant area.

[0058] Specifically, spatial location information refers to the specific coordinates or location identifiers of spectral characteristic parameters in geographic space, which can be implemented using pixel row and column numbers, geographic coordinates (such as longitude and latitude), or plane coordinates based on a specific projection system.

[0059] More specifically, the global spatial autocorrelation index refers to a statistical indicator that measures the degree of spatial correlation of a variable (here, the spectral characteristic parameter) in the entire study area, which can be calculated using the Moran's I index, Geary's C index, or Getis-Ord General G index. The local spatial autocorrelation index refers to a statistical indicator that measures the degree of spatial correlation of a variable (here, the spectral characteristic parameter) between each spatial unit and its neighboring units. It is used to identify spatial aggregation or outlier patterns in local areas, which can be calculated using the Local Moran's I index, Getis-Ord Gi index, or The global spatial autocorrelation index and the local spatial autocorrelation index are commonly used in spatial analysis, and their specific calculation methods are not described here.

[0060] More specifically, spatial distribution characteristic information refers to the spatial distribution pattern and regularity of spectral characteristic parameters revealed by spatial analysis methods, which can be represented by the results of spatial autocorrelation analysis, spatial clustering analysis or spatial interpolation analysis.

[0061] More specifically, the overall spatial clustering characteristic refers to the overall spatial distribution trend of the spectral characteristic parameters in the entire study area, that is, whether areas with similar values tend to cluster together, are randomly distributed, or are dispersed from each other, which can be judged based on the value of the global spatial autocorrelation index and its statistical significance. Locally significant areas refer to local spatial units or areas in the entire study area where the spectral characteristic parameter values show statistical characteristics that are significantly different from those of the surrounding areas, such as areas with significant high-value clustering, significant low-value clustering, or significant outliers of high and low values. They can be identified based on the value of the local spatial autocorrelation index and its statistical significance.

[0062] Specifically, step S41 obtains the spatial position information corresponding to the spectral characteristic parameters, which provides basic data for subsequent spatial analysis. In step 42, the global spatial autocorrelation index is used to evaluate the average spatial correlation of the spectral characteristic parameters within the entire field, and to determine whether its overall distribution is clustered, dispersed or random; the local spatial autocorrelation index evaluates the correlation between each spatial unit and its adjacent units, thereby identifying statistically significant local clusters or outlier areas. Step S43 concretizes the spatial analysis of spectral characteristic parameters through a method based on spatial autocorrelation analysis, expanding from focusing only on numerical values to focusing on their distribution patterns in space. This spatial distribution information, especially the identification of low-value clustered areas, provides a specific and effective spatial basis for the subsequent steps to combine numerical and spatial information to make nutrient deficiency judgments.

[0063] By combining the numerical information of spectral characteristic parameters with spatial distribution characteristic information, the method of this application can more effectively identify abnormal areas caused by nutrient deficiency. Because nutrient deficiency is often manifested as poor plant growth in a specific area, resulting in low spectral characteristic parameter values, and these low-value areas are often clustered in space. This spatial clustering pattern helps distinguish nutrient deficiency from other randomly distributed stress factors (such as sporadic pests and diseases or accidental mechanical damage), thereby overcoming the spectral information confusion problem mentioned in the background technology and improving the accuracy of nutrient deficiency diagnosis.

[0064] In some preferred embodiments, step S43 includes: S431. Determine the type of overall spatial aggregation characteristics of the spectral characteristic parameters based on the value of the global spatial autocorrelation index and its statistical significance; S432. Identify the local significant region of the spectral characteristic parameters according to the value of the local spatial autocorrelation index and its statistical significance.

[0065] Specifically, statistical significance refers to the degree to which statistical tests are used to determine whether the observed spatial pattern is generated by a random process. It can be judged by using statistics such as p-value and Z-value combined with a preset significance level.

[0066] More specifically, in the embodiment of the present application, the types of overall spatial aggregation characteristics include spatial aggregation, spatial dispersion or spatial random distribution; the local significant areas include high-value aggregation areas, low-value aggregation areas or high-low value outlier areas.

[0067] Specifically, the method of the present application, through step S431, can clearly determine whether the spectral characteristic parameters show a spatially clustered, spatially dispersed, or spatially randomly distributed pattern across the entire rice field based on the numerical value of the global spatial autocorrelation index and its statistical test results. For example, a positive and statistically significant global index indicates spatial clustering, a negative and statistically significant index indicates spatial dispersion, and an insignificant index indicates spatially random distribution. This judgment provides a basis for understanding the overall spatial pattern of nutrient status. Secondly, the method of the present application, through step S432, can identify local areas that exhibit significantly different patterns from surrounding areas based on the numerical value of the local spatial autocorrelation index and its statistical test results. For example, if the local index is positive and statistically significant and the parameter value at that location is high, it is identified as a high-value clustered area; if the local index is positive and statistically significant and the parameter value at that location is low, it is identified as a low-value clustered area; and if the local index is negative and statistically significant, it is identified as a high-low value outlier area. These locally significant areas correspond to places where the spectral characteristic parameters show abnormal spatial clustering or outliers. By identifying these areas and differentiating their types, we can precisely locate potential areas of nutrient excess, nutrient deficiency, or boundary anomalies. Determination of overall spatial clustering provides macroscopic spatial pattern information, while identification of localized significant areas provides microscopic key location information. These two types of information combined form a complete spatial distribution profile of spectral characteristic parameters, providing a precise and geographically meaningful spatial basis for subsequent nutrient deficiency diagnosis.

[0068] In some preferred embodiments, step S5 includes: S51, based on a preset characteristic threshold, identifying abnormal areas in the rice field where the values of the spectral characteristic parameters are lower than the preset threshold; S52. Based on the abnormal area and the local significant area, determine whether the abnormal area conforms to the spatial distribution pattern of nutrient deficiency; S53. When the spatial distribution pattern of nutrient deficiency is met, determining whether the rice field has nutrient deficiency based on the type of overall spatial aggregation characteristics; S54. When determining that nutrient deficiency exists, determining a nutrient deficiency area based on the abnormal area; S55, analyzing and obtaining the numerical deviation degree of different types of spectral characteristic parameters in the missing region; S56. Determine the deficiency type and deficiency severity according to the type of spectral characteristic parameters whose values are lower than a preset threshold and the corresponding degree of deviation of the values, and generate a nutrient deficiency diagnosis result in combination with the deficiency area.

[0069] Specifically, the preset characteristic threshold refers to the critical value used to distinguish normal and abnormal spectral characteristic parameter values, which can be determined based on historical data statistical analysis, expert experience knowledge, rice variety information or based on a specific diagnostic model.

[0070] More specifically, abnormal areas refer to spatial ranges within rice fields where spectral characteristic parameter values fall below preset thresholds. These areas indicate potential nutrient deficiencies or other stresses. The spatial distribution pattern of nutrient deficiency refers to the specific spatial morphology or clustering characteristics typically exhibited by nutrient deficiency within rice fields. For example, it may manifest as a continuous patch or a distribution associated with specific environmental factors. This can be determined through analysis and summary of spatial data from known nutrient-deficient fields or based on agronomic principles. Depletion areas refer to spatial ranges determined to actually contain nutrient deficiencies after determining the spatial distribution pattern. These areas are screened and confirmed from the initially identified abnormal areas. The degree of numerical deviation refers to the degree to which the actual values of different types of spectral characteristic parameters within the identified deficiency area deviate from normal levels or preset thresholds. This can be calculated using methods such as percentage deviation or standardized difference. The type of deficiency refers to the specific type of nutrient deficiency determined based on the type of spectral characteristic parameter whose value falls below the preset threshold. The severity of the deficiency refers to the severity level of the nutrient deficiency determined based on the degree of numerical deviation of the spectral characteristic parameter. The nutrient deficiency diagnosis result is the final diagnostic information that integrates the deficiency area, deficiency type, and deficiency severity.

[0071] Specifically, the method of the present application first preliminarily identifies areas with lower spectral characteristic parameter values in the rice field based on a preset characteristic threshold and the numerical value of the spectral characteristic parameters. These areas may be potential nutrient deficiency areas or areas affected by other stresses, and are defined as abnormal areas. Next, the method of the present application uses the local significant area information of the spectral characteristic parameters obtained in the spatial analysis to compare the preliminarily identified abnormal areas with these statistically significant local clusters or outlier areas. By judging whether the abnormal area conforms to the spatial distribution pattern usually exhibited by nutrient deficiency, for example, whether it is located in a low-value cluster area, it is possible to effectively distinguish abnormalities caused by nutrient deficiency from abnormalities caused by other random or different spatial patterns of stress, thereby reducing misdiagnosis. After confirming that the abnormal area conforms to the spatial distribution pattern of nutrient deficiency, the method of the present application further combines the overall spatial aggregation characteristics of the spectral characteristic parameters obtained in the spatial analysis, for example, whether the overall area presents low-value clustering, and judges whether the entire rice field has nutrient deficiency based on the type of overall spatial aggregation characteristics. This step once again verifies the possibility of nutrient deficiency from a macroscopic perspective. When it is determined that there is a nutrient deficiency, the method of the present application uses the previously identified abnormal area to accurately determine the specific spatial range of the nutrient deficiency, that is, the deficiency area. Subsequently, the different types of spectral characteristic parameters in the determined deficiency area are analyzed to calculate the degree of deviation of their values relative to the normal level or the preset threshold. Finally, based on the type of spectral characteristic parameters whose values are lower than the preset threshold and the corresponding degree of numerical deviation, combined with the determined deficiency area, a nutrient deficiency diagnosis result including the deficiency type, deficiency area and deficiency severity is generated. Through this diagnostic process that combines numerical thresholds, local spatial patterns and overall spatial characteristics, the method of the present application can more accurately identify and diagnose ammonia, phosphorus and potassium nutrient deficiencies in rice, providing a more reliable basis for subsequent yield estimation.

[0072] In some preferred embodiments, based on the above content, the nutrient deficiency diagnosis result includes the deficiency type, deficiency region, and deficiency severity. Step S6 includes: S61. Obtaining the expected yield of the rice field in the absence of nutrient deficiency; S62. Based on a preset rule or prediction model, according to the type and severity of the missing area, predict the missing yield for the corresponding missing area to obtain a yield loss value; S63. Calculate and obtain the predicted yield of the rice field based on the yield loss value and the expected yield.

[0073] Specifically, expected yield refers to the potential yield of a rice field under the condition of adequate nutrient supply and no nutrient stress, which can be obtained by means of historical yield data, simulation results based on crop growth models, or expert experience values. Preset rules or prediction models refer to algorithms or models used to establish a correspondence between the type and severity of nutrient deficiency and yield loss, which can be implemented by means of empirical formulas, table lookup methods, regression models, machine learning models, etc. The preset rules or prediction models are obtained by training based on historical spectral characteristic parameters and yield data. Missing yield prediction refers to estimating the yield reduction caused by nutrient deficiency based on the results of nutrient deficiency diagnosis. Yield loss value refers to the specific yield reduction value obtained through missing yield prediction. Predicted yield refers to the estimated yield obtained after comprehensively considering the potential yield of the field and the loss caused by nutrient deficiency.

[0074] Specifically, the method of the present application obtains the expected yield of a rice field plot in the absence of nutrient deficiencies in step S61. This provides a benchmark for yield estimation, namely the potential yield of the field plot under ideal nutrient supply, allowing subsequent yield estimates to reflect the actual yield reduction caused by nutrient deficiencies. Next, step S62, based on preset rules or prediction models, predicts the yield loss for these areas based on the deficiency type, deficiency severity, and corresponding deficiency area in the nutrient deficiency diagnosis results, thereby obtaining specific yield loss values. This step converts the qualitative or semi-quantitative nutrient deficiency diagnosis results into quantitative yield loss. The rules or models take into account the different impacts of different nutrient deficiency types and severities on yield, and the calculation is limited to the areas where the deficiency actually occurs, making the yield loss calculation more accurate and targeted. Finally, step S63 obtains the predicted yield of the rice field plot through a simple subtraction calculation based on the expected yield obtained in step S61 and the yield loss value calculated in step S62. This method combines potential yield with the loss caused by nutrient deficiencies, resulting in a predicted yield that is closer to actual conditions and improves the reliability of yield estimates.

[0075] Second, please refer to Figure 2 Some embodiments of the present application further provide a spectral-based rice ammonia, phosphorus, and potassium deficiency and yield prediction system for estimating the yield of rice fields, the system comprising: An acquisition module 201 is used to acquire spectral data of a rice field; A correction module 202 is used to perform correction processing on the spectral data to obtain reflectance data of the rice canopy; A feature extraction module 203 is used to extract spectral feature parameters related to the nutrient status of ammonia, phosphorus and potassium based on the reflectance data of the rice canopy; A spatial analysis module 204 is used to perform spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters on the rice fields; The diagnosis module 205 is used to determine whether nutrient deficiency occurs in the rice field by combining the numerical value and spatial distribution characteristic information of the spectral characteristic parameters, and to analyze and obtain the nutrient deficiency diagnosis result if nutrient deficiency occurs; The estimation module 206 is used to estimate the yield of the rice field according to the nutrient deficiency diagnosis result.

[0076] The spectral-based rice ammonia, phosphorus and potassium deficiency and yield prediction system of the present application determines whether there is nutrient deficiency in the rice field by combining the numerical information of spectral characteristic parameters with the spatial distribution characteristic information obtained by spatial analysis, thereby effectively distinguishing anomalies caused by nutrient deficiency from spectral anomalies caused by other stress factors. It solves the problem in the existing technology that spectral information is easily confused and leads to inaccurate diagnosis, improves the accuracy of nutrient deficiency diagnosis, and thus improves the accuracy of rice yield estimation, providing a scientific basis for precise fertilization and management of rice.

[0077] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0079] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0080] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A spectrum-based method for estimating rice ammonia, phosphorus, and potassium deficiency and yield, for estimating rice field yield, characterized by: The steps of the method include: S1, obtain spectral data of rice fields; S2. performing correction processing on the spectral data to obtain reflectance data of the rice canopy; S3. extracting spectral characteristic parameters related to the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy; S4. performing spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters with respect to the rice field; S5. Determine whether nutrient deficiency occurs in the rice field based on the numerical value of the spectral characteristic parameter and the spatial distribution characteristic information, and obtain a nutrient deficiency diagnosis result by analyzing if nutrient deficiency occurs; S6. Estimating the yield of the rice field according to the nutrient deficiency diagnosis result.

2. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 1, wherein: The correction process includes radiation calibration and geometric correction; step S2 includes: S21, performing radiometric calibration and geometric correction on the spectral data to obtain preliminary reflectivity data and corresponding position information; S22. Filter the preliminary reflectivity data based on the reflectivity characteristics of pixels of different ground object types to obtain reflectivity data on rice canopy pixels.

3. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 2, wherein: The correction process also includes atmospheric correction, and step S2 further includes: S23. Performing atmospheric correction on the reflectance data of the rice canopy pixels.

4. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 3, wherein: Step S2 further includes: S24, obtaining observation geometry information corresponding to the spectral data; S25. Perform bidirectional reflection distribution characteristic correction based on the observation geometry information and the reflectivity data after atmospheric correction to obtain reflectivity data of the rice canopy under standard observation geometry.

5. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 1, wherein: Step S3 includes: S31, obtaining a range or combination of target bands related to the ammonia, phosphorus, and potassium nutrient status of the rice based on the rice growth period information and / or variety information of the rice field; S32. Obtain spectral characteristic parameters regarding the nutrient status of ammonia, phosphorus, and potassium based on the reflectance data of the rice canopy and the band range or band combination, wherein the spectral characteristic parameters include a vegetation index, a reflectance combination value of a target band, and an absorption peak characteristic value.

6. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 5, wherein: Step S31 includes: S311, obtaining current growth period information and / or variety information of the rice field; S312. According to the current growth period information and / or variety information, search for a range or combination of target bands related to the ammonia, phosphorus, and potassium nutrient status from preset corresponding relationship data.

7. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 1, wherein: Step S4 includes: S41, obtaining spatial position information corresponding to the spectral characteristic parameters; S42, calculating a global spatial autocorrelation index and a local spatial autocorrelation index of the spectral characteristic parameter according to the spectral characteristic parameter value and the spatial position information; S43. Acquire spatial distribution characteristic information of the spectral characteristic parameters according to the global spatial autocorrelation index and the local spatial autocorrelation index, where the spatial distribution characteristic information includes overall spatial aggregation characteristics and local significant areas of the spectral characteristic parameters.

8. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 7, wherein: Step S43 includes: S431, judging the type of the overall spatial aggregation characteristics of the spectral feature parameters according to the value of the global spatial autocorrelation index and its statistical significance; S432: Identify a local significant region of the spectral characteristic parameter according to the value of the local spatial autocorrelation index and its statistical significance.

9. The method for estimating rice ammonia, phosphorus, potassium deficiency and yield based on spectroscopy according to claim 1, wherein: The nutrient deficiency diagnosis result includes the deficiency type, deficiency area and deficiency severity. Step S6 includes: S61, obtaining the expected yield of the rice field in the absence of nutrient deficiency; S62. Based on a preset rule or prediction model, according to the type of deficiency and the severity of deficiency, predict the deficiency yield for the corresponding deficiency area to obtain a yield loss value; S63. Calculate and obtain the predicted yield of the rice field based on the yield loss value and the expected yield.

10. A spectrum-based rice ammonia, phosphorus, potassium deficiency and yield prediction system for rice fields, characterized by: The system includes: Acquisition module, used to obtain spectral data of rice fields; a correction module, configured to perform correction processing on the spectral data to obtain reflectance data of the rice canopy; a feature extraction module for extracting spectral feature parameters related to the nutrient status of ammonia, phosphorus and potassium based on the reflectance data of the rice canopy; A spatial analysis module, configured to perform spatial analysis on the spectral characteristic parameters to obtain spatial distribution characteristic information of the spectral characteristic parameters on rice fields; a diagnosis module for determining whether nutrient deficiency occurs in the rice paddy field based on the numerical value of the spectral characteristic parameter and the spatial distribution characteristic information, and analyzing and obtaining a nutrient deficiency diagnosis result if nutrient deficiency occurs; An estimation module is used to estimate the yield of the rice field according to the nutrient deficiency diagnosis result.

Images