Grassland year-on-year accumulated temperature and accumulated rain budgeting method, equipment and medium

Abstract

The invention discloses a grassland year-on-year accumulated temperature and rain budgeting method and device and a medium. The method comprises the steps that meteorological station data, remote sensing vegetation index data and soil moisture content data of a target grassland are collected; based on the conditions that the average temperature of continuous preset days is not lower than the preset base temperature and the soil volumetric water content exceeds the humidity threshold value of the seedling establishment period, determining a phenological seedling establishment period starting day, and based on the condition that the remote sensing vegetation index is decreased to the peak proportion of the growth season for continuous preset days, determining a phenological yellow-blight period ending day; planning an accumulated temperature and accumulated rain calculation window according to the phenological reviving period starting day and the phenological yellow-dry period ending day, and calculating effective accumulated temperature and accumulated rain budget values in the accumulated temperature and accumulated rain calculation window; adopting partial correlation analysis to quantify the lag influence of the number of seasonal rainfall days on vegetation growth to generate a time lag correction coefficient so as to adjust the rainfall budget value; and inputting the historical accumulated temperature, the historical accumulated rain, the soil water content and the time delay correction coefficient into a pre-trained machine learning model, and outputting a year-on-year accumulated temperature and accumulated rain change rate.

Description

Technical Field

[0001] This application relates to the field of accumulated temperature and rainfall estimation technology, and in particular to a method, equipment and medium for estimating the same accumulated temperature and rainfall over grasslands. Background Technology

[0002] Accumulated temperature and rainfall measurements in grasslands are crucial for monitoring forage growth, planning rotational grazing, and providing drought early warning. Traditional methods typically use fixed time windows to calculate accumulated temperature and rainfall, such as using fixed dates as the start and end points of the growing season, while ignoring interannual fluctuations in phenological periods. Due to the influence of climate change, the greening-up period and the yellowing-off period of grasslands may vary significantly from year to year. Fixed-window calculations can lead to biases in accumulated temperature and rainfall measurements, thus affecting the accuracy of grassland management.

[0003] Furthermore, most existing methods do not consider the time-lag effect of climate factors on vegetation growth. For example, spring precipitation may affect summer grassland biomass, but traditional calculation models are usually based only on meteorological data within the current growing season, failing to quantify the lagged effects of pre-season climate factors, leading to inconsistencies between predicted results and actual vegetation growth. Simultaneously, existing technologies largely rely on single meteorological data, lacking fusion analysis of multi-source data such as remote sensing vegetation indices and soil moisture, making it difficult for models to accurately reflect the dynamic response mechanisms of vegetation. Summary of the Invention

[0004] This application provides a method, equipment, and medium for estimating the year-on-year accumulated temperature and rainfall in grasslands and pastures, in order to solve the above-mentioned technical problems.

[0005] On the one hand, embodiments of this application provide a method for estimating the year-on-year accumulated temperature and rainfall of grasslands, including:

[0006] Collect meteorological station data, remote sensing vegetation index data, and soil moisture data of the target grassland;

[0007] Based on the conditions that the average temperature for a consecutive preset number of days is not lower than the preset base temperature and the soil volumetric water content exceeds the humidity threshold of the greening period, the start date of the phenological greening period is determined, and based on the condition that the remote sensing vegetation index decreases to the proportion of the peak of the growing season for a consecutive preset number of days, the end date of the phenological yellowing and withering period is determined.

[0008] Based on the start date of the phenological greening period and the end date of the phenological yellowing and withering period, the accumulated temperature and rainfall calculation window is dynamically planned, and within the accumulated temperature and rainfall calculation window, the effective accumulated temperature and rainfall budget value is calculated.

[0009] Partial correlation analysis was used to quantify the lagged effect of preseason precipitation days on vegetation growth and generate time lag correction coefficients to adjust the accumulated rainfall budget.

[0010] The historical accumulated temperature, historical accumulated rainfall, soil moisture content, and the time lag correction coefficient are input into a pre-trained machine learning model, which outputs the year-on-year change rate of accumulated temperature and accumulated rainfall.

[0011] In one implementation of this application, the start date of the phenological greening period is determined based on the conditions that the average temperature over a consecutive preset number of days is not lower than a preset base temperature and the soil volumetric moisture content exceeds the humidity threshold for the greening period. Specifically, this includes:

[0012] Traverse the daily average temperature sequence in the meteorological station data to identify all intervals where the daily average temperature for a consecutive preset number of days is not lower than the preset greening temperature threshold.

[0013] The first interval in the selected intervals whose average soil moisture content exceeds a preset humidity threshold is selected, and the starting date of the first interval is determined as the starting date of the phenological greening period.

[0014] In one implementation of this application, the termination date of the phenological yellowing and withering period is determined based on the condition that the remotely sensed vegetation index decreases to the proportion of the peak value during the growing season for a consecutive preset number of days, specifically including:

[0015] Traverse the remote sensing vegetation index data and extract the peak vegetation index of the target grassland during the growing season;

[0016] If the remote sensing vegetation index of the target grassland decreases to a preset percentage of the peak value of the vegetation index for a preset number of consecutive preset days, the first day that meets the condition is marked as the end date of the phenological yellowing and withering period.

[0017] In one implementation of this application, partial correlation analysis is used to quantify the lagged impact of preseason precipitation days on vegetation growth, generating a time-lag correction coefficient to adjust the accumulated rainfall budget value, specifically including:

[0018] Extract the precipitation days sequence of the target grassland in the preset months before the growing season from the meteorological station data, and extract the peak vegetation index sequence of the target grassland in the preset months before the growing season from the remote sensing vegetation index data.

[0019] Partial correlation analysis was performed on the precipitation days sequence and the vegetation index peak sequence to calculate the partial correlation coefficient between the precipitation days and the vegetation index peak.

[0020] If the partial correlation coefficient exceeds a preset significance threshold, a time lag correction coefficient corresponding to the target grassland is generated, and the rain accumulation budget value of the target grassland is adjusted based on the time lag correction coefficient.

[0021] In one implementation of this application, calculating the effective accumulated temperature and accumulated rainfall budget value within the accumulated temperature and rainfall calculation window specifically includes:

[0022] Based on the grassland type corresponding to the target grassland, a preset base temperature threshold for the target grassland is determined, and within the accumulated temperature and rainfall calculation window, dates with daily average temperatures exceeding the preset base temperature threshold are selected.

[0023] The temperature values ​​exceeding the threshold corresponding to the stated date are accumulated to obtain the effective accumulated temperature.

[0024] In one implementation of this application, before inputting historical accumulated temperature, historical accumulated rainfall, soil moisture content, and the time lag correction coefficient into a pre-trained machine learning model and outputting the year-on-year accumulated temperature and accumulated rainfall change rate, the method further includes:

[0025] An input feature set is constructed based on historical data, and the year-on-year change rate of accumulated temperature and rainfall is used as the target variable to train a regression model; the historical data includes historical accumulated temperature, rainfall, number of days with precipitation, soil moisture content, and time lag coefficient;

[0026] The model outputs a ranking of feature importance based on the trained model, and the model's prediction weights are optimized according to this ranking.

[0027] In one implementation of this application, after collecting meteorological station data, remote sensing vegetation index data, and soil moisture data of the target grassland, the method further includes:

[0028] Outliers in the meteorological station data are removed, and missing data in the meteorological station data is imputed.

[0029] The spatial interpolation algorithm unifies multi-source data to a standard grid resolution and normalizes the units and sampling frequencies of different data sources.

[0030] In one implementation of this application, it further includes:

[0031] Historical remote sensing vegetation index data is acquired, and vegetation biomass is obtained by inversion based on the historical remote sensing vegetation index data.

[0032] The parameters of the Logistic growth model were fitted to establish the correlation between accumulated temperature and vegetation biomass, and vegetation feedback optimization was performed on the accumulated temperature based on the correlation.

[0033] On the other hand, this application also provides a grassland and pasture year-on-year accumulated temperature and rainfall estimation device, the device comprising:

[0034] At least one processor;

[0035] And, a memory communicatively connected to the at least one processor;

[0036] The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a grassland and pasture year-on-year accumulated temperature and rainfall budgeting method as described above.

[0037] On the other hand, this application embodiment also provides a non-volatile computer storage medium storing computer-executable instructions, which, when executed, implement the above-described method for estimating the year-on-year accumulated temperature and rainfall of grasslands.

[0038] This application provides a method, equipment, and medium for estimating the year-on-year accumulated temperature and rainfall in grasslands, which has at least the following beneficial effects:

[0039] By dynamically defining the calculation window for accumulated temperature and rainfall, and adjusting the calculation cycle based on the actual phenological characteristics of the greening and withering periods, the interannual deviation caused by fixed time windows is avoided, making the calculation of accumulated temperature and rainfall more consistent with the actual growth patterns of grassland vegetation. Partial correlation analysis is used to quantify the lagged impact of pre-season precipitation days on vegetation growth, and the rainfall budget value is adjusted based on the time lag correction coefficient, solving the problem of traditional methods ignoring the delayed effect of climate factors. Combining meteorological station data, remote sensing vegetation indices, and soil moisture data, a machine learning model is used for comprehensive analysis, so that the calculation results not only rely on meteorological data, but also reflect the dynamic response of vegetation and soil moisture conditions. Attached Figure Description

[0040] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0041] Figure 1 A flowchart illustrating a method for estimating the year-on-year accumulated temperature and rainfall of grasslands and pastures, provided in an embodiment of this application;

[0042] Figure 2 This is a schematic diagram of the internal structure of a grassland and pasture accumulated temperature and rainfall budgeting device provided in an embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0045] Figure 1 This is a flowchart illustrating a method for estimating the year-on-year accumulated temperature and rainfall of grasslands, as provided in an embodiment of this application.

[0046] The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using a server as an example.

[0047] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server. This application does not make any specific limitations on this.

[0048] like Figure 1 As shown in the embodiment of this application, a method for estimating the year-on-year accumulated temperature and rainfall of grasslands includes:

[0049] Step 101: Collect meteorological station data, remote sensing vegetation index data, and soil moisture data of the target grassland.

[0050] Accumulated temperature refers to the sum of daily average temperatures ≥10℃ over a certain period. It is an important indicator for measuring the heat conditions during crop growth and development, measured in ℃·d. Accumulated temperature reflects the cumulative heat demand of crops during their growth cycle; different crops have different requirements for accumulated temperature at different growth stages. Accumulated rainfall refers to the cumulative precipitation in a specific region over a specific period, measured in mm. Accumulated rainfall reflects the total precipitation in a region over a period and is of significant reference value for agricultural irrigation, water resource management, and building drainage design. Days of precipitation (DOP) represent the number of days with precipitation ≥0.1 mm during the growing season, a key factor regulating vegetation phenology. Time lag effect represents the delayed impact of climatic factors (such as precipitation and temperature) on vegetation growth (e.g., 1-4 months). Dynamic phenological window refers to the accumulated temperature / accumulated rainfall calculation period adaptively defined based on the greening-up period and the yellowing-off period. The greening-up period refers to 5 consecutive days of T... mean ≥0℃ and SWC>0.25m³ / m 3 During the yellowing and withering period (EVI drops to 50% of its peak).

[0051] In this embodiment, data acquisition is a fundamental step in the budgeting method. Meteorological station data is acquired through IoT weather stations deployed on the grassland, including daily average temperature (calculated from the highest / lowest temperature), daily precipitation, and sunshine duration sequences. For example, the temperature sensor needs to be shielded from direct sunlight interference, and precipitation data is collected using a tipping bucket rain gauge.

[0052] Remote sensing vegetation index data originates from satellite platforms (such as MODIS) and requires the acquisition of Enhanced Vegetation Index (EVI) time-series data. It should be noted that EVI is calculated using red and near-infrared reflectance, and its resistance to atmospheric interference is superior to NDVI, making it more suitable for grassland vegetation monitoring. Soil moisture data is collected by volumetric water content sensors buried at a depth of 5-10 cm, directly reflecting the moisture status of the root zone.

[0053] Understandably, after data acquisition, preprocessing of the raw data is necessary. Specifically, for abrupt changes in meteorological data caused by sensor malfunctions, such as a sudden temperature rise of 10°C followed by immediate recovery, median filtering is used to identify and remove them. If single-station data is missing, the complete sequence is reconstructed through spatial correlation of neighboring stations, such as using the inverse distance weighting method. An adaptive gridding algorithm is used to uniformly map multi-source data to a standard geographic grid, such as 1km×1km, to eliminate scale differences between remote sensing and ground data.

[0054] Step 102: Based on the condition that the average temperature for a consecutive preset number of days is not lower than the preset base temperature and the soil volumetric water content exceeds the humidity threshold of the greening period, determine the start date of the phenological greening period, and based on the condition that the remote sensing vegetation index decreases to the proportion of the growing season peak for a consecutive preset number of days, determine the end date of the phenological yellowing and withering period.

[0055] In this embodiment, a multi-condition collaborative determination method is used to determine the start date of the phenological greening-up period. It is understood that traditional greening-up period determination often considers only temperature as a single indicator, while this application significantly improves the accuracy of the determination by introducing soil moisture as a key parameter. Specifically, the system first traverses the daily average temperature sequence in the meteorological station data, identifying all intervals where the average temperature for a consecutive preset number of days is not lower than a preset greening-up temperature threshold. It should be noted that the consecutive preset number of days is an observation window set according to the growth characteristics of different grassland vegetation types to ensure the stability of the temperature rise.

[0056] For example, after identifying all temperature ranges that meet the criteria, the system further filters out the first range where the average soil moisture content exceeds a preset humidity threshold. Understandably, the innovation of this step lies in incorporating the soil thawing state into the judgment criteria, because even if the temperature meets the requirements, vegetation cannot properly regrow if the soil remains frozen. Specifically, the system determines the starting date of the first range that simultaneously meets both temperature and humidity conditions as the starting date of the phenological regrowth period. This dual-condition judgment mechanism effectively avoids misjudgments that may be caused by a single indicator, especially when temperatures fluctuate significantly in early spring.

[0057] It should be noted that the accuracy of the judgment can only be ensured after the quality control and standardization of meteorological data and soil moisture data are completed in this embodiment. It is understood that this method is particularly suitable for the grassland regions of northern my country, where the spring soil thawing process and temperature rise often occur asynchronously, making traditional methods prone to errors.

[0058] In this embodiment, the determination of the end date of the phenological yellowing and withering period adopts a dynamic determination method based on vegetation growth curves. It is understood that, compared with methods using fixed dates or fixed temperature drops, this application determines the yellowing and withering period by monitoring the degree of decay of the vegetation index relative to its growth peak, which better reflects the actual physiological state of the vegetation. Specifically, the system first needs to traverse the remote sensing vegetation index data for the entire growing season and extract the peak vegetation index of the target grassland during that growing season. It should be noted that this peak value represents the optimal growth state of the vegetation for that year and is the benchmark value for determining the degree of decay.

[0059] For example, after determining the peak of the growing season, the system continuously monitors changes in the remote sensing vegetation index of the target grassland. Understandably, as vegetation enters its yellowing period, its photosynthetic capacity continuously weakens, manifested as a continuous decline in the vegetation index. Specifically, when the vegetation index is monitored to have decreased for a preset number of consecutive days to a preset proportion of the growing season peak, the system marks the first day that meets this condition as the end date of the phenological yellowing period. It should be noted that this relative value-based determination method can automatically adapt to growth differences in different years and grassland types, avoiding the bias that may arise from absolute value determinations.

[0060] Understandably, this method is particularly suitable for large-scale grassland monitoring because remote sensing data can provide continuous spatial coverage, overcoming the limitations of sparse ground observation stations. For example, this method can detect signs of vegetation decline earlier than traditional ground observation methods, providing more timely scientific evidence for grassland management.

[0061] Step 103: Based on the start date of the phenological greening period and the end date of the phenological yellowing and withering period, dynamically plan the accumulated temperature and rainfall calculation window, and calculate the effective accumulated temperature and rainfall budget value within the accumulated temperature and rainfall calculation window.

[0062] In this embodiment, the calculation of effective accumulated temperature employs a method based on grassland type differentiation. It is understood that different grassland types have significantly different heat requirements, and traditional methods using a uniform base temperature threshold cannot accurately reflect this difference. Specifically, the system first automatically matches the corresponding grassland type classification based on the geographical location and vegetation characteristics of the target grassland, including but not limited to major types such as meadow steppe, typical steppe, and desert steppe. It should be noted that each grassland type has a preset base temperature threshold, which is the initiation temperature of vegetation physiological activity determined through long-term observation and experimental research.

[0063] For example, after determining the base temperature threshold, the system filters out days with daily average temperatures exceeding that threshold within a dynamic calculation window. This filtering process ensures that only temperatures truly effective for vegetation growth are included in the calculation. Specifically, for each effective temperature day, the system calculates the difference between the daily average temperature and the base temperature threshold, then accumulates all these excess values ​​over the entire window to obtain the effective accumulated temperature. It should be noted that this calculation method excludes ineffective accumulated temperature below the vegetation physiological activity threshold, making the calculation results more reflective of the actual heat resources obtained by the vegetation.

[0064] Understandably, the above method is applicable to vast grassland areas where different types of grasslands are distributed from east to west, and the vegetation's response characteristics to heat vary. For example, compared to the traditional uniform threshold method, this differentiated calculation method significantly improves the correlation between accumulated temperature measurement results and vegetation growth status, providing a more reliable basis for assessing heat resources for precise grassland management. It should be noted that this method considers both spatial variability and temporal dynamics, achieving precise quantification of grassland vegetation heat conditions through the combination of dynamic windows and differentiated thresholds.

[0065] In this embodiment, the effective accumulated temperature is calculated using the following formula:

[0066]

[0067] Among them, AT eff The effective accumulated temperature of the target grassland is represented by T, where started indicates the start date of the phenological greening-up period, end indicates the end date of the phenological yellowing-off period, and max() represents a non-negative constraint function that ensures the accumulated temperature contribution is zero when the daily average temperature is less than the base temperature threshold. mean T represents the average daily temperature of the target grassland. base This represents the base temperature threshold of grassland during the growing season, for example, the base temperature T of desert steppe. base =0℃, the base temperature T of a typical grassland base =5.7℃.

[0068] Step 104: Use partial correlation analysis to quantify the lagged impact of preseason precipitation days on vegetation growth and generate time lag correction coefficients to adjust the accumulated rainfall budget value.

[0069] In this embodiment, the quantification of the time lag effect employs an innovative method based on partial correlation analysis. It is understood that grassland vegetation growth is not only affected by current precipitation but also exhibits a complex lag response relationship with previous precipitation, a crucial characteristic often overlooked by traditional methods. Specifically, the system first extracts the precipitation day sequence for the target grassland in a preset month before the growing season from meteorological station data. It should be noted that the preset month is an observation period set according to the vegetation growth characteristics of different grassland areas, typically covering the critical water accumulation period before vegetation germination. The statistics of precipitation days, rather than the total amount, better reflect the sustainability of water supply.

[0070] For example, the system simultaneously extracts the peak vegetation index sequence for the corresponding period from the remote sensing vegetation index data. It is understood that the peak vegetation index objectively reflects the optimal growth state of vegetation and is an ideal indicator for measuring the lagged effects of precipitation. Specifically, by performing partial correlation analysis on these two sets of sequences, the system can eliminate interference from other climatic factors, accurately calculate the partial correlation coefficient between the number of precipitation days and the peak vegetation index, effectively isolate the influence of covariates such as temperature, and reveal the net effect of precipitation lag alone.

[0071] Understandably, when the calculated partial correlation coefficient exceeds a preset significance threshold, the system generates a corresponding time-lag correction coefficient. This accurately captures the lagged impact of spring precipitation on summer grassland productivity, making the accumulated rainfall budget more consistent with the actual water requirements of vegetation. Specifically, this coefficient reflects the actual degree to which previous precipitation promoted vegetation growth and will be used to adjust the current accumulated rainfall budget value. It should be noted that this adjustment is not a simple linear superposition, but a dynamic correction achieved by establishing a precipitation lag response model.

[0072] It should be noted that this application, by integrating meteorological station data and remote sensing monitoring data, achieves spatiotemporal quantification of precipitation lag effects, providing a new technical approach for accurately assessing grassland water use efficiency. Understandably, this time-lag correction mechanism is particularly suitable for arid and semi-arid grassland areas with uneven precipitation distribution, and can significantly improve the accuracy of grassland productivity prediction.

[0073] In this embodiment, the lagged effect of preseason precipitation days on vegetation growth is quantified using the following partial correlation analysis formula:

[0074]

[0075] Where, r xy·z This represents the intensity of the pure lag effect of the number of precipitation days on vegetation growth, excluding temperature interference.xy The original correlation coefficient, r, represents the relationship between the number of precipitation days and the peak vegetation index. xz The value r represents the strength of the correlation between the number of precipitation days and temperature factors (such as accumulated temperature). yz This indicates the strength of the correlation between the peak vegetation index and temperature factors (such as accumulated temperature). This represents the weighting to eliminate the interference of accumulated temperature on precipitation and vegetation.

[0076] Step 105: Input historical accumulated temperature, historical accumulated rainfall, soil moisture content and time lag correction coefficient into the pre-trained machine learning model and output the year-on-year accumulated temperature and accumulated rainfall change rate.

[0077] In this embodiment, an input feature set is first constructed based on historical data, including historical accumulated temperature, accumulated rainfall, number of days with precipitation, soil moisture content and time lag coefficient, etc.; then, a regression model is trained with the year-on-year change rate of accumulated temperature and accumulated rainfall as the target variable.

[0078] It should be noted that after the model training is complete, the system outputs a ranking of the importance of each feature and optimizes the model's prediction weights based on this ranking. For example, ensemble learning methods such as random forests are preferred due to their good feature selection capabilities and resistance to overfitting. Ultimately, the trained model can accurately predict future trends in accumulated temperature and rainfall, providing decision support for grassland management.

[0079] In this embodiment, the relationship between grassland vegetation growth and accumulated temperature is not a simple linear one, but rather exhibits a significant physiological response threshold and saturation effect. Specifically, the system first acquires historical remote sensing vegetation index data of the target grassland, which typically comes from continuous observation records over many years. It should be noted that by inverting these vegetation index data, vegetation biomass information for the corresponding period can be obtained, which is the foundational data for establishing the growth model.

[0080] For example, after acquiring vegetation biomass data, the system fits the parameters of a Logistic growth model. Understandably, the Logistic model effectively describes the typical S-shaped curve characteristic of vegetation growth, from slow accumulation to rapid growth, and finally to saturation. Specifically, the model fitting process focuses on determining two key parameters: one is the parameter k, reflecting the growth rate, and the other is the parameter AT0, characterizing the growth threshold. It should be noted that these parameters are determined by inverting the correspondence between vegetation biomass and accumulated temperature from historical data, ensuring the model accurately portrays the local vegetation growth characteristics.

[0081] Understandably, after fitting the model parameters, the system establishes a quantitative correlation between accumulated temperature and vegetation biomass. Specifically, this relationship will be used for vegetation feedback optimization of accumulated temperature, that is, adjusting the calculation weight of accumulated temperature based on the actual growth response of the vegetation. It should be noted that this optimization is not a simple numerical correction, but rather a transformation of accumulated temperature data into a quantitative indicator of the degree of vegetation physiological response through a growth model. This accurately identifies the key thresholds and saturation points of vegetation growth's response to accumulated temperature, making the accumulated temperature calculation results more consistent with the actual growth patterns of vegetation.

[0082] It should be noted that by introducing a vegetation growth feedback mechanism, meteorological data and ecological processes are organically combined, overcoming the problem of disconnect between meteorological indicators and vegetation responses in traditional methods. Understandably, this vegetation feedback optimization is particularly suitable for grassland management in climate change-sensitive areas, and can provide a scientific basis for accurately assessing the impact of climate warming on grassland productivity.

[0083] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a grassland accumulated temperature and rainfall estimation device, the structure of which is as follows: Figure 2 As shown.

[0084] Figure 2 This is a schematic diagram of the internal structure of a grassland and pasture accumulated temperature and rainfall estimation device provided in an embodiment of this application. Figure 2 As shown, the device includes:

[0085] At least one processor;

[0086] And, a memory that is communicatively connected to at least one processor;

[0087] The memory stores instructions that can be executed by at least one processor, and the instructions, when executed by at least one processor, enable at least one processor to:

[0088] Collect meteorological station data, remote sensing vegetation index data, and soil moisture data of the target grassland;

[0089] Based on the conditions that the average temperature for a consecutive preset number of days is not lower than the preset base temperature and the soil volumetric water content exceeds the humidity threshold of the greening period, the start date of the phenological greening period is determined, and based on the condition that the remote sensing vegetation index decreases to the proportion of the growing season peak for a consecutive preset number of days, the end date of the phenological yellowing and withering period is determined.

[0090] Based on the start date of the phenological greening period and the end date of the phenological yellowing and withering period, the accumulated temperature and rainfall calculation window is dynamically planned, and the effective accumulated temperature and rainfall budget value is calculated within the accumulated temperature and rainfall calculation window;

[0091] Partial correlation analysis was used to quantify the lagged effect of preseason precipitation days on vegetation growth and generate time lag correction coefficients to adjust the accumulated rainfall budget.

[0092] Historical accumulated temperature, historical accumulated rainfall, soil moisture content, and time lag correction coefficients are input into a pre-trained machine learning model, which outputs the year-on-year change rate of accumulated temperature and accumulated rainfall.

[0093] This application also provides a non-volatile computer storage medium storing computer-executable instructions, which, when executed, can:

[0094] Collect meteorological station data, remote sensing vegetation index data, and soil moisture data of the target grassland;

[0095] Based on the conditions that the average temperature for a consecutive preset number of days is not lower than the preset base temperature and the soil volumetric water content exceeds the humidity threshold of the greening period, the start date of the phenological greening period is determined, and based on the condition that the remote sensing vegetation index decreases to the proportion of the growing season peak for a consecutive preset number of days, the end date of the phenological yellowing and withering period is determined.

[0096] Based on the start date of the phenological greening period and the end date of the phenological yellowing and withering period, the accumulated temperature and rainfall calculation window is dynamically planned, and the effective accumulated temperature and rainfall budget value is calculated within the accumulated temperature and rainfall calculation window;

[0097] Partial correlation analysis was used to quantify the lagged effect of preseason precipitation days on vegetation growth and generate time lag correction coefficients to adjust the accumulated rainfall budget.

[0098] Historical accumulated temperature, historical accumulated rainfall, soil moisture content, and time lag correction coefficients are input into a pre-trained machine learning model, which outputs the year-on-year change rate of accumulated temperature and accumulated rainfall.

[0099] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0100] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0101] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0107] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0109] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for calculating the prorated accumulated temperature and rainfall budget of a grassland pasture, characterized by, The method comprises: Collecting meteorological station data, remote sensing vegetation index data and soil moisture data of the target grassland; Determining the starting date of the phenological green-up period based on the condition that the average temperature for a continuous preset number of days is not lower than a preset base temperature and the soil volume water content exceeds a green-up period humidity threshold, and determining the ending date of the phenological yellowing period based on the condition that the remote sensing vegetation index decreases to a peak value proportion in the growing season for a continuous preset number of days; According to the starting date of the phenological green-up period and the ending date of the phenological yellowing period, a dynamic planning accumulated temperature and accumulated rain calculation window is planned, and within the accumulated temperature and accumulated rain calculation window, effective accumulated temperature and accumulated rain budget values are calculated; Using partial correlation analysis to quantify the lag effect of pre-season precipitation days on vegetation growth, a time lag correction coefficient is generated to adjust the accumulated rain budget value; The historical accumulated temperature, historical accumulated rain, soil water content and the time lag correction coefficient are input into a pre-trained machine learning model to output the same period accumulated temperature and accumulated rain change rate.

2. The method of claim 1, wherein, Based on the condition that the average temperature for a continuous preset number of days is not lower than a preset base temperature and the soil volume water content exceeds a green-up period humidity threshold, the starting date of the phenological green-up period is determined, specifically comprising: Traverse the daily average temperature sequence in the meteorological station data, identify all intervals that satisfy the condition that the daily average temperature for a continuous preset number of days is not lower than a preset green-up temperature threshold; Filter the first interval in which the average soil water content exceeds the preset humidity threshold, and determine the interval starting date of the first interval as the starting date of the phenological green-up period.

3. The method for estimating the year-on-year accumulated temperature and rainfall of grasslands according to claim 1, characterized in that, Based on the condition that the remote sensing vegetation index decreases to a peak value proportion in the growing season for a continuous preset number of days, the ending date of the phenological yellowing period is determined, specifically comprising: Traverse the remote sensing vegetation index data to extract the vegetation index peak value of the target grassland in the growing season; Monitor whether the remote sensing vegetation index of the target grassland decreases to a preset proportion of the vegetation index peak value for a continuous preset number of days, if yes, mark the first day that meets the condition as the ending date of the phenological yellowing period.

4. The method of claim 1, wherein, Using partial correlation analysis to quantify the lag effect of pre-season precipitation days on vegetation growth, a time lag correction coefficient is generated to adjust the accumulated rain budget value, specifically comprising: Extract the precipitation day sequence of the target grassland in the preset month before the growing season from the meteorological station data, and extract the vegetation index peak value sequence of the target grassland in the preset month before the growing season from the remote sensing vegetation index data; Perform partial correlation analysis on the precipitation day sequence and the vegetation index peak value sequence to calculate the partial correlation coefficient between precipitation days and vegetation index peak values; If the partial correlation coefficient exceeds a preset significance threshold, generate the time lag correction coefficient corresponding to the target grassland, and adjust the accumulated rain budget value of the target grassland based on the time lag correction coefficient.

5. The method for estimating the year-on-year accumulated temperature and rainfall of grasslands according to claim 1, characterized in that, Within the accumulated temperature and accumulated rain calculation window, the effective accumulated temperature and accumulated rain budget values are calculated, specifically comprising: According to the grassland type corresponding to the target grassland, determine the preset base temperature threshold of the target grassland, and within the accumulated temperature and accumulated rain calculation window, filter the dates with daily average temperature exceeding the preset base temperature threshold; Add the temperature values exceeding the threshold of the dates to obtain the effective accumulated temperature.

6. The method for estimating the year-on-year accumulated temperature and rainfall of grasslands according to claim 1, characterized in that, The method further comprises, before inputting the historical accumulated temperature, the historical accumulated rain, the soil moisture content and the time lag correction coefficient into the pre-trained machine learning model and outputting the same-period accumulated temperature and accumulated rain change rate: Based on historical data, an input feature set is constructed, and a regression model is trained with the same-period accumulated temperature and accumulated rain change rate as the target variable; the historical data includes historical accumulated temperature, accumulated rain, number of precipitation days, soil moisture content and time lag coefficient; Based on the trained model, the feature importance ranking is output, and the model prediction weight is optimized according to the feature importance ranking.

7. The method for estimating the year-on-year accumulated temperature and rainfall of grasslands according to claim 1, characterized in that, After collecting the meteorological station data, remote sensing vegetation index data and soil moisture data of the target grassland, the method further comprises: The abnormal values in the meteorological station data are removed, and the missing data in the meteorological station data are interpolated; The multi-source data is unified to a standard grid resolution through a spatial interpolation algorithm, and the dimensions and sampling frequencies of different data sources are normalized.

8. The method for estimating the year-on-year accumulated temperature and rainfall of grasslands according to claim 1, characterized in that, The method further comprises: Obtaining historical remote sensing vegetation index data and inverting based on the historical remote sensing vegetation index data to obtain vegetation biomass; Fitting the Logistic growth model parameters to establish the correlation between accumulated temperature and vegetation biomass, and optimizing the cumulative accumulated temperature based on the correlation.

9. A grassland grass field same ratio accumulated temperature and rainfall budget device, characterized by, The device comprises: At least one processor; and a memory connected in communication with the at least one processor; Wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the grassland grassland same-period accumulated temperature and accumulated rain budget method of any one of claims 1-8.

10. A non-transitory computer storage medium storing computer-executable instructions that, when executed, cause a computer to perform: The computer executable instructions are executed to implement the grassland grassland same-period accumulated temperature and accumulated rain budget method of any one of claims 1-8.

Images