Irrigated farmland region identification method, device and equipment and storage medium

Abstract

The application provides an irrigation farmland identification method, device and equipment and a storage medium. The method comprises the following steps: acquiring satellite image data of a to-be-identified mapping area, and determining a drought period of the to-be-identified mapping area; calculating a target vegetation index of each farmland pixel point in the satellite image data in the drought period based on the satellite image data; and for each farmland pixel point, determining whether the farmland pixel point is an irrigation farmland based on the target vegetation index of the farmland pixel point and a pre-calculated index threshold of the to-be-identified mapping area. The application solves the technical problem of low accuracy of irrigation farmland division.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural monitoring management, and in particular to an irrigated farmland region identification method, device, equipment and storage medium. BACKGROUND

[0002] Agricultural civilization is an integral part of human history. With the birth and development of farming technology, mankind has moved from suitable river basins to every corner of the world, and this process cannot be separated from irrigation agriculture. In particular, in arid and semi-arid areas where precipitation is much less than evaporation, irrigation provides the necessary humidity conditions for the germination, growth and maturation of crops, and to a large extent enables land that is not suitable for cultivation to produce enough food. Therefore, in order to achieve the goal of food security and sustainable development of land use, it is necessary to use large-scale high-resolution actual irrigation data as decision-making materials. Under the dual influence of population growth and global change, the irrigation situation in some areas has changed, and the application value of some data produced in the past has decreased in time and spatial scale.

[0003] At present, the method of using spectral features for classification is usually used to draw irrigation distribution maps. However, the spectral features of irrigation in remote sensing data are quite ambiguous and have strong spatial heterogeneity. Moreover, due to the high computational complexity of using spectral features for classification and the unavailability of training data, the accuracy of irrigated farmland extraction and division is low. SUMMARY

[0004] The present application provides an irrigated farmland region identification method, device, equipment and storage medium, which aims to improve the accuracy of irrigated farmland division.

[0005] The present application provides an irrigated farmland region identification, which comprises:

[0006] Obtaining satellite image data of a to-be-identified mapping region, and determining a drought period of the to-be-identified mapping region;

[0007] Based on the satellite image data, calculating a target vegetation index of each farmland pixel point in the satellite image data in the drought period;

[0008] For each farmland pixel point: based on the target vegetation index of the farmland pixel point and the pre-calculated index threshold of the to-be-identified mapping region, determining whether the farmland pixel point is an irrigated farmland region.

[0009] Optionally, according to the irrigated farmland region identification provided by the present application, the drought period comprises a drought month and a drought year, and the determination of the drought period of the to-be-identified mapping region comprises:

[0010] statistically determine annual rainfall and monthly rainfall of the to-be-identified mapping region in a first preset time range;

[0011] determine whether the to-be-identified mapping region has a fixed drought period based on regional climate information of the to-be-identified mapping region;

[0012] if yes, determine drought months of the to-be-identified mapping region based on monthly rainfall in the first preset time range;

[0013] if no, determine drought years of the to-be-identified mapping region based on annual rainfall of each year in the first preset time range.

[0014] Optionally, according to the irrigation farmland region identification provided by the present application, if the to-be-identified mapping region has a fixed drought period, the target vegetation index of each farmland pixel point in the satellite image data in the drought period is calculated based on the satellite image data, including:

[0015] the maximum vegetation index of the drought months in each year in a second preset time range is calculated based on the satellite image data, and the maximum vegetation index of the drought months is taken as the target vegetation index, wherein the second preset time range is smaller than the first preset time range.

[0016] Optionally, according to the irrigation farmland region identification provided by the present application, if the to-be-identified mapping region has no fixed drought period, the target vegetation index of each farmland pixel point in the satellite image data in the drought period is calculated based on the satellite image data, including:

[0017] determine a target drought month in the drought years;

[0018] the maximum vegetation index and the average vegetation index of the target drought month are calculated based on the satellite image data;

[0019] the vegetation index deviation value of the target drought month is calculated based on the maximum vegetation index and the average vegetation index of the target drought month, and the vegetation index deviation value of the target drought month is taken as the target vegetation index.

[0020] Optionally, according to the irrigation farmland region identification provided by the present application, the vegetation index deviation value of the target drought month is calculated based on the maximum vegetation index and the average vegetation index of the target drought month, including

[0021] the index difference value between the maximum vegetation index and the average vegetation index of the target drought month is calculated;

[0022] calculating a ratio between the index difference and the vegetation index average value, to obtain the vegetation index average value of the target drought month.

[0023] Optionally, according to the irrigation farmland region identification provided by the present application, before judging whether the farmland pixel point is an irrigation farmland region based on the vegetation index of each farmland pixel point and the index threshold value of the to-be-identified mapping region calculated in advance, the method further comprises the following steps of:

[0024] acquiring training data of a plurality of training sample points in the to-be-identified mapping region, wherein the training sample points include irrigation points and non-irrigation points;

[0025] if the to-be-identified mapping region has a fixed drought period, then based on the training data, maximum vegetation indexes corresponding to each irrigation point and each non-irrigation point are respectively calculated, and based on the maximum vegetation indexes corresponding to each irrigation point and each non-irrigation point, an index threshold value of the to-be-identified mapping region is calculated;

[0026] if the to-be-identified mapping region does not have a fixed drought period, then based on the training data, vegetation index deviation values corresponding to each irrigation point and each non-irrigation point are respectively calculated, and based on the vegetation index deviation values corresponding to each irrigation point and each non-irrigation point, an index threshold value of the to-be-identified mapping region is calculated.

[0027] Optionally, according to the irrigation farmland region identification provided by the present application, the judgment of whether the farmland pixel point is an irrigation farmland region based on the target vegetation index of the farmland pixel point and the index threshold value of the to-be-identified mapping region calculated in advance comprises the following steps of:

[0028] if the to-be-identified mapping region has a fixed drought period and the target vegetation index is greater than the index threshold value, then it is determined that the farmland pixel point is an irrigation farmland region;

[0029] if the to-be-identified mapping region does not have a fixed drought period and the target vegetation index is less than the index threshold value, then it is determined that the farmland pixel point is an irrigation farmland region.

[0030] The present application also provides an irrigation farmland region identification device, comprising:

[0031] an acquisition module, configured to acquire satellite image data of a to-be-identified mapping region and determine a drought period of the to-be-identified mapping region;

[0032] a calculation module, configured to calculate a target vegetation index of each farmland pixel point in the satellite image data in the drought period based on the satellite image data;

[0033] A judgment module is configured to, for each of the farmland pixels: based on the target vegetation index of the farmland pixel and the index threshold of the to-be-identified mapping region that is calculated in advance, judging whether the farmland pixel is an irrigated farmland region.

[0034] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the irrigation farmland region identification method according to any one of the above when executing the program.

[0035] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the irrigation farmland region identification method according to any one of the above.

[0036] The application further provides a computer program product, which includes a computer program, and the computer program is executable on a processor to implement the irrigation farmland region identification method according to any one of the above.

[0037] The irrigation farmland region identification method, device, equipment and storage medium provided by the application, by acquiring satellite image data of a to-be-identified mapping region, and determining a drought period of the to-be-identified mapping region; based on the satellite image data, calculating a target vegetation index of each farmland pixel in the satellite image data in the drought period; for each of the farmland pixels: based on the target vegetation index of the farmland pixel and the index threshold of the to-be-identified mapping region that is calculated in advance, judging whether the farmland pixel is an irrigated farmland region. Since the NDVI vegetation index of irrigated farmland can be relieved in the drought period, and the growth of crops in rain-fed farmland is poor under the drought stress, resulting in that the NDVI vegetation index is also low, so that the irrigated farmland and the rain-fed farmland can be distinguished based on the NDVI vegetation index in the drought period, the application determines the drought period corresponding to the to-be-identified mapping region, then calculates the vegetation index corresponding to the drought period, and judges whether each farmland pixel belongs to the irrigated farmland region based on the index threshold of the mapping region, so as to accurately identify the irrigated farmland region based on the vegetation index under the drought stress condition and the index threshold of the mapping region. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0039] Figure 1is one of flow schematic diagrams of the irrigation farmland region identification method provided by the present application;

[0040] Figure 2 is one of flow schematic diagrams of the irrigation farmland region identification method provided by the present application;

[0041] Figure 3 is one of flow schematic diagrams of the irrigation farmland region identification method provided by the present application;

[0042] Figure 4 is a structural schematic diagram of the irrigation farmland region identification device provided by the present application;

[0043] Figure 5 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in conjunction with the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0045] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms "a", "said" and "the" used in one or more embodiments of the present application are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application means and includes any or all possible combinations of one or more associated listed items.

[0046] It should be understood that although the terms first, second, etc. may be employed in one or more embodiments of the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, first can also be referred to as second, and similarly, second can also be referred to as first. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0047] The specific embodiments of the present application will be described below in conjunction with Figures 1-5 The specific embodiments of the present application will be described below in conjunction with

[0048] As Figure 1 is a flowchart of an irrigation farmland region identification method according to an embodiment of the present application. As Figure 1As shown, the irrigation farmland region identification method comprises the following steps:

[0049] In step S10, satellite image data of a to-be-identified mapping region is acquired, and a drought period of the to-be-identified mapping region is determined.

[0050] It should be noted that, according to the changes in climate and phenology, the world is divided into different regions. In this embodiment, the region division is performed by using 65 monitoring and reporting units (MRUs) introduced by Cropwatch (a leading crop monitoring system in China). The division of these monitoring and reporting units (MRUs) is based on the global ecological map of the Food and Agriculture Organization of the United Nations (FAO), and is performed according to crop types, agricultural production potential, and environmental conditions. Some regions are further divided due to their climate variability, and there are a total of 110 irrigation mapping regions (IMZs). The to-be-identified mapping region is one of the 110 irrigation mapping regions (IMZs).

[0051] It should be further noted that, before the satellite image data is subjected to high-definition picture synthesis, relevant data is collected in each waveband of the full spectrum, so that a corresponding vegetation index can be calculated based on the ratio analysis between different wavebands based on the satellite image data. In an embodiment, the satellite image data can be selected from image data corresponding to Landsat8 or Sentinel 2.

[0052] It should be further noted that, due to differences in conditions such as climate, phenology, and crop types, each irrigation mapping region can be divided into a region with fixed drought months and a region without fixed drought months (for example, the Great Plains in the northeastern United States). For the region with fixed drought months, regular irrigation is required, for example, the dry season of tropical savanna and monsoon climate, the winter of temperate monsoon climate, and the summer of Mediterranean climate all have obvious drought periods, and irrigation is required if crops grow during the drought period.

[0053] The drought period includes drought months and drought years. The determination of the drought period of the to-be-identified mapping region comprises the following steps:

[0054] In step S11, the annual rainfall and monthly rainfall of the to-be-identified mapping region in a first predetermined time range are counted.

[0055] In step S12, whether the to-be-identified mapping region has a fixed drought period is determined based on regional climate information of the to-be-identified mapping region.

[0056] In step S13, if there is a fixed drought period, the drought months of the to-be-identified mapping region are determined based on the monthly rainfall in the first predetermined time range.

[0057] Step S14, if not, determining the drought year of the to-be-identified mapping region based on the annual rainfall of each year within the first preset time range.

[0058] As an implementable manner, specifically, satellite rainfall data is acquired, optionally, the satellite rainfall data can be based on TRMM (Tropical Rainfall Measuring Mission) satellite, and then based on the satellite rainfall data, the annual rainfall and the monthly rainfall within a first preset time range are counted, the first preset time range can be set according to actual conditions, optionally, set to 5-10 years, preferably, set to 10 years, further, it is inquired whether there is a fixed drought period in the to-be-identified mapping region, if there is a fixed drought period, the difference between the monthly rainfall and the corresponding potential evapotranspiration in a year is calculated to determine the drought month of the to-be-identified mapping region, if there is no fixed drought period, the year with the least annual rainfall is determined as the drought year of the to-be-identified mapping region based on the annual rainfall of each year within the first preset time range, and additionally, in the corresponding monthly rainfall in the drought year, the month with the least monthly rainfall is divided as the target drought month in the drought year.

[0059] Step S20, based on the satellite image data, calculating the target vegetation index of each cultivated field pixel point in the satellite image data in the drought period;

[0060] It should be noted that the target vegetation index includes NDVI normalized vegetation index, maximum NDVI vegetation index or NDVI vegetation index deviation value. The NDVI vegetation index is determined by measuring the difference (also can be the reflection value) between the near-infrared band reflectivity and the red band reflectivity, and the specific calculation formula is as follows:

[0061] NDVI = (NIR-R) / (NIR-R)

[0062] Wherein, NIR refers to the near-infrared band reflectivity, and R refers to the red band reflectivity.

[0063] In this embodiment, the following steps are performed for each of the cultivated field pixel points corresponding to the to-be-identified mapping region:

[0064] As an implementable manner, specifically, for the to-be-identified mapping area, there is a fixed drought period: based on the data of different bands in the satellite image data, the NDVI vegetation index corresponding to the drought month is calculated, and the NDVI vegetation index is taken as the target vegetation index. In order to more accurately identify whether the to-be-identified mapping area belongs to irrigated land, optionally, satellite image data in a second preset time range is selected, and then the NDVI vegetation index corresponding to the drought month of each year in the second preset time range is calculated, wherein the second preset time range is smaller than the first preset time range, and the second preset time range can be set according to actual conditions, which is not limited here. Then, the maximum NDVI vegetation index is selected as the target vegetation index, for example, the drought months are July to August, the NDVI vegetation index corresponding to July to August of each year from 2019 to 2021 is calculated, and the maximum NDVI vegetation index is selected as the target vegetation index of the cultivated land pixel point.

[0065] As another implementable manner, specifically, for the to-be-identified mapping area, there is no fixed drought period: based on the monthly rainfall of each month in the drought year, the target drought month in the drought year is determined, and then the data corresponding to different bands in the satellite image data is combined to calculate the maximum NDVI vegetation index in the target drought month and the average value of the NDVI vegetation index corresponding to the target drought month. Further, based on the maximum NDVI vegetation index and the average value of the NDVI vegetation index, the NDVI vegetation index deviation value corresponding to the cultivated land pixel point is calculated, and the NDVI vegetation index deviation value is taken as the target vegetation index of the cultivated land pixel point, for example, the drought year is 2014, the drought month is July, the maximum NDVI vegetation index and the average value of the NDVI vegetation index corresponding to July 2014 are calculated, and then the NDVI vegetation index deviation value of the cultivated land pixel point is calculated.

[0066] In addition, it should be noted that, since the present application is based on the growth of irrigated crops under drought stress to identify the irrigation area, the crops cannot grow in the drought period, and the target vegetation index in the preset time after the drought period is calculated for identification, wherein the preset time can be set according to the growth of crops, for example: the drought period is from January to February, and the crops may not be able to grow in January and February. Therefore, it is not possible to identify and distinguish the target vegetation index corresponding to January and February, and the target vegetation index in March is calculated for identification according to the growth of crops.

[0067] Step S30, for each of the cultivated land pixel points: based on the target vegetation index of the cultivated land pixel point and the index threshold value of the to-be-identified mapping region pre-calculated, judging whether the cultivated land pixel point is an irrigated cultivated land region.

[0068] In the embodiment, it is to be noted that the target threshold value corresponding to different mapping regions is not the same, and the index threshold value is determined based on the vegetation index NDVI corresponding to each irrigation point and each non-irrigation point in the to-be-identified mapping region.

[0069] As an implementable manner, specifically, for the case that there is a fixed drought period in the to-be-identified mapping region: comparing the target vegetation index of the cultivated land pixel point with the maximum vegetation index of the to-be-identified mapping region, if the target vegetation index is greater than the index threshold value, it is proved that the cultivated land pixel point belongs to the irrigated cultivated land region, and if the target vegetation index is not greater than the index threshold value, it is proved that the cultivated land pixel point does not belong to the irrigated cultivated land region, for example, there is a fixed drought period in the Ganges Plain in northern India, and the index threshold value is 0.32, if the NDVI target vegetation index in February is greater than 0.32, the cultivated land with vegetation is regarded as irrigated cultivated land.

[0070] As another implementable manner, specifically, for the case that there is no fixed drought period in the to-be-identified mapping region: comparing the target vegetation index of the cultivated land pixel point with the maximum vegetation index of the to-be-identified mapping region, if the target vegetation index is less than the index threshold value, it is proved that the cultivated land pixel point belongs to the irrigated cultivated land region, and if the target vegetation index is not less than the index threshold value, it is proved that the cultivated land pixel point does not belong to the irrigated cultivated land region, for example, there is no fixed drought period in the Great Plains in the northeastern United States, and the index threshold value is -10%, if the target vegetation index in May and June 2012 is less than -10%, the cultivated land is considered to be irrigated cultivated land.

[0071] Table 1

[0072]

[0073] It can be understood that the irrigated land identified by the method of the present application is slightly larger than the irrigated region recorded in the FAO 2000 statistical database of the United Nations by referring to Table 1.

[0074] The embodiment of the present application also has the above scheme, that is, satellite image data of a to-be-identified mapping region is acquired, and a drought period of the to-be-identified mapping region is determined; target vegetation indexes of each cultivated field pixel point in the satellite image data in the drought period are calculated based on the satellite image data; for each cultivated field pixel point: whether the cultivated field pixel point is an irrigated cultivated region is judged based on the target vegetation index of the cultivated field pixel point and a pre-calculated index threshold value of the to-be-identified mapping region. Because in the drought period, the NDVI vegetation index of the irrigated cultivated land can be relieved, and the rain-fed cultivated land is seriously stressed by drought, the growth of crops will be poor, and the NDVI vegetation index will also be low, so that the irrigated cultivated land and the rain-fed cultivated land can be distinguished based on the NDVI vegetation index in the drought period. The present application determines the drought period corresponding to the to-be-identified mapping region, then calculates the vegetation index corresponding to the drought period, and judges whether each cultivated field pixel point belongs to the irrigated cultivated region based on the index threshold value of the mapping region, so as to accurately identify the irrigated cultivated region based on the vegetation index under the drought stress condition and the index threshold value of the mapping region.

[0075] Reference Figure 2 Based on the first embodiment, in another embodiment of the present application, the calculation of the target vegetation index of each cultivated field pixel point in the satellite image data in the drought period based on the satellite image data comprises:

[0076] Step S21, determining a target drought month in the drought year;

[0077] Step S22, combining the satellite image data, calculating a maximum vegetation index and a vegetation index average value of the target drought month;

[0078] Step S23, calculating a vegetation index deviation value of the target drought month based on the maximum vegetation index and the vegetation index average value of the target drought month, and taking the vegetation index deviation value of the target drought month as the target vegetation index.

[0079] In the embodiment, in the case that there is no fixed drought period in the to-be-identified mapping area, a monthly surplus amount is calculated based on the monthly rainfall and the corresponding monthly potential evapotranspiration of each month in the drought year, a target drought month in the drought year is determined based on the monthly surplus amount, and then the NDVI vegetation index corresponding to the target drought month is calculated in combination with the satellite image data, so as to determine the maximum vegetation index and the average value of the NDVI vegetation index corresponding to the maximum vegetation index. Further, an index difference value between the maximum vegetation index of the target drought month and the average value of the NDVI vegetation index is calculated, a ratio between the index difference value and the average value of the NDVI vegetation index is calculated, a vegetation index deviation value of the target drought month is obtained, the vegetation index deviation value of the target drought month is calculated, and the vegetation index deviation value of the target drought month is taken as the target vegetation index, so as to realize accurate identification of the irrigated farmland region in the region without a fixed drought period by calculating the vegetation index deviation value of the drought month in the driest year, and then identifying the irrigated farmland region based on the vegetation index deviation value and the index threshold value of the region. The vegetation index deviation value calculation formula is as follows:

[0080] NDVI dev = (NDVI max -DriestM-NDVI DM ) / NDVI DM

[0081] wherein, NDVI dev represents the vegetation index deviation value of the target drought month, NDVI max-DriestM represents the maximum vegetation index of the target drought month in the drought year in the first predetermined time range, and NDVI DM represents the average value of the vegetation index of the target drought month.

[0082] With reference to Figure 3 the first embodiment, in another embodiment of the present application, before step S30: determining whether the farmland pixel point is an irrigated farmland region based on the vegetation index of each farmland pixel point and the index threshold value of the to-be-identified mapping area calculated in advance, the following step is further included.

[0083] Step A10, acquiring training data of a plurality of training sample points in the to-be-identified mapping area, wherein the training sample points include irrigation points and non-irrigation points.

[0084] In the embodiment, it is to be noted that the index threshold corresponding to different mapping areas in the 110 irrigation mapping areas (IMZs) is not the same, the index threshold corresponding to each farmland pixel point in the same irrigation mapping area is the same, a plurality of training sample points are selected in the to-be-identified mapping area, wherein the training sample points include irrigation points and non-irrigation points, and satellite image data corresponding to the irrigation points and the non-irrigation points (that is, training data) are collected.

[0085] In step A20, if the to-be-identified mapping area has a fixed drought period, the maximum NDVI vegetation index corresponding to each irrigation point and the maximum NDVI vegetation index corresponding to each non-irrigation point are calculated based on the training data, and the index threshold of the to-be-identified mapping area is calculated based on the maximum NDVI vegetation index corresponding to each irrigation point and the maximum NDVI vegetation index corresponding to each non-irrigation point.

[0086] In step A30, if the to-be-identified mapping area does not have a fixed drought period, the vegetation index deviation value corresponding to each irrigation point and the vegetation index deviation value corresponding to each non-irrigation point are calculated based on the training data, and the index threshold of the to-be-identified mapping area is calculated based on the vegetation index deviation value corresponding to each irrigation point and the vegetation index deviation value corresponding to each non-irrigation point.

[0087] It is to be noted that the maximum vegetation index is the maximum value of the NDVI vegetation index. The index threshold can be calculated and determined based on the distance discrimination method, the Bayes discrimination method, and the Fisher linear discrimination method.

[0088] As an implementable manner, specifically, if the to-be-identified mapping area has a fixed drought period, the NDVI vegetation index corresponding to each irrigation point is calculated based on the training data corresponding to each irrigation point in the drought month, so as to determine the maximum NDVI vegetation index corresponding to the irrigation point, in addition, the NDVI vegetation index corresponding to each non-irrigation point is calculated based on the training data corresponding to each non-irrigation point in the drought month, so as to determine the maximum NDVI vegetation index corresponding to the non-irrigation point, and then the index threshold of the to-be-identified mapping area is calculated based on the maximum NDVI vegetation index corresponding to the irrigation point and the maximum NDVI vegetation index corresponding to the non-irrigation point.

[0089] As another possible implementation, specifically, based on the training data corresponding to the target drought month in a drought year within a first predetermined time range for each irrigation point, the maximum NDVI vegetation index and the average vegetation index corresponding to each irrigation point are calculated. Then, based on the maximum NDVI vegetation index and the average vegetation index corresponding to the irrigation point, the vegetation index deviation value corresponding to the irrigation point is calculated. In addition, the calculation process of the vegetation index deviation value corresponding to the non-irrigated point is basically the same as that of the irrigation point, and will not be repeated here. Then, based on the vegetation index deviation values ​​corresponding to each irrigation point and each non-irrigated point, the index threshold of the mapping area to be identified is calculated.

[0090] The formula for calculating the exponential threshold is as follows:

[0091]

[0092] Wherein, Nmidpoint represents the index threshold, Nirrgated represents the maximum vegetation index or vegetation index deviation value corresponding to the irrigation point, and Nnon-irrgated represents the maximum vegetation index or vegetation index deviation value corresponding to the non-irrigation point.

[0093] This invention, through the above-described scheme, acquires training data for several training sample points within the mapping area to be identified, including irrigated and non-irrigated points. If the mapping area experiences a fixed drought period, the maximum vegetation index corresponding to each irrigated and non-irrigated point is calculated based on the training data. An index threshold for the mapping area is then calculated based on these maximum vegetation indices. If the mapping area does not experience a fixed drought period, the vegetation index deviation value corresponding to each irrigated and non-irrigated point is calculated based on the training data. An index threshold for the mapping area is then calculated based on these deviation values. This method achieves the training and determination of the index threshold based on the vegetation index corresponding to the drought period, thereby more accurately distinguishing between irrigated and non-irrigated areas based on crop growth and the index threshold under drought stress.

[0094] The irrigation farmland area identification device provided by the present invention is described below. The irrigation farmland area identification device described below and the irrigation farmland area identification method described above can be referred to in correspondence.

[0095] like Figure 4 As shown, an embodiment of the present invention provides an irrigated farmland area identification device, which includes:

[0096] The acquisition module 10 is used to acquire satellite image data of the mapping area to be identified and to determine the drought period of the mapping area to be identified;

[0097] Calculation module 20 is used to calculate the target vegetation index of each cultivated field pixel in the satellite image data during the drought period based on the satellite image data;

[0098] The judgment module 30 is used to determine whether each cultivated field pixel is an irrigated cultivated land area based on the target vegetation index of the cultivated field pixel and the index threshold of the pre-calculated mapping area to be identified.

[0099] Optionally, the irrigated farmland area identification device further includes:

[0100] Acquire training data for several training sample points within the mapping area to be identified, wherein the training sample points include irrigation points and non-irrigation points;

[0101] If the mapping area to be identified has a fixed drought period, then based on the training data, the maximum vegetation index corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the maximum vegetation index corresponding to each irrigation point and each non-irrigation point, the index threshold of the mapping area to be identified is calculated.

[0102] If the mapping area to be identified does not have a fixed drought period, then based on the training data, the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point respectively, the index threshold of the mapping area to be identified is calculated.

[0103] Optionally, the irrigated farmland area identification device further includes:

[0104] The annual and monthly rainfall of the area to be identified for mapping are statistically analyzed within a first predetermined time range.

[0105] Based on the regional climate information of the area to be identified in the mapping, determine whether there is a fixed drought period in the area to be identified in the mapping;

[0106] If such a month exists, then based on the monthly rainfall within the first pre-defined time range, the dry months of the mapping area to be identified are determined.

[0107] If not, then the drought year of the mapping area to be identified is determined based on the annual rainfall of each year within the first pre-defined time range.

[0108] Optionally, the computing module 20 is further configured to:

[0109] Based on the satellite image data, the maximum vegetation index for each dry month within a second preset time range is calculated, and the maximum vegetation index for the dry month is used as the target vegetation index, wherein the second preset time range is smaller than the first preset time range.

[0110] Optionally, the computing module 20 is further configured to:

[0111] Determine the target drought month in the drought year;

[0112] Based on the satellite image data, calculate the maximum vegetation index and the average vegetation index for the target drought month;

[0113] Based on the maximum vegetation index and the average vegetation index of the target drought month, the vegetation index deviation value of the target drought month is calculated, and the vegetation index deviation value of the target drought month is used as the target vegetation index.

[0114] Optionally, the computing module 20 is further configured to:

[0115] Calculate the difference between the maximum vegetation index and the average vegetation index for the target drought month;

[0116] The vegetation index deviation value for the target drought month is obtained by calculating the ratio between the index difference and the average vegetation index.

[0117] Optionally, the determination module 30 is further configured to:

[0118] If the mapping area to be identified has a fixed drought period and the target vegetation index is greater than the index threshold, then the cultivated land pixel is determined to be an irrigated cultivated land area.

[0119] If the mapping area to be identified does not have a fixed drought period, and the target vegetation index is less than the index threshold, then the cultivated land pixel is determined to be an irrigated cultivated land area.

[0120] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail here.

[0121] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute an irrigated farmland area identification method. This method includes: acquiring satellite image data of a mapping area to be identified and determining the drought period of the mapping area; calculating a target vegetation index for each farmland pixel in the satellite image data during the drought period based on the satellite image data; and for each farmland pixel: determining whether the farmland pixel is an irrigated farmland area based on the target vegetation index of the farmland pixel and a pre-calculated index threshold for the mapping area to be identified.

[0122] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the irrigated farmland area identification method provided by the above methods. The method includes: acquiring satellite image data of a mapping area to be identified and determining the drought period of the mapping area to be identified; calculating a target vegetation index for each farmland pixel in the satellite image data during the drought period based on the satellite image data; and for each farmland pixel: determining whether the farmland pixel is an irrigated farmland area based on the target vegetation index of the farmland pixel and a pre-calculated index threshold for the mapping area to be identified.

[0124] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the irrigated farmland area identification method provided by the above methods. The method includes: acquiring satellite image data of a mapping area to be identified and determining the drought period of the mapping area to be identified; calculating the target vegetation index of each farmland pixel in the satellite image data during the drought period based on the satellite image data; and for each farmland pixel: determining whether the farmland pixel is an irrigated farmland area based on the target vegetation index of the farmland pixel and a pre-calculated index threshold of the mapping area to be identified.

[0125] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0126] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying irrigated farmland areas, characterized in that, include: Acquire satellite image data of the area to be mapped and determine the drought period of the area; Based on the satellite image data, calculate the target vegetation index for each cultivated land pixel in the satellite image data during the drought period; For each cultivated land pixel: based on the target vegetation index of the cultivated land pixel and the index threshold of the pre-calculated mapping area to be identified, determine whether the cultivated land pixel is an irrigated cultivated land area; The drought period includes drought months and drought years, and determining the drought period of the mapping area to be identified includes: The annual and monthly rainfall of the area to be identified for mapping are statistically analyzed within a first predetermined time range. Based on the regional climate information of the area to be identified in the mapping, determine whether there is a fixed drought period in the area to be identified in the mapping; If such a month exists, then based on the monthly rainfall within the first pre-defined time range, the dry months of the mapping area to be identified are determined. If not, then the drought year of the mapping area to be identified is determined based on the annual rainfall of each year within the first pre-defined time range; Before determining whether a cultivated land pixel is an irrigated cultivated land area based on the vegetation index of each cultivated land pixel and the pre-calculated index threshold of the mapping area to be identified, the method further includes: Acquire training data for several training sample points within the mapping area to be identified, wherein the training sample points include irrigation points and non-irrigation points; If the mapping area to be identified has a fixed drought period, then based on the training data, the maximum vegetation index corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the maximum vegetation index corresponding to each irrigation point and each non-irrigation point, the index threshold of the mapping area to be identified is calculated. If the mapping area to be identified does not have a fixed drought period, then based on the training data, the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point respectively, the index threshold of the mapping area to be identified is calculated.

2. The method for identifying irrigated farmland areas according to claim 1, characterized in that, If the area to be mapped exists during a fixed period of drought, the step of calculating the target vegetation index for each cultivated land pixel in the satellite image data during that drought period, based on the satellite image data, includes: Based on the satellite image data, the maximum vegetation index for each dry month in a second pre-defined time range is calculated, and the maximum vegetation index for the dry month is used as the target vegetation index, wherein the second pre-defined time range is smaller than the first pre-defined time range.

3. The method for identifying irrigated farmland areas according to claim 1, characterized in that, If the area to be mapped does not have a fixed drought period, the step of calculating the target vegetation index for each cultivated land pixel in the satellite image data during the drought period, based on the satellite image data, includes: Determine the target drought month in the drought year; Based on the satellite image data, calculate the maximum vegetation index and the average vegetation index for the target drought month; Based on the maximum vegetation index and the average vegetation index of the target drought month, the vegetation index deviation value of the target drought month is calculated, and the vegetation index deviation value of the target drought month is used as the target vegetation index.

4. The method for identifying irrigated farmland areas according to claim 3, characterized in that, The vegetation index deviation value for the target drought month is calculated based on the maximum vegetation index and the average vegetation index for the target drought month, including... Calculate the difference between the maximum vegetation index and the average vegetation index for the target drought month; The vegetation index deviation value for the target drought month is obtained by calculating the ratio between the index difference and the average vegetation index.

5. The method for identifying irrigated farmland areas according to claim 1, characterized in that, The step of determining whether a cultivated land pixel is an irrigated cultivated land area based on the target vegetation index of the cultivated land pixel and the pre-calculated index threshold of the mapping area to be identified includes: If the mapping area to be identified has a fixed drought period and the target vegetation index is greater than the index threshold, then the cultivated land pixel is determined to be an irrigated cultivated land area. If the mapping area to be identified does not have a fixed drought period, and the target vegetation index is less than the index threshold, then the cultivated land pixel is determined to be an irrigated cultivated land area.

6. A device for identifying irrigated farmland areas, characterized in that, include: The acquisition module is used to acquire satellite image data of the area to be identified and mapped, and to determine the drought period of the area to be identified and mapped; The calculation module is used to calculate the target vegetation index for each cultivated land pixel in the satellite image data during the drought period, based on the satellite image data. The judgment module is used to determine whether each cultivated field pixel is an irrigated cultivated land area based on the target vegetation index of the cultivated field pixel and the index threshold of the pre-calculated mapping area to be identified. The drought period includes drought months and drought years, and determining the drought period of the mapping area to be identified includes: The annual and monthly rainfall of the area to be identified for mapping are statistically analyzed within a first predetermined time range. Based on the regional climate information of the area to be identified in the mapping, determine whether there is a fixed drought period in the area to be identified in the mapping; If such a month exists, then based on the monthly rainfall within the first pre-defined time range, the dry months of the mapping area to be identified are determined. If not, then the drought year of the mapping area to be identified is determined based on the annual rainfall of each year within the first pre-defined time range; Before determining whether a cultivated land pixel is an irrigated cultivated land area based on the vegetation index of each cultivated land pixel and the pre-calculated index threshold of the mapping area to be identified, the method further includes: Acquire training data for several training sample points within the mapping area to be identified, wherein the training sample points include irrigation points and non-irrigation points; If the mapping area to be identified has a fixed drought period, then based on the training data, the maximum vegetation index corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the maximum vegetation index corresponding to each irrigation point and each non-irrigation point, the index threshold of the mapping area to be identified is calculated. If the mapping area to be identified does not have a fixed drought period, then based on the training data, the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point is calculated respectively, and based on the vegetation index deviation value corresponding to each irrigation point and each non-irrigation point respectively, the index threshold of the mapping area to be identified is calculated.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the irrigated farmland area identification method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the irrigated farmland area identification method as described in any one of claims 1 to 5.

Images