Agricultural resource environment monitoring method and device fusing multi-source remote sensing data

Abstract

The invention relates to the technical field of agricultural resource environment monitoring, and discloses an agricultural resource environment monitoring method and device fusing multi-source remote sensing data, equipment and a computer program product. The method comprises the following steps: acquiring agricultural resource environment information based on multi-source remote sensing data; performing data preprocessing according to the agricultural resource environment information; performing fusion according to the preprocessed data; and agricultural resource environment monitoring and analysis are carried out according to the fused data. Compared with the limitation problem of a single data source in the prior art, the method has the advantages that the satellite remote sensing data, the unmanned aerial vehicle remote sensing data and the ground sensor data are fused, and the artificial intelligence algorithm and the time sequence analysis method are combined, so that high-precision and real-time agricultural resource environment monitoring is realized; and the scientificity and efficiency of agricultural management and decision making are improved.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural resource and environment monitoring, and in particular to an agricultural resource and environment monitoring method, device, equipment, and computer program product that integrates multi-source remote sensing data. Background Art

[0002] At present, agricultural resource and environmental monitoring mainly relies on a single data source, such as satellite remote sensing data or ground sensor data, and is usually monitored by collecting and analyzing the data provided by these devices. Although this monitoring method can provide certain environmental information, it has great limitations in accuracy and timeliness, and it is difficult to fully reflect the actual situation of agricultural resources and environment. For example, although satellite remote sensing data has a wide coverage, its spatial resolution and temporal resolution are limited, and it is difficult to provide detailed local information. Although ground sensors can provide high-precision data, they have a small coverage area and are difficult to reflect the situation in large areas. When high-precision and real-time agricultural resource and environmental monitoring is required over a large area, the existing technology cannot fully meet this demand. Therefore, there is an urgent need for an agricultural resource and environmental monitoring method that integrates multi-source remote sensing data, which can achieve high-precision and real-time agricultural resource and environmental monitoring over a large area without relying on a single data source, so as to improve the accuracy and efficiency of monitoring, thereby providing a scientific basis for agricultural management and decision-making. Summary of the invention

[0003] The main purpose of the present invention is to provide an agricultural resource and environment monitoring method, device, equipment and computer program product that integrates multi-source remote sensing data, aiming to solve the technical problem that the existing technology has great limitations in accuracy and timeliness, and it is difficult to fully reflect the actual situation of agricultural resources and environment, especially under the conditions of high-precision and real-time agricultural resource and environment monitoring over a large range, and it is impossible to achieve high-precision and real-time agricultural resource and environment monitoring over a large range.

[0004] To achieve the above object, the present invention provides an agricultural resource environment monitoring method integrating multi-source remote sensing data.

[0005] Preferably, the method comprises:

[0006] Step S10: obtaining agricultural resource and environmental information of an area exceeding 500 square kilometers based on satellite remote sensing data, and obtaining agricultural resource and environmental information with sub-meter resolution by improving multi-scale segmentation method in combination with UAV remote sensing data;

[0007] Step S20: using a data cleaning method to remove noise from the high-resolution agricultural resource and environmental information, and performing standardization processing on the denoised data to obtain standardized information from different data sources;

[0008] Step S30: using a weight distribution algorithm to process the standardized information of different data sources and extracting feature data of different data sources, and using an improved long short-term memory network time series method to process the feature data to obtain feature fusion data;

[0009] Step S40: combining the feature fusion data with an enhanced random forest algorithm to perform agricultural resource environment monitoring and analysis.

[0010] Preferably, in step S10, the improved multi-scale segmentation method introduces an adaptive scale parameter, and the adaptive scale parameter is adjusted according to the terrain complexity and crop types in the agricultural resource environment.

[0011] Preferably, the data cleaning method in step S20 includes detecting and removing outliers in the data, and filling in missing data in combination with an interpolation method.

[0012] Preferably, the standardization process in step S20 includes converting the values ​​of different data sources into the same dimension by using a Z-score standardization method.

[0013] Preferably, in step S40, the step of combining the feature fusion data with an enhanced random forest algorithm to monitor and analyze agricultural resources and environment includes:

[0014] Based on the fused multi-source data, the enhanced random forest algorithm was used to preliminarily classify the agricultural resource environment. The classification results included different crop types, land use conditions, and the distribution status of agricultural resources.

[0015] Regression analysis was performed based on the classification results to predict the changing trends of agricultural resources and environment.

[0016] Preferably, after the step of performing regression analysis based on the classification results to predict the changing trend of agricultural resources and environment, the method further comprises:

[0017] The changing trends of agricultural resource environment are dynamically displayed on the three-dimensional geographic model, including the distribution of agricultural resources, density changes and the transfer of crop types in different time periods.

[0018] Preferably, before step S10, the method further includes determining the spatial boundary and time range of the monitoring area according to the agricultural resource distribution data in the geographic information system.

[0019] Preferably, the agricultural resource environment monitoring device integrating multi-source remote sensing data comprises:

[0020] The data acquisition module is used to obtain agricultural resource and environmental information of an area of ​​more than 500 square kilometers based on satellite remote sensing data, and obtain agricultural resource and environmental information with sub-meter resolution by improving the multi-scale segmentation method combined with UAV remote sensing data;

[0021] The data preprocessing module is used to remove noise from high-resolution agricultural resource and environmental information by using data cleaning methods, and to standardize the denoised data to obtain standardized information from different data sources;

[0022] A data fusion module is used to process the standardized information of different data sources by using a weight distribution algorithm and extract feature data of different data sources, and process the feature data by using an improved long short-term memory network time series method to obtain feature fusion data;

[0023] The monitoring and analysis module is used to combine the feature fusion data with the enhanced random forest algorithm to monitor and analyze agricultural resources and environment.

[0024] The beneficial effects of the present invention are: compared with the limitations of a single data source in the prior art, this application achieves high-precision and real-time monitoring of agricultural resources and environment by integrating satellite remote sensing data, UAV remote sensing data and ground sensor data while combining artificial intelligence algorithms and time series analysis methods, thereby improving the scientificity and efficiency of agricultural management and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a flow chart of the first embodiment of the agricultural resource environment monitoring method integrating multi-source remote sensing data of the present invention;

[0027] Figure 2 This is a schematic diagram of the agricultural resource environment monitoring equipment that integrates multi-source remote sensing data in the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Embodiment 1: Figure 1 FIG. 1 is a flow chart of a first embodiment of a method for monitoring agricultural resources and environment by fusing multi-source remote sensing data according to the present invention.

[0030] Step S10: obtaining agricultural resource and environmental information of an area exceeding 500 square kilometers based on satellite remote sensing data, and obtaining agricultural resource and environmental information with sub-meter resolution by improving multi-scale segmentation method in combination with UAV remote sensing data;

[0031] It should be noted that agricultural resource and environmental information includes but is not limited to crop distribution, soil moisture, meteorological conditions, crop health, distribution of pests and diseases, soil fertility, and terrain and landform information.

[0032] It should be noted that satellite remote sensing data has the advantages of wide coverage and high frequency of data acquisition, and is suitable for monitoring large-scale agricultural resources. For example, satellite images can be used to obtain a wide range of environmental information such as crop distribution, soil moisture, and meteorological conditions in real time. Satellite remote sensing data has a low spatial resolution, but a high temporal resolution, which can provide reliable data support for macro-monitoring of agricultural resources.

[0033] It is understandable that drone remote sensing data has a higher spatial resolution than satellite remote sensing data and can capture detailed agricultural resource information. For example, drone flights can obtain high-precision local detail data such as crop growth status, pest distribution, etc. at a lower altitude. Images obtained by drones can identify the health status of individual plants, analyze local moisture changes in the soil, and accurately monitor local conditions such as the microclimate of farmland.

[0034] It should be understood that the method of fusing multi-source remote sensing data combines the macro information of satellite remote sensing with the high-resolution information of drones, which can better achieve comprehensive monitoring of agricultural resources. For example, in agricultural drought monitoring, satellite remote sensing data can quickly identify large areas of drought, but the precise moisture conditions need to be supplemented by drone data. By fusing the two types of remote sensing data, the system can provide more comprehensive agricultural resource monitoring results at different spatial scales to ensure the accuracy and practicality of decision-making. For example, satellite remote sensing can preliminarily determine areas with abnormal crop growth, while drones can further refine monitoring of specific problems in these areas, such as pests and diseases or malnutrition, thereby helping farmers or agricultural managers to take more precise intervention measures.

[0035] It should be understood that the specific implementation step of improving the multi-scale segmentation method can be to introduce dynamic weight adjustment, formula:

[0036]

[0037] Among them, W(x,y) is the final fused image result, α i (t) is a weight coefficient that is dynamically adjusted based on the characteristics of data source i (such as temporal sensitivity and spatial resolution), and f i (x,y,r i ) is to consider the spatial resolution r i The data feature function. Weight coefficient α i (t) Optimize the effect of data fusion through real-time adjustment through an algorithm based on data characteristics and task requirements.

[0038] For example, suppose a pest and disease monitoring campaign is being conducted in an agricultural area and real-time information on the health of crops is needed.

[0039] (1) Application of satellite data:

[0040] For the satellite data source (i=1), the resolution r1 is low and the coverage is wide; the dynamic weight α1(t) is higher in the non-pest and disease outbreak period because a large area needs to be scanned quickly to monitor whether there is an abnormal development trend; the characteristic function f1(x, y, r1) provides a wide range of crop growth status and environmental information.

[0041] (2) Application of drone data:

[0042] For the drone data source (i=2), the resolution r2 is high, which can observe the crop condition in detail. The dynamic weight α2(t) increases significantly after monitoring the potential pest and disease area to conduct detailed local inspection and analysis. The feature function f2(x,y,r2) provides detailed crop health status, such as leaf color changes, size abnormalities, and other details to identify the specific type and extent of pests and diseases.

[0043] By dynamically adjusting the weights of different data sources and combining their respective characteristic functions, seamless monitoring from macro to micro can be achieved. This approach makes it possible to quickly locate potential problem areas over a large area, while making accurate diagnoses locally, greatly improving the efficiency and accuracy of monitoring, ensuring that appropriate agricultural management measures are taken in a timely manner to reduce economic losses.

[0044] Step S20: using a data cleaning method to remove noise from the high-resolution agricultural resource and environmental information, and performing standardization processing on the denoised data to obtain standardized information from different data sources;

[0045] It should be noted that agricultural resource and environmental data often come from a variety of remote sensing equipment and sensors, and these data may contain noise, such as equipment failure, environmental interference, or errors in the data transmission process. These noises will affect the accuracy of data analysis. Therefore, data cleaning is a very critical step. Common data cleaning methods include outlier detection, missing value processing, smoothing filtering, etc., the purpose of which is to remove invalid or erroneous data, making subsequent analysis more accurate and reliable.

[0046] It is understandable that the denoised data usually has different measurement units, ranges, and distribution characteristics, so it needs to be standardized. The purpose of standardization is to convert data from different sources to the same scale to ensure that data of different dimensions can be compared and analyzed under the same framework. Standardization methods can include Z-score standardization and minimum-maximum standardization. For example, although temperature data and humidity data have different units, they can be adjusted to the same range through standardization, so that the model can be more consistent when processing these data.

[0047] It should be understood that the standardized data may still have spatial or temporal incompleteness, such as missing data information in certain areas due to sensor failure. To solve this problem, interpolation processing can help fill these data gaps. Interpolation processing is a technique for estimating unknown data points based on known data points. Common methods include linear interpolation, spline interpolation, and Kriging interpolation. For example, in agricultural monitoring, if soil moisture data in certain areas is missing, the system can estimate the data of these missing areas through interpolation methods based on the moisture values ​​of surrounding known points. Through interpolation, the system can obtain more complete and coherent agricultural resource and environmental information, providing more reliable data support for subsequent analysis.

[0048] For example, suppose we use remote sensing equipment to obtain soil moisture and temperature data in different regions in agricultural resource monitoring. However, these data may contain noise, such as outliers caused by sensor failure or data information lost during transmission. Therefore, we first denoise the data to remove unreasonable outliers. After denoising, there may still be incomplete data information. Next, we perform standardization and interpolation processing. The specific implementation steps can be:

[0049] (1) Denoised data:

[0050] Humidity data (%): 40, 45, 42, missing values, 38, 44, 46

[0051] Temperature data (℃): 15, 18, 16, missing values, 20, 19, 21

[0052] (2) Standardization processing:

[0053] Calculate the mean and standard deviation of the humidity data, assuming the mean is 42.5% and the standard deviation is 3.2.

[0054] Calculate the mean and standard deviation of the temperature data, assuming the mean is 18.2°C and the standard deviation is 2.2.

[0055] Standardized humidity data: -0.78, 0.78, -0.16, missing value, -1.41, 0.47, missing value, 1.09

[0056] Standardized temperature data: -1.45, -0.09, -1.00, missing value, 0.82, missing value, 0.36, 1.36

[0057] Interpolation:

[0058] (3) Use linear interpolation to fill in missing data:

[0059] Humidity data: The first missing value is interpolated to 40, and the second missing value is interpolated to 45.

[0060] Temperature data: The first missing value is interpolated to 18, and the second missing value is interpolated to 19.5.

[0061] (4) Standardized data after interpolation:

[0062] Humidity data: -0.78, 0.78, -0.16, -0.78, -1.41, 0.47, 0.78, 1.09

[0063] Temperature data: -1.45, -0.09, -1.00, -0.09, 0.82, 0.58, 0.36, 1.36

[0064] Step S30: using a weight distribution algorithm to process the standardized information of different data sources and extracting feature data of different data sources, and using an improved long short-term memory network time series method to process the feature data to obtain feature fusion data;

[0065] It should be noted that the data collected by different data sources (such as satellite remote sensing, drone remote sensing, ground sensors, etc.) vary in accuracy, resolution, coverage, etc. The information provided by these data sources needs to be integrated during the processing to ensure the consistency and accuracy of the data. The weight allocation algorithm is used to assign appropriate weights to each data source and adjust its contribution to the overall analysis according to its importance and data quality. This can reduce the impact of low-quality data and enhance the reliability of data integration.

[0066] It is understandable that the application of the weight allocation algorithm can assign different weights to data sources according to their characteristics (such as data accuracy, timeliness, spatial resolution, etc.). For example, satellite remote sensing data has a wide coverage but low resolution, which may be suitable for large-scale regional analysis; while drone data has high resolution but limited coverage, which is suitable for refined regional monitoring. Therefore, the weight allocation algorithm optimizes the effect of data integration based on these characteristics. The system automatically weights the data according to these weights to obtain more accurate integrated data.

[0067] It should be understood that in traditional time series data fusion, weighted average method is usually used to integrate remote sensing data at different times. For example, given remote sensing feature data (such as NDVI, vegetation index) at multiple time points, we can use the following weighted average formula for data fusion:

[0068]

[0069] Among them, X f represents the fused time series data; X i is the characteristic data at time point i; w i is the weight at time point i.

[0070] This method is simple and direct, but there is a problem that it cannot fully consider the changes in data quality over time. If the data quality at certain time points is poor or the data is missing, this method will affect the accuracy of the fusion result.

[0071] We can introduce a dynamic weight allocation mechanism to adjust the weight of each time point by evaluating the data quality. The weight no longer depends solely on the time interval or data source, but is dynamically allocated based on the quality and timeliness of the data. For example, we can combine the time decay function with the data quality evaluation, and the improved fusion formula is:

[0072]

[0073] Among them, w i (t i ) is the time decay weight of time point i, indicating that as time goes by, the weight of data farther away from the current moment gradually decreases; q i is the data quality weight, indicating the reliability or accuracy of the data; X i is the characteristic data at time point i.

[0074] Time decay weight, time decay can be represented by an exponential decay function:

[0075] where t now is the current moment; ti is the moment at time point i; λ is the attenuation coefficient, which controls the attenuation speed.

[0076] Data quality weight: Data quality weight q i This can be determined by evaluating factors such as sensor accuracy, data integrity, noise level, etc. For example, for high-quality data, q i can be close to 1, and for poor quality data can be significantly less than 1.

[0077] For example, suppose we have data (NDVI values) at three time points, namely X1=0.6, X2=0.7, X3=0.65, and the corresponding collection times are 1 day ago, 3 days ago, and 7 days ago. We set the attenuation coefficient, set the attenuation coefficient λ=0.5, and assume that the data quality weights are q1=1, q2=0.9, q3=0.8.

[0078] (1) Calculate the time decay weight:

[0079] w1=e -0.5(1) =0.6065

[0080] w2=e -0.5(3) =0.2231

[0081] w3=e -0.5(7) =0.0302

[0082] (2) According to the improved formula, the fusion result is:

[0083] X f =(0.6065×1×0.6)+(0.2231×0.9×0.7)+(0.0302×0.8×0.65)

[0084] X f =0.3639+0.1403+0.0157=0.5199

[0085] The final fusion result X f ≈0.52. This result fully considers the timeliness and quality of data at different time points and gives lower weight to long-term and poor-quality data.

[0086] Step S40: combining the feature fusion data with an enhanced random forest algorithm to perform agricultural resource environment monitoring and analysis.

[0087] It should be noted that the fused data is comprehensive data obtained by integrating multiple data sources (such as satellite remote sensing, drone monitoring, ground sensors, etc.). After processing, these data contain various key information of agricultural resources, such as soil moisture, meteorological conditions, crop growth status, etc. Through these fused data, the system can realize real-time monitoring and accurate analysis of agricultural resources and environment.

[0088] It can be understood that through agricultural resource environmental monitoring, the system can track and analyze multiple important environmental variables in real time, such as soil moisture, temperature, vegetation index (NDVI), etc. Fused data provides a more comprehensive perspective, allowing the system to monitor changes in agricultural resources across different time and space scales. For example, satellite remote sensing provides low-resolution data over a large area, while drones and ground sensors provide high-resolution local data, which can be combined to simultaneously monitor macro and micro levels.

[0089] It should be understood that data fusion is not only used for current monitoring, but also includes future prediction and decision support. For example, the system can predict future agricultural resource needs based on current monitoring data, combined with historical data and weather forecasts, such as predicting the risk of drought or pests and diseases that may occur in the next few days. Through time series analysis, the system can identify potential problems in advance and give optimized management suggestions (such as adjusting irrigation plans, fertilization strategies, etc.). This monitoring and analysis method based on data fusion can help farmers make more informed agricultural management decisions, improve agricultural production efficiency, and reduce environmental impact.

[0090] In addition, this application also provides an agricultural resource environment monitoring device that integrates multi-source remote sensing data, please refer to Figure 2 The agricultural resource environment monitoring device integrating multi-source remote sensing data comprises:

[0091] Data acquisition module, used to obtain a wide range of agricultural resource and environmental information based on satellite remote sensing data, and to obtain high-resolution agricultural resource and environmental information in combination with UAV remote sensing data;

[0092] The data preprocessing module is used to remove noise from agricultural resource and environmental information based on data cleaning methods, and perform interpolation processing on the de-noised data after standardization;

[0093] A data fusion module, used to integrate information from different data sources based on a weight distribution algorithm, extract features of remote sensing data based on the integrated data, and perform time series data fusion on the feature data;

[0094] The monitoring and analysis module is used to monitor and analyze agricultural resources and environment based on the fused data.

[0095] The agricultural resource and environment monitoring device provided by the present application, which integrates multi-source remote sensing data, adopts a method for monitoring agricultural resource and environment integrating multi-source remote sensing data in the above-mentioned embodiment, and can solve the technical problem of monitoring agricultural resource and environment integrating multi-source remote sensing data. Compared with the prior art, the beneficial effects of the agricultural resource and environment monitoring device integrated with multi-source remote sensing data provided by the present application are the same as the beneficial effects of the method for monitoring agricultural resource and environment integrating multi-source remote sensing data provided by the above-mentioned embodiment, and the other technical features of the agricultural resource and environment monitoring device integrated with multi-source remote sensing data are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0096] The present application provides an agricultural resource and environment monitoring device that integrates multi-source remote sensing data. The agricultural resource and environment monitoring device that integrates multi-source remote sensing data includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute an agricultural resource and environment monitoring method that integrates multi-source remote sensing data in the above-mentioned embodiment 1. An agricultural resource and environment monitoring device that integrates multi-source remote sensing data in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. An agricultural resource and environment monitoring device that integrates multi-source remote sensing data is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present application.

[0097] An agricultural resource and environment monitoring device that integrates multi-source remote sensing data may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In RAM 1004, various programs and data required for the operation of an agricultural resource and environment monitoring device that integrates multi-source remote sensing data are also stored. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow an agricultural resource and environment monitoring device that integrates multi-source remote sensing data to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an agricultural resource and environment monitoring device that integrates multi-source remote sensing data with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or provided alternatively.

[0098] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned agricultural resource environment monitoring method that integrates multi-source remote sensing data.

[0099] The computer program product provided by this application can solve the technical problem of agricultural resource and environmental monitoring by integrating multi-source remote sensing data. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the agricultural resource and environmental monitoring method by integrating multi-source remote sensing data provided by the above embodiment, and will not be repeated here.

[0100] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0101] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring agricultural resources and environment by integrating multi-source remote sensing data, characterized in that: The method comprises: Step S10: obtaining agricultural resource and environmental information of an area exceeding 500 square kilometers based on satellite remote sensing data, and obtaining agricultural resource and environmental information with sub-meter resolution by improving multi-scale segmentation method in combination with UAV remote sensing data; Step S20: using a data cleaning method to remove noise from the high-resolution agricultural resource and environmental information, and performing standardization processing on the denoised data to obtain standardized information from different data sources; Step S30: using a weight distribution algorithm to process the standardized information of different data sources and extracting feature data of different data sources, and using an improved long short-term memory network time series method to process the feature data to obtain feature fusion data; Step S40: combining the feature fusion data with an enhanced random forest algorithm to perform agricultural resource environment monitoring and analysis.

2. The method according to claim 1, characterized in that In step S10, the improved multi-scale segmentation method introduces an adaptive scale parameter, and the adaptive scale parameter is adjusted according to the terrain complexity and crop types in the agricultural resource environment.

3. The method according to claim 1, characterized in that The data cleaning method in step S20 includes detecting and removing outliers in the data, and filling in missing data in combination with an interpolation method.

4. The method according to claim 1, characterized in that: The standardization process in step S20 is to convert the values ​​of different data sources into the same dimension through the Z-score standardization method.

5. The agricultural resource environment monitoring method integrating multi-source remote sensing data as claimed in claim 1, characterized in that: In step S40, the step of combining the feature fusion data with the enhanced random forest algorithm to monitor and analyze agricultural resources and environment includes: Based on the fused multi-source data, the enhanced random forest algorithm was used to preliminarily classify the agricultural resource environment. The classification results included different crop types, land use conditions, and the distribution status of agricultural resources. Regression analysis was performed based on the classification results to predict the changing trends of agricultural resources and environment.

6. The agricultural resource environment monitoring method integrating multi-source remote sensing data as claimed in claim 5, characterized in that: After the step of performing regression analysis based on the classification results to predict the changing trend of agricultural resources and environment, the method further includes: The changing trends of agricultural resource environment are dynamically displayed on the three-dimensional geographic model, including the distribution of agricultural resources, density changes and the transfer of crop types in different time periods.

7. The agricultural resource environment monitoring method integrating multi-source remote sensing data as claimed in claim 1, characterized in that: Before step S10, the process also includes determining the spatial boundary and time range of the monitoring area according to the agricultural resource distribution data in the geographic information system.

8. An agricultural resource and environment monitoring device based on the fusion of multi-source remote sensing data, characterized in that: The agricultural resource environment monitoring device integrating multi-source remote sensing data comprises: The data acquisition module is used to obtain agricultural resource and environmental information of an area of ​​more than 500 square kilometers based on satellite remote sensing data, and obtain agricultural resource and environmental information with sub-meter resolution by improving the multi-scale segmentation method combined with UAV remote sensing data; The data preprocessing module is used to remove noise from high-resolution agricultural resource and environmental information by using data cleaning methods, and to standardize the denoised data to obtain standardized information from different data sources; A data fusion module is used to process the standardized information of different data sources by using a weight distribution algorithm and extract feature data of different data sources, and process the feature data by using an improved long short-term memory network time series method to obtain feature fusion data; The monitoring and analysis module is used to combine the feature fusion data with the enhanced random forest algorithm to monitor and analyze agricultural resources and environment.

9. An agricultural resource and environment monitoring device integrating multi-source remote sensing data, characterized in that: The agricultural resource environment monitoring equipment integrating multi-source remote sensing data includes: A memory, a processor, and an agricultural resource and environment monitoring program that integrates multi-source remote sensing data and is stored in the memory and can be run on the processor. When the agricultural resource and environment monitoring program that integrates multi-source remote sensing data is executed by the processor, the agricultural resource and environment monitoring method that integrates multi-source remote sensing data as described in any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product includes an agricultural resource and environment monitoring program that integrates multi-source remote sensing data. When the agricultural resource and environment monitoring program that integrates multi-source remote sensing data is executed by a processor, it implements the agricultural resource and environment monitoring method that integrates multi-source remote sensing data as described in any one of claims 1 to 7.

Images