Method and device for generating a report on urban construction based on remote sensing satellite resource scheduling

Abstract

This disclosure presents a method and apparatus for generating urban construction reports based on remote sensing satellite resource scheduling. One specific implementation of the method includes: determining a satellite observation transmission resource scheduling route set; transmitting and identifying a set of remote sensing images of tidal flat wetlands to obtain a wetland edge identification image set; determining target monitoring area information and identifying the target monitoring area information to obtain Spartina alterniflora identification and monitoring information; performing cascaded soil quality prediction on the wetland image set and the target tidal flat wetland remote sensing image set to obtain multi-source cascaded soil quality prediction distribution information; performing soil quality prediction on the historical Spartina alterniflora invasion soil quality information sequence and the multi-source cascaded soil quality prediction distribution information to obtain predicted invasion soil quality distribution information; generating an urban construction report; and controlling Spartina alterniflora control equipment to perform area clearing. This implementation can improve the quality of urban construction reports, reduce equipment wear and tear, and improve control efficiency.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and specifically to a method and apparatus for generating urban construction reports based on remote sensing satellite resource scheduling. Background Technology

[0002] Spartina alterniflora is a typical invasive alien plant. Statistics show that my country has cumulatively eradicated over 73,000 hectares of Spartina alterniflora. However, due to its strong reproductive capacity and ecological adaptability, the resurgence rate of Spartina alterniflora has been found to be as high as 8% in some areas (e.g., Ningde, Fujian). Therefore, it is necessary to establish an effective identification system for Spartina alterniflora resurgence based on remote sensing satellites to reduce its damage to coastal soils and improve the effectiveness of urban construction. The typical method for generating urban construction reports based on Spartina alterniflora resurgence identification is as follows: Remote sensing images of tidal flat wetlands are transmitted via direct satellite-to-ground transmission to obtain the target tidal flat wetland remote sensing image set. Then, Spartina alterniflora areas are identified within the target tidal flat wetland remote sensing image set to obtain the target monitoring area. Next, soil quality testing is performed on the target tidal flat wetland remote sensing image set corresponding to the target monitoring area to obtain soil distribution information. Finally, based on the soil distribution information, an urban construction report is generated, and based on the urban construction report, Spartina alterniflora control equipment is controlled to perform area removal treatment.

[0003] However, in practice, it has been found that when using the above method to generate urban construction reports based on the identification of Spartina alterniflora re-emergence, the following technical problems often exist: the direct satellite-to-ground transmission mode temporarily stores the data in the onboard memory and cannot filter it in real time. It only transmits the data after the satellite passes through the deployed ground receiving stations, resulting in low transmission timeliness and efficiency, as well as transmission blind spots, which prolongs data transmission latency and wastes satellite resources. Furthermore, soil quality detection is only performed using a single remote sensing image of the tidal flat wetland. The complex terrain of the wetlands where Spartina alterniflora grows leads to low detection accuracy, reduces the quality of urban construction reports, increases the wear and tear rate of Spartina alterniflora control equipment during operation, and reduces the efficiency of removal.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the present disclosure concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure propose a method and apparatus for generating urban construction reports based on remote sensing satellite resource scheduling, in order to solve one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a method for generating urban construction reports based on remote sensing satellite resource scheduling, comprising: determining a satellite observation transmission resource scheduling route set for transmitting a set of remote sensing images of tidal flat wetlands collected for a tidal flat wetland area via satellite internet; transmitting the remote sensing images of the tidal flat wetlands according to the satellite observation transmission resource scheduling route set to obtain a target tidal flat wetland remote sensing image set; performing wetland edge identification on the target tidal flat wetland remote sensing image set to obtain a wetland edge identification image set, wherein the wetland edge identification image set includes a set of wetland water area edge marking lines; determining a monitoring and identification area for Spartina alterniflora from the wetland edge identification image set according to a preset buffer radius and the set of wetland water area edge marking lines; and determining a monitoring and identification area for Spartina alterniflora from the monitoring and identification area for Spartina alterniflora according to historical monitoring results of Spartina alterniflora. The process involves identifying target monitoring areas and performing Spartina alterniflora identification on these areas to obtain Spartina alterniflora identification and monitoring information. A cascaded soil quality prediction is then performed on the wetland image set of the target monitoring areas captured by UAVs and the corresponding remote sensing image set of the target tidal flat wetlands to obtain multi-source cascaded soil quality prediction distribution information. Soil quality prediction is then performed on the historical Spartina alterniflora invasion soil quality information sequence and the multi-source cascaded soil quality prediction distribution information to obtain predicted invasion soil quality distribution information. Based on the predicted invasion soil quality distribution information and the Spartina alterniflora identification and monitoring information, an urban construction report is generated for the target monitoring areas, including Spartina alterniflora control information and invasion soil remediation information. Based on the urban construction report, Spartina alterniflora control equipment is controlled to perform area removal treatment.

[0008] Secondly, some embodiments of this disclosure provide an urban construction report generation device based on remote sensing satellite resource scheduling, comprising: a first determining unit configured to determine a satellite observation transmission resource scheduling route set for transmitting a set of remote sensing images of tidal flat wetlands collected in a tidal flat wetland area via satellite internet; a transmission unit configured to transmit the remote sensing images of the tidal flat wetlands according to the satellite observation transmission resource scheduling route set to obtain a target tidal flat wetland remote sensing image set; a wetland edge identification unit configured to perform wetland edge identification on the target tidal flat wetland remote sensing image set to obtain a wetland edge identification image set, wherein the wetland edge identification image set includes a set of wetland water area edge marking lines; a second determining unit configured to determine a monitoring and identification area for Spartina alterniflora from the wetland edge identification image set according to a preset buffer radius and the set of wetland water area edge marking lines; and a Spartina alterniflora identification unit configured to identify the Spartina alterniflora monitoring and identification area from the Spartina alterniflora monitoring and identification area based on historical monitoring results of Spartina alterniflora. The system identifies target monitoring areas within the Spartina alterniflora monitoring and identification area, and performs Spartina alterniflora identification on these target monitoring areas to obtain Spartina alterniflora identification monitoring information. A cascaded soil quality prediction unit is configured to perform cascaded soil quality prediction on a set of wetland images of the target monitoring area captured by a drone and a set of remote sensing images of the corresponding target tidal flat wetlands, obtaining multi-source cascaded soil quality prediction distribution information. A soil quality prediction unit is configured to perform soil quality prediction on a sequence of historical Spartina alterniflora invasion soil quality information and the multi-source cascaded soil quality prediction distribution information, obtaining predicted invasion soil quality distribution information. A report generation unit is configured to generate an urban construction report based on the predicted invasion soil quality distribution information and the Spartina alterniflora identification monitoring information, providing Spartina alterniflora control information and invasion soil remediation information for the target monitoring area, and to control Spartina alterniflora control equipment to perform area removal treatment based on the urban construction report.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The urban construction report generation method based on remote sensing satellite resource scheduling in some embodiments of this disclosure improves the accuracy of identifying Spartina alterniflora areas, improves the quality of urban construction reports, reduces equipment wear and tear, and improves governance efficiency. Specifically, the reasons for the low detection accuracy, reduced quality of urban construction reports, increased wear and tear rate of Spartina alterniflora control equipment, and reduced clearance efficiency are as follows: The direct satellite-to-ground transmission mode temporarily stores data in the onboard memory and cannot filter it in real time. It only transmits the data after the satellite passes through the deployed ground receiving stations, resulting in low transmission timeliness and efficiency, and the existence of transmission blind spots, which prolongs data transmission delay and wastes satellite resources. Furthermore, soil quality detection is only performed using a single remote sensing image of the tidal flat wetland. The wetland terrain where Spartina alterniflora grows is complex, leading to low detection accuracy, reduced quality of urban construction reports, increased wear and tear rate of Spartina alterniflora control equipment, and reduced clearance efficiency. Based on this, the urban construction report generation method based on remote sensing satellite resource scheduling in some embodiments of this disclosure can firstly determine the satellite observation transmission resource scheduling route set for transmitting the remote sensing image set of tidal flat wetland areas collected in the satellite internet. Here, the seamless coverage of the integrated remote sensing and communication satellite internet can simultaneously perform the acquisition of the tidal flat wetland remote sensing image set and the determination of the satellite observation transmission resource scheduling route set for multi-dimensional resource scheduling of the satellite internet, so as to efficiently utilize the storage and transmission resources of the satellite internet, realize the dynamic scheduling of satellite multi-dimensional resources, reduce transmission latency, and reduce resource waste. Secondly, according to the above-mentioned satellite observation transmission resource scheduling route set, the above-mentioned tidal flat wetland remote sensing image set is transmitted to obtain the target tidal flat wetland remote sensing image set. Here, the efficiency of data transmission can be improved and the data transmission latency can be reduced. Thirdly, wetland edge recognition is performed on the above-mentioned target tidal flat wetland remote sensing image set to obtain a wetland edge recognition image set, wherein the above-mentioned wetland edge recognition image set includes a set of wetland water area edge marking lines. Here, wetland edge recognition can accurately distinguish the boundaries between water bodies and wetlands, facilitating the precise identification of wetland areas where Spartina alterniflora (Spartina alterniflora) grows. Next, based on a preset buffer radius and the aforementioned set of wetland water boundary markers, the Spartina alterniflora monitoring and identification area is determined from the aforementioned wetland edge recognition image set. Here, the buffer radius and the set of wetland water boundary markers narrow the detection range, accurately identifying the Spartina alterniflora growth and re-germination monitoring and identification area, reducing the scope of subsequent monitoring. Subsequently, based on historical Spartina alterniflora monitoring results, target monitoring area information is determined from the aforementioned Spartina alterniflora monitoring and identification area, and Spartina alterniflora is identified within this target monitoring area information, yielding Spartina alterniflora identification and monitoring information. Here, further adjustments to the area based on historical Spartina alterniflora monitoring results can improve the accuracy of target monitoring area information and the precision of Spartina alterniflora identification, reducing the amount of data processed for Spartina alterniflora identification and improving identification efficiency.Subsequently, cascaded soil quality prediction is performed on the wetland image set of the aforementioned target monitoring area captured by drones and the remote sensing image set of the corresponding target tidal flat wetland, yielding multi-source cascaded soil quality prediction distribution information. Here, using more comprehensive, cascaded, integrated air-space-ground data for soil quality prediction improves the accuracy of multi-source cascaded soil quality prediction distribution information and avoids the limitations of a single data source. Then, soil quality prediction is performed on the historical Spartina alterniflora invasion soil quality information sequence and the aforementioned multi-source cascaded soil quality prediction distribution information, yielding predicted invasive soil quality distribution information. This improves prediction accuracy and allows for precise understanding of the changing trends of Spartina alterniflora's impact on soil quality, providing foundational data for subsequent urban construction report generation. Finally, based on the predicted invasive soil quality distribution information and the aforementioned Spartina alterniflora identification and monitoring information, an urban construction report is generated targeting the aforementioned target monitoring area information, providing Spartina alterniflora control information and invasive soil remediation information. Based on the urban construction report, Spartina alterniflora control equipment is controlled to perform area removal treatment. This improves the quality, comprehensiveness, and accuracy of the urban construction report, reduces the wear and tear on Spartina alterniflora control equipment, and increases control efficiency. Therefore, this method for generating urban construction reports based on remote sensing satellite resource scheduling can improve the accuracy of identifying Spartina alterniflora areas, improve the quality of urban construction reports, reduce equipment wear and tear, and improve governance efficiency. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 These are flowcharts of some embodiments of the urban construction report generation method based on remote sensing satellite resource scheduling according to this disclosure; Figure 2 This is a schematic diagram of a time-varying topology map of acquisition and transmission resources in some embodiments of the urban construction report generation method based on remote sensing satellite resource scheduling according to this disclosure; Figure 3 This is a schematic diagram of the structure of some embodiments of the urban construction report generation device based on remote sensing satellite resource scheduling according to the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flowchart 100 is shown, illustrating some embodiments of a method for generating urban construction reports based on remote sensing satellite resource scheduling according to this disclosure. This method for generating urban construction reports based on remote sensing satellite resource scheduling includes the following steps: Step 101: Determine the satellite observation transmission resource scheduling route set for the transmission of remote sensing images of tidal flat wetlands collected in the tidal flat wetland area via satellite internet.

[0021] In some embodiments, the implementing entity (e.g., an electronic device) of the aforementioned urban construction report generation method based on remote sensing satellite resource scheduling can determine a satellite observation transmission resource scheduling route set for transmitting a set of remote sensing images of tidal flat wetlands collected for the tidal flat wetland area via satellite internet. The aforementioned tidal flat wetland area can be an area requiring data collection. The tidal flat wetland remote sensing images in the aforementioned tidal flat wetland remote sensing image set can be images obtained by remote sensing satellites or integrated remote sensing satellites included in the satellite internet, capturing images of the aforementioned tidal flat wetland area. The aforementioned satellite internet can be a dynamically changing network composed of multiple remote sensing satellites, multiple communication satellites, multiple integrated communication and remote sensing satellites, multiple ground stations, and a ground data processing center, conducting observations of the tidal flat wetland area, acquiring and transmitting tidal flat wetland remote sensing images. The aforementioned multiple remote sensing satellites, multiple communication satellites, and multiple integrated communication and remote sensing satellites are interconnected via inter-satellite laser links. The aforementioned multiple ground stations and ground data processing centers are respectively connected to multiple communication satellites and multiple integrated communication and remote sensing satellites via satellite-to-ground communication links (e.g., microwave links). Each of the aforementioned ground stations is connected to the aforementioned ground data processing center via a terrestrial fiber optic link. The aforementioned remote sensing satellites may be satellites that observe and collect data on tidal flat wetlands via unidirectional inter-satellite laser transmitting terminals, and then unidirectionally unload the data to a communication satellite. The aforementioned integrated remote sensing and communication satellites may be satellites that collect and transmit observational data on tidal flat wetlands using both remote sensing and communication payloads. The aforementioned remote sensing payloads may be devices installed on the integrated remote sensing and communication satellites for non-contact acquisition of images and data of tidal flat wetlands. The aforementioned communication payloads may be devices installed on the integrated remote sensing and communication satellites for transmitting the acquired images and data of tidal flat wetlands. The aforementioned communication satellites may be satellites that receive tidal flat wetland remote sensing image sets collected from multiple remote sensing satellites or multiple integrated remote sensing and communication satellites, perform multi-hop transmission using inter-satellite laser links, and transmit the data to multiple ground stations via satellite-to-ground communication links. The aforementioned ground stations may be satellite ground stations that physically communicate with multiple communication satellites or multiple integrated communication and remote sensing satellites to receive remote sensing image sets of tidal flat wetlands. The aforementioned ground data processing center may be a data processing center that processes the received tidal flat wetland remote sensing image sets. The aforementioned execution entity may be a server within the aforementioned ground data processing center. The aforementioned satellite observation transmission resource scheduling route may be a data transmission path formed from the remote sensing satellite or integrated communication and remote sensing satellite, through the communication satellite or integrated communication and remote sensing satellite, to the ground station, and finally to the data processing center.

[0022] In some optional implementations of certain embodiments, the above-described method of determining a satellite observation transmission resource scheduling route set for transmitting remote sensing images of tidal flat wetlands collected for the tidal flat wetland area via satellite internet may include the following steps: The first step involves discretizing the dynamically changing satellite internet over a preset duration to obtain a sequence of static satellite time slot topology sub-graphs. These static satellite time slot topology sub-graphs can be topologies where the time slot duration is a preset duration, and the satellite internet remains static. This preset duration can be 1 minute. Alternatively, the preset duration can be a pre-defined time period during which the positions of multiple remote sensing satellites, multiple communication satellites, and multiple integrated remote sensing and communication satellites included in the satellite internet continuously change. For example, the preset duration could be 5 minutes.

[0023] The second step involves generating a set of information for maximizing transmission throughput, minimizing transmission energy consumption, and data acquisition and transmission constraints for the aforementioned satellite internet and the aforementioned tidal flat wetland remote sensing image set. The information for maximizing transmission throughput can be a function that maximizes the total throughput of the satellite internet by addressing the multi-dimensional competition and coupling conflicts arising from acquisition, transmission, and observation during the spatiotemporal dynamic evolution of satellite internet observation and transmission tasks. Specifically, it represents the total amount of data acquired and transmitted from multiple remote sensing satellites and multiple integrated communication and remote sensing satellites for the tidal flat wetland remote sensing image set. This information can be expressed as the sum of the product of the unknown observation rate parameter of the observation task (i.e., the image acquisition task of the tidal flat wetland area) to the remote sensing satellite or integrated communication and remote sensing satellite within each time slot duration, multiplied by the number of target nodes and the preset duration. The number of target nodes can be the sum of the number of multiple remote sensing satellites and multiple integrated communication and remote sensing satellites. The information for minimizing transmission energy consumption can be a function that minimizes the total transmission consumption while achieving the total data transmission volume in a resource-scheduled satellite internet. The aforementioned energy consumption minimization information can be expressed as the sum of the energy consumption per unit bit of data transmission between any two nodes within each time slot duration, the unknown data transmission rate parameter, and the time slot duration, over the total number of nodes and the preset duration. The energy consumption per unit bit of data transmission can be the product of the square of the distance between any two nodes in inter-satellite or satellite-to-ground transmission, the transmission time, and a constant. The constant can be the ratio of 16, the square of π, the satellite receiving power, the square of the laser carrier wavelength, and the product of the satellite's transmitting antenna gain and receiving antenna gain. The total number of nodes can be the total number of nodes including multiple remote sensing satellites, multiple communication satellites, multiple integrated remote sensing and communication satellites, multiple ground stations, and ground data processing centers. The unknown observation rate parameter can be a parameter not exceeding the preset maximum observation rate. The unknown data transmission rate parameter can be a parameter not exceeding the preset upper limit of the physical transmission rate of inter-satellite or satellite-to-ground links. The aforementioned data acquisition and transmission constraint information set can be the constraint information of the communication satellites, integrated remote sensing and communication satellites, and communication satellites included in the satellite internet regarding transmission rate and total transmitted data.The aforementioned data acquisition and transmission constraints may include: a first constraint that the amount of data acquired by the remote sensing satellite cannot exceed the maximum data amount of the observation mission; a second constraint that the available observation rate cannot exceed the upper limit of the maximum observable rate; a third constraint that the sum of the observation rates of all observation missions cannot exceed the sum of the maximum observation rates of all imaging payloads on the satellite; a fourth constraint that the total amount of data transmitted and received by the satellite cannot exceed the amount of data corresponding to the tidal flat wetland remote sensing image set; a fifth constraint that the inter-satellite link transmission rate cannot exceed the maximum transmission rate supported by the inter-satellite link; a sixth constraint that the satellite-to-ground link transmission rate cannot exceed the maximum transmission rate supported by the satellite-to-ground link; a seventh constraint that the amount of data obtained by the observation mission is equal to the amount of data transmitted to the data processing center; an eighth constraint that the total amount of data received is equal to the total amount of data sent; a ninth constraint that the data remaining at the previous moment plus the newly received data minus the sent data equals the data stored at the next moment; and a tenth constraint that the amount of data stored in the satellite and ground station from one time slot duration to the duration of an adjacent time slot cannot exceed its storage size.

[0024] Third, for each satellite time slot static topology subgraph in the above satellite time slot static topology subgraph sequence, perform the following determination steps: Sub-step 1: Based on the aforementioned data acquisition and transmission constraint information set, adjust the aforementioned satellite time slot static topology subgraph to obtain an adjusted static topology subgraph. This adjusted static topology subgraph can be a subgraph that adds observation task nodes, virtual node sets corresponding to the aforementioned data acquisition and transmission constraint information set, and virtual connection edges to the aforementioned satellite time slot static topology subgraph. In practice, the executing entity can first determine the aforementioned multiple communication satellites, multiple remote sensing satellites, multiple integrated communication and remote sensing satellites, multiple ground stations, and ground data processing centers as node sets. Secondly, add connection edges between the observation task nodes and the node sets corresponding to the communication satellites and / or integrated communication and remote sensing satellites receiving the observation task nodes to the aforementioned satellite time slot static topology subgraph to obtain a first adjusted static topology subgraph. Thirdly, using the data acquisition and transmission constraint information set, add remote sensing virtual node sets between the observation task nodes and the remote sensing node sets corresponding to the remote sensing satellite sets included in the first adjusted static topology subgraph, and add connection edges from the observation task nodes to the remote sensing virtual node sets, and between the remote sensing virtual node sets and the remote sensing node sets, to obtain a second adjusted static topology subgraph. In this process, since the first and third constraint information may allow remote sensing satellites to conduct multiple observations within the time slot duration corresponding to the satellite time slot static topology subgraph, but the number of imaging payloads carried by the remote sensing satellites and the amount of remote sensing data collected are constrained, flow conservation and capacity limitations are used to meet the observation capabilities of the remote sensing satellites to avoid observation conflicts. Next, based on the data acquisition and transmission constraint information set, virtual receiving node sets, virtual transmitting node sets, and virtual receiving node sets are added to the communication node sets corresponding to the multiple communication satellites and the ground station nodes corresponding to the multiple ground stations included in the second adjusted static topology subgraph. Connection edge sets are also added from the virtual transmitting node sets to the communication node sets, from the communication node sets to the virtual receiving node sets, and from the ground station node sets to the ground station virtual receiving node sets, resulting in the third adjusted static topology subgraph, which serves as the adjusted static topology subgraph. The fourth constraint information, through the addition of virtual receiving node sets and virtual transmitting node sets of the communication nodes, is used to describe the flow conservation, receiving link capacity constraints, transmitting flow conservation, and transmitting link capacity constraints of the communication nodes.

[0025] Sub-step 2 involves adding transmission connection edges to the adjusted static topology subgraph to obtain the target static topology subgraph. This target static topology subgraph can be a topology graph created by adding transmission connection edges between satellites and between satellites and ground stations within the node set, based on internet topology visibility during the time slot duration. In practice, the implementing entity can first use a satellite orbit model to determine the instantaneous position information set of each satellite in the satellite time slot static topology subgraph based on the orbital parameters (e.g., orbital root numbers) of each satellite in the node set. This satellite orbit model can be SGP4 (Simplified General Perturbations 4). Secondly, based on the instantaneous position information set, the set of connecting lines between the satellite node pair set and the satellite-ground node pair set is determined, along with the shortest distance from the Earth's center to the straight line containing the connecting line set, resulting in a node pair distance set. The satellite node pairs in the above set can be any two satellites from multiple communication satellites, multiple remote sensing satellites, or multiple integrated communication and remote sensing satellites. The aforementioned satellite-to-ground node pair set can consist of node pairs composed of individual satellites and multiple ground stations. Then, at least one connecting line corresponding to at least one node pair distance greater than or equal to the Earth's radius is selected from the node pair distance set. Next, using the ATP (Acquisition, Tracking, and Pointing) system, satellite node pairs within each satellite's antenna beam coverage area are identified as the target node pair set. Finally, the aforementioned at least one connecting line and the connecting line set corresponding to the target node pair set are added to the aforementioned adjusted static topology subgraph to obtain the target static topology subgraph.

[0026] Sub-step 3 involves determining the transmission capacity weight set and transmission energy consumption weight set of the connection edge set included in the target static topology subgraph, and adding these weight sets to the target static topology subgraph to obtain the target static weighted directed topology subgraph. The transmission capacity weight in the transmission capacity weight set can be the product of the maximum transmission rate and the time slot duration between the corresponding two nodes. The transmission energy consumption weight in the transmission energy consumption weight set can be the energy consumption per unit bit of data transmission between the corresponding two nodes.

[0027] The fourth step involves adding inter-layer time-varying directed edges to the obtained target static weighted directed topological subgraph sequence to obtain a time-varying topological graph of acquisition and transmission resources. This time-varying topological graph can be a topological graph that identifies the node sets of identical satellites in adjacent target static weighted directed topological subgraphs, adds directed edges representing time series between the nodes of these identical satellites, and uses the upper limit of the satellite's storage capacity as the capacity weight of the directed edges representing time series, and 0 as the energy consumption weight of the directed edges representing time series. For example... Figure 2 As shown, Figure 2 The time-varying topology diagram of the acquired and transmitted resources is displayed, showing the nodes and connecting edges. This represents the global source node. This indicates the node for the observation task. This indicates the node corresponding to the integrated communication and remote sensing satellite. express The integrated remote sensing satellite is a virtual node for remote sensing during the first time slot duration. express The integrated remote sensing satellite is a virtual node for remote sensing during the first time slot duration. These represent the node corresponding to the remote sensing satellite and the virtual remote sensing node of the remote sensing satellite during the first time slot, respectively. This indicates the node corresponding to the ground station. They represent The virtual receiving node of the ground station during the first time slot duration and The ground station is the virtual receiving node for the first time slot duration. This indicates the nodes corresponding to the first and second communication satellites. express The virtual receiving node of the communication satellite during the first time slot duration. This represents the node corresponding to the ground data processing center. A straight, single-arrow directed edge can be an observation link, a dashed, single-arrow directed edge can be a storage link, and a dashed, double-arrow directed edge can be a transmission link. Figure 2 The numerical pairs of the connecting edges can represent the transmission capacity weight set and the transmission energy consumption weight set. For example, (3, 0) can represent that the transmission capacity weight of node 3 and the transmission energy consumption weight of node 0.

[0028] The fifth step involves adding a starting node to the aforementioned time-varying topology graph of the acquisition and transmission resources to obtain the time-varying topology graph of the target resources. This target resource time-varying topology graph can be formed by adding a global source node to the aforementioned acquisition and transmission resource time-varying topology graph, and adding a directed line connecting the global source node and the observation task node set, where the directed line has an infinite capacity weight and a zero energy consumption weight. The global source node can be the starting virtual node for all observation task nodes.

[0029] Step 6: Based on the aforementioned information on maximizing transmission throughput and minimizing transmission energy consumption, resource path planning and scheduling are performed on the time-varying topology map of the data acquisition and transmission resources to obtain the satellite observation transmission resource scheduling route set. In practice, the aforementioned execution entity can utilize the Successive Shortest Augmenting Path Algorithm to solve for the minimum cost maximum flow on the time-varying topology map of the data acquisition and transmission resources based on the information on maximizing transmission throughput, minimizing transmission energy consumption, and the data acquisition and transmission constraint information set, thereby obtaining the satellite observation transmission resource scheduling route set.

[0030] In addressing the technical problems mentioned above, the application scenario—the remote sensing image transmission in an area infested by Spartina alterniflora, involving multi-dimensional resource coordination of observation, transmission, and storage resources within a satellite internet integrated with communication and remote sensing—often presents the following challenges: Due to resource competition among limited onboard energy, cache, and bandwidth resources, and significant spatiotemporal dynamic coupling among these three tasks, existing linear programming methods fail to fully utilize the satellite internet's topology and real-time changing characteristics. This results in low routing efficiency, transmission delays, task interruptions, wasted transmission resources, and high energy consumption. To meet the following requirements for this application scenario: adapting to the real-time changes in satellite internet data transmission under integrated communication and remote sensing; adapting to the joint scheduling of multi-dimensional resources and multiple tasks; adapting to spatiotemporal dynamic coupling; adapting to limited satellite multi-dimensional resources; and maximizing network throughput while minimizing transmission energy consumption, we have decided to adopt the following solution: Optionally, the above-mentioned resource path planning and scheduling of the time-varying topology map of the acquisition and transmission resources based on the above-mentioned transmission throughput maximization information and the above-mentioned transmission energy consumption minimization information to obtain the satellite observation transmission resource scheduling route set may include the following steps: The first step, based on the target static weighted directed topology subgraph sequence corresponding to the time-varying topology graph of the acquired and transmitted resources, is to perform the following inter-layer and intra-layer search path determination steps: Sub-step 1: Based on the initial target static weighted directed topological subgraph, perform the following intra-layer search path determination steps: The first sub-step involves performing an energy-consuming path search on the initial target static weighted directed topology subgraph based on the aforementioned information regarding maximizing transmission throughput and minimizing transmission energy consumption, thereby obtaining the resource energy-consuming path. The initial target static weighted directed topology subgraph can be the target static weighted directed topology subgraph located at the initial position in the target static weighted directed topology subgraph sequence. The resource energy-consuming path can be the path with the minimum energy consumption from the observation task node (starting node) in the initial target static weighted directed topology subgraph to the corresponding termination node of the ground data processing center. In practice, the executing entity can utilize the Bellman-Ford algorithm to perform an energy-consuming path search on the initial target static weighted directed topology subgraph based on the aforementioned information regarding maximizing transmission throughput and minimizing transmission energy consumption, thereby obtaining the resource energy-consuming path. If multiple paths with minimum energy consumption are found simultaneously, one of these paths is arbitrarily selected as the resource energy-consuming path. When the aforementioned initial target static weighted directed topological subgraph can be a set of directed edges representing the time series and a target static weighted directed topological subgraph, the aforementioned resource energy consumption path can be a path that includes connecting edges representing the time series.

[0031] The second sub-step involves determining the maximum traffic increment information for the resource energy consumption path. This maximum traffic increment information can be the minimum transmission capacity weight among the transmission capacity weights of each connected edge included in the resource energy consumption path.

[0032] The third sub-step involves updating the initial target static weighted directed topology subgraph with reverse edge subgraphs based on the resource energy consumption path and the maximum traffic increment information, resulting in a target directed reverse topology subgraph. This target directed reverse topology subgraph can be a subgraph created by adding a set of reverse connection edges to the initial target static weighted directed topology subgraph, and updating the transmission capacity weight set and transmission energy consumption weight set of the included forward connection edges and the added reverse connection edges. In practice, the execution entity can first add a set of reverse connection edges to the initial target static weighted directed topology subgraph with directions opposite to those of the connection edges included in the resource energy consumption path, thus obtaining a reverse topology subgraph. Secondly, based on the maximum traffic increment information and the resource energy consumption path, the transmission capacity weight set and transmission energy consumption weight set of the reverse connection edges and the connection edges included in the resource energy consumption path are determined, serving as the reverse capacity weight set, reverse energy consumption weight set, forward update energy consumption weight set, and forward update capacity weight set. The reverse capacity weights in the reverse capacity weight set can be the maximum traffic increment information of the path. The reverse energy consumption weight in the aforementioned reverse energy consumption weight set can be the inverse of the transmission energy consumption weight of the corresponding forward connection edge. The forward update energy consumption weight in the aforementioned forward update energy consumption weight set can be the transmission energy consumption weight. The forward update capacity weight in the aforementioned forward update capacity weight set can be the difference between the transmission capacity weight and the aforementioned maximum flow increment information of the path. Then, at least one forward update capacity less than or equal to a preset capacity threshold is selected from the aforementioned forward update capacity weight set. The preset capacity threshold can be a pre-set value that will not be searched for on connection edges during subsequent energy consumption path searches. For example, the preset capacity threshold can be 0. Finally, the reverse capacity weight set, reverse energy consumption weight set, forward update energy consumption weight set, and forward update capacity weight set are added to the reverse topology subgraph to obtain the target directed reverse topology subgraph. When the forward update capacity weight in the aforementioned target directed reverse topology subgraph is 0, it will not be searched again during energy consumption path searches.

[0033] The fourth sub-step involves performing an energy-efficient path search on the target directed reverse topology subgraph to obtain path search result information. This path search result information can be determined by whether a path from the observation task node to the termination node exists within the target directed reverse topology subgraph. If the path search result information indicates the existence of a search path, then the path search result information can be the search path with the minimum energy consumption obtained from the energy-efficient path search. If the path search result information indicates the absence of a search path, then the path search result information can be that no search path with the minimum energy consumption exists.

[0034] The fifth sub-step, in response to the determination that the path search result information indicates that there is no search path, and the initial target static weighted directed topological subgraph is the target static weighted directed topological subgraph located at the termination position in the above target static weighted directed topological subgraph sequence, determines the multiple resource energy consumption paths obtained as a satellite observation transmission resource scheduling route set, and transmits the above tidal wetland remote sensing image set according to the above satellite observation transmission resource scheduling route set.

[0035] Sub-step 2: In response to the determination of the path search result information indicating the existence of a search path, the target directed reverse topological subgraph is determined as the initial target static weighted directed topological subgraph, so as to execute the above-mentioned intra-layer search path determination step again.

[0036] Sub-step 3, in response to determining that the initial target static weighted directed topological subgraph is not a target static weighted directed topological subgraph located at the termination position in the above target static weighted directed topological subgraph sequence, determines the next target static weighted directed topological subgraph and the inter-layer temporal directed edge set as the initial target static weighted directed topological subgraph, and then executes the above inter-layer and intra-layer search path determination steps again. The next target static weighted directed topological subgraph can be a topological subgraph located at the next time slot duration following the initial target static weighted directed topological subgraph. The inter-layer temporal directed edges in the above inter-layer temporal directed edge set can be directed edges representing temporal sequence between the same nodes in the initial target static weighted directed topological subgraph and the next target static weighted directed topological subgraph. The transmission capacity weight of the inter-layer temporal directed edges can be the upper limit of the remaining storage capacity of the satellite node, and the transmission energy consumption weight can be 0.

[0037] The above-described technical solution and its related content, as an inventive point of this disclosure, solve the technical problem of "low timeliness of the solved routing set, transmission delay and task interruption, wasting a large amount of transmission resources, and high transmission energy consumption." The factors leading to low timeliness of the solved routing set, transmission delay and task interruption, wasting a large amount of transmission resources, and high transmission energy consumption are often as follows: Due to resource competition among limited on-board energy, cache, and bandwidth resources in the observation, transmission, and storage tasks of integrated satellite internet, and the significant spatiotemporal dynamic coupling of the three tasks, existing linear programming methods fail to fully utilize the topology and real-time changing characteristics of the satellite internet, resulting in low timeliness of the solved routing set, transmission delay and task interruption, wasting a large amount of transmission resources, and high transmission energy consumption. Solving these factors can improve the timeliness of routing set transmission, reduce transmission delay, reduce the occurrence of task interruption problems, and achieve the effect of maximizing transmission throughput and minimizing transmission energy consumption. To achieve this effect, this disclosure firstly transforms the dynamic topology problem into an incremental flow problem iteratively solved on a static graph by processing each target statically weighted directed topology subgraph in the order of the target sequence. The first step maps the physical energy consumption of the link to the transmission energy consumption weight of the connecting edges, prioritizing the path with the minimum transmission energy consumption to ensure the minimum energy consumption of resource-energy-consuming paths. For directed connecting edges representing time sequences, the transmission energy consumption weight is set to 0 to avoid energy consumption increases due to varying storage time. The second step updates the reverse edge subgraph using the determined maximum path traffic increment information. This maximum path traffic increment information accurately reflects the actual data volume that a resource-energy-consuming path can carry under bandwidth and storage constraints, ensuring that subsequent traffic allocation does not violate the data acquisition transmission constraint information set and avoiding data overflow or link overload. Adding reverse connecting edges allows for the revocation or redirection of capacity in subsequent iterations. This allows for the withdrawal of traffic previously allocated to inefficient paths and redirection to newly discovered high-efficiency paths by traversing the reverse connecting edges, thereby overcoming the local optimum trap of greedy algorithms and approaching the global minimum energy consumption. The third step is to determine whether the path search within the target directed reverse topology subgraph is complete by analyzing the results of the path search. If not, the path search continues; if it is complete, multiple paths can be obtained to truly reflect the situation of multi-path concurrent transmission in satellite internet.Then, the path search within the subgraph is completed, and since the subgraph is not the last subgraph to be searched for inter-layer paths, by activating the storage edge representing the time sequence, it is possible to temporarily store data on the satellite during the current time slot duration when no data is transmitted due to link congestion, so that transmission can continue in the next time slot duration. The data transmission situation can be dynamically adjusted within a globally preset duration, which improves the satellite network's rapid adaptation to traffic and topology, improves the timeliness of route set transmission, reduces transmission latency, reduces the occurrence of task interruption problems, and achieves the goal of maximizing transmission throughput and minimizing transmission energy consumption.

[0038] Step 102: Based on the satellite observation transmission resource scheduling routing set, transmit the remote sensing image set of the tidal flat wetland to obtain the remote sensing image set of the target tidal flat wetland.

[0039] In some embodiments, the aforementioned executing entity can transmit the aforementioned tidal flat wetland remote sensing image set according to the aforementioned satellite observation transmission resource scheduling routing set to obtain a target tidal flat wetland remote sensing image set. The target tidal flat wetland remote sensing images in the aforementioned target tidal flat wetland remote sensing image set can be images transmitted to the aforementioned executing entity after edge-end preprocessing of tidal flat wetland remote sensing image sets acquired from remote sensing satellites or integrated communication and remote sensing satellites via the aforementioned satellite observation transmission resource scheduling routing set. The aforementioned edge-end preprocessing can be image preprocessing performed at the remote sensing satellite or integrated communication and remote sensing satellite end. The aforementioned image preprocessing can include, but is not limited to, at least one of the following: radiometric calibration, atmospheric correction, orthorectification, decompression processing, and encryption / decryption processing.

[0040] Step 103: Perform wetland edge recognition on the remote sensing image set of the target tidal flat wetland to obtain a wetland edge recognition image set.

[0041] In some embodiments, the executing entity may perform wetland edge recognition on the aforementioned remote sensing image set of the target tidal flat wetland to obtain a wetland edge recognition image set, wherein the wetland edge recognition image set includes a set of wetland water boundary marker lines. The wetland edge recognition image in the aforementioned wetland edge recognition image set may be a remote sensing image in which an edge marker line distinguishing the tidal flat wetland from the water area is marked in the aforementioned remote sensing image of the target tidal flat wetland. The wetland water boundary marker lines in the aforementioned set of wetland water boundary marker lines may be boundary lines used to separate wetlands and water areas.

[0042] In some optional implementations of certain embodiments, the above-mentioned wetland edge recognition of the target tidal flat wetland remote sensing image set to obtain a wetland edge recognition image set may include the following steps: The first step is to preprocess the aforementioned remote sensing image set of the target tidal flat wetland to obtain a preprocessed remote sensing image set of the tidal flat wetland. The preprocessing may include, but is not limited to, at least one of the following: image enhancement, noise reduction, and filtering.

[0043] The second step involves edge recognition of the preprocessed tidal flat wetland remote sensing image set to obtain an edge recognition result information set, which includes a set of wetland water boundary coordinate sequences. This edge recognition result information can be the information of the boundary line between wetlands and water areas identified in the preprocessed tidal flat wetland remote sensing image. The wetland water boundary coordinate sequence in the wetland water boundary coordinate sequence set can be a sequence composed of multiple discrete coordinates that distinguish the boundary line between wetlands and water areas. In practice, the execution entity can perform the following edge recognition steps for each preprocessed tidal flat wetland remote sensing image: First, determine the Normalized Difference Water Index (NDWI) set for each pixel value in the preprocessed tidal flat wetland remote sensing image in the green and near-red light bands. Second, use the Otsu's method (OTSU) to perform threshold segmentation on the NDWI set to obtain a binary image. Then, use the Canny edge detection algorithm to extract edge lines from the binary image to obtain initial edge lines. Finally, mathematical morphology methods are used to perform morphological filtering on the initial edge lines, first opening and then closing, to obtain the edge recognition results.

[0044] The third step involves using the aforementioned wetland water area edge coordinate sequence set to perform edge annotation on the aforementioned preprocessed tidal flat wetland remote sensing image set, thereby obtaining a wetland edge recognition image set. Specifically, the wetland edge recognition images in the aforementioned wetland edge recognition image set can be obtained by adding the boundary edges corresponding to the aforementioned wetland water area edge coordinate sequence to the aforementioned preprocessed tidal flat wetland remote sensing images.

[0045] In addressing the aforementioned technical challenges by employing technical solutions, the application scenario—specifically, the determination and removal of *Spartina alterniflora* (a type of grass) in areas with mixed water bodies and tidal wetlands—often presents the following technical problems: *Spartina alterniflora* frequently grows in tidal wetlands, which are characterized by mixed water and land areas, high sediment content, and shadowing, making it difficult to accurately delineate the boundaries between water bodies and wetlands. This results in low accuracy in edge recognition, leading to lower quality urban construction reports and increased wear and tear on *Spartina alterniflora* control equipment. Considering the following requirements for this application scenario—adaptability to spatial neighborhood growth, adaptability to joint judgment of multiple water body indices, adaptability to multi-band edge recognition, adaptability to edge recognition of various water bodies and wetlands, and ambiguity in water and wetland boundaries—we have decided to adopt the following solution: Optionally, the preprocessed remote sensing image set of tidal flat wetlands includes: a blue light band image set, a green light band image set, a near-infrared band image set, and a short-infrared band image set. The aforementioned blue light band images can be images of the preprocessed tidal flat wetland remote sensing images acquired by remote sensing satellites or integrated remote sensing satellites using multispectral sensors, and can be located in the blue light band. The aforementioned green light band images can be located in the green light band. The aforementioned near-infrared band images can be located in the near-infrared band. The aforementioned short-infrared band images can be located in the short-infrared band.

[0046] The above-mentioned edge recognition of the preprocessed tidal flat wetland remote sensing image set to obtain an edge recognition result information set may include the following steps: The first step is to perform the following processing sub-steps for each pixel in each preprocessed tidal flat wetland remote sensing image in the above preprocessed tidal flat wetland remote sensing image set: Sub-step 1 involves determining the reflectance of the pixels corresponding to the aforementioned blue light band image, green light band image, near-infrared band image, and short-infrared band image set, thus obtaining the blue light reflectance, green light reflectance, near-infrared reflectance, and short-infrared reflectance. Specifically, the blue light reflectance can be the reflectance of the water surface or wetland surface to incident blue light, i.e., the pixel value of the blue light band image. The green light reflectance can be the reflectance of the water surface or wetland surface to incident green light, i.e., the pixel value of the green light band image. The near-infrared reflectance can be the reflectance of the water surface or wetland surface to incident near-infrared light, i.e., the pixel value of the near-infrared band image. The short-infrared reflectance can be the reflectance of the water surface or wetland surface to incident short-infrared light, i.e., the pixel value of the short-infrared band image.

[0047] Sub-step 2: Determine the difference and sum of the green light reflectance with the near-infrared reflectance and the short-infrared reflectance, respectively, as the first difference, the second difference, the first sum, and the second sum.

[0048] Sub-step 3: Determine the ratio of the first difference to the first sum as the first water body index.

[0049] Sub-step 4: Determine the ratio of the second difference to the second sum as the second water index.

[0050] Sub-step 5: The ratio of the above-mentioned blue light reflectance to the above-mentioned green light reflectance is determined as the third water body index.

[0051] Sub-step 6: In response to determining that the first water body index is greater than a first preset threshold, the pixel is identified as a first water body pixel. The first preset threshold may be a pre-set critical value determined in the green light and near-infrared bands, used to distinguish between water bodies and wetlands. For example, the first preset threshold may be 0.

[0052] Sub-step 7: In response to determining that the second water body index is greater than the second preset threshold, the aforementioned pixel is identified as a second water body pixel. The second preset threshold can be a pre-set critical value that effectively distinguishes between water bodies and bare soil wetlands in the green light and shortwave infrared bands, and it varies with the seasons. For example, the second preset threshold could be 0.34 during the high-water season (spring and summer) and 0.58 during the low-water season (autumn and winter).

[0053] Sub-step 8: In response to determining that the third water body index is greater than a third preset threshold, the aforementioned pixel is identified as a third water body pixel. The third preset threshold can be a pre-set critical value used to distinguish between water bodies and wetlands, determined by the differences in absorption and reflection characteristics of substances in the water body (e.g., chlorophyll) in the blue and green light bands. The third preset threshold can be determined based on specific circumstances (e.g., remote sensing satellite data, tidal flat wetland area data, and water body type information), and will not be elaborated further here.

[0054] The second step is to select pixels that meet the first preset condition from the aforementioned preprocessed remote sensing image set of tidal flats and wetlands as a water body pixel set. The first preset condition can be that a pixel is at least two of the following: a first water body pixel, a second water body pixel, and a third water body pixel.

[0055] The third step is to select pixels that do not meet the first preset condition from the above preprocessed remote sensing image set of tidal flat wetlands as undetermined pixels, thus obtaining a set of undetermined pixels.

[0056] Fourth step: For each undetermined pixel in the above undetermined pixel set, perform the following determination sub-step: Sub-step 1: Determine whether the above-mentioned undetermined pixel is adjacent to any water body pixel. Among them, the water body pixels adjacent to the above-mentioned undetermined pixel can be four directly adjacent water body pixels located above, below, left, and right of the above-mentioned undetermined pixel, as well as four water body pixels on the diagonal.

[0057] Sub-step 2: In response to determining that the above-mentioned undetermined pixel is adjacent to any water body pixel, the above-mentioned undetermined pixel is determined as a water body pixel.

[0058] The fifth step involves extracting edge contours from the obtained water body pixel set and the obtained undetermined pixel set to obtain an edge recognition result information set. Using the wetland water area edge coordinate sequence set included in the edge recognition result information set, edge annotation is performed on the preprocessed tidal flat wetland remote sensing image set to obtain a wetland edge recognition image set. The obtained water body pixel set can be a set of pixels composed of multiple water body pixels obtained in the fourth step and the water body pixel set obtained in the second step. The obtained undetermined pixel set can be a set of pixels obtained by removing the water body pixel set identified in the fourth step from the undetermined pixel set obtained in the third step. In practice, the executing entity can first stitch the obtained water body pixel set and the obtained undetermined pixel set into a remote sensing binary map set according to the preprocessed tidal flat wetland remote sensing image set. Then, the remote sensing binary map set is input into the contour extraction function to obtain the edge recognition result information set. The aforementioned contour extraction function can be the cvFindContours function in the OpenCV image processing library, which is used to extract contours from binary images.

[0059] The above technical solution, combined with steps 104 to 108 and related content, serves as an inventive point of this disclosure, solving the technical problem of "low edge recognition accuracy, leading to low quality of urban construction reports and increased wear and tear on Spartina alterniflora control equipment." Factors contributing to low edge recognition accuracy, low quality of urban construction reports, and increased wear and tear on Spartina alterniflora control equipment often include: Spartina alterniflora often grows in tidal flats and wetlands, which are characterized by mixed water and land areas, high sediment content, and shadows, making it difficult to accurately delineate the boundaries between water areas and wetlands. This results in low edge recognition accuracy, leading to low quality of urban construction reports and increased wear and tear on Spartina alterniflora control equipment. Solving these factors can improve edge recognition accuracy, enhance the quality of urban construction reports, and reduce wear and tear on Spartina alterniflora control equipment. To achieve this effect, this disclosure introduces the blue light reflectance, green light reflectance, near-infrared reflectance, and short-infrared reflectance of pixels in remote sensing images to address the aforementioned technical problem. The first, second, and third water body indices were determined using blue light reflectance, green light reflectance, near-infrared reflectance, and short-wave infrared reflectance. The first water body index, utilizing green light and near-infrared, is sensitive to open, clean water bodies. The second water body index, utilizing green light and short-wave infrared, is more sensitive to water content and can effectively identify complex water bodies (e.g., turbid muddy water), reducing the accuracy of edge misjudgment caused by building and bare soil shadows. The third water body index, utilizing the blue-to-green light ratio, can enhance water body signals in shallow water areas or areas with high suspended sediment, improving the accuracy of wetland water body edge identification under different water body conditions. Then, pixels that can be identified as water bodies were selected from the preprocessed tidal wetland remote sensing images based on the first, second, and third water body indices, and the remaining pixels were designated as undetermined pixels. Next, the undetermined pixels were further filtered based on their adjacency relationships with water body pixels. Therefore, preprocessing remote sensing images of tidal flats and wetlands can ensure the continuity and integrity of the water body and wetland boundary lines by using adjacency relationships, which can prevent the identified edge lines from being discontinuous and improve the accuracy of identification and the quality of the edge lines, due to the presence of voids inside the water body caused by cloud shadows, fog, or extremely thin water layers.

[0060] Step 104: Based on the preset buffer radius and the set of wetland water boundary marking lines, determine the monitoring and identification area of ​​Spartina alterniflora from the set of wetland boundary recognition images.

[0061] In some embodiments, the execution entity can determine the *Spartina alterniflora* monitoring and identification area from the wetland edge recognition image set based on a preset buffer radius and the wetland water area edge marker line set. The preset buffer radius can be a pre-set radius used to determine the *Spartina alterniflora* monitoring and identification area based on the wetland water area edge marker line set. The preset buffer radius can be a value determined through expert experience; its specific value can be determined according to specific circumstances and will not be elaborated further here. The *Spartina alterniflora* monitoring and identification area can be an area used to monitor the presence and re-germination of *Spartina alterniflora*. In practice, the execution entity can use the wetland water area edge marker line set as a center line and determine the area in the wetland edge recognition image set whose distance from the center line is less than or equal to the preset buffer radius as the *Spartina alterniflora* monitoring and identification area.

[0062] Step 105: Based on the historical monitoring results of Spartina alterniflora, determine the target monitoring area information from the Spartina alterniflora monitoring and identification area, and identify Spartina alterniflora in the target monitoring area information to obtain Spartina alterniflora identification monitoring information.

[0063] In some embodiments, the aforementioned executing entity can determine target monitoring area information from the aforementioned Spartina alterniflora monitoring and identification area based on historical monitoring results, and perform Spartina alterniflora identification on the target monitoring area information to obtain Spartina alterniflora identification monitoring information. The aforementioned historical monitoring results can be the results of Spartina alterniflora identification and monitoring performed on the aforementioned Spartina alterniflora monitoring and identification area prior to the current time. The aforementioned target monitoring area information can be the area information of Spartina alterniflora generation and re-germination areas determined at the current time. The aforementioned Spartina alterniflora identification monitoring information can be the area information of the target monitoring area corresponding to the identified target monitoring area information where Spartina alterniflora exists and the identification information of the reduced area. The aforementioned reduced area can be the monitoring information of areas where Spartina alterniflora has historically grown but where Spartina alterniflora generation has not been identified currently.

[0064] In some optional implementations of certain embodiments, the aforementioned historical monitoring results of Spartina alterniflora include a set of coordinate sequences of historical Spartina alterniflora growth areas. Specifically, the coordinate sequences of historical Spartina alterniflora growth areas in this set can be sequences composed of coordinates of Spartina alterniflora generation areas located prior to the current time.

[0065] The process of determining target monitoring area information from the aforementioned Spartina alterniflora monitoring and identification areas based on historical monitoring results, and identifying Spartina alterniflora within the target monitoring area information to obtain Spartina alterniflora identification monitoring information, may include the following steps: The first step involves using the coordinate sequences of each historical growth region of *Spartina alterniflora* from the aforementioned historical growth region coordinate sequence set to mark the historical growth regions of *Spartina alterniflora* in the aforementioned wetland edge recognition image set, thus obtaining historically marked regions. These historically marked regions can be the historically generated regions of *Spartina alterniflora* that have been marked on the wetland edge recognition image set using the aforementioned historical growth region coordinate sequences. Before marking the historical growth regions of *Spartina alterniflora*, the aforementioned wetland edge recognition image set and the images corresponding to the aforementioned historical monitoring results of *Spartina alterniflora* have already undergone geometric registration processing.

[0066] The second step is to determine the intersection area between the historical marker area and the Spartina alterniflora monitoring and identification area in the above wetland edge recognition image set, and obtain the overlapping area as the target monitoring area information.

[0067] The third step involves inputting the aforementioned historical monitoring results of *Spartina alterniflora*, the corresponding historical tidal wetland remote sensing image set, the wetland edge recognition image set, and the target monitoring area information into the key monitoring area monitoring model to obtain *Spartina alterniflora* identification and monitoring information. The aforementioned historical tidal wetland remote sensing images can be images taken before the current time, representing a set of coordinate sequences of historical *Spartina alterniflora* growth areas. The aforementioned *Spartina alterniflora* identification and monitoring information includes a set of growth area coordinate sequences and a set of reduced area coordinate sequences. The growth area coordinate sequence set can represent the set of coordinate sequences of areas where *Spartina alterniflora* grows. The reduced area coordinate sequence set can represent the set of coordinate sequences of areas where *Spartina alterniflora* once grew but is not currently growing. The aforementioned key monitoring area monitoring model can be a model that identifies the monitoring area from the input historical monitoring results of *Spartina alterniflora*, historical tidal wetland remote sensing images, the aforementioned wetland edge recognition image set, and the aforementioned target monitoring area information, and outputs *Spartina alterniflora* identification and monitoring information. The monitoring model for the aforementioned key monitoring area can be implemented through the following steps: First, resampling and geometric registration are performed on the aforementioned historical tidal wetland remote sensing image set and the aforementioned wetland edge identification image set to obtain a registered remote sensing image set and a registered identification image set. Second, local area images with the same information as the aforementioned target monitoring area are cropped from the aforementioned registered remote sensing image set and the aforementioned registered identification image set to obtain a local remote sensing image set and a local identification image set. Third, on the target single-channel canvas set, the pixel value set corresponding to the coordinate sequence of the aforementioned Spartina alterniflora historical growth area is set to 1, and the remaining pixel value set is set to 0, to obtain a wetland remote sensing binary image set. The aforementioned target single-channel canvas can be a blank canvas of the same size as the aforementioned local identification images. Next, the aforementioned wetland remote sensing binary image set, the aforementioned local remote sensing image set, and the aforementioned local identification image set are normalized to obtain a normalized binary image set, a normalized historical remote sensing image set, and a normalized current identification image set. Then, tensor transformation is performed on the aforementioned normalized historical remote sensing image set to obtain the first historical remote sensing feature tensor. Next, channel concatenation of the aforementioned normalized binary image set and the aforementioned normalized current recognition image set is performed followed by tensor transformation to obtain the first current visual feature tensor. Subsequently, the first current visual feature tensor and the first historical remote sensing feature tensor are input into a two-stream feature coding layer to obtain the second current visual feature map and the second historical remote sensing feature map. The aforementioned two-stream feature coding layer can be a model that performs bi-branch feature extraction on the input first current visual feature tensor and the first historical remote sensing feature tensor to ensure feature space consistency, outputting the second current visual feature map and the second historical remote sensing feature map. For example, the aforementioned two-stream feature coding layer can be a TransUNet model. Then, after determining the feature difference between the second current visual feature map and the second historical remote sensing feature map, channel concatenation is performed with the second current visual feature map to obtain a concatenated feature map.Next, the spliced ​​feature map is input into a convolutional layer with a 1*1 kernel for fusion convolution to obtain a spatiotemporal fusion feature map. Then, the spatiotemporal fusion feature map is upsampled and spliced ​​with the second current visual feature map and the second historical remote sensing feature map to obtain a multi-channel semantic feature map. The upsampling can be such that the spatial size of the spatiotemporal fusion feature map is the same as the spatial size of the second current visual feature map and the second historical remote sensing feature map. Next, the multi-channel semantic feature map is input into a convolutional layer with a 1*1 kernel for channel number adjustment and then input into a Softmax activation function to obtain a three-channel probability feature map. The three-channel probability feature map is then subjected to maximum value indexing along the channel axis to obtain an initial monitoring result raster map. This initial monitoring result raster map can be a raster map where a pixel value of 0 represents an area where Spartina alterniflora has not appeared, 1 represents a growing area, and 2 represents a shrinking area. Finally, the initial monitoring result raster map is subjected to vector post-processing to obtain Spartina alterniflora identification and monitoring information. The aforementioned vector post-processing can involve performing an opening operation and vectorization on the raster map of the initial monitoring results.

[0068] In some optional implementations of certain embodiments, the process of using the coordinate sequences of each historical growth region of Spartina alterniflora in the aforementioned set of historical growth region coordinate sequences to mark the historical growth regions of Spartina alterniflora in the aforementioned wetland edge recognition image set, thereby obtaining historically marked regions, may include the following steps: The first step is to obtain a set of historical remote sensing images of tidal flat wetlands corresponding to the historical monitoring results of Spartina alterniflora mentioned above.

[0069] The second step involves performing feature point matching processing on the aforementioned historical tidal flat wetland remote sensing image set and the aforementioned wetland edge recognition image set to obtain feature point matching results. These matching results include a set of feature point pairs. The feature point matching results can be the result of matching feature points (extreme points at the spatial scale) from the aforementioned historical tidal flat wetland remote sensing image set with the corresponding feature points from the aforementioned wetland edge recognition image set. The feature point pairs in the feature point pair set can be matched feature points. In practice, the executing entity can utilize the SIFT (Scale-Invariant Feature Transform) algorithm to perform feature point matching processing on the aforementioned historical tidal flat wetland remote sensing images and the aforementioned wetland edge recognition image set to obtain feature point matching results.

[0070] The third step involves using the feature point pairs from the feature point matching results to establish an equation for the coordinate transformation from the historical tidal flat wetland remote sensing image set to the wetland edge recognition image set. This coordinate transformation equation can be a first-order affine transformation equation characterizing the transformation relationship between the coordinates of the historical tidal flat wetland remote sensing image set and the wetland edge recognition image set. In practice, the executing entity can use the least squares method to establish the equation for the coordinate transformation from the historical tidal flat wetland remote sensing image set to the wetland edge recognition image set.

[0071] The fourth step involves transforming the historical growth area coordinate sequence set of Spartina alterniflora from the historical monitoring results, based on the aforementioned coordinate transformation equation, to obtain the transformed coordinate sequence set of Spartina alterniflora historical growth areas. In practice, the implementing entity can input the historical growth area coordinate sequence set of Spartina alterniflora from the historical monitoring results into the aforementioned coordinate transformation equation to obtain the transformed coordinate sequence set of Spartina alterniflora historical growth areas.

[0072] The fifth step involves using the aforementioned set of transformed coordinate sequences of historical growth areas of Spartina alterniflora to mark the historical growth areas of Spartina alterniflora in the aforementioned wetland edge recognition image set, thereby obtaining the historically marked areas.

[0073] Step 106: Perform cascaded soil quality prediction on the wetland image set of the target monitoring area information captured by the UAV and the remote sensing image set of the target tidal flat wetland corresponding to the target monitoring area information to obtain multi-source cascaded soil quality prediction distribution information.

[0074] In some embodiments, the aforementioned implementing entity can perform cascaded soil quality prediction on a set of wetland images of the target monitoring area captured by a drone and a set of remote sensing images of the target tidal flat wetland corresponding to the target monitoring area information, to obtain multi-source cascaded soil quality prediction distribution information. The wetland images in the aforementioned wetland image set can be images of the target monitoring area information captured by a drone. The multi-source cascaded soil quality prediction distribution information can be the distribution information of organic carbon capacity of soil quality information obtained by collaborative cascading estimation of soil quality information from air-space-ground data, i.e., the wetland image set and the target tidal flat wetland remote sensing image set corresponding to the target monitoring area information, can be image data acquired at the same time.

[0075] In addressing the aforementioned technical challenges by employing technical solutions, the application scenario—soil quality prediction in Spartina alterniflora-invaded areas based on space-air-ground data collaboration, followed by Spartina alterniflora control equipment—often presents the following technical problems: Due to the complex terrain and intermingled distribution of water bodies, wetlands, and vegetation in the target monitoring area, on-site sampling of wetland soil is difficult. Soil prediction using a single remote sensing image, while offering a wide satellite coverage, suffers from low spatial resolution. Furthermore, the diverse vegetation types, including Spartina alterniflora, make it difficult to capture changes in wetland soil, resulting in low accuracy in soil quality prediction and low-quality reports. Consequently, this leads to higher wear and tear on Spartina alterniflora control equipment, lower control efficiency, and prolonged treatment time. Considering the following requirements for this application scenario: adaptability to collaborative prediction using multi-source space-air-ground data, adaptability to complex wetland environments, adaptability to non-contact soil quality prediction, and adaptability to high precision, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the cascaded soil quality prediction of the wetland image set of the target monitoring area information captured by the UAV and the remote sensing image set of the target tidal flat wetland corresponding to the target monitoring area information, to obtain multi-source cascaded soil quality prediction distribution information, may include the following steps: The first step involves image preprocessing of the aforementioned wetland image set and the remote sensing image set of the target tidal flat wetland corresponding to the aforementioned target monitoring area information, resulting in UAV wetland orthophoto mosaic images and remote sensing optical mosaic images. The image preprocessing for the aforementioned wetland image set may include: aerial triangulation processing, orthorectification, radiometric calibration, and wetland image set stitching and cropping. The image preprocessing for the remote sensing image set of the target tidal flat wetland corresponding to the aforementioned target monitoring area information may include: orbit correction, thermal noise reduction, radiometric calibration, multi-view processing, speckle filtering, terrain correction, and resampling stitching. The aforementioned UAV wetland orthophoto images may be multispectral images that cover each preset sampling control point in the aforementioned target monitoring area information, and include geographic coordinates in the WGS84 UTM (World Geodetic System 1984, Universal Transverse Mercator) coordinate system, characterizing surface reflectance. The aforementioned remote sensing optical mosaic image can be a remote sensing image covering the aforementioned target monitoring area information and with a coordinate system of WGS84 UTM Zone 51N.

[0076] The second step involves geometrically registering the aforementioned UAV wetland orthophoto mosaic image and the aforementioned remote sensing optical mosaic image to obtain a registered orthophoto image and a registered remote sensing image. The registered orthophoto image and the registered remote sensing image can be images where the error of the matching points in the overlapping area does not exceed a preset pixel error threshold. The preset pixel error threshold can be 0.5 pixels.

[0077] The third step involves extracting features from the registered orthophoto and the registered remote sensing images to obtain an orthophoto feature information set and a remote sensing feature information set, respectively. The orthophoto feature information in the orthophoto feature information set can be obtained by integrating the spectral reflectance characteristics of different bands of the registered orthophoto to characterize vegetation biomass, chlorophyll content, and vegetation cover.The aforementioned orthophoto feature information may include: blue band parameters, green band parameters, red band parameters, red edge band parameters, near-infrared band parameters, NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), RVI (Ratio Vegetation Index), DVI (Difference Vegetation Index), NDRE (Normalized Difference Red Edge Index), BI (Brightness Index), BI2 (The Second Brightness Index), GNDVI (Green Normalized Difference Vegetation Index), TVI (Transform Vegetation Index), EVI2 (Enhanced Vegetation Index 2), NDVI_gb (Normalized Green-Blue Difference Vegetation Index), and MSR (Modified Simple The parameters used in this study include: Ratio (modified simple ratio), NLI (Non-linear Index), RDVI (Re-normalized Difference Vegetation Index), EXG (Excess Green Index), NRBDI (Normalized Red-Blue Difference Index), TNDVI (Transformed Normalized Difference Vegetation Index), GDVI (Greenness Difference Vegetation Index), NNIR (Normalized NIR Index), and GRNDVI (Green-Red Normalized Difference Vegetation Index). The blue band, green band, red band, red edge band, and near-infrared band parameters mentioned above can be the center wavelength and bandwidth parameters of the registered orthophoto image in the blue, green, red, red edge, and near-infrared bands.The remote sensing feature information in the aforementioned remote sensing feature information set can be information that characterizes vegetation biomass, chlorophyll content, and vegetation cover by integrating the spectral reflectance characteristics of different bands of registered remote sensing images. The aforementioned remote sensing feature information set may include: blue band parameters, green band parameters, red band parameters, shortwave infrared band 1 parameters, shortwave infrared band 2 parameters, NDGI (Normalized Difference Green Index), SATVI (Soil-Adjusted Total Vegetation Index), NDVI, RVI, OSAVI (Optimized Soil-Adjusted Vegetation Index), BI, VARI (Visible Atmospherically Resistant Index), RI (Redness Index), CI (Chlorophyll Index), TVI, MSR, NLI, GI (Green Index), NGRDI (Normalized Green-Red Difference Index), NRBDI, and TNDVI.

[0078] The fourth step involves predicting soil quality using the orthophoto feature information set to obtain the predicted distribution information of soil quality in the first region. This predicted soil quality information can be the predicted soil organic carbon density information set for each preset sampling control point in the target monitoring area. In practice, the implementing entity can first input the orthophoto feature information set into a trained random forest model to obtain the UAV soil prediction information set. Secondly, it determines the soil quality residual value set corresponding to the UAV soil prediction information in the preset target area soil quality detection information and the UAV soil prediction distribution information. The preset target area soil quality detection information can be the wetland soil quality information of the actual target monitoring area obtained from the sample data of the statistical training random forest model. Thirdly, using the Kriging method, it performs spatial interpolation on the soil quality residual value set to obtain the soil quality interpolation set. Finally, it determines the sum of the UAV soil prediction information set and the soil quality interpolation set to obtain the predicted soil quality information set for the first region, which serves as the predicted distribution information of soil quality in the first region.

[0079] The fifth step involves inputting the aforementioned remote sensing feature information set into the trained remote sensing soil quality prediction model to obtain the predicted distribution information of soil quality in the second region. This predicted distribution information can be the predicted organic carbon density in the soil of the target monitoring area. The aforementioned remote sensing soil quality prediction model can be a machine learning model that predicts soil organic carbon density from the input remote sensing feature information set and outputs the predicted distribution information of soil quality in the second region. For example, the machine learning model could be a random forest. Both the aforementioned remote sensing soil quality prediction model and the random forest corresponding to the aforementioned orthophoto feature information set use random forest as their base model, but the number of decision trees, the maximum number of features for node splits, the minimum number of samples per node, and the maximum tree depth are different. These are model hyperparameters obtained through grid search and 10-fold cross-validation based on their respective training samples. The training data for the aforementioned remote sensing soil quality prediction model and the random forest corresponding to the aforementioned orthophoto feature information set are, respectively, a remote sensing image sample set for the target monitoring area and the corresponding collected soil quality detection distribution information, i.e., the set of true soil quality values; and a UAV orthophoto image sample set and the corresponding collected soil quality detection distribution information, i.e., the set of true soil quality values. The training loss function can be the mean squared error. The aforementioned soil quality detection distribution information can be the soil organic carbon density information obtained by collecting and processing soil samples at a depth of 0-30cm at various preset sampling control points in the target monitoring area, which is the product of soil organic carbon content, soil bulk density, and soil depth. The aforementioned preset sampling control points can be pre-defined soil sampling points uniformly distributed in the target monitoring area.

[0080] The sixth step involves aggregating remote sensing pixels into the aforementioned first region soil quality prediction information set to obtain the third region soil quality prediction distribution information. This third region soil quality prediction distribution information can have the same resolution and scale as the second region soil quality prediction distribution information. In practice, the implementing entity can first determine multiple pixels in the registered orthophoto corresponding to each pixel in the registered remote sensing image, as a target orthophoto pixel set. Then, it determines the mean of the first region soil quality prediction information set corresponding to each target orthophoto pixel set, as the third region soil quality prediction information set. Finally, the third region soil quality prediction information set is determined as the third region soil quality prediction distribution information.

[0081] Step 7: In response to determining that the pixel error sets of the predicted soil quality distribution information for the second and third regions satisfy a preset pixel error condition, the product of the predicted quality information of each pixel in the predicted soil quality distribution information for the second region and its corresponding pixel area is determined as the multi-source cascaded soil quality prediction distribution information. The pixel error in the pixel error set can be the difference between the predicted soil quality information for the third region corresponding to each pixel in the predicted soil quality distribution information for the third region and the predicted soil quality information for the second region corresponding to the predicted soil quality distribution information for the second region. The preset pixel error condition can be the condition that the pixel error is within a preset error range. The preset error range can be a pre-set range, and its value can be determined according to specific circumstances, which will not be elaborated here. The predicted pixel quality information can be the predicted soil quality information for the second region corresponding to each pixel in the predicted soil quality distribution information for the second region. The pixel area can be the area of ​​the actual wetland corresponding to each pixel in the registered remote sensing image. When the pixel error set does not meet the preset pixel error conditions, the remote sensing image set of the target tidal flat wetland corresponding to the target monitoring area information is reacquired in order to repeat the steps one through seven.

[0082] The above technical solution, combined with steps 107-108 and related content, serves as an inventive point of this disclosure, solving the technical problem of "low accuracy in predicting soil quality in the target monitoring area, low quality of generated reports, leading to high wear and tear on Spartina alterniflora control equipment, low control efficiency, and prolonged control time." The factors contributing to the low accuracy in predicting soil quality in the target monitoring area, low quality of generated reports, and consequently high wear and tear on Spartina alterniflora control equipment, low control efficiency, and prolonged control time are often as follows: Due to the complex terrain and the intermingling of water bodies, wetlands, and vegetation in the target monitoring area, on-site sampling of wetland soil is difficult. While satellite remote sensing has a large coverage area, its spatial resolution is low, and the presence of multiple vegetation types, including Spartina alterniflora, makes it difficult to capture changes in wetland soil. This results in low accuracy in predicting soil quality in the target monitoring area, low quality of generated reports, and consequently, high wear and tear on Spartina alterniflora control equipment, low control efficiency, and prolonged control time. Solving the above factors can improve the accuracy of soil quality prediction in the target monitoring area, enhance the quality of generated reports, reduce the wear and tear on Spartina alterniflora control equipment, increase control efficiency, and shorten control time. To achieve this, this disclosure first performs image preprocessing and geometric registration on the wetland image set and the target tidal wetland remote sensing image set. This removes radiation distortion and noise caused by the complex topography of the wetland, improves the surface reflectance of the images, and ensures pixel-level spatial alignment across different data sources. Second, it fully utilizes the sensitivity of UAV red-edge bands to vegetation parameters and satellite shortwave infrared bands to soil characteristics for multi-dimensional feature extraction. This enhances the richness of feature information, achieves complementary enhancement of feature information, and compensates for the data deficiencies of single data sets, thereby improving subsequent prediction accuracy. Third, based on the orthophoto feature information set, soil quality prediction uses a random forest model to explore the nonlinear relationship between vegetation indices and soil quality. Simultaneously, spatial interpolation of the residuals using the Kriging method captures the local spatial autocorrelation caused by micro-topography, improving prediction accuracy. Finally, based on the remote sensing feature information set, soil quality prediction can predict the soil quality of the entire target monitoring area. Then, pixel aggregation and size transformation are performed to generate multi-source cascaded soil quality prediction distribution information. The pixel aggregation and size transformation ensures consistency between the UAV and satellite dimensions, preserving not only the high-precision information density of UAV predictions but also the wide coverage of satellites. By comparing the pixel errors of the second and third region soil quality prediction distribution information, the accuracy of the cascaded soil quality predictions can be further improved. Finally, generating urban construction reports using the multi-source cascaded soil quality prediction distribution information can improve the accuracy of urban construction reports, reduce the wear and tear on Spartina alterniflora control equipment, increase control efficiency, and shorten the control time.

[0083] Step 107: Soil quality prediction is performed on the historical Spartina alterniflora invasion soil quality information sequence and multi-source cascade soil quality prediction distribution information to obtain the predicted invasion soil quality distribution information.

[0084] In some embodiments, the aforementioned executing entity can perform soil quality prediction on the historical *Spartina alterniflora* invasion soil quality information sequence and the aforementioned multi-source cascaded soil quality prediction distribution information to obtain predicted invasion soil quality distribution information. The historical *Spartina alterniflora* invasion soil quality information in the aforementioned historical *Spartina alterniflora* invasion soil quality information sequence can be soil quality information collected from the target monitoring area prior to the current time. The predicted invasion soil quality distribution information can be information on the degree of impact of *Spartina alterniflora* invasion on the soil carbon content of the aforementioned target monitoring area if *Spartina alterniflora* is not cleared within the predicted future time period. The predicted future time period can be the next 3 days. In practice, the aforementioned executing entity can input the historical *Spartina alterniflora* invasion soil quality information sequence and the aforementioned multi-source cascaded soil quality prediction distribution information into a long short-term memory neural network model to perform soil quality prediction, obtaining predicted invasion soil quality distribution information. The input can be the historical *Spartina alterniflora* invasion soil quality information sequence as the time step input sequence of the long short-term memory neural network, and the aforementioned multi-source cascaded soil quality prediction distribution information as the latest observation value at the current time appended to the end of the sequence to construct a complete time-series input tensor before input.

[0085] Step 108: Based on the predicted invasive soil quality distribution information and Spartina alterniflora identification and monitoring information, generate an urban construction report on Spartina alterniflora control information and invasive soil remediation information for the target monitoring area, and control the Spartina alterniflora control equipment to perform regional removal treatment based on the urban construction report.

[0086] In some embodiments, the executing entity can generate an urban construction report on Spartina alterniflora control and invasive soil remediation information for the target monitoring area based on the predicted invasive soil quality distribution information and the Spartina alterniflora identification and monitoring information. Based on the urban construction report, the entity can control Spartina alterniflora control equipment to perform area removal treatment. The urban construction report can be a report outlining a control plan for Spartina alterniflora removal to address the decrease in soil organic carbon content and density caused by Spartina alterniflora invasion. The Spartina alterniflora control equipment can be machinery used to remove existing Spartina alterniflora and prevent its re-emergence in previously cleared areas, thereby improving the quality of soil tidal flats and wetlands. For example, the Spartina alterniflora control equipment may include, but is not limited to, at least one of the following: a Spartina alterniflora harvester and a drone spraying pesticides. In practice, the executing entity can add the predicted invasive soil quality distribution information and the Spartina alterniflora identification and monitoring information to the prompt word template of a large language model to obtain Spartina alterniflora re-emergence prompt words. Then, the aforementioned Spartina alterniflora resurgence warning words and the preset expert knowledge base are input into the large language model to obtain Spartina alterniflora resurgence prevention scheme information. The preset expert knowledge base can be the vector database corresponding to the "Technical Guidelines for Spartina alterniflora Control" document. Next, the aforementioned Spartina alterniflora resurgence prevention scheme information, the aforementioned predicted invasive soil quality distribution information, and the aforementioned Spartina alterniflora identification and monitoring information are input into a preset report template to obtain an urban construction report. The preset report template can be a pre-defined report template. Finally, in response to the confirmation that the urban construction report has been approved, the current clearing scheme and the post-clearing resurgence control scheme given in the urban construction report are parsed to obtain equipment control instructions. Finally, the aforementioned equipment control instructions are burned into the aforementioned Spartina alterniflora control equipment to control the Spartina alterniflora control equipment to perform area clearing and resurgence treatment according to the aforementioned equipment control instructions. The aforementioned current clearing scheme can be the clearing planning path and cutting depth scheme for the Spartina alterniflora harvester output by the large language model. The above-mentioned re-emergence management scheme can be a scheme in which the large language model outputs a clearing process followed by a second clearing at preset intervals (e.g., spraying a clearing agent using a drone). The preset interval can be a pre-set interval between each clearing, and can be 3 days.

[0087] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an urban construction report generation device based on remote sensing satellite resource scheduling. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this urban construction report generation device based on remote sensing satellite resource scheduling can be specifically applied to various electronic devices.

[0088] like Figure 3 As shown, a city construction report generation device 300 based on remote sensing satellite resource scheduling includes: a first determining unit 301, a transmission unit 302, a wetland edge identification unit 303, a second determining unit 304, a *Spartina alterniflora* identification unit 305, a cascaded soil quality prediction unit 306, a soil quality prediction unit 307, and a report generation unit 308. The first determining unit 301 is configured to: determine a satellite observation transmission resource scheduling route set for transmitting a set of remote sensing images of tidal flat wetlands collected in a tidal flat wetland area via satellite internet. The transmission unit 302 is configured to: transmit the remote sensing images of the tidal flat wetlands according to the aforementioned satellite observation transmission resource scheduling route set, thereby obtaining a target tidal flat wetland remote sensing image set. The wetland edge identification unit 303 is configured to: perform wetland edge identification on the target tidal flat wetland remote sensing image set, thereby obtaining a wetland edge identification image set, wherein the wetland edge identification image set includes a set of wetland water area edge marking lines. The second determining unit 304 is configured to: determine the Spartina alterniflora monitoring and identification area from the wetland edge identification image set based on a preset buffer radius and the aforementioned wetland water area edge marking line set. The Spartina alterniflora identification unit 305 is configured to: determine the target monitoring area information from the aforementioned Spartina alterniflora monitoring and identification area based on historical Spartina alterniflora monitoring results, and perform Spartina alterniflora identification on the aforementioned target monitoring area information to obtain Spartina alterniflora identification monitoring information. The cascaded soil quality prediction unit 306 is configured to: perform cascaded soil quality prediction on the wetland image set of the aforementioned target monitoring area information captured by the UAV and the target tidal flat wetland remote sensing image set corresponding to the aforementioned target monitoring area information to obtain multi-source cascaded soil quality prediction distribution information. The soil quality prediction unit 307 is configured to: perform soil quality prediction on the historical Spartina alterniflora invasion soil quality information sequence and the aforementioned multi-source cascaded soil quality prediction distribution information to obtain predicted invasion soil quality distribution information. The report generation unit 308 is configured to: generate an urban construction report on Spartina alterniflora control information and invasive soil remediation information for the target monitoring area based on the above-mentioned predicted invasive soil quality distribution information and the above-mentioned Spartina alterniflora identification and monitoring information; and control the Spartina alterniflora control equipment to perform area removal treatment based on the urban construction report.

[0089] It is understandable that the units recorded in the urban construction report generation device 300 based on remote sensing satellite resource scheduling are related to the reference... Figure 1 The steps described in the method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the urban construction report generation device 300 based on remote sensing satellite resource scheduling and the units contained therein, and will not be repeated here.

[0090] The following is for reference. Figure 4It shows a schematic diagram of the structure of an electronic device (e.g., an electronic device) 400 suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0091] like Figure 4 As shown, the electronic device 400 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory 402 or a program loaded from a storage device 408 into a random access memory 403. The random access memory 403 also stores various programs and data required for the operation of the electronic device 400. The processing unit 401, the read-only memory 402, and the random access memory 403 are interconnected via a bus 404. An input / output interface 405 is also connected to the bus 404.

[0092] Typically, the following devices can be connected to the input / output interface 405: input devices 406 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 408 including, for example, magnetic tape, hard disk, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0093] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a storage device 408, or installed from a read-only memory 402. When the computer program is executed by the processing device 401, it performs the functions defined in the methods of some embodiments of this disclosure.

[0094] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0095] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0096] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: determine, via satellite internet, a satellite observation transmission resource scheduling route set for transmitting a set of remote sensing images of tidal flat wetlands collected for the tidal flat wetland area; transmit the aforementioned tidal flat wetland remote sensing image set according to the aforementioned satellite observation transmission resource scheduling route set, to obtain a target tidal flat wetland remote sensing image set; perform wetland edge identification on the aforementioned target tidal flat wetland remote sensing image set, to obtain a wetland edge identification image set, wherein the aforementioned wetland edge identification image set includes a set of wetland water area edge marking lines; determine the monitoring and identification area of ​​*Spartina alterniflora* from the aforementioned wetland edge identification image set according to a preset buffer radius and the aforementioned wetland water area edge marking line set; and, based on historical monitoring results of *Spartina alterniflora*, determine the monitoring and identification area of ​​*Spartina alterniflora* from the aforementioned *Spartina alterniflora* monitoring and identification area. The system identifies target monitoring areas within the region and identifies *Spartina alterniflora* within these areas to obtain *Spartina alterniflora* identification and monitoring information. It then performs cascaded soil quality prediction on wetland image sets captured by drones and remote sensing images of corresponding target tidal flat wetlands within these areas to obtain multi-source cascaded soil quality prediction distribution information. Finally, it predicts soil quality based on historical *Spartina alterniflora* invasion soil quality information sequences and the multi-source cascaded soil quality prediction distribution information to obtain predicted invasion soil quality distribution information. Based on the predicted invasion soil quality distribution information and the *Spartina alterniflora* identification and monitoring information, it generates an urban construction report on *Spartina alterniflora* control and invasion soil remediation for the target monitoring areas. Based on the urban construction report, it controls *Spartina alterniflora* control equipment to perform area eradication treatment.

[0097] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0099] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0100] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for generating urban construction reports based on remote sensing satellite resource scheduling, comprising: Using satellite internet, determine the satellite observation transmission resource scheduling route set for transmitting remote sensing images of tidal flat wetlands collected in tidal flat wetland areas; Based on the satellite observation transmission resource scheduling routing set, the remote sensing image set of the tidal flat wetland is transmitted to obtain the remote sensing image set of the target tidal flat wetland. Wetland edge recognition is performed on the remote sensing image set of the target tidal flat wetland to obtain a wetland edge recognition image set, wherein the wetland edge recognition image set includes a set of wetland water area edge annotation lines; Based on the preset buffer radius and the set of wetland water area edge marking lines, the monitoring and identification area of ​​Spartina alterniflora is determined from the set of wetland edge identification images; Based on the historical monitoring results of Spartina alterniflora, target monitoring area information is determined from the Spartina alterniflora monitoring and identification area, and Spartina alterniflora is identified in the target monitoring area information to obtain Spartina alterniflora identification monitoring information; A cascaded soil quality prediction is performed on the wetland image set of the target monitoring area information captured by the UAV and the remote sensing image set of the target tidal wetland corresponding to the target monitoring area information to obtain multi-source cascaded soil quality prediction distribution information. Soil quality is predicted by analyzing the historical Spartina alterniflora invasion soil quality information sequence and the multi-source cascaded soil quality prediction distribution information to obtain the predicted invasion soil quality distribution information. Based on the predicted invasive soil quality distribution information and the Spartina alterniflora identification and monitoring information, an urban construction report is generated for the target monitoring area, including Spartina alterniflora control information and invasive soil remediation information. Based on the urban construction report, the Spartina alterniflora control equipment is controlled to perform area removal treatment.

2. The method according to claim 1, wherein, The process of performing wetland edge recognition on the remote sensing image set of the target tidal flat wetland to obtain a wetland edge recognition image set includes: The target tidal flat wetland remote sensing image set is preprocessed to obtain a preprocessed tidal flat wetland remote sensing image set. Edge recognition is performed on the preprocessed tidal wetland remote sensing image set to obtain an edge recognition result information set, wherein the edge recognition result information set includes a set of wetland water area edge coordinate sequences; Using the set of wetland water area edge coordinate sequences, edge annotation is performed on the preprocessed tidal wetland remote sensing image set to obtain a wetland edge recognition image set.

3. The method according to claim 1, wherein, The historical monitoring results of Spartina alterniflora include a set of coordinate sequences of historical growth areas of Spartina alterniflora; and The process of determining target monitoring area information from the Spartina alterniflora monitoring and identification area based on historical monitoring results of Spartina alterniflora, and identifying Spartina alterniflora in the target monitoring area information to obtain Spartina alterniflora identification monitoring information, includes: Using the coordinate sequences of Spartina alterniflora historical growth areas in the set of historical growth area coordinate sequences, the wetland edge recognition image set is marked with historical growth areas of Spartina alterniflora to obtain historical marked areas. The intersection area of ​​the historical marker area and the Spartina alterniflora monitoring and identification area in the wetland edge recognition image set is determined to obtain the overlapping area, which is used as the target monitoring area information; The historical monitoring results of Spartina alterniflora, the historical remote sensing image set of tidal flat wetlands corresponding to the historical monitoring results of Spartina alterniflora, the wetland edge identification image set, and the target monitoring area information are input into the key monitoring area monitoring model to obtain Spartina alterniflora identification and monitoring information, wherein the Spartina alterniflora identification and monitoring information includes a growth area coordinate sequence set and a reduced area coordinate sequence set.

4. The method according to claim 3, wherein, The process involves using the coordinate sequences of each historical growth region of Spartina alterniflora in the set of historical growth region coordinate sequences to mark the historical growth regions of Spartina alterniflora in the wetland edge recognition image set, resulting in historically marked regions, including: Obtain the set of historical tidal flat wetland remote sensing images corresponding to the historical monitoring results of Spartina alterniflora; Feature point matching processing is performed on the historical tidal wetland remote sensing image set and the wetland edge recognition image set to obtain feature point matching results; Using the feature point pair set in the feature point matching result, an equation for coordinate transformation is established from the historical tidal wetland remote sensing image set to the wetland edge recognition image set, resulting in the coordinate transformation equation; Based on the coordinate transformation equation, the coordinate sequence set of historical growth areas of Spartina alterniflora in the historical monitoring results of Spartina alterniflora is transformed to obtain the transformed coordinate sequence set of historical growth areas of Spartina alterniflora. Using the historical growth region transformation coordinate sequence set of Spartina alterniflora, the historical growth region of Spartina alterniflora is marked on the wetland edge recognition image set to obtain the historical marked region.

5. The method according to claim 1, wherein, The method of determining the satellite observation transmission resource scheduling route set for transmitting remote sensing images of tidal flat wetlands collected in the tidal flat wetland area via satellite internet includes: The satellite internet, which changes dynamically within a preset time period, is subjected to topological discretization to obtain a sequence of static topological subgraphs for satellite time slots; Generate a set of information for maximizing transmission throughput, minimizing transmission energy consumption, and data acquisition and transmission constraints for the satellite internet and the remote sensing image set of the tidal wetland; For each satellite time slot static topology subgraph in the sequence of satellite time slot static topology subgraphs, the following determination steps are performed: Based on the data acquisition and transmission constraint information set, the satellite time slot static topology subgraph is adjusted to obtain the adjusted static topology subgraph. Add transmission connection edges to the adjusted static topology subgraph to obtain the target static topology subgraph; Determine the transmission capacity weight set and transmission energy consumption weight set of the connection edge set included in the target static topology subgraph, and add the transmission capacity weight set and the transmission energy consumption weight set to the target static topology subgraph to obtain the target static weighted directed topology subgraph; Inter-layer time-directed edges are added to the obtained target static weighted directed topological subgraph sequence to obtain a time-varying topological graph of acquisition and transmission resources; Based on the information on maximizing transmission throughput and minimizing transmission energy consumption, resource path planning and scheduling are performed on the time-varying topology map of the acquisition and transmission resources to obtain a set of satellite observation transmission resource scheduling routes.

6. A device for generating urban construction reports based on remote sensing satellite resource scheduling, comprising: The first determining unit is configured to determine the satellite observation transmission resource scheduling route set for the transmission of remote sensing images of tidal flat wetlands collected for the tidal flat wetland area via satellite Internet; The transmission unit is configured to transmit the remote sensing image set of the tidal flat wetland according to the satellite observation transmission resource scheduling routing set, so as to obtain the target tidal flat wetland remote sensing image set. The wetland edge recognition unit is configured to perform wetland edge recognition on the remote sensing image set of the target tidal flat wetland to obtain a wetland edge recognition image set, wherein the wetland edge recognition image set includes a set of wetland water area edge marking lines; The second determining unit is configured to determine the Spartina alterniflora monitoring and identification area from the wetland edge identification image set based on a preset buffer radius and the set of wetland water area edge marking lines; The Spartina alterniflora identification unit is configured to determine target monitoring area information from the Spartina alterniflora monitoring and identification area based on historical monitoring results of Spartina alterniflora, and to identify Spartina alterniflora in the target monitoring area information to obtain Spartina alterniflora identification monitoring information; The cascaded soil quality prediction unit is configured to perform cascaded soil quality prediction on the wetland image set of the target monitoring area information captured by the UAV and the remote sensing image set of the target tidal wetland corresponding to the target monitoring area information, so as to obtain multi-source cascaded soil quality prediction distribution information. The soil quality prediction unit is configured to predict soil quality based on the historical Spartina alterniflora invasion soil quality information sequence and the multi-source cascaded soil quality prediction distribution information, thereby obtaining the predicted invasion soil quality distribution information. The report generation unit is configured to generate an urban construction report on Spartina alterniflora control information and invasive soil remediation information for the target monitoring area based on the predicted invasive soil quality distribution information and the Spartina alterniflora identification and monitoring information, and to control Spartina alterniflora control equipment to perform area removal treatment based on the urban construction report.

7. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images