Method for predicting harvest date of a crop, storage medium and processor

Abstract

This application provides a method, storage medium, and processor for predicting crop harvest dates. The method includes: acquiring a remote sensing image of the planting area of ​​the crop to be predicted; determining the initial date of the crop's growth period based on the remote sensing image; determining the baseline accumulated temperature value required for the crop to grow from a first initial date of the first growth period to a second initial date of the second growth period; determining the predicted accumulated temperature value for each growth day of the crop within a preset time period after the second initial date; determining the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value; and determining the growth day corresponding to the predicted accumulated temperature value that reaches the accumulated temperature difference as the predicted harvest date of the crop. Through the above technical solution, the predicted harvest date corresponding to the loss rate and yield can be determined more accurately, significantly increasing crop yield and avoiding high loss rates when crops are harvested on inappropriate dates.

Description

Technical Field

[0001] This application relates to the agricultural field, and more specifically to a method, storage medium, and processor for predicting crop harvest dates. Background Technology

[0002] In actual agricultural production, accurately predicting crop harvest dates is crucial for increasing crop yields and managing agricultural production. Currently, farmers generally rely on their traditional experience to determine crop maturity and then decide on the harvest date based on weather conditions and the availability of agricultural machinery and operators. Taking rice as an example, the harvest date determined based on farmers' traditional experience often differs from the optimal harvest date by 10 days or even more than half a month. Timely harvesting can increase crop yield by an average of 10%. Furthermore, timely harvesting can increase yield by up to 22.8% compared to harvesting too early, and it effectively improves the processing quality of rice and enhances its economic benefits compared to harvesting too late. In 2020, China's rice production was approximately 212 million tons. If we calculate based on a 10% actual loss, the losses incurred during the rice harvesting process exceeded 20 million tons.

[0003] Therefore, the harvest date predicted by farmers based on traditional experience usually differs significantly from the optimal harvest time, resulting in a relatively lower crop yield. Furthermore, whether crops are harvested by agricultural machinery or manually, there is always direct loss of crop grains during harvesting, drastically increasing the loss rate and making it difficult to guarantee a successful harvest. Summary of the Invention

[0004] The purpose of this application is to provide a method, storage medium, and processor for predicting crop harvest dates.

[0005] To achieve the above objectives, a first aspect of this application provides a method for predicting crop harvest dates, comprising:

[0006] Obtain remote sensing images of the planting area where the crop to be predicted is located;

[0007] The initial date of the growth period of the crop to be predicted is determined based on remote sensing images. The growth period of the crop includes at least the first growth period and the second growth period.

[0008] Determine the baseline accumulated temperature required for the crop to grow from the first initial date of the first growth stage to the second initial date of the second growth stage;

[0009] Determine the predicted accumulated temperature value for each growing day of the crop to be predicted within a preset time period after the second initial date;

[0010] Determine the difference in accumulated temperature between the baseline accumulated temperature value and the target accumulated temperature value. The target accumulated temperature value is the accumulated temperature value required for a historically planted crop to grow from the first initial date of its first growth stage to the optimal harvest date. The optimal harvest date is determined based on the loss rate and yield of the historical crop during the actual harvest date.

[0011] The growing days corresponding to the predicted accumulated temperature value that reaches the accumulated temperature difference are determined as the predicted harvest dates of the crops to be predicted.

[0012] In embodiments of this application, the growth period of crops also includes a third growth period. The method further includes: acquiring historical remote sensing images of historically planted crops before determining the accumulated temperature difference between the base accumulated temperature value and the target accumulated temperature value; determining the first initial date of the first growth period and the third initial date of the third growth period of historical crops based on the historical remote sensing images; randomly selecting N dates within a preset time period after the third initial date as the actual harvest dates of historical crops, and determining the loss rate and yield of crops harvested on each actual harvest date; and determining the actual harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date of historical crops.

[0013] In embodiments of this application, the method further includes: after determining the harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date for historical crops, determining the historical average daily temperature for each date within the time period from the first initial date of the first growth period to the optimal harvest date for historical crops; determining the historical accumulated temperature value for each date based on the temperature range in which the historical average daily temperature falls; and determining the accumulated temperature value required for historical crops to grow from the first initial date of the first growth period to the optimal harvest date based on all historical accumulated temperature values.

[0014] In the embodiments of this application, determining the historical accumulated temperature value for each date based on the temperature range of the historical average daily temperature includes determining the historical accumulated temperature value for each date according to formula (1):

[0015]

[0016] Where GDD is the historical accumulated temperature value, T mean This is the historical average daily temperature.

[0017] In the embodiments of this application, there are multiple remote sensing images, each corresponding to a growth day of the crop to be predicted, and the growth period also includes a third growth period. Determining the initial date of the growth period of the crop to be predicted based on the remote sensing images includes: defining any two consecutive growth days as a date group; preprocessing the remote sensing images corresponding to each date group and determining a first vegetation index for each preprocessed remote sensing image; determining a second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image; arranging each date group in the order of growth days; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group following the selected date group is higher than the second vegetation index of the selected date group, it is determined that the crop to be predicted has entered the first growth period, and the earliest date in the first date group following the selected date group is determined as the first growth period of the crop to be predicted. The first initial date of the second growth period; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group following the selected date group is lower than the second vegetation index of the selected date group, and the second vegetation index of the date group following the selected date group is less than the preset value, then the crop to be predicted enters the second growth period, and the earliest date in the first date group after the selected date group with the second vegetation index less than the preset value is determined as the second initial date of the second growth period; for any selected date group, if the second vegetation index corresponding to the selected date group is lower than the second vegetation index of the date group preceding the selected date group, and the second vegetation index corresponding to the selected date group is less than the second vegetation index of the date group following the selected date group, then the crop to be predicted enters the third growth period, and the earliest date in the selected date group is determined as the third initial date of the third growth period.

[0018] In the embodiments of this application, determining the second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image includes: determining the second vegetation index corresponding to each date group according to formula (2):

[0019] NDVI FD =(NDVI) i+1 -NDVI i ) / Δ DOY (2)

[0020] Among them, NDVI FD The second vegetation index, NDVI i+1 NDVI is the first vegetation index of the preprocessed remote sensing image corresponding to the (i+1)th growing day. iLet Δ be the first vegetation index of the preprocessed remote sensing image corresponding to the i-th growth day. DOY This represents the date interval between the (i+1)th growth day and the ith growth day.

[0021] In embodiments of this application, the method further includes: after determining the predicted harvest date of the crop to be predicted, acquiring meteorological data for a period before or after the predicted harvest date; if the meteorological data meets preset meteorological conditions, adjusting the predicted harvest date of the crop to be predicted based on the meteorological data; and if the meteorological data does not meet the preset meteorological conditions, harvesting the crop to be predicted according to the predicted harvest date.

[0022] In the embodiments of this application, the crop to be predicted is rice.

[0023] A second aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned method for predicting crop harvest dates.

[0024] A third aspect of this application provides a processor configured to perform the above-described method for predicting crop harvest dates.

[0025] The above technical solutions can more accurately determine the predicted harvest date corresponding to the loss rate and yield, enabling crops to be harvested on the predicted date. This can significantly increase crop yield while avoiding high loss rates during harvest, and reducing labor and time costs.

[0026] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0027] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0028] Figure 1 The illustration shows a flowchart of a method for predicting crop harvest dates according to an embodiment of this application;

[0029] Figure 2 A schematic flowchart of a method for predicting crop harvest dates according to yet another embodiment of this application is shown.

[0030] Figure 3 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0032] Figure 1 A schematic flowchart illustrating a method for predicting crop harvest dates according to an embodiment of this application is shown. Figure 1 As shown in one embodiment of this application, a method for predicting crop harvest dates is provided, comprising the following steps:

[0033] Step 101: Obtain remote sensing images of the planting area where the crop to be predicted is located.

[0034] Step 102: Determine the initial date of the growth period of the crop to be predicted based on the remote sensing image. The growth period of the crop includes at least the first growth period and the second growth period.

[0035] Step 103: Determine the base accumulated temperature required for the crop to grow from the first initial date of the first growth period to the second initial date of the second growth period.

[0036] Step 104: Determine the predicted accumulated temperature value for each growing day of the crop to be predicted within a preset time period after the second initial date.

[0037] Step 105: Determine the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value. The target accumulated temperature value is the accumulated temperature value required for a historically planted crop to grow from the first initial date of its first growth period to the optimal harvest date. The optimal harvest date is determined based on the loss rate and yield of the historical crop during the actual harvest date.

[0038] Step 106: The growing day corresponding to the predicted accumulated temperature value that reaches the accumulated temperature difference is determined as the predicted harvest date of the crop to be predicted.

[0039] The crop to be predicted can refer to various plants cultivated in agriculture. In one embodiment, the crop to be predicted can refer to rice. The crop to be predicted can be planted in a preset planting area. The planting area can refer to farmland. When predicting the harvest date of the crop, the processor can first acquire remote sensing images of the planting area where the crop to be predicted is located. The remote sensing images can refer to satellite remote sensing images or UAV multispectral images.

[0040] In one embodiment, if there is significant overcast or rainy weather before and after acquiring satellite remote sensing images, it may be difficult to obtain clear images. In this case, a device with image acquisition capabilities can be used to acquire multispectral images of the planting area of ​​the crop to be predicted. Image stitching and atmospheric correction can then be performed using surveying and photogrammetry software to obtain a clearer image of the planting area. The device with image acquisition capabilities can be a drone. The surveying and photogrammetry software can refer to drone surveying and photogrammetry software, specifically Pix4D software.

[0041] After acquiring remote sensing images of the planting area where the crop to be predicted is located, the processor can determine the initial date of the crop's growth period based on the images. The growth period of the crop to be predicted can include at least a first growth period and a second growth period. The first growth period can refer to the transplanting date of the crop. The second growth period can refer to the milk-ripe stage of the crop. The processor can further determine the baseline accumulated temperature value required for the crop to grow from the first initial date of the first growth period to the second initial date of the second growth period.

[0042] After determining the baseline accumulated temperature value, the processor determines the predicted accumulated temperature value for each growing day within a preset time period following the second initial date of the second growth stage of the crop. The preset time period can be customized based on actual conditions. For example, it could be 10 to 15 days after the second initial date of the second growth stage of the crop. The predicted accumulated temperature value is the cumulative accumulated temperature value of the crop within this time period. For example, if the initial date of the second growth stage is the 15th, and the preset time period is the 15th to the 25th, then all growing days after the second initial date are from the 16th to the 25th. If the predicted accumulated temperature value on the 16th is X, then the predicted accumulated temperature value on the 17th is X+Y, and the predicted accumulated temperature value on the 18th is X+Y+Z. That is, for each growing day, the corresponding predicted accumulated temperature value is a cumulative accumulated temperature value.

[0043] After determining the predicted accumulated temperature for each growing day, the processor can first determine the initial date of the growing season for historically planted crops. The growing season of historical crops can include at least the first growing season. The first growing season of historical crops can refer to the transplanting period. Specifically, the processor can determine the first initial date of the first growing season of historical crops and the actual harvest date. Then, the processor can further determine the optimal harvest date of historical crops based on the loss rate and yield of historical crops within the actual harvest date. After determining the optimal harvest date of historical crops, the processor can determine the accumulated temperature value required for the historical crops to grow from the first initial date of the first growing season to the optimal harvest date, i.e., the target accumulated temperature value.

[0044] After determining the target accumulated temperature value, the processor can determine the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value. Specifically, the processor can determine this difference using AGDD0 = AGDD - AGDD. 第二生育期 Determine the difference in accumulated temperature between the baseline accumulated temperature value and the target accumulated temperature value. Here, AGDD refers to the target accumulated temperature value. 第二生育期 This refers to the base accumulated temperature value. AGDD 第二生育期 It can be done Determined. Here, GDD represents the historical accumulated temperature value for each date from the first initial date of the first growth period to the second initial date of the second growth period. The processor can determine the growing day corresponding to the predicted accumulated temperature value that reaches the accumulated temperature difference as the predicted harvest date for the crop to be predicted. The predicted harvest date can refer to a predicted, more suitable harvest date. That is, if harvested on the predicted harvest date, the accumulated temperature value of the crop may have already reached the historical accumulated temperature value required for the crop to grow from the first initial date of the first growth period to the optimal harvest date. Harvesting at this time can, to some extent, ensure crop yield and reduce loss rate.

[0045] The above technical solutions can more accurately determine the predicted harvest date corresponding to the loss rate and yield, enabling crops to be harvested on the predicted date. This can significantly increase crop yield while avoiding high loss rates during harvest, and reducing labor and time costs.

[0046] In one embodiment, there are multiple remote sensing images, each corresponding to a growth day of the crop to be predicted, and the growth period also includes a third growth period. Determining the initial date of the growth period of the crop to be predicted based on the remote sensing images includes: defining any two consecutive growth days as a date group; preprocessing the remote sensing images corresponding to each date group and determining a first vegetation index for each preprocessed remote sensing image; determining a second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image; arranging each date group in the order of growth days; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date groups following the selected date group is higher than the second vegetation index of the selected date group, then the crop to be predicted has entered the first growth period, and the earliest date in the first date group following the selected date group is determined as the first growth period of the crop to be predicted. The first initial date; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group following the selected date group is lower than the second vegetation index of the selected date group, and the second vegetation index of the date group following the selected date group is less than the preset value, then the crop to be predicted enters the second growth period, and the earliest date in the first date group after the selected date group with the second vegetation index less than the preset value is determined as the second initial date of the second growth period; for any selected date group, if the second vegetation index corresponding to the selected date group is lower than the second vegetation index of the date group preceding the selected date group, and the second vegetation index corresponding to the selected date group is less than the second vegetation index of the date group following the selected date group, then the crop to be predicted enters the third growth period, and the earliest date in the selected date group is determined as the third initial date of the third growth period.

[0047] The system can use multiple remote sensing images. Each image corresponds to a specific growing day of the crop to be predicted. The growing season of the crop may also include a third growing season, which can refer to the yellow-ripe to full-ripe stage. When determining the initial date of the growing season of the crop based on the remote sensing images, the processor can first group any two consecutive growing days into a date group. Then, before preprocessing each remote sensing image, the processor can determine the vegetation index for each image. Specifically, the processor can determine the vegetation index of the remote sensing image based on NDVI = (NIR - RED) / (NIR + RED), where NDVI is the vegetation index of the remote sensing image, NIR is the near-infrared reflectance, and RED is the red light reflectance.

[0048] After determining the vegetation index for each remote sensing image, the processor can preprocess the remote sensing images corresponding to each date group. For example, the SG filter algorithm can be used to smooth the remote sensing images. The processor can further determine the first vegetation index for each preprocessed remote sensing image. The first vegetation index refers to the vegetation index of the smoothed remote sensing image. Specifically, the processor can determine the first vegetation index using `NDVI_smooth = scipy.signal.savgol_filter(NDVI, windows_length, k)`. Here, `NDVI_smooth` refers to the first vegetation index, and `NDVI` refers to the vegetation index of the remote sensing image before preprocessing. `windows_length` refers to the length of the window. The smaller the `window_length` value, the closer the curve is to the true curve. The larger the `window_length` value, the stronger the smoothing effect. Specifically, the range of `window_length` values ​​can be 9 to 11. `k` is the fitted value after performing a k-th order polynomial fitting on the data points within the window. The larger the `k` value, the closer the curve is to the true curve. The smaller the `k` value, the stronger the curve smoothing effect. Specifically, the value of k can range from 3 to 5.

[0049] The processor can determine the second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image. Specifically, in one embodiment, determining the second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image includes: determining the second vegetation index corresponding to each date group according to formula (2):

[0050] NDVI FD =(NDVI) i+1 -NDVI i ) / Δ DOY (2)

[0051] Among them, NDVI FD The second vegetation index, NDVI i+1 NDVI is the first vegetation index of the preprocessed remote sensing image corresponding to the (i+1)th growing day. i Let Δ be the first vegetation index of the preprocessed remote sensing image corresponding to the i-th growth day. DOY Let be the date interval between the (i+1)th growth day and the ith growth day. Wherein, the date interval Δ DOY It can be 1.

[0052] The processor can arrange each date group in chronological order of growth days. For any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group following the selected date group is higher than the second vegetation index of the selected date group, the processor can determine that the crop to be predicted has entered its first growth stage, and can determine the earliest date in the first date group following the selected date group as the first initial date of the first growth stage of the crop to be predicted. Here, the first growth stage of the crop to be predicted can refer to the transplanting period. For example, if the order of date groups A, B, and C is: A < B < C, the second vegetation index corresponding to date group A is A1, the second vegetation index corresponding to date group B is B1, and the second vegetation index corresponding to date group C is C1. Furthermore, date groups A, B, and C can each include two consecutive growth days; that is, date group A can include two consecutive growth days, date group B can include two consecutive growth days, and date group C can include two consecutive growth days. Therefore, for the selected date group A, if A1 is 0 and both B1 and C1 are greater than A1, the processor can determine that the crop has entered the transplanting period and can determine the earliest date in date group B as the first initial date of the transplanting period.

[0053] For any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date groups following the selected date group is lower than the second vegetation index of the selected date group, and the second vegetation index of the date groups following the selected date group is less than the preset value, the processor can determine that the crop to be predicted has entered its second growth stage. The processor can then determine the earliest date within the first date group following the selected date group whose second vegetation index is less than the preset value as the second initial date of the crop's second growth stage. Here, the second growth stage of the crop to be predicted can refer to the milk stage. For example, if the order of date groups A, B, and C is A < B < C, the second vegetation index corresponding to date group A is A1, the second vegetation index corresponding to date group B is B1, and the second vegetation index corresponding to date group C is C1. Furthermore, date groups A, B, and C can each include two consecutive growing days; that is, date group A can include two consecutive growing days, date group B can include two consecutive growing days, and date group C can include two consecutive growing days. Therefore, for the selected date group A, if A1 is 0, and both B1 and C1 are less than A1 and both B1 and C1 are less than the preset value Z, the processor can determine that the crop has entered the milk stage, and can determine the earliest date in date group B as the first initial date of the milk stage. The preset difference Z can be -0.0065.

[0054] For any selected date group, if the second vegetation index corresponding to the selected date group is less than the second vegetation index of the date groups preceding the selected date group, and the second vegetation index corresponding to the selected date group is less than the second vegetation index of the date groups following the selected date group, the processor can determine that the crop to be predicted has entered its third growth stage, and can determine the earliest date within the selected date group as the third initial date of the third growth stage of the crop to be predicted. Here, the third growth stage of the crop to be predicted can refer to the yellow-ripe to full-ripe stage. For example, if the order of date groups A, B, and C is: A < B < C, the second vegetation index corresponding to date group A is A1, the second vegetation index corresponding to date group B is B1, and the second vegetation index corresponding to date group C is C1. Furthermore, date groups A, B, and C can each include two consecutive growing days; that is, date group A can include two consecutive growing days, date group B can include two consecutive growing days, and date group C can include two consecutive growing days. Therefore, for the selected date group B, if B1 < A1 and B1 < C1, the processor can determine that the second vegetation index corresponding to date group B is B1 as the minimum value. The processor can determine that the crop has entered the yellow-ripe to full-ripe stage, and can determine the earliest date in date group B as the first initial date of the yellow-ripe to full-ripe stage.

[0055] In one embodiment, the crop's growth period also includes a third growth period. The method further includes: acquiring historical remote sensing images of historically planted crops before determining the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value; determining the first initial date of the first growth period and the third initial date of the third growth period of the historical crops based on the historical remote sensing images; randomly selecting N dates within a preset time period after the third initial date as the actual harvest dates of the historical crops, and determining the loss rate and yield of the crops harvested on each actual harvest date; and determining the actual harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date of the historical crops.

[0056] The growth period of crops can also include a third growth period. The third growth period of historical crops can refer to the yellow-ripe to full-ripe stage of historical crops. Before determining the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value, the processor can acquire historical remote sensing images of historically planted crops and determine the first initial date of the first growth period and the third initial date of the third growth period based on these images. Here, the historical crop can refer to rice. The first growth period of historical crops can refer to the transplanting period of historical crops.

[0057] The processor can randomly select N dates as the actual harvest dates of the historical crops within a preset time period following the third initial date. Specifically, within the preset time period following the third initial date of the historical crops, the processor can select N dates as the actual harvest dates of the historical crops at preset intervals. For example, starting from the third initial date of the historical crops, N dates can be selected every 3 / 4 / 5 days as the actual harvest dates of the historical crops.

[0058] After determining the actual harvest dates of historical crops, the processor can determine the loss rate and yield of the harvested crops on each actual harvest date. The processor can then determine the actual harvest date corresponding to the minimum loss rate and maximum yield as the optimal harvest date for the historical crops. The crops can be harvested using an agricultural harvester. During harvesting, the crop yield can be determined by the detection results of a grain yield sensor, and the crop loss rate can be determined by the detection results of a harvest loss rate measurement sensor on the agricultural harvester. The crop yield can refer to the harvested crop yield. The harvest loss rate measurement sensor can include a cleaning loss measurement sensor and an entrainment loss measurement sensor. The cleaning loss measurement sensor can be used to measure the number of grains lost during cleaning within the threshing chamber of the harvester. The entrainment loss measurement sensor can be used to measure the number of grains lost due to entrainment within the threshing chamber of the harvester.

[0059] For example, an agricultural harvester could be a rice harvester. Before harvesting crops with a rice harvester, a cleaning loss sensor can be installed under the cutter baffle of the rice harvester's straw cutter, and an entrainment loss sensor can be installed on the inner wall of the threshing drum. Thus, when harvesting crops with a rice harvester, the number of grains lost during cleaning can be obtained through the cleaning loss sensor, and the number of grains lost due to entrainment can be obtained through the entrainment loss sensor. Then, the processor can determine the crop loss rate based on the area of ​​the harvested crop area, the number of grains lost during cleaning, and the number of grains lost due to entrainment. Specifically, the processor can determine the crop loss rate using the formula S = N / A. Where S is the loss rate of the threshing machine of the agricultural harvester, i.e., the crop loss rate; N is the number of grains lost during cleaning or the number of grains lost due to entrainment; and A is the area of ​​the harvested crop area.

[0060] In one embodiment, the method further includes: after determining the harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date for the historical crop, determining the historical average daily temperature for each date within the time period from the first initial date of the first growth stage to the optimal harvest date for the historical crop; determining the historical accumulated temperature value for each date based on the temperature range in which the historical average daily temperature falls; and determining the accumulated temperature value required for the historical crop to grow from the first initial date of the first growth stage to the optimal harvest date based on all the historical accumulated temperature values.

[0061] After determining the harvest date corresponding to the minimum loss rate and maximum yield as the optimal harvest date for historical crops, the processor can first obtain the historical maximum and minimum temperatures for each date within the time period from the first initial date of the first growth stage to the optimal harvest date. Here, the first initial date of the historical crop can refer to the transplanting date. Then, the processor can determine the historical average daily temperature for each date based on the historical maximum and minimum temperatures. Specifically, the processor can determine the historical average daily temperature based on T... mean =T max +T min / 2 Determine the historical average daily temperature for each day of the period from the first initial date of the first growth stage to the optimal harvest date for historical crops. Wherein, T mean This refers to the historical average daily temperature, T. max This refers to the highest historical temperature, T. min This refers to the lowest temperature in history.

[0062] After determining the historical average daily temperature for each date within the timeframe from the first initial date of the first growth stage to the optimal harvest date for the historical crop, the processor can obtain the temperature range in which the historical average daily temperature falls and determine the historical accumulated temperature value for each date based on the temperature range. Specifically, in one embodiment, determining the historical accumulated temperature value for each date based on the temperature range in which the historical average daily temperature falls includes determining the historical accumulated temperature value for each date according to formula (1):

[0063]

[0064] Where GDD is the historical accumulated temperature value, T mean This is the historical average daily temperature.

[0065] The processor can determine the historical accumulated temperature value for each date according to the formula (1) above. For example, if the historical daily average temperature T on a certain date is... mean Within the first temperature range, i.e., T mean <9 or T mean If T is ≥36, then the historical accumulated temperature value for that date can be determined to be 0. mean It is in the first temperature range, i.e., 9≤Tmean If the temperature is less than 36 degrees Celsius, then the historical accumulated temperature value for that date can be determined as T. mean -9.

[0066] After determining the historical accumulated temperature value for each date, the processor can determine the accumulated temperature value required for a historical crop to grow from the first initial date of its first growth stage to its optimal harvest date, i.e., the target accumulated temperature value, based on all historical accumulated temperature values. Here, the first growth stage of the historical crop can refer to the transplanting date of the historical crop. Specifically, the processor can determine the target accumulated temperature value based on all historical accumulated temperature values. Determine the target accumulated temperature value. Here, AGDD can refer to the target accumulated temperature value, and GDD refers to the historical accumulated temperature value for each day from the first initial date of the first growing season to the optimal harvest date.

[0067] In one embodiment, the method further includes: after determining the predicted harvest date of the crop to be predicted, acquiring meteorological data for a period of time before or after the predicted harvest date; if the meteorological data meets preset meteorological conditions, adjusting the predicted harvest date of the crop to be predicted based on the meteorological data; and if the meteorological data does not meet the preset meteorological conditions, harvesting the crop to be predicted according to the predicted harvest date.

[0068] After determining the predicted harvest date for the crop, the processor can acquire meteorological data for a period before or after the predicted harvest date. This meteorological data may include rainfall and humidity. If the meteorological data meets preset meteorological conditions, the processor can adjust the predicted harvest date based on the data. For example, the crop can be harvested two days after the predicted harvest date to avoid difficulties in harvesting machinery operations due to unfavorable meteorological data on the predicted harvest date, thus preventing increased crop losses and reduced yields. If the meteorological data does not meet the preset meteorological conditions, the processor can harvest the crop according to the predicted harvest date. The preset meteorological conditions can be set according to the meteorological data. For example, if the meteorological data is rainfall, the preset meteorological condition can be preset rainfall; if the meteorological data is humidity, the preset meteorological condition can be preset humidity.

[0069] In one embodiment, such as Figure 2 As shown, a flowchart illustrating another method for predicting crop harvest dates is provided.

[0070] The processor can acquire historical remote sensing images of the planting area where crops have already been planted and perform SG filtering on these images. Then, the processor can acquire the NDVI time series of the SG-filtered historical remote sensing images, which corresponds to the first vegetation index. The processor can determine the first derivative of the NDVI for each date group, i.e., the corresponding second vegetation index, by taking the first derivative of the first vegetation index of the SG-filtered historical remote sensing images. The processor can determine the minimum NDVI first derivative to determine the yellow-ripe to full-ripe stage of the planted crops based on the date group corresponding to the minimum NDVI first derivative. Here, the planted crops can refer to rice. The processor can further determine the harvest loss rate of the crop to be predicted on different dates within the yellow-ripe to full-ripe stage, and determine the date corresponding to the minimum loss rate as the optimal harvest period. The crop to be predicted can refer to rice.

[0071] The above technical solutions can more accurately determine the predicted harvest date corresponding to the loss rate and yield, enabling crops to be harvested on the predicted date. This can significantly increase crop yield while avoiding high loss rates during harvest, and reducing labor and time costs.

[0072] Figure 1-2 This is a flowchart illustrating a method for predicting crop harvest dates in one embodiment. It should be understood that, although... Figure 1-2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1-2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0073] This application provides a storage medium storing a program that, when executed by a processor, implements the above-described method for predicting crop harvest dates.

[0074] This application provides a processor for running a program, wherein the program executes the above-described method for predicting crop harvest dates.

[0075] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data such as remote sensing images. The network interface A02 communicates with external terminals via a network connection. When the processor A01 executes the computer program B02, it implements a method for predicting crop harvest dates.

[0076] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0077] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring a remote sensing image of the planting area of ​​the crop to be predicted; determining the initial date of the crop's growth period based on the remote sensing image, wherein the crop's growth period includes at least a first growth period and a second growth period; determining the baseline accumulated temperature value required for the crop to grow from the first initial date of the first growth period to the second initial date of the second growth period; determining the predicted accumulated temperature value for each growth day of the crop within a preset time period after the second initial date; determining the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value, wherein the target accumulated temperature value is the accumulated temperature value required for a historically planted crop to grow from the first initial date of the first growth period to the optimal harvest date, and the optimal harvest date is determined based on the loss rate and yield of the historical crop during the actual harvest date; and determining the growth day corresponding to the predicted accumulated temperature value that reaches the accumulated temperature difference as the predicted harvest date of the crop to be predicted.

[0078] In one embodiment, the crop's growth period also includes a third growth period. The method further includes: acquiring historical remote sensing images of historically planted crops before determining the accumulated temperature difference between the baseline accumulated temperature value and the target accumulated temperature value; determining the first initial date of the first growth period and the third initial date of the third growth period of the historical crops based on the historical remote sensing images; randomly selecting N dates within a preset time period after the third initial date as the actual harvest dates of the historical crops, and determining the loss rate and yield of the crops harvested on each actual harvest date; and determining the actual harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date of the historical crops.

[0079] In one embodiment, the method further includes: after determining the harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date for the historical crop, determining the historical average daily temperature for each date within the time period from the first initial date of the first growth stage to the optimal harvest date for the historical crop; determining the historical accumulated temperature value for each date based on the temperature range in which the historical average daily temperature falls; and determining the accumulated temperature value required for the historical crop to grow from the first initial date of the first growth stage to the optimal harvest date based on all the historical accumulated temperature values.

[0080] In one embodiment, determining the historical accumulated temperature value for each date based on the temperature range of the historical average daily temperature includes determining the historical accumulated temperature value for each date according to formula (1):

[0081]

[0082] Where GDD is the historical accumulated temperature value, T mean This is the historical average daily temperature.

[0083] In one embodiment, there are multiple remote sensing images, each corresponding to a growth day of the crop to be predicted, and the growth period also includes a third growth period. Determining the initial date of the growth period of the crop to be predicted based on the remote sensing images includes: defining any two consecutive growth days as a date group; preprocessing the remote sensing images corresponding to each date group and determining a first vegetation index for each preprocessed remote sensing image; determining a second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image; arranging each date group in the order of growth days; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date groups following the selected date group is higher than the second vegetation index of the selected date group, then the crop to be predicted has entered the first growth period, and the earliest date in the first date group following the selected date group is determined as the first growth period of the crop to be predicted. The first initial date; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group following the selected date group is lower than the second vegetation index of the selected date group, and the second vegetation index of the date group following the selected date group is less than the preset value, then the crop to be predicted enters the second growth period, and the earliest date in the first date group after the selected date group with the second vegetation index less than the preset value is determined as the second initial date of the second growth period; for any selected date group, if the second vegetation index corresponding to the selected date group is lower than the second vegetation index of the date group preceding the selected date group, and the second vegetation index corresponding to the selected date group is less than the second vegetation index of the date group following the selected date group, then the crop to be predicted enters the third growth period, and the earliest date in the selected date group is determined as the third initial date of the third growth period.

[0084] In one embodiment, determining the second vegetation index corresponding to each date group based on the first vegetation index of each preprocessed remote sensing image includes: determining the second vegetation index corresponding to each date group according to formula (2):

[0085] NDVI FD =(NDVI) i+1 -NDVI i ) / Δ DOY (2)

[0086] Among them, NDVI FD The second vegetation index, NDVI i+1 NDVI is the first vegetation index of the preprocessed remote sensing image corresponding to the (i+1)th growing day. iLet Δ be the first vegetation index of the preprocessed remote sensing image corresponding to the i-th growth day. DOY This represents the date interval between the (i+1)th growth day and the ith growth day.

[0087] In one embodiment, the method further includes: after determining the predicted harvest date of the crop to be predicted, acquiring meteorological data for a period of time before or after the predicted harvest date; if the meteorological data meets preset meteorological conditions, adjusting the predicted harvest date of the crop to be predicted based on the meteorological data; and if the meteorological data does not meet the preset meteorological conditions, harvesting the crop to be predicted according to the predicted harvest date.

[0088] In one embodiment, the crop to be predicted is rice.

[0089] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes method steps for predicting crop harvest dates.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0095] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0096] 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 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.

[0097] 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.

[0098] 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 predicting a harvest date of a crop, characterized in that, The method comprises: acquiring remote sensing images of a planting area where a crop to be predicted is located, wherein the number of the remote sensing images is multiple, and each remote sensing image corresponds to each growth day of the crop to be predicted respectively; determining any two consecutive growth days as a date group; preprocessing remote sensing images corresponding to each date group, and determining a first vegetation index of each preprocessed remote sensing image; determining a second vegetation index corresponding to each date group according to the first vegetation index of each preprocessed remote sensing image; arranging each date group in the order of growth days; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group after the selected date group is higher than that of the selected date group, it is determined that the crop to be predicted enters a first growth period, and the earliest date in the first date group after the selected date group is determined as a first initial date of the first growth period of the crop to be predicted; for any selected date group, if the second vegetation index corresponding to the selected date group is a preset value, and the second vegetation index of the date group after the selected date group is lower than that of the selected date group, and the second vegetation index of the date group after the selected date group is less than a preset value, it is determined that the crop to be predicted enters a second growth period, and the earliest date in the first date group after the selected date group is determined as a second initial date of the second growth period; for any selected date group, if the second vegetation index corresponding to the selected date group is less than that of the date group before the selected date group, and the second vegetation index corresponding to the selected date group is less than that of the date group after the selected date group, it is determined that the crop to be predicted enters a third growth period, and the earliest date in the selected date group is determined as a third initial date of the third growth period; determining a basic accumulated temperature value required for the crop to be predicted to grow from the first initial date of the first growth period to the second initial date of the second growth period; determining a predicted accumulated temperature value of each growth day of the crop to be predicted in a preset time period after the second initial date; acquiring historical remote sensing images of a historical crop that has been planted before determining an accumulated temperature difference value between the basic accumulated temperature value and a target accumulated temperature value; determining a first initial date of a first growth period and a third initial date of a third growth period of the historical crop according to the historical remote sensing images; selecting N dates in a preset time period after the third initial date as actual harvesting dates of the historical crop, and determining a loss rate and a yield of the crop harvested in each actual harvesting date; determining an actual harvesting date corresponding to the minimum loss rate and the maximum yield as an optimal harvesting date of the historical crop; determining a difference in accumulated temperature between the base accumulated temperature value and a target accumulated temperature value, wherein the target accumulated temperature value is an accumulated temperature value required for a historical crop that has been planted to grow from a first initial date of a first growth period to an optimal harvest date, the optimal harvest date being determined according to a loss rate and a yield of the historical crop within an actual harvest date; determining a growth day corresponding to a predicted accumulated temperature value reaching the difference in accumulated temperature as the predicted harvest date of the to-be-predicted crop.

2. The method for predicting a harvest date of a crop according to claim 1, characterized in that, The method further comprises: after determining the harvest date corresponding to the minimum loss rate and the maximum yield as the optimal harvest date of the historical crop, determining a historical daily average temperature of each date within a time period from the first initial date of the first growth period to the optimal harvest date of the historical crop; determining a historical accumulated temperature value of each date according to a temperature interval in which the historical daily average temperature is located; determining the accumulated temperature value required for the historical crop to grow from the first initial date of the first growth period to the optimal harvest date according to all historical accumulated temperature values.

3. The method for predicting a harvest date of a crop according to claim 2, characterized in that, determining the historical accumulated temperature value of each date according to a temperature interval in which the historical daily average temperature is located comprises determining the historical accumulated temperature value of each date according to formula (1): （1） GDD is the historical accumulated temperature value, is the historical daily average temperature.

4. The method for predicting a harvest date of a crop according to claim 1, wherein, The determining of the second vegetation index corresponding to each date group according to the first vegetation index of each pre-processed remote sensing image comprises: determining the second vegetation index corresponding to each date group according to formula (2): （2） wherein, is a second vegetation index, is a first vegetation index of the pre-processed remote sensing image corresponding to the i+1th growth day, is a first vegetation index of the pre-processed remote sensing image corresponding to the ith growth day, is a date interval between the i+1th growth day and the ith growth day.

5. The method for predicting a harvest date of a crop according to claim 1, wherein, The method further comprises: after determining the predicted harvest date of the to-be-predicted crop, obtaining meteorological data within a period of time before or after the predicted harvest date; in a case where the meteorological data satisfies a preset meteorological condition, adjusting the predicted harvest date of the to-be-predicted crop according to the meteorological data; in a case where the meteorological data does not satisfy the preset meteorological condition, harvesting the to-be-predicted crop according to the predicted harvest date.

6. The method for predicting a harvest date of a crop according to any one of claims 1 to 5, characterized in that, The to-be-predicted crop is rice.

7. A machine-readable storage medium having stored thereon instructions, the instructions being executable by a machine to cause the machine to perform operations comprising: The instructions, when executed by a processor, cause the processor to be configured to perform the method for predicting a harvest date of a crop according to any one of claims 1 to 6.

8. A processor, comprising: The processor is configured to perform the method for predicting a harvest date of a crop according to any one of claims 1 to 6. The processor is configured to perform the method for predicting a harvest date of a crop according to any one of claims 1 to 6.

Images