Dynamic monitoring method and system of forest cultivation based on remote sensing technology

By building a dynamic monitoring system of remote sensing technology in forest cultivation, including real-time and historical data processing, classification identification and modular analysis, the problem of low survival rate of forest vegetation is solved, and efficient survival and intelligent management of forest vegetation is achieved.

CN118485961BActive Publication Date: 2024-11-12莒县龙山镇农业综合服务中心
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410609973.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-12
Estimated Expiration
2044-05-16

AI Technical Summary

Technical Problem

The existing forest cultivation monitoring methods based on remote sensing technology have problems with imperfect data processing and analysis, lack of intelligence and automation, resulting in low survival rates of forest vegetation.

Method used

By determining the target area and laying sensor devices, real-time and historical remote sensing data are obtained, timing analysis and classification identification are carried out, and forest cultivation systems are built, including vegetation identification, growth prediction, early warning and cultivation modules, and dynamic information and strategies are monitored in real time.

Benefits of technology

The survival rate of forest vegetation has been improved, real-time, dynamic monitoring and intelligent management of forest cultivation process have been achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118485961B_ABST
    Figure CN118485961B_ABST
Patent Text Reader

Abstract

The present invention discloses a forest cultivation dynamic monitoring method and system based on remote sensing technology, which relates to the field of forest cultivation technology. The method includes: determining a target area, monitoring the target area in real time, and obtaining real-time monitoring data; setting a fixed period, activating a collection device based on the fixed period, and obtaining historical remote sensing data; processing the historical remote sensing data based on time series analysis, and obtaining historical time series remote sensing data; classifying and identifying forest vegetation based on a forest management system, and obtaining forest images, wherein the forest images have species identifications; building a forest cultivation system based on forest images and historical time series remote sensing data; inputting real-time monitoring data into the forest cultivation system, and outputting forest dynamic information; and monitoring and cultivating guidance for the target area. The present invention solves the technical problem in the prior art that the survival rate of forest vegetation is low due to the single data monitoring and processing method, and achieves the technical effect of improving the survival rate of forest vegetation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of forest cultivation, and in particular to a dynamic monitoring method and system for forest cultivation based on remote sensing technology. Background Art

[0002] With the intensification of global climate change and human activities, forest ecosystems are facing increasingly serious threats, including forest fires, pests and diseases, illegal logging and other risks. These risks not only threaten the healthy growth of forests, but also have a profound impact on ecological security and sustainable development. Therefore, it is particularly important to conduct real-time, dynamic and efficient monitoring of the forest cultivation process.

[0003] Traditional forest cultivation monitoring methods mostly rely on manual inspections and ground station observations, which have many shortcomings. First, manual inspections are inefficient and difficult to cover large areas of forests; second, although ground station observations can obtain relatively accurate data, the distribution of stations is limited and cannot fully reflect the overall condition of the forest; finally, the data update speed of these methods is slow, making it difficult to respond to emergencies in forest ecosystems in a timely manner.

[0004] In recent years, remote sensing technology has been widely used in the field of forest cultivation monitoring due to its advantages of wide coverage, fast data update, and large amount of information. Through remote sensing technology, we can obtain information on forest vegetation coverage, growth status, distribution of pests and diseases, etc., providing strong data support for forest cultivation.

[0005] However, although remote sensing technology plays an important role in forest cultivation monitoring, the existing forest cultivation monitoring methods based on remote sensing technology still have some shortcomings. For example, the data processing and analysis methods are not perfect, making it difficult to fully mine the useful information in remote sensing data; at the same time, the existing monitoring system lacks intelligent and automated functions, and cannot achieve real-time and dynamic monitoring of the forest cultivation process. Summary of the invention

[0006] The present application provides a forest cultivation dynamic monitoring method and system based on remote sensing technology, which is used to solve the technical problem in the prior art that the survival rate of forest vegetation is low due to the single data monitoring and processing method.

[0007] In view of the above problems, the present application provides a forest cultivation dynamic monitoring method and system based on remote sensing technology.

[0008] The first aspect of the present application provides a method for dynamic monitoring of forest cultivation based on remote sensing technology, the method comprising:

[0009] Determine the target area and deploy sensor devices, monitor the target area in real time, and obtain real-time monitoring data; set a fixed period, activate the collection device based on the fixed period, and obtain multiple groups of historical remote sensing data of forest vegetation, the historical remote sensing data including spatial details and spectral information; process the historical remote sensing data based on time series analysis to obtain historical time series remote sensing data; classify and identify the multiple groups of forest vegetation based on the forest management system to obtain forest images, and the forest images have species identification; build a forest cultivation system based on the forest images and the historical time series remote sensing data, the forest cultivation system including a vegetation identification module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; input the real-time monitoring data into the forest cultivation system, and output forest dynamic information, the forest dynamic information including forest status and corresponding strategies; monitor and guide the cultivation of the target area based on the forest dynamic information.

[0010] The second aspect of the present application provides a dynamic monitoring system for forest cultivation based on remote sensing technology, the system comprising:

[0011] A real-time monitoring data acquisition unit, wherein the real-time monitoring data acquisition unit determines a target area and deploys a sensor device, performs real-time monitoring on the target area, and acquires real-time monitoring data; a historical remote sensing data acquisition unit, wherein the historical remote sensing data acquisition unit sets a fixed period, activates a collection device based on the fixed period, and acquires multiple groups of historical remote sensing data of forest vegetation, wherein the historical remote sensing data includes spatial details and spectral information; a historical time series remote sensing data acquisition unit, wherein the historical time series remote sensing data acquisition unit processes the historical remote sensing data based on time series analysis to acquire historical time series remote sensing data; and a forest image acquisition unit, wherein the forest image acquisition unit processes the multiple groups of forest vegetation based on a forest management system. Classification and identification are performed to obtain a forest image, wherein the forest image has a species identification; a forest cultivation system building unit, wherein the forest cultivation system building unit builds a forest cultivation system according to the forest image and the historical time series remote sensing data, wherein the forest cultivation system includes a vegetation identification module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; a forest dynamic information acquisition unit, wherein the forest dynamic information acquisition unit inputs the real-time monitoring data into the forest cultivation system and outputs forest dynamic information, wherein the forest dynamic information includes forest status and corresponding strategies; a monitoring and cultivation guidance unit, wherein the monitoring and cultivation guidance unit monitors and guides the target area based on the forest dynamic information.

[0012] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0013] The present application determines the target area and deploys the sensing device, monitors the target area in real time, and obtains the real-time monitoring data; sets a fixed period, activates the acquisition device based on the fixed period, obtains multiple groups of historical remote sensing data of forest vegetation, and the historical remote sensing data includes spatial details and spectral information; processes the historical remote sensing data based on time series analysis to obtain historical time series remote sensing data; classifies and identifies multiple groups of forest vegetation based on the forest management system, obtains forest images, and the forest images have species identification; builds a forest cultivation system based on the forest image and the historical time series remote sensing data, and the forest cultivation system includes a vegetation identification module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; inputs the real-time monitoring data into the forest cultivation system, and outputs forest dynamic information, and the forest dynamic information includes forest status and corresponding strategies; monitors and cultivates the target area based on the forest dynamic information. The present invention solves the technical problem that the survival rate of forest vegetation is low due to the single data monitoring and processing method in the prior art, and dynamically monitors the forest through remote sensing technology to achieve the technical effect of improving the survival rate of forest vegetation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0015] Figure 1 A schematic diagram of a method for dynamic monitoring of forest cultivation based on remote sensing technology provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the structure of a dynamic monitoring system for forest cultivation based on remote sensing technology provided in an embodiment of the present application.

[0017] Explanation of the accompanying drawings: real-time monitoring data acquisition unit 11, historical remote sensing data acquisition unit 12, historical time series remote sensing data acquisition unit 13, forest image acquisition unit 14, forest cultivation system construction unit 15, forest dynamic information acquisition unit 16, monitoring and cultivation guidance unit 17. DETAILED DESCRIPTION

[0018] This application provides a dynamic monitoring method and system for forest cultivation based on remote sensing technology, aiming to solve the technical problem in the prior art that the survival rate of forest vegetation is low due to the single data monitoring and processing method. By dynamically monitoring the forest through remote sensing technology, the technical effect of improving the survival rate of forest vegetation is achieved.

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] Embodiment 1:

[0022] like Figure 1 As shown, the present application provides a forest cultivation dynamic monitoring method based on remote sensing technology, the method comprising:

[0023] Step S100: determining a target area and deploying a sensor device to monitor the target area in real time and obtain real-time monitoring data;

[0024] In the embodiment of the present application, the purpose of monitoring is determined according to the needs of forest resource management, such as forest growth conditions, etc. The characteristics of the forest area are determined, including the distribution of the forest, the main tree species, the ecological environment, etc. Based on the above analysis, the target area is determined, which can reflect the ecological characteristics and management needs of the entire forest area.

[0025] According to the monitoring purpose and the characteristics of the target area, select appropriate sensor devices, including satellite remote sensors, sensors carried by drones, etc. Plan the layout of sensor devices in the target area to ensure that the target area can be fully covered.

[0026] The target area is monitored in real time according to the deployed sensor devices to obtain real-time monitoring data.

[0027] Step S200: setting a fixed period, activating a collection device based on the fixed period, and acquiring multiple groups of historical remote sensing data of forest vegetation, wherein the historical remote sensing data includes spatial details and spectral information;

[0028] In the embodiment of the present application, a suitable cycle is set according to the growth cycle of forest vegetation, seasonal changes, environmental factors and other aspects, such as data collection once a month, once a quarter or once a year.

[0029] Within a set fixed period, the acquisition device is activated to obtain multiple sets of historical remote sensing data of forest vegetation. The historical remote sensing data includes spatial details and spectral information. Spatial details reflect the distribution, shape and size of forest vegetation. Spectral information provides key information about vegetation growth, health and chlorophyll content.

[0030] Step S300: Processing the historical remote sensing data based on time series analysis to obtain historical time series remote sensing data;

[0031] In an embodiment of the present application, a time series analysis method is used to process historical remote sensing data, and through preprocessing operations such as data cleaning, filtering, and interpolation, noise and outliers are eliminated, the quality of the data is improved, and the data is standardized or normalized.

[0032] In the process of processing data, according to the characteristics and laws of time series, the trend, seasonality, periodicity and random fluctuations of the data are analyzed to determine the growth and change process of forest vegetation and the impact of different factors on it.

[0033] Finally, historical time series remote sensing data are obtained based on the time series analysis results.

[0034] Step S400: Based on the forest management system, the plurality of groups of forest vegetation are classified and identified to obtain a forest image, wherein the forest image has a type identification;

[0035] In the embodiment of the present application, the forest management system has the ability to collect, store, process and analyze data, and can integrate various forest resource information, including remote sensing data, geospatial data, ecological data, etc. Through the forest management system, forest vegetation can be efficiently monitored and managed.

[0036] Next, the forest management system was used to classify and identify multiple groups of forest vegetation using remote sensing image classification technology. Computer vision and machine learning technology were used to classify and process historical remote sensing data. During the classification process, some commonly used remote sensing image classification algorithms, such as convolutional neural networks, were used to extract feature information from the image and divide forest vegetation into different categories. For example, classification was performed based on characteristics such as species composition, structure, or ecological function of vegetation.

[0037] After classification, a forest image with species identification is obtained.

[0038] Step S500: constructing a forest cultivation system according to the forest image and the historical time series remote sensing data, wherein the forest cultivation system includes a vegetation recognition module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module;

[0039] In the embodiment of the present application, the vegetation recognition module is one of the components of the forest cultivation system. The vegetation recognition module uses computer vision and image recognition technology based on the acquired forest image to accurately classify and identify the forest vegetation in the image. By comparing images of different time periods, the change trend of vegetation is analyzed.

[0040] The vegetation growth prediction module uses historical time-series remote sensing data and combines it with vegetation growth models to predict the growth trend of forest vegetation. The vegetation growth prediction module analyzes the vegetation growth cycle, environmental factors, and historical growth data to establish an accurate prediction model to predict the growth of vegetation in the future.

[0041] The vegetation early warning module monitors and warns the health status of forest vegetation in real time. By comparing the real-time remote sensing data with historical data, the vegetation early warning module detects abnormal changes in vegetation, such as the occurrence of pests and diseases, and the increase in fire risk levels. Once an abnormal situation is found, an early warning is issued immediately.

[0042] The vegetation cultivation module is the practical part of the forest cultivation system. The vegetation cultivation module integrates and identifies the information provided by the vegetation identification, growth prediction and early warning modules, forms a comprehensive assessment of vegetation and environmental conditions, and formulates specific vegetation cultivation plans. These plans include selecting suitable tree species for planting, adjusting forest structure to improve biodiversity, and implementing pest and disease control measures.

[0043] It enables them to develop cultivation plans and select suitable tree species for planting: According to the current vegetation distribution and health status, select suitable tree species to enhance the diversity and resilience of the forest. Consider the predicted growth trend and select tree species that are adapted to future environmental conditions. And adjust the tree species and age structure of the forest according to the vegetation distribution information provided by the identification module. Improve biodiversity and enhance ecosystem stability through mixed planting and rotation strategies. And formulate and implement prevention and control measures based on the pest and disease risk information provided by the early warning module. Including biological control, chemical control and physical control methods. And continuously monitor the forest condition and record the implementation effect.

[0044] Regularly evaluate the effectiveness of the cultivation plan and make adjustments based on feedback. Use new remote sensing data and analysis results to dynamically optimize the cultivation plan.

[0045] The forest cultivation system is built through forest images and historical time series remote sensing data.

[0046] Step S600: inputting the real-time monitoring data into the forest cultivation system, and outputting forest dynamic information, wherein the forest dynamic information includes forest status and corresponding strategies;

[0047] In the embodiment of the present application, the real-time monitoring data is input into the forest cultivation system, which classifies, identifies and statistically analyzes the real-time monitoring data to extract key information about the forest status, including the health status, growth rate, distribution of pests and diseases, etc. of forest vegetation. While parsing the data, the forest cultivation system evaluates and predicts the forest status according to preset rules and strategies. According to the forest type, environmental conditions, historical data, etc., it is determined whether the current state of the forest is within the normal range and whether there are potential risks or problems.

[0048] Based on the above steps, the forest cultivation system outputs forest dynamic information.

[0049] Step S700: monitoring and providing cultivation guidance for the target area based on the forest dynamic information.

[0050] In the embodiment of the present application, targeted cultivation strategies are formulated based on forest dynamic information. These strategies include improving soil conditions, adjusting planting structure, increasing nutrient supply, implementing pest control measures, etc. Finally, monitoring and cultivation guidance are carried out according to the cultivation strategy.

[0051] Furthermore, step S200 in the method provided in the application embodiment also includes:

[0052] Set a fixed cycle based on monitoring accuracy and timeliness;

[0053] According to the fixed period, a remote sensing acquisition device is configured, and the remote sensing acquisition device is activated based on the fixed period;

[0054] Historical remote sensing data are collected for the multiple groups of forest vegetation to obtain historical remote sensing data.

[0055] In the embodiments of the present application, monitoring accuracy refers to the detail and accuracy of the information obtained from the remote sensing data, and timeliness refers to the time efficiency of obtaining information. Based on monitoring accuracy and timeliness, a fixed period is set, such as daily, weekly or monthly remote sensing data collection.

[0056] Next, the remote sensing collection device is configured according to the fixed period, that is, the remote sensing collection device is activated in each fixed period to collect data according to a predetermined plan.

[0057] After activating the remote sensing acquisition device, historical remote sensing data of multiple groups of forest vegetation are collected by determining the monitoring area, setting the acquisition parameters, starting the acquisition program, etc. Through remote sensing technology, historical remote sensing data is obtained.

[0058] Furthermore, step S300 in the method provided in the application embodiment also includes:

[0059] Performing data preprocessing on the historical remote sensing data to obtain historical processed remote sensing data, wherein the historical processed remote sensing data has a time stamp;

[0060] Overlaying the historically processed remote sensing data in time series to ensure that the historically processed remote sensing data are aligned within the multiple groups of forest vegetation;

[0061] Extracting features from the historically processed remote sensing data to obtain remote sensing data features, wherein the remote sensing data features include chlorophyll content, vegetation index, surface temperature and soil moisture;

[0062] Perform time series change analysis on the remote sensing data characteristics respectively to obtain the historical time series remote sensing data.

[0063] In the embodiment of the present application, data preprocessing is performed on the historical remote sensing data, and the influence of atmospheric scattering, absorption and other factors on the remote sensing data is eliminated through radiation calibration and atmospheric correction. Geometric correction is used to correct the geometric distortion of the remote sensing image caused by factors such as sensors and earth curvature, and remove noise in the image. Through preprocessing, historical processed remote sensing data is obtained, and the historical processed remote sensing data has a clear time mark.

[0064] Through time series overlay, the historically processed remote sensing data at different time points are aligned in time series to analyze the spatiotemporal changes of vegetation. When overlaying, ensure that the remote sensing data at different time points are consistent in geographic coordinates to facilitate spatial comparison. For multiple groups of forest vegetation areas, it is necessary to ensure that each pixel corresponds to the same geographic location at different time points to achieve accurate matching of pixels. Overlay the matched remote sensing data in chronological order to form a time series dataset.

[0065] After that, feature extraction is performed on the historical processed remote sensing data to extract specific indicators that reflect the vegetation growth status, health status, etc. Specific indicators include vegetation index, surface temperature and soil moisture.

[0066] Finally, the time series change analysis of remote sensing data features is carried out. Linear regression, sliding average and other methods are used to analyze the change trend of vegetation index, surface temperature, soil moisture and other features over time. Spectral analysis, wavelet analysis and other methods are used to identify the periodic change law of vegetation growth, health status and other features. The time series mutation detection algorithm is used to identify the time points and areas where vegetation growth conditions suddenly change. Through the above steps, historical time series remote sensing data with time stamps are obtained.

[0067] Furthermore, step S500 in the method provided in the application embodiment also includes:

[0068] The forest cultivation system is constructed according to the forest image and the historical time series remote sensing data, and the vegetation recognition module is used to perform vegetation recognition from the forest image and obtain vegetation recognition results;

[0069] The vegetation growth prediction module is constructed by the historical time series remote sensing data and the vegetation identification result, and the vegetation growth prediction situation is obtained by using the vegetation growth prediction module;

[0070] Setting a warning threshold in the vegetation warning module, wherein the warning threshold is used to determine the vegetation growth prediction situation;

[0071] When the vegetation growth prediction meets the warning threshold, obtaining a warning result;

[0072] Inputting the early warning result into the vegetation cultivation module to obtain a cultivation strategy;

[0073] The early warning results and the cultivation strategies are integrated to obtain forest dynamic information.

[0074] In the embodiment of the present application, the forest cultivation system is a comprehensive platform that integrates multiple modules such as image processing, data analysis, and model prediction.

[0075] When constructing the vegetation recognition module, the input forest image is preprocessed, including denoising, contrast enhancement and other operations to improve image quality. Using image segmentation, edge detection and other technologies, vegetation features such as color, texture, shape, etc. are extracted from the image. Based on the extracted features, machine learning or deep learning algorithms are used to identify vegetation. The recognition results include information such as vegetation type and distribution range. Through the above steps, the construction of the vegetation recognition module is completed.

[0076] When constructing the vegetation growth prediction module, the historical time series remote sensing data is combined with the vegetation identification results to form a complete data set. Based on the data set, a suitable prediction model is selected, such as a time series analysis model or a machine learning regression model for training. The vegetation growth prediction module is obtained through training.

[0077] Set warning thresholds in the vegetation warning module. Warning thresholds include the minimum limit of growth rate, abnormal changes in growth trend, etc. Compare the vegetation growth prediction results with the set warning thresholds. If the prediction results are lower than or higher than the threshold range, an early warning is triggered. When an early warning is triggered, record the early warning information, including the warning type, warning area, and warning level.

[0078] The early warning results are input into the vegetation cultivation module, and targeted vegetation cultivation strategies are formulated based on the early warning results and combined with the professional knowledge and experience of forest cultivation. These strategies include fertilization, irrigation, pest control and other measures.

[0079] Integrate early warning results and cultivation strategies to form complete forest dynamic information, which comprehensively reflects the growth status of forest vegetation, potential risks and corresponding management measures.

[0080] Furthermore, the vegetation growth prediction module is constructed by the historical time series remote sensing data and the vegetation identification result, and the vegetation growth prediction situation is obtained by using the vegetation growth prediction module. The method also includes:

[0081] Performing data preprocessing on the historical time series remote sensing data and the vegetation identification results to obtain a preprocessed data set;

[0082] Establishing the initial vegetation growth prediction module based on the neural network model;

[0083] The initial vegetation growth prediction module is supervisedly trained according to the preprocessed data set to obtain the vegetation growth prediction module.

[0084] In the embodiment of the present application, data preprocessing is performed on the historical time series remote sensing data and the vegetation identification results, and missing values, abnormal values ​​and duplicate values ​​in the historical time series remote sensing data and the vegetation identification results are checked and processed accordingly. At the same time, the data is standardized or normalized. According to the needs of vegetation growth prediction and the availability of data, appropriate features are selected. Through preprocessing, a preprocessed data set is obtained.

[0085] When establishing the initial vegetation growth prediction module, select the recurrent neural network as the model, set the number of neural network layers, the number of neurons in each layer, the activation function and other parameters, and initialize the model weights and bias items. Select a suitable loss function, such as mean square error, cross entropy, etc. to measure the difference between the model prediction and the actual value, and select an optimizer, such as gradient descent, Adam, etc. to update the model weights and bias items to minimize the loss function.

[0086] The initial vegetation growth prediction module is supervised and trained using the preprocessed dataset. The vegetation growth prediction module is obtained through training.

[0087] Furthermore, the method further comprises:

[0088] Setting a division ratio, dividing the preprocessed data set according to the division ratio, and obtaining a training data set and a training verification set;

[0089] Setting the model accuracy, training the initial vegetation growth prediction module through the training data set, and obtaining a training vegetation growth prediction module;

[0090] Verifying the training vegetation growth prediction module based on the training verification set and calculating a verification coefficient;

[0091] When the training vegetation growth prediction module function converges, determining whether the verification coefficient meets the model accuracy;

[0092] If it meets the requirements, the vegetation growth prediction module is output.

[0093] In the embodiment of the present application, the preprocessed data set is divided according to the division ratio to obtain the training data set and the training verification set. The division ratio determines the size of the training data set and the training verification set, which is set according to historical experience. For example, 70% training set and 30% verification set.

[0094] Model accuracy is an important indicator for evaluating model performance, which is measured by the model's accuracy, recall rate, F1 value, etc. Set an appropriate model accuracy threshold based on the problem requirements and the characteristics of the data. This threshold will be used to determine whether the model meets the requirements in the future. Use the training data set to train the initial vegetation growth prediction module. During the training process, the model will learn and adjust its parameters based on the input training data and the corresponding labels, that is, the vegetation growth situation, to minimize the prediction error. During the training process, regularly save the current state of the model, including the model's parameters and weights.

[0095] The validation set is used to evaluate the performance of the model on unseen data to avoid overfitting. When performing validation, the training validation set is input into the trained vegetation growth prediction module to obtain the model's prediction results. The validation coefficient is calculated based on the model's prediction results and the actual labels in the training validation set. The validation coefficient is an indicator that can reflect the performance of the model, such as accuracy, recall, and F1 value.

[0096] During the training process, monitor the convergence of the model and whether the verification coefficient meets the preset accuracy requirements. Determine whether the model has converged by observing the changes in the loss function during the training process. When the loss function value gradually stabilizes and tends to the minimum value, the model is considered to have converged. Compare the calculated verification coefficient with the set model accuracy threshold. If the verification coefficient reaches or exceeds the threshold, it means that the model performance meets the requirements; otherwise, adjust the model structure or parameters and retrain.

[0097] When the model converges and the verification coefficient meets the accuracy requirement, it means that a vegetation growth prediction module with good performance has been obtained. At this time, the vegetation growth prediction module is output.

[0098] Furthermore, step S700 in the method provided in the application embodiment also includes:

[0099] Determining vegetation cultivation goals and corresponding strategies based on the forest dynamic information;

[0100] Implementing the corresponding strategy on the target area according to the forest dynamic information;

[0101] The target area where the corresponding strategy is implemented is monitored for effectiveness, monitoring results are obtained, dynamic adjustments are made based on the monitoring results, and monitoring, cultivation and guidance are provided for the target area.

[0102] In the embodiment of the present application, vegetation cultivation goals are set based on forest dynamic information. Goals include increasing forest coverage, improving vegetation health, reducing the incidence of pests and diseases, and promoting biodiversity. According to the vegetation cultivation goals, corresponding vegetation cultivation strategies are formulated. These strategies include selecting appropriate tree species for replanting, adjusting forest structure to enhance stability, implementing pest and disease control measures, and improving soil conditions to promote vegetation growth.

[0103] After determining the vegetation cultivation goals and corresponding strategies, the next step is to implement the strategies in the target areas. First, according to the needs of implementing the strategies, prepare the corresponding resources, including tree species, fertilizers, pesticides, machinery and equipment, etc. Then, carry out replanting, pruning, fertilization, pest and disease control, etc. according to the requirements of the strategies.

[0104] After implementing the strategy, collect vegetation growth data, pest and disease occurrence and other information in the target area through regular remote sensing monitoring. Analyze the collected monitoring data, compare the changes before and after the implementation of the strategy, and evaluate the effectiveness of the strategy. According to the monitoring results and analysis conclusions, dynamically adjust the vegetation cultivation strategy. If the implementation of the strategy is effective, continue to maintain it; if the effect is not good or there are problems, it is necessary to adjust the strategy in time to better achieve the cultivation goals.

[0105] Finally, based on the dynamically adjusted strategy, the target areas are continuously monitored, cultivated and guided.

[0106] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0107] The present application determines the target area and deploys the sensing device, monitors the target area in real time, and obtains the real-time monitoring data; sets a fixed period, activates the acquisition device based on the fixed period, obtains multiple groups of historical remote sensing data of forest vegetation, and the historical remote sensing data includes spatial details and spectral information; processes the historical remote sensing data based on time series analysis to obtain historical time series remote sensing data; classifies and identifies multiple groups of forest vegetation based on the forest management system, obtains forest images, and the forest images have species identification; builds a forest cultivation system based on the forest image and the historical time series remote sensing data, and the forest cultivation system includes a vegetation identification module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; inputs the real-time monitoring data into the forest cultivation system, and outputs forest dynamic information, and the forest dynamic information includes forest status and corresponding strategies; monitors and cultivates the target area based on the forest dynamic information. The present invention solves the technical problem that the survival rate of forest vegetation is low due to the single data monitoring and processing method in the prior art, and dynamically monitors the forest through remote sensing technology to achieve the technical effect of improving the survival rate of forest vegetation.

[0108] Embodiment 2:

[0109] Based on the same inventive concept as the forest cultivation dynamic monitoring method based on remote sensing technology in the aforementioned embodiment, Figure 2 As shown, the present application provides a dynamic monitoring system for forest cultivation based on remote sensing technology. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0110] A real-time monitoring data acquisition unit 11, wherein the real-time monitoring data acquisition unit 11 determines a target area and deploys a sensor device to perform real-time monitoring on the target area and acquire real-time monitoring data;

[0111] A historical remote sensing data acquisition unit 12, wherein the historical remote sensing data acquisition unit 12 sets a fixed period, activates a collection device based on the fixed period, and acquires multiple groups of historical remote sensing data of forest vegetation, wherein the historical remote sensing data includes spatial details and spectral information;

[0112] A historical time series remote sensing data acquisition unit 13, wherein the historical time series remote sensing data acquisition unit 13 processes the historical remote sensing data based on time series analysis to acquire the historical time series remote sensing data;

[0113] A forest image acquisition unit 14, wherein the forest image acquisition unit 14 classifies and identifies the plurality of groups of forest vegetation based on a forest management system to acquire a forest image, wherein the forest image has a type identification;

[0114] A forest cultivation system building unit 15, wherein the forest cultivation system building unit 15 builds a forest cultivation system according to the forest image and the historical time series remote sensing data, and the forest cultivation system includes a vegetation recognition module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module;

[0115] A forest dynamic information acquisition unit 16, wherein the forest dynamic information acquisition unit 16 inputs the real-time monitoring data into the forest cultivation system and outputs forest dynamic information, wherein the forest dynamic information includes forest status and corresponding strategies;

[0116] A monitoring, cultivation and guidance unit 17 is configured to monitor, cultivate and guide the target area based on the forest dynamic information.

[0117] Furthermore, the system also includes:

[0118] Set a fixed cycle based on monitoring accuracy and timeliness;

[0119] According to the fixed period, a remote sensing acquisition device is configured, and the remote sensing acquisition device is activated based on the fixed period;

[0120] Historical remote sensing data are collected for the multiple groups of forest vegetation to obtain historical remote sensing data.

[0121] Furthermore, the system also includes:

[0122] Performing data preprocessing on the historical remote sensing data to obtain historical processed remote sensing data, wherein the historical processed remote sensing data has a time stamp;

[0123] Overlaying the historically processed remote sensing data in time series to ensure that the historically processed remote sensing data are aligned within the multiple groups of forest vegetation;

[0124] Extracting features from the historically processed remote sensing data to obtain remote sensing data features, wherein the remote sensing data features include vegetation index, surface temperature, and soil moisture;

[0125] Perform time series change analysis on the remote sensing data characteristics respectively to obtain the historical time series remote sensing data.

[0126] Furthermore, the system also includes:

[0127] The forest cultivation system is constructed according to the forest image and the historical time series remote sensing data, and the vegetation recognition module is used to perform vegetation recognition from the forest image and obtain vegetation recognition results;

[0128] The vegetation growth prediction module is constructed by the historical time series remote sensing data and the vegetation identification result, and the vegetation growth prediction situation is obtained by using the vegetation growth prediction module;

[0129] Setting a warning threshold in the vegetation warning module, wherein the warning threshold is used to determine the vegetation growth prediction situation;

[0130] When the vegetation growth prediction meets the warning threshold, obtaining a warning result;

[0131] Inputting the early warning result into the vegetation cultivation module to obtain a cultivation strategy;

[0132] The early warning results and the cultivation strategies are integrated to obtain forest dynamic information.

[0133] Furthermore, the system also includes:

[0134] Performing data preprocessing on the historical time series remote sensing data and the vegetation identification results to obtain a preprocessed data set;

[0135] Establishing the initial vegetation growth prediction module based on the neural network model;

[0136] The initial vegetation growth prediction module is supervisedly trained according to the preprocessed data set to obtain the vegetation growth prediction module.

[0137] Furthermore, the system also includes:

[0138] Setting a division ratio, dividing the preprocessed data set according to the division ratio, and obtaining a training data set and a training verification set;

[0139] Setting the model accuracy, training the initial vegetation growth prediction module through the training data set, and obtaining a training vegetation growth prediction module;

[0140] Verifying the training vegetation growth prediction module based on the training verification set and calculating a verification coefficient;

[0141] When the training vegetation growth prediction module function converges, determining whether the verification coefficient meets the model accuracy;

[0142] If it meets the requirements, the vegetation growth prediction module is output.

[0143] Furthermore, the system also includes:

[0144] Determining vegetation cultivation goals and corresponding strategies based on the forest dynamic information;

[0145] Implementing the corresponding strategy on the target area according to the forest dynamic information;

[0146] The target area where the corresponding strategy is implemented is monitored for effectiveness, monitoring results are obtained, dynamic adjustments are made based on the monitoring results, and monitoring, cultivation and guidance are provided for the target area.

[0147] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0148] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0149] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A dynamic monitoring method for forest cultivation based on remote sensing technology, characterized in that: The method comprises: Determine the target area and deploy sensor devices to monitor the target area in real time and obtain real-time monitoring data; Setting a fixed period, activating a collection device based on the fixed period, and acquiring multiple sets of historical remote sensing data of forest vegetation, wherein the historical remote sensing data includes spatial details and spectral information; Processing the historical remote sensing data based on time series analysis to obtain historical time series remote sensing data; Based on the forest management system, the plurality of groups of forest vegetation are classified and identified to obtain a forest image, wherein the forest image has a species identification; Building a forest cultivation system according to the forest image and the historical time series remote sensing data, wherein the forest cultivation system includes a vegetation recognition module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; Inputting the real-time monitoring data into the forest cultivation system and outputting forest dynamic information, wherein the forest dynamic information includes forest status and corresponding strategies; Conducting monitoring and cultivation guidance on the target area based on the forest dynamic information; Wherein: a forest cultivation system is built according to the forest image and the historical time series remote sensing data, the forest cultivation system includes a vegetation recognition module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module, and the method includes: The forest cultivation system is constructed according to the forest image and the historical time series remote sensing data, and the vegetation recognition module is used to perform vegetation recognition from the forest image and obtain vegetation recognition results; The vegetation growth prediction module is constructed by the historical time series remote sensing data and the vegetation identification result, and the vegetation growth prediction situation is obtained by using the vegetation growth prediction module; Setting a warning threshold in the vegetation warning module, wherein the warning threshold is used to determine the vegetation growth prediction situation; When the vegetation growth prediction meets the warning threshold, obtaining a warning result; Inputting the early warning result into the vegetation cultivation module to obtain a cultivation strategy; Integrate the early warning results and the cultivation strategy to obtain forest dynamic information; Wherein: the vegetation growth prediction module is constructed by the historical time series remote sensing data and the vegetation identification result, and the vegetation growth prediction situation is obtained by using the vegetation growth prediction module, and the method includes: Performing data preprocessing on the historical time series remote sensing data and the vegetation identification results to obtain a preprocessed data set; Establishing the initial vegetation growth prediction module based on the neural network model; The initial vegetation growth prediction module is supervisedly trained according to the preprocessed data set to obtain the vegetation growth prediction module.

2. The method according to claim 1, characterized in that A fixed period is set, and a collection device is activated based on the fixed period to obtain historical remote sensing data of the target area, wherein the historical remote sensing data includes spatial details and spectral information. The method includes: Set a fixed cycle based on monitoring accuracy and timeliness; According to the fixed period, a remote sensing acquisition device is configured, and the remote sensing acquisition device is activated based on the fixed period; Historical remote sensing data are collected for the multiple groups of forest vegetation to obtain historical remote sensing data.

3. The method according to claim 1, characterized in that The historical remote sensing data is processed based on time series analysis to obtain historical time series remote sensing data, the method comprising: Performing data preprocessing on the historical remote sensing data to obtain historical processed remote sensing data, wherein the historical processed remote sensing data has a time stamp; Overlaying the historically processed remote sensing data in time series to ensure that the historically processed remote sensing data are aligned within the multiple groups of forest vegetation; Extracting features from the historically processed remote sensing data to obtain remote sensing data features, wherein the remote sensing data features include vegetation index, surface temperature, and soil moisture; Perform time series change analysis on the remote sensing data characteristics respectively to obtain the historical time series remote sensing data.

4. The method according to claim 1, characterized in that Methods include: Setting a division ratio, dividing the preprocessed data set according to the division ratio, and obtaining a training data set and a training verification set; Setting the model accuracy, training the initial vegetation growth prediction module through the training data set, and obtaining a training vegetation growth prediction module; Verifying the training vegetation growth prediction module based on the training verification set and calculating a verification coefficient; When the training vegetation growth prediction module function converges, determining whether the verification coefficient meets the model accuracy; If it is in compliance, the vegetation growth prediction module is output.

5. The method according to claim 1, characterized in that Based on the forest dynamic information, the target area is monitored and cultivated, and the method includes: Determining vegetation cultivation goals and corresponding strategies based on the forest dynamic information; Implementing the corresponding strategy on the target area according to the forest dynamic information; The target area where the corresponding strategy is implemented is monitored for effectiveness, monitoring results are obtained, dynamic adjustments are made based on the monitoring results, and monitoring, cultivation and guidance are provided for the target area.

6. A dynamic monitoring system for forest cultivation based on remote sensing technology, characterized in that: The system is used to execute the method according to any one of claims 1 to 5, characterized in that the system comprises: A real-time monitoring data acquisition unit, which determines a target area and deploys a sensor device to perform real-time monitoring on the target area and acquire real-time monitoring data; A historical remote sensing data acquisition unit, wherein the historical remote sensing data acquisition unit is set to a fixed period, and based on the fixed period, a collection device is activated to acquire multiple groups of historical remote sensing data of forest vegetation, wherein the historical remote sensing data includes spatial details and spectral information; A historical time series remote sensing data acquisition unit, which processes the historical remote sensing data based on time series analysis to acquire the historical time series remote sensing data; A forest image acquisition unit, wherein the forest image acquisition unit classifies and identifies the plurality of groups of forest vegetation based on a forest management system to acquire a forest image, wherein the forest image has a type identification; A forest cultivation system building unit, wherein the forest cultivation system building unit builds a forest cultivation system according to the forest image and the historical time series remote sensing data, wherein the forest cultivation system includes a vegetation recognition module, a vegetation growth prediction module, a vegetation early warning module and a vegetation cultivation module; A forest dynamic information acquisition unit, which inputs the real-time monitoring data into the forest cultivation system and outputs forest dynamic information, wherein the forest dynamic information includes forest status and corresponding strategies; A monitoring, cultivation and guidance unit is provided, wherein the monitoring, cultivation and guidance unit performs monitoring, cultivation and guidance on the target area based on the forest dynamic information.