A method for distinguishing sources of nitrogen gas production in flooded soil by in-situ observation and model combination prediction

Abstract

The application discloses a method for distinguishing nitrogen source of flooded soil by in-situ observation and model combination, and relates to the field of agricultural ecology technology. 15 The target area is divided into field micro areas, and an intelligent sensing system is deployed to monitor soil environmental parameters in real time; soil sampling is carried out in the target area to determine the soil bulk density, root layer depth, total nitrogen content and 15 N abundance parameters of the soil sample, and obtain basic soil data; according to the recommended nitrogen fertilizer amount of the target area, the soil nitrogen content, the fertilizer application amount and the soil background 15 N abundance are combined to calculate the optimal N fertilizer abundance. The application combines in-situ observation and an intelligent sensing system to capture the dynamic changes of soil environmental parameters and synchronously monitor the generation rate of nitrogen isotope, avoids the limitation of traditional methods relying on a single parameter, significantly improves the distinguishing accuracy of nitrogen loss sources, and can quickly calculate the contribution rates of the two to nitrogen loss by combining model analysis.

Description

Technical Field

[0001] This invention relates to the field of agricultural ecological technology, specifically to a method for rapidly identifying nitrogen production sources in flooded soils by combining in-situ observation and modeling. Background Technology

[0002] In agricultural ecosystems, paddy fields, as important food production bases, have a profound impact on environmental quality and agricultural sustainability due to their nitrogen cycling and loss mechanisms. Gaseous nitrogen loss is one of the main pathways of nitrogen loss in paddy fields, accounting for 40% to 60% of the total nitrogen application. Among these, denitrification and anaerobic ammonium oxidation are key microbial processes that lead to nitrogen loss in the form of nitrogen gas. These processes are particularly active under flooded conditions, resulting in nitrogen losses of up to 20% to 50% of the applied nitrogen, which seriously affects the nitrogen use efficiency and crop yield in paddy fields. However, nitrogen transformation in paddy soil is a dynamic process, affected by multiple factors such as temperature, humidity, and microbial activity. In-situ field observations can continuously record these changes and capture the key moments and rates of nitrogen loss.

[0003] Nitrogen in paddy field soil mainly comes from the soil nitrogen pool and nitrogen applied to the soil as fertilizer during the current season. The soil nitrogen pool is mostly organic nitrogen, which changes slowly, while the nitrogen applied to the soil as fertilizer is mainly inorganic nitrogen, which decomposes quickly. It is generally believed that nitrogen loss due to nitrogen gas mainly comes from fertilizer nitrogen, with the contribution of the soil nitrogen pool being relatively small. However, due to the lack of effective differentiation methods, there is currently a lack of empirical evidence on the contribution of the soil nitrogen pool to nitrogen loss. Since it is impossible to effectively distinguish the sources of nitrogen production in paddy field soil, there is a lack of accurate targets in finding corresponding methods and technologies to reduce nitrogen loss. Therefore, how to combine intelligent sensing systems and in-situ field observations, and conduct model analysis to distinguish the sources of nitrogen production in flooded soil, thereby improving the efficiency of distinguishing nitrogen loss sources, is the problem that this invention aims to solve. To this end, a method for rapidly distinguishing nitrogen production sources in flooded soil by combining in-situ observations and models is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling, in order to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A rapid method for identifying nitrogen production sources in flooded soils by combining in-situ observation and modeling includes the following steps:

[0007] S1. Divide the target area into field micro-plots and deploy an intelligent sensing system to monitor soil environmental parameters in real time;

[0008] S2. Soil samples are taken in the target area to determine the soil bulk density, root depth, total nitrogen content, and other parameters. 15 N abundance parameter, to obtain basic soil data;

[0009] S3. Based on the recommended nitrogen fertilizer application rate for the target area, combined with soil nitrogen pool content, fertilizer application rate, and soil background, 15 N abundance, calculate optimal 15 N fertilizer abundance;

[0010] S4. Apply after soaking the soil. 15 N fertilizer, and utilize deployed smart sensing systems to monitor changes in soil environmental parameters, including temperature, humidity and pH;

[0011] S5. Water samples are continuously collected in situ in the field using a sampler, and the components in the water samples are determined using a mass spectrometer. 28 N2、 29 N2 and 30 Nitrogen isotope content of N2;

[0012] S6. Combine field observation data and intelligent sensing system data to construct a nitrogen production model and optimize the model parameters to improve prediction accuracy.

[0013] S7. Based on the output of the nitrogen production model, calculate the contribution rate of soil nitrogen pool and fertilizer nitrogen to nitrogen loss, predict the nitrogen production source of flooded soil, and quickly distinguish the sources of nitrogen loss.

[0014] A further improvement to the technical solution of the present invention is that: S1 includes:

[0015] Select the observation area in the target paddy field area, divide it into several micro-areas with an area of ​​not less than 0.15 square meters according to the topography and soil uniformity, use stainless steel or plastic fences to isolate the micro-areas, and plant them in the soil to a depth of not less than 0.4 meters to ensure the isolation of soil and water exchange, and to ensure the independence and stability of the micro-areas.

[0016] An integrated intelligent sensing system is deployed in each micro-zone, including temperature, humidity, pH value and redox potential sensors, to ensure that the sensor probes are evenly distributed within the root layer depth range, and the data is transmitted back to the cloud platform in real time through a wireless transmission module.

[0017] After the deployment of the intelligent sensor system is completed, a 12-hour continuous pre-run test is conducted to verify the stability of data transmission and the accuracy of parameters. Once the system is confirmed to be normal, all-weather real-time monitoring is started, and dynamic soil environmental data is recorded every 10 minutes and synchronously stored in the database of the cloud platform.

[0018] A further improvement to the technical solution of the present invention is that: S2 includes:

[0019] Based on the topography, soil type and planting layout of the target area, sampling points are planned evenly to ensure coverage of different areas. The root depth range is determined according to the distribution of crop roots, and the sampling layer is located.

[0020] Using standard sampling tools, soil samples were collected at planned locations and depths. Surface debris was removed, and the soil samples were placed in clean, sealed containers to avoid contamination and changes in composition, ensuring that the samples accurately reflected the soil conditions.

[0021] The collected soil samples were sent to the laboratory for sequential determination of soil bulk density, root depth, total nitrogen content, and... 15 N abundance was measured to obtain basic soil data, and the results were compiled to establish a basic soil database.

[0022] A further improvement to the technical solution of the present invention is that: S3 includes:

[0023] Consult the recommended nitrogen fertilizer application rate for the target area, and measure the soil nitrogen pool content (total nitrogen content) and soil background. 15 N abundance data;

[0024] Based on the obtained recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background. 15 N abundance, calculate optimal 15 N fertilizer abundance ensures the scientific and effective application of fertilizers;

[0025] The calculation results were initially verified, and the optimal... 15 The abundance of nitrogen fertilizer and the recommended application rate of nitrogen fertilizer were adjusted.

[0026] A further improvement to the technical solution of this invention lies in: the optimal... 15 The calculation process for nitrogen (N) fertilizer abundance is as follows:

[0027] By combining total soil nitrogen content, soil bulk density, and root depth, the nitrogen storage in the soil nitrogen pool within the target depth range is calculated. Simultaneously, the soil background level is considered. 15 N abundance was analyzed to determine the isotopic characteristics of nitrogen in the soil nitrogen pool and to clarify its contribution to the soil nitrogen pool.

[0028] Based on the recommended nitrogen fertilizer application rate and the contribution of the soil nitrogen pool, determine the actual amount of nitrogen that needs to be supplemented through fertilizer.

[0029] Combining recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background. 15 N abundance, calculate optimal 15 N fertilizer abundance, among which excessively high 15 While nitrogen abundance can improve the tracking accuracy of fertilizer nitrogen, it increases fertilizer costs. On the other hand, excessively low abundance can cause the signal of fertilizer nitrogen in the soil to be masked by the soil background nitrogen, affecting the tracking effect.

[0030] A further improvement to the technical solution of the present invention is that: S4 includes:

[0031] Within the target area, the top 0-20cm of soil is tilled, and sufficient water is added to cover the soil surface by 3-5cm. The soil is soaked for 5-10 days to simulate flooding conditions and ensure that the soil reaches a flooded state.

[0032] Based on the calculated optimal 15 N fertilizer abundance and recommended nitrogen fertilizer application rate, 24 hours in advance 15 Apply nitrogen fertilizer evenly to the soil surface and mix it thoroughly to ensure that the labeled nitrogen is in full contact with the soil and to initiate the nitrogen conversion process.

[0033] The deployed intelligent sensing system is activated to monitor changes in soil environmental parameters in real time, including temperature, humidity, and pH. The sensors collect data every 10 minutes via wireless modules and transmit it to the cloud platform in real time, where it is automatically integrated with... 15 Establish a time series database based on the time nodes of fertilizer application.

[0034] A further improvement to the technical solution of the present invention is that: S5 includes:

[0035] Water samples were continuously collected in the field using a sampler, ensuring that the water samples did not come into contact with air during the collection process and avoiding external interference. Each collection was spaced 2 hours apart, and at least 3 consecutive collections were conducted. The water samples were then sealed, stored, and sent to the laboratory.

[0036] The collected water sample was transferred to a sealed gas phase extraction device, where dissolved N2 gas was separated by low-temperature distillation. The purified gas was then injected into an isotope mass spectrometer to quantitatively determine the components in the water sample. 28 N2、 29 N2 and 30 The nitrogen isotope content of N2 was determined, and based on the measurement results and the sampling time interval, the production rate of each nitrogen isotope per unit time was calculated.

[0037] A further improvement to the technical solution of the present invention is that: S6 includes:

[0038] The nitrogen isotope production rate observed in the field, soil temperature, humidity and pH value monitored in real time by the intelligent sensing system were integrated and simultaneously imported into the database. The data were cleaned (outliers were removed), standardized (Z-score normalization) and time aligned to ensure that the spatiotemporal resolution of different parameters was consistent, and a basic dataset was constructed.

[0039] Based on the theory of microbial-driven nitrogen cycle, a nitrogen production model including denitrification and anaerobic ammonium oxidation was established. Soil environmental parameters were used as driving variables and nitrogen isotope production rate was used as response variable to construct a nonlinear relationship equation.

[0040] A Bayesian optimization algorithm is adopted, with the root mean square error between the predicted and measured values ​​as the objective function. The model parameters are dynamically adjusted, and the generalization ability of the model is evaluated through cross-validation. Finally, a high-precision nitrogen generation model and the optimal solution of parameters are output.

[0041] A further improvement to the technical solution of the present invention is that: S7 includes:

[0042] Nitrogen isotope production rate data were obtained from nitrogen production models to calculate the total N2 production rate in paddy field soil, and the data from nitrogen production models were analyzed. 15 The N2 production rate of nitrogen fertilizer, and further based on the total N2 production rate of paddy field soil, from 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance, to obtain the N2 contribution rate from fertilizer nitrogen;

[0043] The N2 production rate of rice was statistically analyzed at each sampling point during the rice growth period, and the total nitrogen loss and fertilizer nitrogen contribution rate during the entire growth period were calculated.

[0044] Based on the calculated contribution rate and total nitrogen loss, the nitrogen production sources in flooded soils can be predicted, and the contribution ratios of soil nitrogen pool and fertilizer nitrogen to nitrogen loss can be quickly distinguished, providing a scientific basis for precision fertilization and nitrogen management.

[0045] A further improvement to the technical solution of this invention lies in the following: the calculation process for the total nitrogen loss and fertilizer nitrogen contribution rate throughout the entire growth period is as follows:

[0046] Based on the characteristics of the rice growth period, a sampling plan was formulated. Water samples were collected every 1-2 days after fertilization for 3-6 consecutive times. Before fertilization, samples were collected every 5-10 days until the rice was harvested. No samples were collected during the drying period of the rice.

[0047] Each time a sample is taken, the sampling point number, sampling time, soil environmental parameters, and nitrogen isotope production rate are recorded in detail. All sampling data are organized into a unified database to ensure the integrity and consistency of the data.

[0048] Within the sampling period n throughout the entire growth period, the total N2 production rate of the nth sampling is calculated. This total N2 production rate is then multiplied by the time interval between adjacent sampling periods, and the sum is obtained to obtain the total nitrogen loss for the entire growth period. The time interval between adjacent sampling periods is the time interval between the nth and (n-1)th sampling periods. Within the sampling period n throughout the entire growth period, the total nitrogen loss from the sampling rate n is calculated. 15 The N2 production rate of nitrogen fertilizer;

[0049] Based on the total nitrogen loss during the entire reproductive period, from 15 N2 production rate of nitrogen fertilizer and fertilizer15 N abundance, used to calculate the contribution rate of fertilizer nitrogen throughout the entire growth period.

[0050] Due to the adoption of the above technical solution, the technical progress achieved by this invention compared to the prior art is as follows:

[0051] 1. This invention provides a method for rapidly distinguishing nitrogen sources in flooded soil by combining in-situ observation and modeling. By combining in-situ observation with an intelligent sensing system, the dynamic changes of soil environmental parameters are captured in real time, and the production rate of nitrogen isotopes is monitored simultaneously. This avoids the limitations of traditional methods that rely on a single parameter, significantly improves the accuracy of distinguishing nitrogen loss sources, and, combined with model analysis, can quickly calculate the contribution rate of both to nitrogen loss.

[0052] 2. This invention provides a method for rapidly identifying nitrogen production sources in flooded soils by combining in-situ observation and modeling. 15 The calculation of nitrogen-labeled fertilizer and optimal application rate can accurately track the transformation path of fertilizer nitrogen in the soil. Combined with the nitrogen production model, it can quantify the proportion of fertilizer nitrogen loss caused by denitrification or anaerobic ammonium oxidation, helping to adjust the amount and timing of fertilizer application, avoiding over-fertilization, reducing the risk of agricultural non-point source pollution and saving production costs. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0054] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0055] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example 1, such as Figure 1 , Figure 2 As shown, this invention provides a method for rapidly identifying nitrogen production sources in flooded soils by combining in-situ observation and modeling, comprising the following steps:

[0058] S1. Divide the target area into field micro-plots and deploy an intelligent sensing system to monitor soil environmental parameters in real time. Select the observation range in the target paddy field area and divide it into several micro-plots with an area of ​​not less than 0.15 square meters according to the terrain and soil uniformity. Use stainless steel or plastic fences to isolate the micro-plots and implant them into the soil to a depth of not less than 0.4 meters to ensure the isolation of soil and water exchange and to ensure the independence and stability of the micro-plots. Deploy an integrated intelligent sensing system in each micro-plot, including temperature, humidity, pH value and redox potential sensors, to ensure that the sensor probes are evenly distributed within the root layer depth range. Transmit the data back to the cloud platform in real time through a wireless transmission module. After the deployment of the intelligent sensor system is completed, conduct a 12-hour continuous pre-run test to verify the stability of data transmission and the accuracy of parameters. After confirming that the system is normal, start all-weather real-time monitoring, set to record the dynamic data of the soil environment every 10 minutes, and store it synchronously in the database of the cloud platform.

[0059] The specific process for S1 is as follows:

[0060] Based on the topographic features, soil type distribution, and irrigation system layout of the target paddy field area, a representative observation range was comprehensively selected to ensure that the observation results reflect the overall nitrogen cycle characteristics of the paddy field. According to the topographic relief and soil homogeneity, the observation range was divided into several micro-zones with an area of ​​no less than 0.15 square meters. Stainless steel or plastic fencing was used, ensuring that the fencing was embedded in the soil to a depth of no less than 0.4 meters to effectively isolate soil and water exchange between each micro-zone, ensuring the independence and stability of each micro-zone. Within each micro-zone, an integrated intelligent sensing system was deployed, including temperature sensors, humidity sensors, pH sensors, and redox potential sensors to ensure accurate sensing. The probes are evenly distributed within the root zone depth to accurately reflect the rhizosphere soil environment. The intelligent sensing system connects to the cloud platform via a wireless transmission module to achieve real-time data transmission. After the deployment of the intelligent sensor system is completed, a 12-hour continuous pre-run test is conducted. During this period, the stability of data transmission and the accuracy of parameter measurement are verified to ensure the reliable operation of the sensors in complex field environments. After confirming that the system is operating normally, the all-weather real-time monitoring mode is activated, and dynamic data of the soil environment are recorded every 10 minutes, including key parameters such as temperature, humidity, pH value and redox potential. All data are synchronously stored in the database of the cloud platform.

[0061] S2. Soil samples are taken in the target area to determine the soil bulk density, root depth, total nitrogen content, and other parameters. 15N abundance parameters were used to obtain basic soil data. Based on the topography, soil type, and planting layout of the target area, sampling points were evenly planned to ensure coverage of different areas. The root depth range was determined according to the crop root distribution, and sampling layers were located. Using standard sampling tools, soil samples were collected at the planned points and depths. Surface debris was removed, and soil samples were placed in clean, sealed containers to avoid contamination and compositional changes, ensuring the samples accurately reflected the soil conditions. The collected soil samples were sent to the laboratory for sequential determination of soil bulk density, root depth, total nitrogen content, and... 15 N abundance was measured to obtain basic soil data, and the results were compiled to establish a basic soil database.

[0062] The specific process for S2 is as follows:

[0063] Collect topographic maps, soil type distribution maps, and planting layout maps of the target paddy field area. Identify the main topographic units, soil types, and crop planting patterns within the target paddy field area. Based on the characteristics of crop root distribution (rice roots are mainly distributed in the 0-20cm soil layer), determine the root depth range (0-15cm, 15-30cm, etc.) and divide the area into sampling layers. Use a grid method to evenly distribute sampling points within the target area, ensuring coverage of different terrains, soil types, and planting areas. The number of sampling points is determined based on the area. Record the geographical location (latitude and longitude), topographic features, soil type, and crop growth status of each sampling point. Use a standard soil sampler (stainless steel ring cutter), ensuring the tool is clean and uncontaminated. Equip the sampler with auxiliary tools such as brushes, shovels, labels, sealed bags, or clean glass bottles. After sampling, remove surface debris (dead branches, fallen leaves, stones, etc.) to avoid contamination. Based on the determined root depth range, perform stratified sampling at 0-15cm and 15-30cm depths. For each layer, insert the sampler vertically into the soil layer and extract a complete soil core. When using a ring sampler, ensure the soil inside the ring is compacted without voids. Place the soil samples in a clean, sealed container, avoiding direct sunlight and high temperatures to prevent compositional changes. Label each sample with the sampling point number, depth, date, and sampler information. Bring the collected soil samples back to the laboratory for testing. If storage is required, they can be stored temporarily in a 4℃ refrigerator. Before testing, sieve the soil samples through a 2mm sieve to remove stones and plant debris, mix thoroughly, and then divide into portions for use. Then, determine the basic soil parameters, including soil bulk density, root depth, total nitrogen, and... 15 Nitrogen abundance was determined by measuring soil bulk density using the ring sampler method and calculating the dry weight of soil per unit volume. Root depth was determined by combining field sampling records and laboratory observations to confirm the actual root distribution depth. Total nitrogen content in the soil was measured using an elemental analyzer, and soil nitrogen content was measured using an isotope mass spectrometer. 15N abundance; the measurement results are entered into a spreadsheet, classified and stored according to sampling point number, depth and parameter type, a basic soil database is established, and information such as geographical location, topography and soil type are linked, and the data is quality controlled, outliers are checked and retested to ensure data accuracy;

[0064] S3. Based on the recommended nitrogen fertilizer application rate for the target area, combined with soil nitrogen pool content, fertilizer application rate, and soil background, 15 N abundance, calculate optimal 15 N fertilizer abundance: Refer to the recommended nitrogen fertilizer application rate for the target area in local agricultural production, and measure the soil nitrogen pool content (total nitrogen content) and soil background. 15 N abundance data are based on the obtained recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background. 15 N abundance, calculate optimal 15 N fertilizer abundance ensures the scientific and effective application of fertilizers, performs preliminary verification of the calculation results, and identifies the optimal... 15 The abundance of N fertilizer and the recommended application rate of nitrogen fertilizer were adjusted.

[0065] Furthermore, optimal 15 The calculation process for nitrogen (N) fertilizer abundance is as follows:

[0066] By combining total soil nitrogen content, soil bulk density, and root depth, the nitrogen reserves in the soil nitrogen pool within the target depth range are calculated. The soil nitrogen pool is a crucial source of nitrogen supply for crops, and its size directly influences fertilizer application strategies. Analyzing the soil nitrogen pool's reserves allows for a preliminary assessment of the soil's ability to meet crop nitrogen requirements, thus providing a basis for determining the amount of nitrogen fertilizer to supplement. Furthermore, this analysis is combined with soil background data. 15 Nitrogen abundance was analyzed to determine the isotopic characteristics of nitrogen in the soil nitrogen pool, clarifying its contribution. Based on the recommended nitrogen fertilizer application rate and the contribution of the soil nitrogen pool, the actual amount of nitrogen to be supplemented through fertilizer was determined. The recommended nitrogen fertilizer application rate is a suggested value derived from a comprehensive consideration of crop growth requirements and soil fertility status. In actual fertilization, the actual contribution of the soil nitrogen pool must be taken into account to avoid over-fertilization. The recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background levels should all be considered. 15 N abundance, calculate optimal 15 N fertilizer abundance, among which excessively high 15 While nitrogen abundance can improve the tracking accuracy of fertilizer nitrogen, it increases fertilizer costs. On the other hand, excessively low abundance can cause the signal of fertilizer nitrogen in the soil to be masked by the soil background nitrogen, affecting the tracking effect.

[0067] 15 The formula for calculating nitrogen (N) fertilizer abundance is as follows:

[0068] ;

[0069] In the formula, for 15 N fertilizer abundance For soil bulk density, The root depth, Total nitrogen in soil Soil background 15 N abundance, Recommended application rate of nitrogen fertilizer;

[0070] S4. Apply after soaking the soil. 15 N fertilizer is applied, and a deployed intelligent sensing system monitors changes in soil environmental parameters, including temperature, humidity, and pH. Within a micro-zone of the target area, the top 0-20cm of soil is tilled, and sufficient water is added to cover the soil surface by 3-5cm. This is then soaked for 5-10 days to simulate flooding conditions, ensuring the soil reaches a flooded state. Based on the calculated optimal... 15 N fertilizer abundance and recommended nitrogen fertilizer application rate, 24 hours in advance 15 The nitrogen fertilizer is evenly applied to the soil surface and mixed thoroughly to ensure full contact between the labeled nitrogen and the soil, initiating the nitrogen conversion process. This activates the deployed intelligent sensing system, which monitors changes in soil environmental parameters in real time, including temperature, humidity, and pH. The sensors collect data every 10 minutes via wireless modules and transmit it to a cloud platform in real time, where the sensor data is automatically integrated with... 15 Establish a time series database based on the application time points of N fertilizers;

[0071] The specific process for S4 is as follows:

[0072] Within the target area's micro-zones, the top 0-20cm of soil was tilled to ensure looseness. Sufficient water was added, submerging the soil surface by 3-5cm to simulate flooding conditions. The soaking time was 5-10 days to ensure the soil reached a flooded state, creating suitable environmental conditions for nitrogen transformation. Based on previously calculated optimal... 15 N fertilizer abundance and recommended nitrogen fertilizer application rates, prepare the corresponding... 15 N fertilizer, apply 24 hours in advance 15 Apply nitrogen fertilizer evenly to the soil surface, either manually or mechanically, ensuring uniform distribution. After application, use a tool to thoroughly mix the fertilizer with the topsoil, ensuring full contact between the labeled nitrogen and the soil to initiate the nitrogen conversion process. 15 Before applying fertilizer, check the operating status of the intelligent sensing system to ensure that the sensors are working properly and the data transmission module is fault-free. 15Simultaneously with fertilization, the real-time monitoring function of the intelligent sensing system is activated to ensure that changes in soil environmental parameters are recorded from the moment fertilization begins. Sensors collect data every 10 minutes via wireless modules, including key parameters such as soil temperature, humidity, and pH. The collected data is transmitted to a cloud platform in real time to ensure its timeliness and completeness. On the cloud platform, the sensor data is automatically integrated with… 15 N. Establish a time series database to clearly record the dynamic changes of soil environmental parameters after fertilization by determining the timing of fertilizer application.

[0073] S5. Water samples are continuously collected in situ in the field using a sampler, and the components in the water samples are determined using a mass spectrometer. 28 N2、 29 N2 and 30 To determine the nitrogen isotope content of N2, water samples were continuously collected in situ in the field using a sampler, ensuring the samples remained isolated from air and free from external interference. Each collection was spaced two hours apart, and at least three consecutive collections were performed. The water samples were then sealed and transported to the laboratory. The collected samples were transferred to a sealed gas-phase extraction device, where dissolved N2 gas was separated by low-temperature distillation. The purified gas was then injected into an isotope mass spectrometer to quantitatively determine the nitrogen isotope content in the water samples. 28 N2、 29 N2 and 30 The nitrogen isotope content of N2 was measured, and the production rate of each nitrogen isotope per unit time was calculated based on the measurement results and the sampling time interval.

[0074] The specific process for S5 is as follows:

[0075] Using a sampler based on patent number 201911416804.9, ensure it is clean and free of contamination. Check the sampler's sealing and functionality to ensure it can operate normally underwater without leaks. Select sampling points within the target paddy field micro-area and insert the sampler into the paddy field water layer, ensuring the sampler is completely submerged and the inlet is located in the middle of the water layer, avoiding contact with bottom sediments. Start the sampler to draw water samples from the paddy field into the sampler's sealed container, ensuring the water sample does not come into contact with air during the sampling process and avoiding external interference. Collect samples at 2-hour intervals, for at least 3 consecutive times. After collection, transfer the water sample from the sampler to a sealed glass bottle, ensuring the water sample does not come into contact with air during the transfer. Place the sealed water sample in an insulated box to avoid direct sunlight and high temperatures to prevent changes in the gas composition of the water sample. Label the water sample container with the sampling point number, sampling time, etc. Information such as depth is collected. After bringing the collected water samples back to the laboratory from the field, they should be analyzed as soon as possible. If immediate analysis is not possible, the water samples should be stored in a 4°C refrigerator, but the storage time should not be too long to avoid the influence of microbial activity on nitrogen isotope content. The water samples are then transferred to a sealed gas-phase extraction device equipped with low-temperature distillation capabilities, which can effectively separate dissolved N2 gas. Dissolved N2 gas in the water sample is separated by low-temperature distillation in the gas-phase extraction device. The distillation temperature and pressure are controlled to ensure complete separation of N2 gas without interference from other gases. The separated N2 gas is then passed through a gas purification device to remove impurities (O2, CO2, etc.) to ensure that the gas injected into the isotope mass spectrometer is high-purity N2. The purified N2 gas is then injected into the isotope mass spectrometer. During the injection process, the gas flow rate and pressure must be kept stable. The isotope mass spectrometer is used to quantitatively determine the concentration of N2 in the water sample. 28 N2、 29 N2 and 30 The nitrogen isotope content of N2 was recorded, and the abundance value of each nitrogen isotope was recorded. Based on the measured nitrogen isotope content and the sampling time interval (2 hours), the production rate of each nitrogen isotope per unit time was calculated, and the calculated production rate of each nitrogen isotope was recorded in the data table.

[0076] S6. Combine field observation data and intelligent sensing system data to construct a nitrogen production model and optimize the model parameters to improve prediction accuracy.

[0077] S7. Based on the output of the nitrogen production model, calculate the contribution rate of soil nitrogen pool and fertilizer nitrogen to nitrogen loss, predict the nitrogen production source of flooded soil, and quickly distinguish the sources of nitrogen loss.

[0078] Example 2, as Figure 1 , Figure 2 As shown, based on Embodiment 1, the present invention provides a technical solution: Preferably, S6 includes:

[0079] This study integrates nitrogen isotope production rates observed in the field with soil temperature, humidity, and pH values ​​monitored in real time by an intelligent sensing system. These data are then simultaneously imported into a database. The data is cleaned (outliers are removed), standardized (Z-score normalization), and time-aligned to ensure consistent spatiotemporal resolution for different parameters. A basic dataset is constructed, and a nitrogen production model incorporating denitrification and anaerobic ammonium oxidation is established based on the microbial-driven nitrogen cycle theory. Soil environmental parameters are used as driving variables, and nitrogen isotope production rates are used as response variables. A nonlinear relationship equation is constructed, and a Bayesian optimization algorithm is employed. The root mean square error between predicted and measured values ​​is used as the objective function to dynamically adjust the model parameters. The model's generalization ability is evaluated through cross-validation, and finally, a high-precision nitrogen production model and optimal parameter solutions are output.

[0080] The specific process for S6 is as follows:

[0081] Nitrogen isotope production rates observed in the field, and soil temperature, humidity, and pH values ​​monitored by the intelligent sensing system were uniformly imported into a database. Through timestamp matching, the nitrogen isotope rate data was time-aligned with soil environmental parameters. Linear interpolation was used to fill missing values, ensuring that the time resolution of all parameters was uniformly 10 minutes / time. Spatially, using the location of the intelligent sensing nodes as a reference, the coordinates of nitrogen isotope sampling points were mapped to the same grid (1m×1m resolution) using an inverse distance weighting method to eliminate spatial scale differences. Based on the 3σ principle, data points in the nitrogen isotope rate exceeding the mean ± 3 standard deviations were removed. For soil temperature, humidity, and pH values, box plots were used to identify and remove outliers. The cleaned data were Z-score normalized according to parameter type to eliminate the influence of dimensions. The preprocessed data was then divided into training, validation, and test sets according to time series, ensuring that each dataset covered the complete experimental period and environmental conditions. This generated a dataset containing input variables (soil temperature, humidity, pH value) and output variables (…). 28 N2、 29 N2 and 30A standardized dataset of N2 production rates was used as the basis for model training. Based on the microbial-driven nitrogen cycle theory, a dual-pathway nitrogen production model incorporating denitrification and anaerobic ammonium oxidation was established to determine the dual-pathway nitrogen production rates. Nonlinear equations were constructed, including denitrification rate equations and anaerobic ammonium oxidation rate equations. The denitrification rate equation was a Monod model modified with the Arrhenius equation, using soil temperature, humidity, and pH as driving variables. The anaerobic ammonium oxidation rate equation was a pH-dependent enzyme activity model. The model parameter range was initialized based on literature analysis and preliminary experimental results. Bayeux leaves were used... The Gaussian optimization algorithm is used for parameter tuning. The root mean square error between the predicted and measured values ​​is used as the objective function. The optimal solution is dynamically searched in the parameter space. The number of iterations is set to 100. Each iteration updates the parameter probability distribution based on Gaussian process regression and uses K-fold cross-validation. The training set is randomly divided into 5 folds. Each iteration uses 4 folds for training and 1 fold for validation. After 5 iterations, the average root mean square error is used as the model performance index. The optimized model is run on the test set, and the mean absolute error is calculated. At the same time, according to the preset mean absolute error threshold, the prediction accuracy of the model for unknown data is ensured, and thus the optimal parameter and high-precision nitrogen generation model is output.

[0082] The expression for the two-path nitrogen production model is as follows:

[0083] ;

[0084] In the formula, This represents the nitrogen production rate via a two-pathway system. and These represent the nitrogen production rates of denitrification and anaerobic ammonium oxidation, respectively.

[0085] The expression for the denitrification rate equation is as follows:

[0086] ;

[0087] In the formula, This is the maximum reaction rate constant for denitrification. For activation energy, The gas constant is and The half-saturation constants for humidity and pH are given. For soil temperature, For humidity, pH value;

[0088] The expression for the anaerobic ammonia oxidation rate equation is as follows:

[0089] ;

[0090] In the formula, This is the maximum reaction rate constant for anaerobic ammonium oxidation. and This is the pH inhibition constant. and For the lowest and optimal temperatures;

[0091] The expression for the root mean square error is as follows:

[0092] ;

[0093] In the formula, The root mean square error, The sample size represents the total number of data points used to calculate the root mean square error. For the model to the first Prediction results for each sample For the first The actual observed values ​​of each sample;

[0094] The expression for the mean absolute error is as follows:

[0095] ;

[0096] In the formula, Mean absolute error;

[0097] S7 includes:

[0098] Nitrogen isotope production rate data were obtained from nitrogen production models to calculate the total N2 production rate in paddy field soil, and the data from nitrogen production models were analyzed. 15 The N2 production rate of nitrogen fertilizer, and further based on the total N2 production rate of paddy field soil, from 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance, obtaining the N2 contribution rate from fertilizer nitrogen, is calculated for each sampling. 28 N2、 29 N2 and 30 The sum of N2 production rates is used to obtain the total N2 production rate of paddy field soil, and calculations are performed. 29 The N2 generation rate divided by 2, and... 30 N2 generation rate summation, obtaining from 15 The N2 production rate of nitrogen fertilizer, due to 30 N2 consists of two 15 It is composed of nitrogen atoms, therefore 30 The N2 generation rate mainly comes from 15 N fertilizer, 29 There is also one in N2 15N atoms were used to statistically analyze the N2 production rate of rice samples during the rice growth period, calculate the total nitrogen loss and fertilizer nitrogen contribution rate throughout the growth period, and predict the nitrogen production sources of flooded soil based on the calculated contribution rate and total nitrogen loss. This allowed for a rapid differentiation between the contribution ratio of soil nitrogen pool and fertilizer nitrogen to nitrogen loss, providing a scientific basis for precision fertilization and nitrogen management.

[0099] The specific process for S7 is as follows:

[0100] Obtained from nitrogen production model 28 N2、 29 N2 and 30 Based on the nitrogen isotope production rate data output by the model, the total N2 production rate of paddy field soil is calculated, and the total N2 production rate from the model is calculated. 15 The N2 production rate of nitrogen fertilizer is based on the total N2 production rate of paddy field soil and the N2 production rate from nitrogen fertilizer. 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance was used to calculate the contribution rate of fertilizer nitrogen. According to the field sampling plan, water samples were collected multiple times during the rice growth period, and the N2 production rate was recorded for each sample. Generally, samples were collected every 1-2 days after fertilization, for a total of 3-6 times; samples were collected every 5-10 days before fertilization, until rice harvest. No sampling was performed during the rice drying period. The N2 production rate of each sample throughout the entire growth period was statistically analyzed, and the total nitrogen loss during the entire growth period was calculated. Based on the total nitrogen loss during the entire growth period and the nitrogen from fertilizer sources... 15 The N2 production rate of nitrogen fertilizer is calculated, and the contribution rate of fertilizer nitrogen throughout the growth period is calculated. Based on the calculated contribution rate and the total nitrogen loss, a nitrogen production model is used to predict the nitrogen production sources in flooded soil, quickly distinguish the contribution ratio of soil nitrogen pool and fertilizer nitrogen to nitrogen loss, and identify the main sources of nitrogen loss by comparing the nitrogen production rates of different sources.

[0101] In addition, the calculation process for the total nitrogen loss and fertilizer nitrogen contribution rate throughout the entire growth period is as follows:

[0102] Based on the characteristics of the rice growth period, a sampling plan was formulated. Water samples were collected every 1-2 days after fertilization, for a total of 3-6 times. Before fertilization, samples were collected every 5-10 days until harvest. No sampling was conducted during the rice drying period. Representative sampling points were selected in different micro-regions of the target paddy field to ensure coverage of different terrains, soil types, and planting areas. For each sampling, the sampling point number, sampling time, soil environmental parameters, and nitrogen isotope production rate were recorded in detail. All sampling data were compiled into a unified database to ensure data integrity and consistency. Within the sampling frequency n throughout the entire growth period, the total N2 production rate of the nth sampling was calculated. The total N2 production rate of the nth sampling was multiplied by the time interval between adjacent sampling times, and the sum was obtained to obtain the total nitrogen loss during the entire growth period. The time interval between adjacent sampling times is the time interval between the nth and (n-1)th sampling times. Within the sampling frequency n throughout the entire growth period, the total nitrogen loss from the entire growth period was calculated. 15 The N2 production rate of nitrogen fertilizer is based on the total nitrogen loss during the entire growth period and the amount of nitrogen produced from nitrogen fertilizer. 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance, calculating the contribution rate of fertilizer nitrogen throughout the entire growth period;

[0103] The formula for calculating the total N2 production rate in paddy field soil is as follows:

[0104] ;

[0105] In the formula, For the first The total N2 production rate of the second sampled paddy field soil. They are the first During the second sampling 28 N2、 29 N2 and 30 The rate of N2 production;

[0106] From 15 The formula for calculating the N2 production rate of nitrogen fertilizer is as follows:

[0107] ;

[0108] In the formula, For from 15 The N2 production rate of nitrogen fertilizer;

[0109] The formula for calculating the total nitrogen loss during the rice growth period is as follows:

[0110] ;

[0111] In the formula, This represents the total nitrogen loss during the rice growing season. The number of samplings during the entire reproductive period. For the first The total N2 generation rate during sampling. For the first Sampling and the first The time interval between each sampling;

[0112] The formula for calculating the total N2 production rate from 15N fertilizer during the rice growth period is as follows:

[0113] ;

[0114] In the formula, The total amount of rice during its growth period comes from 15 The N2 production rate of nitrogen fertilizer For the first From sampling 15 The N2 production rate of nitrogen fertilizer;

[0115] The formula for calculating the total N2 contribution rate from fertilizer nitrogen during the rice growth period is as follows:

[0116] ;

[0117] In the formula, The contribution rate of N2 from fertilizer nitrogen during the rice growth period. for 15 N fertilizer abundance.

[0118] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A rapid identification method for predicting nitrogen production sources in flooded soil by combining in-situ observation and modeling, characterized in that, Includes the following steps: S1. Divide the target area into field micro-plots and deploy an intelligent sensing system to monitor soil environmental parameters in real time; S2. Soil samples were taken from the target area to determine the soil bulk density, root depth, total nitrogen content, and other parameters. 15 N abundance parameter, to obtain basic soil data; S3. Based on the recommended nitrogen fertilizer application rate for the target area, combined with soil nitrogen pool content, fertilizer application rate, and soil background, 15 N abundance, calculate optimal 15 N fertilizer abundance; 15 The formula for calculating nitrogen (N) fertilizer abundance is as follows: ； In the formula, for 15 N fertilizer abundance For soil bulk density, The root depth, Total nitrogen in soil Soil background 15 N abundance, Recommended application rate of nitrogen fertilizer; S4. Apply after soaking the soil. 15 N fertilizer, and use deployed intelligent sensing systems to monitor changes in soil environmental parameters; S5. Use a sampler to continuously collect water samples in situ in the field, and use a mass spectrometer to determine the nitrogen isotope content in the water samples; S6. Combining field observation data and data from intelligent sensing systems, a nitrogen production model is constructed, specifically including: Integrate nitrogen isotope production rates observed in the field, soil temperature, humidity and pH values ​​monitored in real time by intelligent sensing systems, and import them into the database simultaneously. Clean, standardize and time-align the data to build a basic dataset. Based on the theory of microbial-driven nitrogen cycle, a nitrogen production model including denitrification and anaerobic ammonium oxidation was established. Soil environmental parameters were used as driving variables and nitrogen isotope production rate was used as response variable to construct a nonlinear relationship equation. The expression for the two-path nitrogen production model is as follows: ； In the formula, This represents the nitrogen production rate via a two-pathway system. and These represent the nitrogen production rates of denitrification and anaerobic ammonium oxidation, respectively. The expression for the denitrification rate equation is as follows: ； In the formula, This is the maximum reaction rate constant for denitrification. For activation energy, The gas constant is... and The half-saturation constants for humidity and pH are given. For soil temperature, For humidity, pH value; The expression for the anaerobic ammonia oxidation rate equation is as follows: ； In the formula, This is the maximum reaction rate constant for anaerobic ammonium oxidation. and This is the pH inhibition constant. and For the lowest and optimal temperatures; A Bayesian optimization algorithm is used, with the root mean square error between the predicted and measured values ​​as the objective function. The model parameters are dynamically adjusted, and the generalization ability of the model is evaluated through cross-validation. Finally, a high-precision nitrogen generation model and the optimal solution of parameters are output. S7. Based on the output of the nitrogen production model, calculate the contribution rate of soil nitrogen pool and fertilizer nitrogen to nitrogen loss, predict the nitrogen production source of flooded soil, and quickly distinguish the sources of nitrogen loss.

2. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling as described in claim 1, characterized in that: S1 includes: Select the observation area in the target paddy field area, divide it into several micro-areas with an area of ​​not less than 0.15 square meters according to the terrain and soil uniformity, isolate the micro-areas with stainless steel or plastic fences, and implant them into the soil to a depth of not less than 0.4 meters. An integrated intelligent sensing system is deployed in each micro-zone, including temperature, humidity, pH value and redox potential sensors, and the data is transmitted back to the cloud platform in real time through a wireless transmission module. After the deployment of the intelligent sensor system is completed, a 12-hour continuous pre-run test is conducted. Once the system is confirmed to be normal, all-weather real-time monitoring is started, and dynamic soil environmental data is recorded every 10 minutes and synchronously stored in the database of the cloud platform.

3. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling as described in claim 1, characterized in that: S2 includes: Based on the topography, soil type and planting layout of the target area, sampling points are planned evenly, and the root depth range is determined according to the distribution of crop roots to locate the sampling layer. Using standard sampling tools, collect soil samples at the planned locations and depths, and place the soil samples into clean, sealed containers. The collected soil samples were sent to the laboratory for sequential determination of soil bulk density, root depth, total nitrogen content, and... 15 N abundance was measured to obtain basic soil data, and the results were compiled to establish a basic soil database.

4. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling as described in claim 1, characterized in that: S3 includes: Consult the recommended nitrogen fertilizer application rate for the target area, and measure the soil nitrogen pool content and soil background. 15 N abundance data; Based on the obtained recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background. 15 N abundance, calculate optimal 15 N fertilizer abundance; The calculation results were initially verified, and the optimal... 15 The abundance of nitrogen fertilizer and the recommended application rate of nitrogen fertilizer were adjusted.

5. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling according to claim 4, characterized in that: The optimal 15 The calculation process for nitrogen (N) fertilizer abundance is as follows: By combining total soil nitrogen content, soil bulk density, and root depth, the nitrogen storage in the soil nitrogen pool within the target depth range is calculated. Simultaneously, the soil background level is considered. 15 N abundance was analyzed to determine the isotopic characteristics of nitrogen in the soil nitrogen pool and to clarify its contribution to the soil nitrogen pool. Based on the recommended nitrogen fertilizer application rate and the contribution of the soil nitrogen pool, determine the actual amount of nitrogen that needs to be supplemented through fertilizer. Combining recommended nitrogen fertilizer application rate, total soil nitrogen content, soil bulk density, root depth, and soil background. 15 N abundance, calculate optimal 15 N fertilizer abundance.

6. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling according to claim 1, characterized in that: S4 includes: Within the target area, the top 0-20cm of soil is tilled, water is added to cover the soil surface by 3-5cm, and the soil is soaked for 5-10 days to simulate flooding conditions. Based on the calculated optimal 15 N fertilizer abundance and recommended nitrogen fertilizer application rate, 24 hours in advance 15 Apply nitrogen fertilizer evenly to the soil surface and mix it thoroughly to initiate the nitrogen conversion process. The deployed intelligent sensing system is activated to monitor changes in soil environmental parameters in real time, including temperature, humidity, and pH. The sensors collect data every 10 minutes via wireless modules and transmit it to the cloud platform in real time, where it is automatically integrated with... 15 Establish a time series database based on the time nodes of fertilizer application.

7. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling according to claim 1, characterized in that: S5 includes: Water samples were continuously collected in the field using a sampler, with a 2-hour interval between each collection, for at least 3 consecutive collections. The water samples were then sealed, preserved, and sent to the laboratory. The collected water sample was transferred to a sealed gas phase extraction device, where dissolved N2 gas was separated by low-temperature distillation. The purified gas was then injected into an isotope mass spectrometer to quantitatively determine the components in the water sample. 28 N2、 29 N2 and 30 The nitrogen isotope content of N2 was determined, and based on the measurement results and the sampling time interval, the production rate of each nitrogen isotope per unit time was calculated.

8. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling according to claim 7, characterized in that: S7 includes: Nitrogen isotope production rate data were obtained from nitrogen production models to calculate the total N2 production rate in paddy field soil, and the data from nitrogen production models were analyzed. 15 The N2 production rate of nitrogen fertilizer, and thus based on the total N2 production rate of paddy field soil, from 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance, to obtain the N2 contribution rate from fertilizer nitrogen; The N2 production rate of rice was statistically analyzed at each sampling point during the rice growth period, and the total nitrogen loss and fertilizer nitrogen contribution rate during the entire growth period were calculated. Based on the calculated contribution rate and total nitrogen loss, the nitrogen production sources of flooded soil are predicted, and the contribution ratios of soil nitrogen pool and fertilizer nitrogen to nitrogen loss are quickly distinguished.

9. The method for rapidly identifying nitrogen production sources in flooded soil by combining in-situ observation and modeling according to claim 8, characterized in that: The calculation process for the total nitrogen loss and fertilizer nitrogen contribution rate during the entire growth period is as follows: Based on the characteristics of the rice growth period, a sampling plan was formulated. Water samples were collected every 1-2 days after fertilization for 3-6 consecutive times. Before fertilization, samples were collected every 5-10 days until the rice was harvested. No samples were collected during the drying period of the rice. Each time a sample is taken, the sampling point number, sampling time, soil environmental parameters, and nitrogen isotope production rate are recorded, and all sampling data are compiled into a unified database. Within the sampling period n throughout the entire growth period, the total N2 production rate of the nth sampling is calculated. This total N2 production rate is then multiplied by the time interval between adjacent sampling periods, and the sum is obtained to obtain the total nitrogen loss for the entire growth period. The time interval between adjacent sampling periods is the time interval between the nth and (n-1)th sampling periods. Within the sampling period n throughout the entire growth period, the total nitrogen loss from the sampling rate n is calculated. 15 The N2 production rate of nitrogen fertilizer; Based on the total nitrogen loss during the entire reproductive period, from 15 N2 production rate of nitrogen fertilizer and fertilizer 15 N abundance, used to calculate the contribution rate of fertilizer nitrogen throughout the entire growth period.

Images