Corn dry matter accumulation prediction method based on root bleeding feature modeling

Abstract

The invention relates to the field of agricultural prediction, in particular to a corn dry matter accumulation prediction method based on root bleeding feature modeling, and the method comprises the steps: carrying out the synchronization preprocessing of multi-source time series data, and obtaining a complete multi-dimensional time series data set; the method comprises the following steps: performing dynamic baseline and local variability analysis on original bleeding data to obtain a self-adaptive input damping factor, and performing bleeding data preliminary correction through the self-adaptive input damping factor; performing peak event and environmental constraint analysis on the smoothed bleeding data to obtain a posterior compensation factor, and performing secondary correction on the smoothed bleeding data through the posterior compensation factor; carrying out modeling prediction on the corrected bleeding characteristics, and obtaining a corn dry matter accumulation rate through a prediction model; the corn yield prediction result is obtained by performing cumulative integration on the corn dry matter accumulation rate, so that the problem of prediction result distortion caused by the bleeding data instantaneous peak value in the post-drought rehydration scene is solved.

Description

Technical Field

[0001] This invention relates to the field of agricultural forecasting technology, and in particular to a method for predicting maize dry matter accumulation based on root sap flow characteristics modeling. Background Technology

[0002] As a crucial food crop globally, maize's yield directly impacts agricultural productivity and food security. During maize's growth, dry matter accumulation is a core physiological indicator for assessing crop growth and predicting final yield. Developing a method for continuously and accurately predicting maize dry matter accumulation is of significant application value and widespread applicability, aiming to achieve precise and scientific field management. Existing research and practice indicate that establishing predictive models based on crop root physiological activity characteristics is a vital technical approach for predicting dry matter accumulation. Roots are key organs for water and nutrient absorption, and their physiological activity is closely related to aboveground biomass accumulation. Root sap, as a comprehensive indicator of root activity, effectively characterizes root water absorption and nutrient supply capacity through its flow rate and the concentration of components such as nitrogen, phosphorus, potassium, and amino acids. Therefore, current techniques typically involve collecting relevant sap characteristic data and combining it with actual maize dry matter accumulation, then utilizing machine learning algorithms such as regression analysis, support vector machines, or random forests to establish predictive models from sap flow characteristics to dry matter accumulation.

[0003] However, in practical applications, the sap flow data collected by sensors is often noisy and fluctuates frequently, necessitating data preprocessing before modeling. To filter out noise and extract baseline signals reflecting stable plant growth trends, the Savitzky-Golay (SG) filter is widely used in processing crop physiological time series data due to its ability to smooth data while preserving signal morphology. The SG filter works by smoothing data points within a sliding window using local polynomial least squares fitting, a common and mature technique in this field. However, the inventors have discovered inherent limitations in handling certain typical scenarios in maize fields. Particularly after a period of drought stress, sudden heavy rainfall or concentrated irrigation can cause compensatory water absorption by the roots, resulting in short-duration, excessively high instantaneous peaks in the sap flow time series. The SG filter cannot distinguish whether these peaks are physiological artifacts caused by short-term stress responses or represent the true dry matter growth trend of the aboveground parts, thus mechanically including these extreme points in the fitting process, significantly inflating the smoothing results within that interval. Subsequent prediction models, when using distorted smoothed data for inference, may misinterpret it as a pulsed increase in the dry matter accumulation rate, leading to a systematic overestimation of the phased prediction results. This error accumulates gradually throughout the growth cycle, severely impacting the accuracy of yield predictions. Therefore, existing technologies cannot effectively distinguish between physiological artifacts caused by compensatory water absorption and the true growth trend in typical scenarios such as post-drought rehydration, resulting in distortion and cumulative errors in maize dry matter accumulation predictions. Effectively identifying and correcting such abnormal peak interferences is a pressing issue that needs to be addressed. Summary of the Invention

[0004] In view of this, the present invention aims to propose a method for predicting maize dry matter accumulation based on root sap flow characteristics modeling, in order to solve the problem of prediction results being distorted due to the instantaneous peak value of sap flow data in the post-drought rehydration scenario.

[0005] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0006] A method for predicting maize dry matter accumulation based on root sap flow characteristics, the method comprising the following steps:

[0007] Step S1: Obtain a complete multidimensional time series dataset by performing synchronization preprocessing on multi-source time series data;

[0008] Step S2: By performing dynamic baseline and local variability analysis on the original wound flow data, the adaptive input damping factor is obtained, and the wound flow data is initially corrected using the adaptive input damping factor;

[0009] Step S3: By performing peak event and environmental constraint analysis on the smoothed wound flow data, the posterior compensation factor is obtained, and the smoothed wound flow data is then corrected a second time using the posterior compensation factor.

[0010] Step S4: Model and predict the corrected wound flow characteristics, and obtain the corn dry matter accumulation rate through the prediction model;

[0011] Step S5: Obtain the corn yield prediction result by cumulatively integrating the corn dry matter accumulation rate.

[0012] Furthermore, the step of obtaining a complete multidimensional time series dataset by performing synchronization preprocessing on multi-source time series data includes:

[0013] After maize enters the jointing stage, representative plants are selected and equipped with stem flow meters to continuously collect and record the sap flow rate data sequence of the stem at a sampling frequency of once every 30 minutes. Soil moisture sensors are deployed in the main distribution area of ​​the plant roots to collect and record soil moisture data sequences at the same sampling frequency as the sap flow rate data. Photosynthetically active radiation sensors are installed above the maize canopy or in field weather stations to collect and record photosynthetically active radiation data sequences at the same sampling frequency as the sap flow rate data. After completing the above data collection, the sap flow rate data sequence, soil moisture data sequence, and photosynthetically active radiation data sequence are timestamped and aligned. Missing data points are filled in using nearest neighbor interpolation or linear interpolation methods to obtain a complete and synchronized multidimensional time series dataset.

[0014] Furthermore, the process of obtaining an adaptive input damping factor by performing dynamic baseline and local variability analysis on the original wound flow data, and then using the adaptive input damping factor to perform preliminary correction of the wound flow data, includes:

[0015] Set the number of assessments for dynamic growth baseline assessment and local data fluctuation assessment; for any target time in the original wound flow data, select continuous wound flow data points before the target time according to the number of assessments, and use the median of the selected continuous wound flow data points as the dynamic growth baseline at the target time; use the standard deviation of the selected continuous wound flow data as the local fluctuation degree at the target time.

[0016] By performing a joint deviation analysis on the original wound flow data based on the dynamic growth baseline and the degree of local fluctuation, an adaptive input damping factor is obtained, and the original wound flow data is preliminarily corrected.

[0017] Furthermore, the process involves performing a joint deviation analysis on the original wound flow data based on the dynamic growth baseline and the degree of local fluctuations to obtain an adaptive input damping factor, and then performing preliminary corrections on the original wound flow data, including:

[0018] For any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline at the target time is used as the numerator, and the result of adding the local fluctuation degree at the target time to the minimum positive number is used as the denominator. The corresponding fraction is used as the first input damping assessment at the target time. The negative of the square of the first input damping assessment at the target time is subjected to an exponential mapping with the natural constant as the base, and the corresponding mapping result is used as the adaptive input damping factor at the target time.

[0019] The original wound flow data is corrected based on baseline deviation by using an adaptive input damping factor to obtain preliminary corrected wound flow data.

[0020] Furthermore, the step of correcting the original wound flow data based on baseline deviation using an adaptive input damping factor to obtain preliminarily corrected wound flow data includes:

[0021] For any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline is used as the first baseline deviation assessment for the target time; the result of multiplying the adaptive input damping factor at the target time with the first baseline deviation assessment for the target time is used as the first correction assessment for the target time; and the result of adding the dynamic growth baseline at the target time to the first correction assessment for the target time is used as the preliminary corrected wound flow data for the target time.

[0022] Furthermore, the step involves performing peak event and environmental constraint analysis on the smoothed wound flow data to obtain a posterior compensation factor, and then using the posterior compensation factor to perform a secondary correction on the smoothed wound flow data, including:

[0023] Set the sliding window length and polynomial fitting order of the SG filter; smooth the initially corrected wound flow data using the SG filter to obtain the smoothed wound flow data;

[0024] Peak compensation baseline is obtained by identifying peak events and calculating their intensity in the smoothed wound flow data.

[0025] Environmental regulation factors were obtained by performing environmental constraint analysis on soil moisture data and photosynthetically active radiation data.

[0026] By jointly processing the peak compensation baseline and the environmental adjustment factor, the posterior compensation factor is obtained, and the smoothed wound flow data is then corrected a second time.

[0027] Furthermore, the step of obtaining a peak compensation benchmark by performing peak event identification and intensity calculation on the smoothed wound flow data includes:

[0028] A peak evaluation coefficient is set. For any target time in the original wound flow data, the peak evaluation coefficient is multiplied by the local fluctuation degree of the target time and added to the dynamic growth baseline of the target time. The result is used as the peak event start evaluation threshold for the target time. For any target time, if the value of the smoothed wound flow data at the target time is greater than the peak event start evaluation threshold, the target time is determined as the start time of the peak event. The first time after the start time of the peak event that is less than the peak time start evaluation threshold is used as the end time of the peak time corresponding to the start time of the peak event. All peak events in the original wound flow data are obtained through the evaluation of the start and end times of the peak events.

[0029] The result of subtracting the initial corrected flow data at the target time from the flow data at any target time in the original flow data is used as the first peak flux assessment at the target time.

[0030] For any target peak event among all peak events in the original wound flow data, the calculation result of summing the first peak flux assessments at all times in the target peak event is used as the peak compensation benchmark for the target peak event.

[0031] Furthermore, the environmental regulation factors are obtained by performing environmental constraint analysis on soil moisture data and photosynthetically active radiation data, including:

[0032] For any target peak event among all peak events in the original wound flow data, the moment when the original wound flow data has the maximum value in the target peak event is taken as the instantaneous peak moment of the target peak event;

[0033] For any instantaneous peak moment of a target peak event, the average value of the soil moisture data in the interval formed by the ten days to the four days prior to the instantaneous peak moment of the target peak event is taken as the reference soil moisture of the target peak event.

[0034] For any instantaneous peak moment of a target peak event, the maximum photosynthetically active radiation data within the seven days preceding the instantaneous peak moment of the target peak event is used as the reference photosynthetically active radiation value of the target peak event;

[0035] For any target time in any target peak event, the soil moisture data at the target time is divided by the calculated result of the reference soil moisture of the target peak event as the first soil moisture assessment at the target time; the photosynthetically active radiation data at the target time is divided by the calculated result of the calculated result of the reference photosynthetically active radiation value at the target peak time as the first photosynthetically active radiation assessment at the target time.

[0036] The result of multiplying the first soil moisture assessment and the first photosynthetically active radiation assessment at the target time during the target peak event is used as the environmental adjustment factor for the target peak event at the target time.

[0037] Furthermore, the step of obtaining a posterior compensation factor by jointly processing the peak compensation baseline and the environmental adjustment factor, and then performing a secondary correction on the smoothed wound flow data, includes:

[0038] Define a physiological response time constant; for any target moment in any target peak event, use the result of subtracting the instantaneous peak moment of the target peak event from the target moment as the numerator, and the square of the physiological response time constant as the denominator. Use the resulting fraction as the first pulse evaluation of the target moment; use the result of subtracting the instantaneous peak moment of the target peak event from the target moment as the numerator, and the physiological response time constant as the denominator. Perform an exponential mapping with the natural constant as the base on the resulting fraction. Use the resulting fraction as the second pulse evaluation of the target moment. Multiply the first pulse evaluation and the second pulse evaluation of the target moment as the pulse response evaluation of the target moment.

[0039] The result of multiplying the environmental adjustment factor of the target peak event at the target time, the peak compensation benchmark of the target peak event, and the impulse response evaluation of the target peak event at the target time is used as the posterior compensation factor of the target peak event at the target time.

[0040] The result of adding the posterior compensation factor of the target peak event at the target time to the corresponding target time data in the smoothed wound flow data is used as the wound flow data for secondary correction.

[0041] Compared with the prior art, the present invention has the following advantages:

[0042] This invention discloses a method for predicting maize dry matter accumulation based on root sap flow characteristics. By introducing a dual optimization mechanism—an adaptive input damping factor and a posterior compensation factor—during the processing of sap flow data, this method effectively suppresses instantaneous peak values ​​of sap flow in drought-induced rehydration scenarios and dynamically restores physiological compensation information. In actual field environments, maize roots are affected by water stress and sudden environmental changes, often resulting in short-term, high-amplitude fluctuations in sensor-collected data. Traditional filtering methods easily misinterpret these peaks as true growth trends, leading to systematic biases in the prediction model. This invention, through joint modeling of dynamic baselines and local variability, automatically identifies and suppresses the interference of abnormal fluctuations, making the processed data closer to the true growth patterns of maize. This improves the stability and reliability of data input while maintaining data fidelity. Furthermore, while suppressing the interference of abnormal peak values ​​on data smoothing, this invention also injects potential physiological gains from environmental improvements into the prediction model through the construction of compensation factors. This compensation process not only considers the intensity of peak events but also integrates environmental constraints such as soil moisture and photosynthetically active radiation, and dynamically adjusts it in conjunction with the physiological response rhythms of crops. This allows for a more accurate reflection of the compensatory growth trend of maize after water recovery. The resulting dry matter accumulation predictions demonstrate higher accuracy in complex and variable field environments, providing reliable support for growth assessment, field management optimization, and yield prediction in agricultural production. Attached Figure Description

[0043] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0044] Figure 1 This is a flowchart illustrating a method for predicting corn dry matter accumulation based on root sap flow characteristics, as described in an embodiment of the present invention. Detailed Implementation

[0045] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0046] See Figure 1 This is a flowchart of a method for predicting maize dry matter accumulation based on root sap flow characteristics, as provided in Embodiment 1 of the present invention. Figure 1 As shown, a method for predicting maize dry matter accumulation based on root sap flow characteristics can include:

[0047] Step S1: Obtain a complete multidimensional time series dataset by performing synchronization preprocessing on multi-source time series data.

[0048] In this embodiment of the invention, it is first necessary to obtain a multi-source time-series dataset reflecting the growth status and environmental conditions of maize. Specifically, after maize enters the jointing stage, representative plants are selected and stem flow meters are installed to continuously collect and record the sap flow rate data sequence of the stem at a sampling frequency of once every 30 minutes. Soil moisture sensors are deployed in the main distribution area of ​​the plant roots to collect and record the soil moisture data sequence at the same sampling frequency as the sap flow rate data. Photosynthetically active radiation sensors are installed above the maize canopy or in field weather stations to collect and record the photosynthetically active radiation data sequence at the same sampling frequency as the sap flow rate data. After completing the above data collection, the sap flow rate data sequence, soil moisture data sequence, and photosynthetically active radiation data sequence are timestamped and aligned. Missing data points are then filled in using nearest neighbor interpolation or linear interpolation methods to obtain a complete and synchronized multi-dimensional time-series dataset.

[0049] This completes the process of obtaining a full multidimensional time series dataset by synchronizing and preprocessing multi-source time series data.

[0050] Step S2: By performing dynamic baseline and local variability analysis on the original wound flow data, an adaptive input damping factor is obtained, and the wound flow data is initially corrected using the adaptive input damping factor.

[0051] The technical problem this invention aims to solve is that the standard Savitzky-Golay (SG) filter, when performing smoothing operations, treats each data point within the sliding window as a signal with equal significance and assigns it a fixed weight determined by the polynomial order and window position. However, in the case of post-drought re-irrigation, the instantaneous peak in the collected sap flow data has a fundamentally different physiological significance from the data points during the stable period. This peak mainly reflects the short-term hydraulic adjustment behavior of the root system under drastic changes in water potential, rather than a synchronous jump in the rate of dry matter accumulation in the aboveground parts. Therefore, directly inputting the raw data sequence containing this instantaneous peak into the SG filter will cause the filter to produce a severely distorted output in order to fit this statistically and physiologically anomalous extreme point. To solve this problem, the peak cannot be removed or flattened, because its appearance itself marks a critical shift in the crop's physiological state. The solution of this invention is to introduce a dynamic preprocessing step before the data enters the SG filter, constructing a mechanism capable of assessing the degree of anomalousness of each data point. Specifically, this mechanism compares the current flow data point with its recent historical context. The degree of anomaly of a data point is not determined by its absolute value, but by its deviation from the recent stable growth trend, combined with the volatility of that trend itself. Therefore, two key features are extracted from historical data: a dynamic baseline representing the current potential growth rate, and local variability quantifying the normal fluctuation range of recent data. An adaptive damping factor is constructed based on these two features. When a data point deviates significantly from the dynamic baseline and local variability, the factor should automatically reduce the influence of that data point; conversely, when the data point is within the normal fluctuation range, the factor should not have any effect to preserve the original information of the data. By applying this damping factor to the original data, excessive interference to the subsequent SG filter fitting process can be effectively suppressed without completely erasing peak information, thus creating conditions for extracting the true growth trend baseline.

[0052] In summary, the number of assessments for dynamic growth baseline assessment and local data fluctuation assessment is first set. In this embodiment of the invention, the number of assessments is set to 48, which corresponds to a 24-hour time window. For any target time in the original wound flow data, continuous wound flow data points are selected before the target time according to the number of assessments. The median of the selected continuous wound flow data points is used as the dynamic growth baseline at the target time. The standard deviation of the selected continuous wound flow data is used as the local fluctuation degree at the target time.

[0053] After obtaining the dynamic growth baseline and the local fluctuation degree at the target time, the adaptive input damping factor is obtained by performing a joint deviation analysis on the original wound flow data based on the dynamic growth baseline and the local fluctuation degree. The original wound flow data is then preliminarily corrected. Specifically, for any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline at the target time is used as the numerator, and the result of adding the local fluctuation degree at the target time to the smallest positive number is used as the denominator. The corresponding fraction is used as the first input damping assessment at the target time. The negative of the square of the first input damping assessment at the target time is then subjected to an exponential mapping with the natural constant as the base, and the corresponding mapping result is used as the adaptive input damping factor at the target time.

[0054] In one implementation, assume the first The original injury flow data at each moment is ;No. The dynamic growth baseline of the raw wound flow data at each time point is: ;No. The degree of local fluctuation at each moment is Then the first The formula for calculating the adaptive input damping factor at time n is:

[0055]

[0056] in, Indicates the first The adaptive input damping factor at each moment; Indicates the first Raw wound flow data at each moment; Indicates the first The dynamic growth baseline of the raw wound flow data at each moment; Indicates the first The degree of local fluctuation at a given moment; Denotes the natural constant e; The use of extremely small positive numbers to prevent the denominator from being 0 is specified in this embodiment of the invention. .

[0057] After obtaining the adaptive input damping factor, the original wound flow data is further corrected based on baseline deviation using the adaptive input damping factor to obtain preliminary corrected wound flow data. Specifically, for any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline is used as the first baseline deviation assessment at the target time; the result of multiplying the adaptive input damping factor at the target time with the first baseline deviation assessment at the target time is used as the first correction assessment at the target time; and the result of adding the dynamic growth baseline at the target time to the first correction assessment at the target time is used as the preliminary corrected wound flow data at the target time.

[0058] In one embodiment, the first The calculation expression for the preliminary corrected injury flow data at each time point is:

[0059]

[0060] in, Indicates the first Preliminary corrected wound flow data at a given moment; Indicates the first The adaptive input damping factor at each moment; Indicates the first Raw wound flow data at each moment; Indicates the first The dynamic growth baseline of the raw wound flow data at each time point.

[0061] It should be noted that the formula is obtained through... This item will take the raw data points at the current moment. Transform its absolute value into a standardized deviation metric. Specifically, this step will... Its dynamic growth baseline The difference is normalized by the local data volatility within its time window. This allows the deviation measure to objectively reflect... The statistical significance under the current physiological context avoids misjudgment that may be caused by the inherent fluctuations in crop growth at different stages.

[0062] Subsequently, this standardized deviation measure is input as an independent variable into a Gaussian function to generate the damping factor. The nonlinear characteristics of this function are the core of achieving selective correction. When When the data values ​​are within the normal physiological fluctuation range, their standardized deviation metric is small, resulting in a smaller calculated value. The value approaches 1. This characteristic ensures that the correction process of this invention does not have a substantial impact on conventional data characterizing true growth dynamics, thus ensuring data fidelity. Conversely, when compensatory water absorption is triggered by post-drought rehydration events, leading to... When a statistically highly improbable instantaneous peak occurs, its standardized deviation metric will become extremely large. In this case, the exponential decay property of the Gaussian function will lead to... The value rapidly and non-linearly approaches 0. This characteristic enables the present invention to accurately identify such physiological artifact signals caused by short-term environmental upheavals. Finally, the formula is modified... To apply this damping factor. The formula structurally transforms the original data points... Decomposed into a baseline trend component and an instantaneous deviation component Damping factor It only applies to the instantaneous deviation component. Therefore, when When the value approaches 0 (i.e., the instantaneous peak value is identified), the instantaneous deviation component is effectively eliminated, resulting in a corrected value. Converging to a stable dynamic baseline This prevents the abnormal peak from distorting the subsequent SG filtering process. When When the value approaches 1 (i.e., when processing regular data), the instantaneous deviation component is fully preserved. Basically equivalent to the original value .

[0063] Thus, the adaptive input damping factor was obtained by performing dynamic baseline and local variability analysis on the original wound flow data, and the wound flow data was initially corrected using the adaptive input damping factor.

[0064] Step S3: By performing peak event and environmental constraint analysis on the smoothed wound flow data, a posterior compensation factor is obtained, and the smoothed wound flow data is then corrected a second time using the posterior compensation factor.

[0065] After processing in step S2, the instantaneous peak artifacts in the original sap flow data have been effectively suppressed, providing a clean input for the SG filter, enabling it to generate a growth baseline unaffected by outliers. However, although the amplitude of the aforementioned instantaneous peak does not represent synchronous dry matter accumulation, its existence itself is a crucial physiological indicator, suggesting a fundamental improvement in the crop's growth environment—a shift from water stress to water abundance—and the activation and significant enhancement of its future growth potential. The damping operation in step S2 essentially removes this peak information from the data sequence, causing the smoothed baseline to fail to reflect this enhanced future growth trend. Specifically, the response of photosynthesis and biomass synthesis in the aboveground parts of the plant to improved root water status exhibits an inherent physiological lag. Therefore, for a period after the peak event, the actual dry matter accumulation rate gradually climbs to a higher steady-state level. The smoothed curve obtained solely through step S2 will underestimate this lag recovery and compensatory growth process. To address this issue, the present invention further constructs an additional compensating factor. This factor functions to inject a compensating signal into the smoothed baseline after the peak event occurs, capable of simulating and quantifying this delayed increase in growth potential. Its triggering should depend on the identification of the peak event; its overall magnitude should be positively correlated with the intensity of the suppressed peak (representing the severity of stress relief); its instantaneous magnitude should also be constrained by current environmental conditions (such as light and soil moisture), as the realization of growth potential depends on a favorable external environment; and its temporal variation should exhibit a dynamic process starting from zero, gradually increasing, reaching a peak, and then slowly stabilizing, to truly reflect the response rhythm of aboveground physiological activities.

[0066] In summary, firstly, the sliding window length and polynomial fitting order of the SG filter are set. In this embodiment of the invention, the sliding window length is set to 11 and the polynomial fitting order is set to 3. The sliding window length and polynomial fitting order can be adjusted according to the actual scenario and are not required. The preliminary corrected wound flow data is smoothed by SG filtering to obtain smoothed wound flow data.

[0067] Subsequently, peak event identification and intensity calculation are performed on the smoothed wound flow data to obtain the peak compensation benchmark. Specifically, a peak evaluation coefficient is set; in this embodiment, the peak evaluation coefficient is set to 3. For any target time in the original wound flow data, the result of multiplying the peak evaluation coefficient by the local fluctuation degree of the target time and adding it to the dynamic growth baseline of the target time is used as the peak event start evaluation threshold for the target time. For any target time, if the value of the smoothed wound flow data at the target time is greater than the peak event start evaluation threshold for the target time, then the target time is determined as the start time of the peak event. The first time after the start time of the peak event that is less than the peak time start evaluation threshold is used as the end time of the peak time corresponding to the start time of the peak event. Through the evaluation of the start time and end time of the peak event, all peak events in the original wound flow data are obtained.

[0068] The result of subtracting the initial corrected flow data at any target time from the flow data at the original flow data is used as the first peak flux assessment at the target time. For any target peak event among all peak events in the original flow data, the result of adding the first peak flux assessments at all times in the target peak event is used as the peak compensation benchmark for the target peak event.

[0069] After obtaining the peak compensation baseline, environmental constraint analysis is performed on the soil moisture data and photosynthetically active radiation data to obtain environmental adjustment factors. Specifically, for any target peak event among all peak events in the original sap flow data, the moment when the original sap flow data of the target peak event is the maximum value is taken as the instantaneous peak moment of the target peak event; for any instantaneous peak moment of the target peak event, the average value of the soil moisture data in the interval formed by the ten days to the four days before the instantaneous peak moment of the target peak event is taken as the reference soil moisture of the target peak event.

[0070] For any instantaneous peak moment of a target peak event, the maximum photosynthetically active radiation data within the seven days preceding the instantaneous peak moment of the target peak event is used as the reference photosynthetically active radiation value of the target peak event;

[0071] For any target time in any target peak event, the soil moisture data at the target time is divided by the calculated result of the reference soil moisture of the target peak event as the first soil moisture assessment at the target time; the photosynthetically active radiation data at the target time is divided by the calculated result of the calculated result of the reference photosynthetically active radiation value at the target peak time as the first photosynthetically active radiation assessment at the target time.

[0072] The result of multiplying the first soil moisture assessment and the first photosynthetically active radiation assessment at the target time during the target peak event is used as the environmental adjustment factor for the target peak event at the target time.

[0073] After obtaining the environmental adjustment factor at the target time, the posterior compensation factor is obtained by jointly processing the peak compensation benchmark and the environmental adjustment factor. The smoothed wound flow data is then corrected a second time. Specifically, a physiological response time constant is set. In this embodiment of the invention, the physiological response time constant is set to 24. For any target time in any target peak event, the result of subtracting the instantaneous peak time of the target peak event from the target time is used as the numerator, and the square of the physiological response time constant is used as the denominator. The resulting fraction is used as the first pulse evaluation of the target time. The result of subtracting the instantaneous peak time of the target peak event from the target time is used as the numerator, and the physiological response time constant is used as the denominator. The resulting fraction is then subjected to an exponential mapping with the natural constant as the base. The resulting fraction is used as the second pulse evaluation of the target time. The result of multiplying the first pulse evaluation and the second pulse evaluation of the target time is used as the pulse response evaluation of the target time.

[0074] The result of multiplying the environmental adjustment factor of the target peak event at the target time, the peak compensation benchmark of the target peak event, and the impulse response evaluation of the target peak event at the target time is used as the posterior compensation factor of the target peak event at the target time.

[0075] In one implementation, assume the first Soil moisture data at each moment is , No. The reference soil moisture for the peak event at each time point is: ;No. The photosynthetically active radiation value at time 1 is , No. The reference photosynthetically active radiation value for the peak event at each time point is ;No. The peak compensation benchmark for the peak event corresponding to each moment is: ;No. The instantaneous peak time of the peak event corresponding to each moment is: The physiological response time constant is Then the first The expression for calculating the posterior compensation factor at time t is:

[0076]

[0077] in, Indicates the first The posterior compensation factor at each time step; Indicates the first Soil moisture data at any given time. Indicates the first Reference soil moisture for the peak event at each time point; Indicates the first The photosynthetically active radiation value at a given time. Indicates the first Reference photosynthetically active radiation value for the peak event corresponding to each moment; Indicates the first The peak compensation baseline for the peak event corresponding to each moment; Indicates the first The instantaneous peak moment of the peak event corresponding to each moment; This represents the physiological response time constant.

[0078] After obtaining the posterior compensation factor at the target time, the result of adding the posterior compensation factor of the target peak event at the target time to the target time data corresponding to the smoothed wound flow data is used as the wound flow data for secondary correction.

[0079] It should be noted that, in this invention, the purpose of the posterior compensation factor is to quantify and recover the physiological information lost after step S2, thereby addressing the problem of underestimating compensatory growth after stress due to a smoothed baseline. The core term of the formula... The total flux of compensatory water uptake by roots during post-drought rehydration events was quantified, and its physical meaning represents the severity of this state transition. As a fundamental measure of total compensation, this ensures that the intensity of compensation is directly correlated with the intensity of the prior event that relieved the coercion, thus providing a solid data foundation for compensation. Secondly, the formula introduces... This environmental potential coefficient provides a realistic constraint on the implementation of compensation. The realization of crop growth potential depends on suitable water and light conditions. This coefficient compares and normalizes real-time measurements of soil moisture and photosynthetically active radiation with their respective reference values. This allows the calculated value of the posterior compensation factor to be dynamically adjusted according to the current sufficiency of environmental resources. Under conditions of sufficient water and good light, the coefficient value is higher, allowing for stronger compensation; conversely, if subsequent cloudy or rainy weather occurs, the coefficient value will decrease, thus reasonably suppressing the intensity of compensation. This impulse response function describes the dynamic process of the compensation effect evolving over time. This function simulates the hysteresis response pattern prevalent in biological systems: at the peak of the event, the compensation value is zero; as time progresses, the compensation effect gradually increases, eventually reaching a state determined by a physiological time constant. The compensation effect peaks at the moment of decision; subsequently, as the plant gradually adapts to the new superior environment and enters a new growth homeostasis, the compensation effect smoothly decays. This design ensures that the application of the compensation signal is not an abrupt step, but a dynamic process consistent with the plant's physiological rhythms. Finally, by adding the smoothed sap flow data to the posterior compensation factor to obtain the secondary corrected sap flow data, the distortion artifacts caused by short-term stress responses in the original data are eliminated, and the lagged growth gain brought about by environmental improvement is restored. Ultimately, a characteristic sequence that accurately reflects the true growth trend of maize after experiencing drastic environmental changes is obtained.

[0080] Thus, the peak event and environmental constraint analysis of the smoothed wound flow data was completed, the posterior compensation factor was obtained, and the smoothed wound flow data was then corrected a second time using the posterior compensation factor.

[0081] Step S4: Model and predict the corrected wound flow characteristics, and obtain the corn dry matter accumulation rate through the prediction model.

[0082] After obtaining the secondary-corrected wound flow data through steps S2 and S3, the wound flow data is used as the core input feature and fed into a pre-trained corn dry matter accumulation prediction model. This prediction model is constructed using existing machine learning algorithms; preferably, a support vector regression model is used for pre-training to obtain the pre-trained corn dry matter accumulation prediction model. During the training phase, the model has learned the nonlinear mapping relationship between various physiological and environmental inputs, including wound flow features, and the corn dry matter accumulation rate per unit time. Therefore, the dynamically corrected secondary-corrected wound flow data obtained by the method of this invention is input into this model to obtain the predicted corn dry matter accumulation rate.

[0083] Thus, the modeling and prediction of the corrected wound flow characteristics were completed, and the corn dry matter accumulation rate was obtained through the prediction model.

[0084] Step S5: Obtain the corn yield prediction result by accumulating and integrating the corn dry matter accumulation rate.

[0085] Through steps S2 to S4, this invention successfully solves the core technical problem of prediction distortion caused by the inability to distinguish between physiological artifacts and true growth trends in special scenarios such as post-drought rehydration. Specifically, this invention achieves automatic identification and interference suppression of instantaneous peaks caused by compensatory water absorption effects through an adaptive input damping factor; and then restores the lag-compensating growth information brought about by environmental improvement through a posterior compensation factor. This dual correction mechanism ensures that the final secondary-corrected sap flow data can truly reflect the root physiological activity related to dry matter accumulation. Therefore, the obtained dry matter accumulation rate prediction results have significantly higher accuracy than existing technologies. By summing and integrating the predicted accumulation rates at each moment throughout the entire growth cycle, the total dry matter accumulation in any time period can be obtained, thus providing reliable data support for accurate assessment of crop growth status, optimization of field management decisions, and prediction of final yield.

[0086] This completes the process of obtaining corn yield prediction results by accumulating the dry matter accumulation rate of corn.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting dry matter accumulation in maize based on root sap flow characteristics, characterized in that, The method includes: Step S1: Obtain a complete multidimensional time series dataset by performing synchronization preprocessing on multi-source time series data; Step S2: By performing dynamic baseline and local variability analysis on the original wound flow data, the adaptive input damping factor is obtained, and the wound flow data is initially corrected using the adaptive input damping factor; Step S3: By performing peak event and environmental constraint analysis on the smoothed wound flow data, the posterior compensation factor is obtained, and the smoothed wound flow data is then corrected a second time using the posterior compensation factor. Step S4: Model and predict the corrected wound flow characteristics, and obtain the corn dry matter accumulation rate through the prediction model; Step S5: Obtain the corn yield prediction result by cumulatively integrating the corn dry matter accumulation rate.

2. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 1, characterized in that, The process of obtaining a complete multidimensional time series dataset by synchronizing and preprocessing multi-source time series data includes: After maize enters the jointing stage, representative plants are selected and equipped with stem flow meters to continuously collect and record the sap flow rate data sequence of the stem at a sampling frequency of once every 30 minutes. Soil moisture sensors are deployed in the main distribution area of ​​the plant roots to collect and record soil moisture data sequences at the same sampling frequency as the sap flow rate data. Photosynthetically active radiation sensors are installed above the maize canopy or in field weather stations to collect and record photosynthetically active radiation data sequences at the same sampling frequency as the sap flow rate data. After completing the above data collection, the sap flow rate data sequence, soil moisture data sequence, and photosynthetically active radiation data sequence are timestamped and aligned. Missing data points are filled in using nearest neighbor interpolation or linear interpolation methods to obtain a complete and synchronized multidimensional time series dataset.

3. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 2, characterized in that, The process involves performing dynamic baseline and local variability analysis on the original wound flow data to obtain an adaptive input damping factor, and then using this adaptive input damping factor to perform preliminary corrections to the wound flow data, including: Set the number of assessments for dynamic growth baseline assessment and local data fluctuation assessment; for any target time in the original wound flow data, select continuous wound flow data points before the target time according to the number of assessments, and use the median of the selected continuous wound flow data points as the dynamic growth baseline at the target time; use the standard deviation of the selected continuous wound flow data as the local fluctuation degree at the target time. By performing a joint deviation analysis on the original wound flow data based on the dynamic growth baseline and the degree of local fluctuation, an adaptive input damping factor is obtained, and the original wound flow data is preliminarily corrected.

4. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 3, characterized in that, The process involves performing a joint deviation analysis on the original wound flow data based on the dynamic growth baseline and the degree of local fluctuations to obtain an adaptive input damping factor, and then performing preliminary corrections on the original wound flow data, including: For any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline at the target time is used as the numerator, and the result of adding the local fluctuation degree at the target time to the minimum positive number is used as the denominator. The corresponding fraction is used as the first input damping assessment at the target time. The negative of the square of the first input damping assessment at the target time is subjected to an exponential mapping with the natural constant as the base, and the corresponding mapping result is used as the adaptive input damping factor at the target time. The original wound flow data is corrected based on baseline deviation by using an adaptive input damping factor to obtain preliminary corrected wound flow data.

5. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 4, characterized in that, The process of correcting the original wound flow data based on baseline deviation using an adaptive input damping factor to obtain preliminarily corrected wound flow data includes: For any target time in the original wound flow data, the result of subtracting the wound flow rate data at the target time from the dynamic growth baseline is used as the first baseline deviation assessment for the target time; the result of multiplying the adaptive input damping factor at the target time with the first baseline deviation assessment for the target time is used as the first correction assessment for the target time; and the result of adding the dynamic growth baseline at the target time to the first correction assessment for the target time is used as the preliminary corrected wound flow data for the target time.

6. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 1, characterized in that, The process involves performing peak event and environmental constraint analysis on the smoothed wound flow data to obtain a posterior compensation factor, and then using this posterior compensation factor to perform a secondary correction on the smoothed wound flow data, including: Set the sliding window length and polynomial fitting order of the SG filter; smooth the initially corrected wound flow data using the SG filter to obtain the smoothed wound flow data; Peak compensation baseline is obtained by identifying peak events and calculating their intensity in the smoothed wound flow data. Environmental regulation factors were obtained by performing environmental constraint analysis on soil moisture data and photosynthetically active radiation data. By jointly processing the peak compensation baseline and the environmental adjustment factor, the posterior compensation factor is obtained, and the smoothed wound flow data is then corrected a second time.

7. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 6, characterized in that, The process of identifying peak events and calculating the intensity of the smoothed wound flow data to obtain the peak compensation benchmark includes: A peak evaluation coefficient is set. For any target time in the original wound flow data, the peak evaluation coefficient is multiplied by the local fluctuation degree of the target time and added to the dynamic growth baseline of the target time. The result is used as the peak event start evaluation threshold for the target time. For any target time, if the value of the smoothed wound flow data at the target time is greater than the peak event start evaluation threshold, the target time is determined as the start time of the peak event. The first time after the start time of the peak event that is less than the peak time start evaluation threshold is used as the end time of the peak time corresponding to the start time of the peak event. All peak events in the original wound flow data are obtained through the evaluation of the start and end times of the peak events. The result of subtracting the initial corrected flow data at the target time from the flow data at any target time in the original flow data is used as the first peak flux assessment at the target time. For any target peak event among all peak events in the original wound flow data, the calculation result of summing the first peak flux assessments at all times in the target peak event is used as the peak compensation benchmark for the target peak event.

8. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 6, characterized in that, The process involves performing environmental constraint analysis on soil moisture data and photosynthetically active radiation data to obtain environmental regulation factors, including: For any target peak event among all peak events in the original wound flow data, the moment when the original wound flow data has the maximum value in the target peak event is taken as the instantaneous peak moment of the target peak event; For any instantaneous peak moment of a target peak event, the average value of the soil moisture data in the interval formed by the ten days to the four days prior to the instantaneous peak moment of the target peak event is taken as the reference soil moisture of the target peak event. For any instantaneous peak moment of a target peak event, the maximum photosynthetically active radiation data within the seven days preceding the instantaneous peak moment of the target peak event is used as the reference photosynthetically active radiation value of the target peak event; For any target time in any target peak event, the soil moisture data at the target time is divided by the calculated result of the reference soil moisture of the target peak event as the first soil moisture assessment at the target time; the photosynthetically active radiation data at the target time is divided by the calculated result of the calculated result of the reference photosynthetically active radiation value at the target peak time as the first photosynthetically active radiation assessment at the target time. The result of multiplying the first soil moisture assessment and the first photosynthetically active radiation assessment at the target time during the target peak event is used as the environmental adjustment factor for the target peak event at the target time.

9. The method for predicting maize dry matter accumulation based on root sap flow characteristics according to claim 6, characterized in that, The process involves jointly processing the peak compensation baseline and the environmental adjustment factor to obtain the posterior compensation factor, and then performing a secondary correction on the smoothed wound flow data, including: Define a physiological response time constant; for any target moment in any target peak event, use the result of subtracting the instantaneous peak moment of the target peak event from the target moment as the numerator, and the square of the physiological response time constant as the denominator. Use the resulting fraction as the first pulse evaluation of the target moment; use the result of subtracting the instantaneous peak moment of the target peak event from the target moment as the numerator, and the physiological response time constant as the denominator. Perform an exponential mapping with the natural constant as the base on the resulting fraction. Use the resulting fraction as the second pulse evaluation of the target moment. Multiply the first pulse evaluation and the second pulse evaluation of the target moment as the pulse response evaluation of the target moment. The result of multiplying the environmental adjustment factor of the target peak event at the target time, the peak compensation benchmark of the target peak event, and the impulse response evaluation of the target peak event at the target time is used as the posterior compensation factor of the target peak event at the target time. The result of adding the posterior compensation factor of the target peak event at the target time to the corresponding target time data in the smoothed wound flow data is used as the wound flow data for secondary correction.

Images