A biological control system for bamboo expansion using big data statistics
Through big data statistics and deep learning models, combined with satellite remote sensing technology to monitor the expansion of mosaic bamboo, the negative impact of the rapid expansion of mosaic bamboo on the forest ecosystem is solved, accurate monitoring and prediction of mosaic bamboo expansion is achieved, and effective biological prevention and control measures are provided. .
Patent Information
- Application Number
- CN202210052303.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-18
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-01-18
AI Technical Summary
The existing bio-control technology for expanding bamboo forests has not yet effectively solved the negative impact of rapid expansion of bamboo on forest ecosystems, especially the reduction of secondary evergreen broad-leaved forest community composition and species diversity.
The expansion biological control system of Momoji bamboo with big data statistics is adopted, combined with satellite remote sensing technology and field measurement, by monitoring the growth of momoji bamboo and adjacent vegetation, an expansion model based on deep learning is established, the expansion of momoji bamboo is predicted and the response strategy is proposed.
Accurate monitoring and prediction of the expansion of mosaic bamboo is achieved, effective biological prevention and control measures are provided, and the negative impact on the forest ecosystem is reduced. The system's modular design is convenient for technological updates and optimization.
Smart Images

Figure CN114419459B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of biological control technology, and in particular to a biological control system for bamboo expansion using big data statistics. Background Art
[0002] Moso bamboo is the bamboo species with the longest cultivation history, the largest area and the most important economic value in my country. Moso bamboo can be used in many fields such as construction, industrial production, handicraft production, and the food industry. Its economic value is significant. Therefore, my country has many large artificial or natural bamboo forests for bamboo farming. However, due to the rapid growth and expansion of moso bamboo, if the forest land it occupies is allowed to expand outward without restriction, it will lead to the simplification of the composition and structure of the secondary evergreen broad-leaved forest community, the decline of species diversity, and a negative impact on the function of the forest ecosystem. Therefore, it is necessary to propose relevant biological control plans to deal with the problem of the wanton expansion of moso bamboo.
[0003] According to the related published technical solutions, the technical solution with the publication number CN112544351 (A) proposes a method of using a sesame extract to irrigate bamboo seedlings to effectively reduce the photosynthesis efficiency of bamboo, thereby regulating the growth rate of bamboo; the technical solution with the publication number CN112712087 (A) provides a portable sampling device for plant invasion ecology research, which effectively improves the research efficiency of invasive plants; the technical solution with the publication number CN112307992 (A) proposes a method for automatic identification of mangrove plants using drones, which effectively monitors and measures the growth of mangrove forests. The above technical solutions have certain guiding significance for the expansion of bamboo forests and biological control, but the technical effects in related fields need to be further improved. Summary of the invention
[0004] The purpose of the present invention is to use the sample big data collected on-site in bamboo forests, combined with the geographic information system, to measure the speed and direction of bamboo expansion, calculate and provide corresponding prevention and control countermeasures for relevant personnel to take practical measures.
[0005] The present invention adopts the following technical solution:
[0006] A biological control system for bamboo expansion using big data statistics, the control system comprising a first vegetation monitoring module, a second vegetation monitoring module, a third monitoring module, a geographic registration module, a calculation module and a control module;
[0007] The first vegetation monitoring module is used to monitor the growth of target vegetation;
[0008] The second vegetation monitoring module is used to monitor the growth of non-target vegetation adjacent to the target vegetation;
[0009] The third monitoring module includes a plurality of sensors for monitoring a plurality of environmental data;
[0010] The geo-registration module is used to match the position coordinates of the measurement data based on multiple time series with the time series;
[0011] The calculation module establishes an expansion model based on the obtained multiple environmental data;
[0012] The control module is communicatively connected to the first vegetation monitoring module, the second vegetation monitoring module, the third monitoring module, the geo-referencing module and the computing module to perform overall control of the prevention and control system;
[0013] The first vegetation monitoring module and the second vegetation monitoring module include:
[0014] Use satellite remote sensing technology to detect vegetation in near-infrared and infrared bands;
[0015] By measuring the vegetation environment on site, the input data of the calculation module, the registration algorithm of the geo-registration module, and the spectral band used by the satellite remote sensing technology are corrected;
[0016] The satellite remote sensing technology includes using a combination of near-infrared band TM432 and band SPOT5 to calculate multiple grayscale values within the observation range, thereby distinguishing target vegetation from non-target vegetation;
[0017] Divide the observation range into grids, calculate the area ratio of target vegetation to non-target vegetation in each grid, and set the grid whose area ratio meets the specified value as the focus grid;
[0018] Furthermore, the monitoring frequency of the concerned grid is increased, and the change and the change rate of the area ratio of the target vegetation to the non-target vegetation in each statistical period are calculated;
[0019] Adding the third monitoring module to the target grid to obtain multiple environmental data of the target grid in multiple time series;
[0020] The monitoring data of the first vegetation monitoring module and the second vegetation monitoring module based on time series are input into the calculation module to calculate the change in occupancy rate of the target vegetation; further, a plurality of monitoring data of the third monitoring module are input into the calculation module to establish an expansion model of the target vegetation based on time series;
[0021] The calculation module establishes the expansion model based on a convolutional neural network of deep learning; the calculation module includes using linear stretching to normalize the monitoring data of the third monitoring module.
[0022] The beneficial effects achieved by the present invention are:
[0023] 1. The prevention and control system of the present invention uses remote sensing technology combined with field measurement to determine the difference between the observation data of the remote sensing technology and the actual data, thereby correcting the observation data of the automatic monitoring module;
[0024] 2. The control system of the present invention includes monitoring the changes in bamboo vegetation and adjacent vegetation, determining the changes in bamboo and other plant vegetation, and non-vegetation areas, thereby determining the expansion of bamboo, or the transformation of vegetation into non-vegetation;
[0025] 3. The prevention and control system of the present invention includes combining environmental data of the concerned area, establishing a mathematical model of bamboo expansion, predicting the further expansion of bamboo, and making response strategies in advance;
[0026] 4. The software and hardware layout requirements of the present invention are based on modular design, which can be easily switched and upgraded during the technology update and modification stage, which is conducive to the optimization and upgrading of future technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.
[0028] Figure 1 Schematic diagram of the composition of the prevention and control system;
[0029] Figure 2 This is a schematic diagram of the expansion process of bamboo;
[0030] Figure 3 It is a schematic diagram of the reflectance values of bamboo and other plants in multiple spectral bands;
[0031] Figure 4 is a schematic diagram of the remote sensing observation image;
[0032] Figure 5 is a schematic diagram of the ratio of the target vegetation to the non-target vegetation;
[0033] Explanation of the accompanying figure numbers: 101 - first vegetation monitoring module; 102 - second vegetation monitoring module; 103 - third monitoring module; 104 - geo-registration module; 105 - calculation module; 106 - control module; 201 - bamboo; 202 - other plants; 203 - bamboo underground stems. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. For those skilled in the art, other systems, methods and / or features of the present embodiment will become apparent after reviewing the following detailed description. It is intended that all such additional systems, methods, features and advantages are included within the scope of this specification and the present invention, and are protected by the appended claims. Additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.
[0035] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation. It is constructed and operated in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as a limitation on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0036] Embodiment 1:
[0037] As attached Figure 1 , a biological control system for bamboo expansion using big data statistics, the control system comprising a first vegetation monitoring module, a second vegetation monitoring module, a third monitoring module, a geographic registration module, a calculation module and a control module;
[0038] The first vegetation monitoring module is used to monitor the growth of target vegetation;
[0039] The second vegetation monitoring module is used to monitor the growth of non-target vegetation adjacent to the target vegetation;
[0040] The third monitoring module includes a plurality of sensors for monitoring a plurality of environmental data;
[0041] The geo-registration module is used to match the position coordinates of the measurement data based on multiple time series with the time series;
[0042] The calculation module establishes an expansion model based on the obtained multiple environmental data;
[0043] The control module is communicatively connected to the first vegetation monitoring module, the second vegetation monitoring module, the third monitoring module, the geo-referencing module and the computing module to perform overall control of the prevention and control system;
[0044] The first vegetation monitoring module and the second vegetation monitoring module include:
[0045] Use satellite remote sensing technology to detect vegetation in near-infrared and infrared bands;
[0046] By measuring the vegetation environment on site, the input data of the calculation module, the registration algorithm of the geo-registration module, and the spectral band used by the satellite remote sensing technology are corrected;
[0047] The satellite remote sensing technology includes using a combination of near-infrared band TM432 and band SPOT5 to calculate multiple grayscale values within the observation range, thereby distinguishing target vegetation from non-target vegetation;
[0048] Divide the observation range into grids, calculate the area ratio of target vegetation to non-target vegetation in each grid, and set the grid whose area ratio meets the specified value as the focus grid;
[0049] Furthermore, the monitoring frequency of the concerned grid is increased, and the change and the change rate of the area ratio of the target vegetation to the non-target vegetation in each statistical period are calculated;
[0050] Adding the third monitoring module to the target grid to obtain multiple environmental data of the target grid in multiple time series;
[0051] The monitoring data of the first vegetation monitoring module and the second vegetation monitoring module based on time series are input into the calculation module to calculate the change in occupancy rate of the target vegetation; further, a plurality of monitoring data of the third monitoring module are input into the calculation module to establish an expansion model of the target vegetation based on time series;
[0052] The calculation module establishes the expansion model based on a convolutional neural network of deep learning; the calculation module includes using linear stretching to normalize the monitoring data of the third monitoring module;
[0053] In this embodiment, the first vegetation monitoring module is for bamboo vegetation; the second vegetation monitoring module is for other plant vegetation, including common vegetation types such as evergreen broad-leaved forest, coniferous forest, and mixed coniferous and broad-leaved forest;
[0054] Further, as attached Figure 2 The expansion of bamboo forests to neighboring areas can be divided into four stages, including:
[0055] Figure 2a, underground infiltration stage: the underground stems (bamboo whips) and culms of moso bamboo grow horizontally, infiltrating underground from the edge of the bamboo vegetation to the adjacent ecosystem, but the whips are young or the resource conditions are insufficient, so no new bamboo is produced. After flowering and fruiting, the seeds spread to the adjacent ecosystem, but have not yet germinated or formed new bamboo;
[0056] Figure 2 b, above-ground bamboo stage: a small number of young bamboo stalks or seeds grow from the bamboo rhizomes that penetrate underground and begin to grow into seedlings, but they have little impact on the composition of adjacent vegetation;
[0057] Figure 2 c. Competition exclusion stage: the number of bamboos increases or the individual bamboos grow slowly. At this time, the number of plants that die in the invaded adjacent vegetation increases and gradually withdraws from the mixed community. Bamboos gain an advantage in the canopy, understory or shrub layer of the community.
[0058] Figure 2 d. Dominance maintenance stage: Moso bamboo becomes the dominant population in the invaded ecosystem and continues to hinder the renewal of other plant species through various competition methods, inhibiting community succession until it blooms, bears fruit and dies. Even after flowering, some bamboo seeds will quickly germinate and grow into new bamboos, continuing to maintain its dominant position;
[0059] In each of the above stages, bamboo vegetation and adjacent vegetation have different occupancy rates in a specified area; by calculating the occupancy rate of the target vegetation and the non-target vegetation, the expansion stage of bamboo vegetation can be judged from a macroscopic perspective and discovered in time;
[0060] Furthermore, the traditional method of observing the proportion of bamboo vegetation based on human observation from the ground is inefficient and tends to ignore the overall statistical situation. Satellite remote sensing technology can sense the expansion of bamboo vegetation from a large area. Remote sensing technology is a technology that uses satellites to conduct long-distance and large-scale observations. High-altitude satellites sense various types of vegetation on the ground in multiple optical spectrum bands. Figure 3 , among which the reflectivity of bamboo in the near-infrared band TM432 and the band SPOT5 is significantly higher than that of other vegetation. Therefore, in the band combination observation image based on the two near-infrared bands, bamboo vegetation can be easily distinguished from other plant vegetation;
[0061] As attached Figure 4 The remote sensing image schematic diagram shown in the figure shows the reflection of light by an object, which is also called the spectral feature of the object. As intuitive information that is easy to obtain in an image, spectral features are of great significance in image classification. By analyzing the spectral features of multiple pixels in the observed image, we can further understand the types of objects existing in the geographical location corresponding to the pixels, thereby distinguishing objects on the ground. By conducting remote sensing observations on a large area of the ground, we can further understand the distribution of objects on the ground in that area.
[0062] Furthermore, several common spectral features can be measured as important judgment bases, including: the mean proportion of each band; the mean light intensity of a specific band; the standard deviation of a specific band; the spectral proportion of multiple bands; the calculation of spectral features can be determined by evaluating the grayscale value of the image; for example, the reflectivity of bamboo vegetation in a certain observation area is higher for the above-mentioned near-infrared band TM432, and lower for other bands such as TM543; the reflectivity of the two bands in the observation area can be measured to determine the distribution probability, distribution position and occupied area of bamboo vegetation in the observation area; the following formula is used to calculate the reflectivity of the near-infrared band and the infrared band, and calculate the normalized vegetation index of bamboo vegetation, that is, the target vegetation:
[0063]
[0064] Wherein, B4 is the reflectivity of the target vegetation in the near-infrared band, and B3 is the reflectivity of the target vegetation in the infrared band; by calculation according to formula 1-1, when the vegetation index O exceeds a preset threshold, the area can be defined as being occupied by the target vegetation;
[0065] Furthermore, the area ratio of target vegetation and non-target vegetation is calculated; Figure 5 Schematic diagram, within a specified range, the area proportion of the target vegetation is counted β b , the area proportion of the non-target vegetation is β p , calculate the target vegetation proportion index N as:
[0066] N=β b -β p , Formula 1-2;
[0067] Furthermore, for the study of the expansion of the target vegetation, more attention can be paid to the boundary between the target vegetation and the non-target vegetation. Therefore, within a specified range, when the proportion index N is between -0.4≤N≤0.4, it indicates that the area is the boundary between the target vegetation and the non-target vegetation, and the target vegetation has the possibility and tendency to continue to expand.
[0068] Furthermore, dividing the remote sensing observation image into multiple networks for observation is more conducive to the refined calculation of the expansion degree of the target vegetation in the specified area; optionally, the network division is performed according to the actual length, for example, according to the standard that the network side length is 5 meters, the observation image is divided into multiple 5m*5m grids, and the grids are numbered;
[0069] Further, the proportion index N in the grid is calculated, and the grids with -0.4≤N≤0.4 are set as focus grids, and the focus grids are numbered Gr1, Gr2, ... Gr n ;
[0070] Further, the third monitoring module is arranged in the actual area where the concerned grid is located;
[0071] The third monitoring module includes sensors for monitoring data of multiple meteorological factors, such as a temperature sensor, a humidity sensor, a wind force sensor, a wind direction sensor, a rainfall sensor, and a sunshine sensor;
[0072] Furthermore, the third monitoring module also includes an automated or manually operated soil measuring instrument for monitoring the composition of the soil where the vegetation is located;
[0073] Furthermore, the third monitoring module also includes a plurality of geographical parameters of the area where the vegetation is located, such as longitude and latitude, and altitude;
[0074] Through the third monitoring module, a plurality of monitoring data are measured to generate a third data set of the third monitoring module, that is, M = (a, b, c...z), wherein a, b, c...z are the plurality of monitoring data acquired by the third monitoring module;
[0075] For a said grid Gr j Based on the time series, the third data set includes data at multiple moments, thereby obtaining a third data matrix M T ,Right now:
[0076]
[0077] Furthermore, the change rate d of the proportion index can be understood through the recorded values of the proportion index at multiple times. N ,Right now:
[0078]
[0079] Therefore, the change rate of the proportion index d can be further studied N The relationship between the data set M and the third data set M is established, and the expansion model is established;
[0080] Based on the change rate d of the same time series T N The collection of NT With the third data matrix M TAs the original data set L, input into the calculation module for training and establishing a mathematical model; the multiple monitoring data of the third data set are used as multiple feature vectors, each feature vector is based on multiple monitoring values of the time series, which are the feature values of the feature vector;
[0081] The computing module is a computing system using a convolutional neural network; the original data set L is divided into a training set and a validation set; wherein the training set is 80% of the original data set L, and the validation set is 20% of the original data set L;
[0082] Furthermore, the gradient descent algorithm in the linear regression algorithm can be used to obtain the change rate d N With the third data matrix M T The model function, that is, the expansion model y dn :
[0083] y dn =f(M)=f(ωM T +h), formula 1-2;
[0084] In formula 1-2, ω is the third data matrix M T is the set of weight values of multiple monitoring data, and h is the bias of the model;
[0085] Furthermore, the third data matrix M of each of the focus grids T In response to the differences in actual conditions, the differences in objective conditions are crucial to the growth of bamboo. Therefore, by obtaining multiple expansion models y of multiple grids of interest dn , using a weekly or biweekly time period to monitor whether there is a situation in which bamboo accelerates its invasion of other vegetation in the areas of multiple focus grids, so as to arrange different response strategies.
[0086] Embodiment 2:
[0087] This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;
[0088] Furthermore, since the third data matrix M TThere are multiple types of data in it, some of which are fixed values, such as altitude, longitude and latitude, etc.; some data have small discrete values, such as various soil components; some data have large discrete values, such as air pressure, temperature, humidity, etc.; different evaluation monitoring data have different dimensions and dimensional units, which will affect the results of data analysis, and commonly make the neural network spend a lot of time when performing gradient descent optimization; in order to eliminate the dimensional influence between indicators, data normalization processing is required to solve the comparability between data indicators; among them, for the data type of this embodiment, the following formula 2-1 can be used to normalize the linear stretching of the data, and the third data matrix M T Preprocess the data;
[0089]
[0090] Where x is the feature vector to be normalized; x min is the minimum value of the feature vector x in the data set; x max is the maximum value of the eigenvector x in the data set; x′ is the normalized eigenvalue;
[0091] For example, one of the monitoring data a is represented as the monitored temperature data, and the set of a records multiple temperature values a1, a2, ... a n ; Perform linear stretch normalization on a:
[0092]
[0093] The same method is used to normalize other eigenvectors, which is conducive to the standardization of the original data. All indicators are at the same order of magnitude, which is suitable for comprehensive comparative evaluation and makes the iterative process of the gradient descent algorithm smoother.
[0094] Embodiment three:
[0095] This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;
[0096] This embodiment includes: according to the target field investigation situation, the expansion model y dn Further optimization of the original data set;
[0097] In some cases, the area where the grid of interest is located is different from other areas. For example, some areas where the grid of interest is located have pests and diseases, or there is human influence, which makes the area proportion of the target vegetation β b The area ratio of non-target vegetation is β pIf the vegetation is continuously decreasing, there may be vegetation destruction. When conducting statistics for this area, this area can be excluded or set as an area to be investigated.
[0098] Furthermore, the feature vectors of the third data set are added to the area of interest to correct the influence of more special factors; for example, there is mixed vegetation of various plants in the area of interest, and the various plants compete and depend on each other for survival, making the regional situation complicated; therefore, the plant species existing in the area of interest are added to the third data set, and the weights and bias values of each feature vector of the third data set are optimized according to the growth characteristics of the plant species.
[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0100] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the present invention. That is, the methods, systems and devices discussed above are examples. Various configurations may appropriately omit, replace or add various processes or components. For example, in alternative configurations, the method may be performed in an order different from the order described, and / or various components may be added, omitted and / or combined. Moreover, the features described with respect to certain configurations may be combined in various other configurations, such as different aspects and elements of the configurations may be combined in a similar manner. In addition, the elements therein may be updated as the technology develops, i.e., many elements are examples and do not limit the scope of the present disclosure or claims.
[0101] Specific details are given in the specification to provide a thorough understanding of the exemplary configurations including implementations. However, the configurations may be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary details to avoid obscuring the configurations. This description provides only example configurations and does not limit the scope, applicability, or configurations of the claims. On the contrary, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made to the functions and arrangements of the elements without departing from the spirit or scope of the present disclosure.
[0102] In summary, it is intended that the above detailed description is considered to be illustrative rather than restrictive, and it should be understood that the above embodiments should be understood to be only used to illustrate the present invention and not to limit the scope of protection of the present invention. After reading the contents of the present invention, the technician can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.
Claims
1. A biological control system for bamboo expansion using big data statistics, characterized in that: The control system includes a first vegetation monitoring module, a second vegetation monitoring module, a third monitoring module, a geo-reference module, a calculation module and a control module; The first vegetation monitoring module is used to monitor the growth of target vegetation; The second vegetation monitoring module is used to monitor the growth of non-target vegetation adjacent to the target vegetation; The third monitoring module includes a plurality of sensors for monitoring a plurality of environmental data; The geo-registration module is used to match the position coordinates of the measurement data based on multiple time series with the time series; The calculation module establishes an expansion model based on the obtained multiple environmental data; The control module is communicatively connected to the first vegetation monitoring module, the second vegetation monitoring module, the third monitoring module, the geo-referencing module and the computing module to perform overall control of the prevention and control system; The first vegetation monitoring module and the second vegetation monitoring module include: Use satellite remote sensing technology to detect vegetation in near-infrared and infrared bands; By measuring the vegetation environment on site, the input data of the calculation module, the registration algorithm of the geo-registration module, and the spectral band used by the satellite remote sensing technology are corrected; Divide the observation range into grids, calculate the area ratio of target vegetation and non-target vegetation in each grid, and set the grid whose area ratio meets the specified value as the focus grid; Increasing the monitoring frequency of the concerned grid, and calculating the change and change rate of the area ratio of the target vegetation to the non-target vegetation in each statistical period; Adding the third monitoring module to the concerned grid to obtain multiple environmental data of the concerned grid in multiple time series; Inputting the monitoring data of the first vegetation monitoring module and the second vegetation monitoring module based on time series into the calculation module to calculate the change in occupancy rate of the target vegetation; inputting multiple monitoring data of the third monitoring module into the calculation module to establish an expansion model of the target vegetation based on time series; The calculation module establishes the expansion model based on a convolutional neural network of deep learning; the calculation module includes using linear stretching to normalize the monitoring data of the third monitoring module; Through the third monitoring module, a plurality of monitoring data are measured to generate a third data set of the third monitoring module, namely: ,in A plurality of monitoring data acquired by the third monitoring module; For a said attention grid Based on the time series, the third data set includes data at multiple moments, thereby obtaining a third data matrix M T ,Right now: ; By recording the values of multiple proportion indexes at multiple times, the change rate d of the proportion index is understood N ,Right now: ; Study the change rate of the proportion index d N The relationship between the data set M and the third data set M is established, and the expansion model is established; The gradient descent algorithm in the linear regression algorithm is used to obtain the change rate d N With the third data matrix M T The model function, that is, the expansion model : ; ω is the third data matrix M T is the set of weight values of multiple monitoring data, and h is the bias of the model.
2. According to claim 1, a biological control system for bamboo expansion using big data statistics is characterized in that: The satellite remote sensing technology includes using a combination of near-infrared band TM432 and band SPOT5 to calculate multiple grayscale values within the observation range, thereby distinguishing target vegetation from non-target vegetation.
Citation Information
Patent Citations
Mangrove plant automatic identification method based on unmanned aerial vehicle visible light remote sensing
CN112307992A
Moso bamboo seedling growth regulation and control method
CN112544351A
Remote sensing image ground object semantic segmentation method based on deep convolutional neural network
CN112712087A
Intelligent bamboo fertilization system
CN103942649A
Moso bamboo forest distribution recognition method, device and equipment and storage medium
CN113723254A
