Farmland heavy metal remediation path planning system driven by UAV remote sensing data

Abstract

The present invention discloses a farmland heavy metal remediation path planning system based on unmanned aerial vehicle remote sensing data, which relates to the field of farmland remediation technology. The system comprises: a data acquisition module configured to collect real-time remote sensing image data; a pollution remediation sub-area division module configured to divide the pollution remediation sub-areas; an attribute recognition module configured to identify plot attribute information; a heavy metal remediation means evaluation module configured to evaluate the initial remediation coefficient; a pollution remediation sub-area correlation effect evaluation module configured to evaluate the remediation migration effect; a composite remediation coefficient calculation module configured to comprehensively evaluate the composite remediation coefficient; a global remediation optimization module configured to globally plan the heavy metal remediation means to be implemented in each pollution remediation sub-area; and a solution output module configured to output the remediation path for each heavy metal remediation means. The present invention has the advantage of providing powerful intelligent decision-making support for the efficient, accurate, and coordinated remediation of complex farmland heavy metal pollution.

Description

Technical Field

[0001] The present invention relates to the field of farmland restoration technology, and in particular to a farmland heavy metal restoration path planning system driven by unmanned aerial vehicle (UAV) remote sensing data. Background Art

[0002] Remediation of heavy metal contamination in farmland soil is a complex and critical environmental remediation task. Currently, planning for this type of remediation primarily relies on data from limited locations obtained through manual field sampling, combined with expert experience and simple cost-benefit analysis. This approach has significant limitations. First, farmland is highly spatially heterogeneous, making it difficult for these point-by-point sampling data to comprehensively and accurately depict the entire contaminated area. In particular, the complex spatial patterns of heavy metal concentrations and the spatial variations in soil properties that influence remediation effectiveness are difficult to fully and accurately capture. This leads to insufficient understanding of the environmental characteristics and remediation needs of different areas within the contaminated area, resulting in a "one-size-fits-all" approach to remediation plans and the inability to achieve precise, targeted, and categorized implementation. Second, traditional planning approaches seriously overlook the potential interrelated effects of remediation measures during spatial implementation. Heavy metal contaminants and their remediation agents can migrate through the environment due to water flow, wind, or their own diffusion characteristics. This means that the effects of heavy metal remediation measures implemented in one sub-area can often ripple through neighboring or even more distant sub-areas. Existing methods generally lack systematic assessment and quantitative consideration of these spatial interrelated effects, resulting in potentially inefficient and costly plans, and even unintended secondary pollution or counterproductive effects.

[0003] With the development of UAV remote sensing technology, it has shown advantages in obtaining large-scale, high-resolution spectral information of farmland, providing a new data source for depicting the spatial distribution of pollution. However, existing research and application of farmland heavy metal remediation based on spatial data mainly focus on pollution identification, mapping and risk assessment. In the actual planning stage of remediation measures, although some spatial information has been introduced, the core problem has not been fundamentally solved: how to efficiently use high-resolution spatial data to deeply understand the specific remediation background of each sub-unit in the region, and on this basis, how to quantitatively measure and integrate the spatial impact effects of implementing heavy metal remediation measures in specific sub-units on other sub-units. The lack of in-depth mining and comprehensive application of these two aspects of information makes it difficult for existing methods to generate a truly globally optimal remediation implementation path planning plan that truly considers the overall spatial synergy of remediation measures. Summary of the Invention

[0004] In order to solve the above technical problems, a farmland heavy metal remediation path planning system driven by UAV remote sensing data is provided. This technical solution solves the problem that the above-mentioned existing technologies lack in-depth mining and comprehensive application of these two aspects of information, making it difficult for existing methods to generate a truly globally optimal remediation implementation path planning plan that truly considers the overall spatial synergy of remediation measures.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] The farmland heavy metal remediation path planning system based on UAV remote sensing data includes:

[0007] A data acquisition module configured to acquire historical heavy metal pollution basic data of the target farmland pollution area and real-time remote sensing image data covering the target farmland pollution area collected by a multispectral or hyperspectral sensor carried by an unmanned aerial vehicle;

[0008] The pollution remediation sub-area division module is configured to divide the target farmland pollution area into N pollution remediation sub-areas (S1, S2, ..., S N ), where N is the number of pollution remediation sub-areas divided into target farmland pollution areas;

[0009] Attribute recognition module, the attribute recognition module is configured to combine the real-time remote sensing image data to identify each of the pollution repair sub-areas S i (i=1, 2, ..., N) plot attribute information, wherein the plot attribute information includes at least one or more of a soil heavy metal pollutant concentration distribution map, soil type, land use status, crop distribution, and surface cover status;

[0010] A heavy metal remediation means evaluation module is configured to evaluate the initial remediation coefficient of each available heavy metal remediation means for the contaminated remediation sub-area based on the land attribute information of the contaminated remediation sub-area;

[0011] The pollution repair sub-region association effect evaluation module is configured to evaluate the pollution repair sub-region association effect evaluation in any pollution repair sub-region S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l (l≠k) The resulting repair migration effect;

[0012] A composite remediation coefficient calculation module is configured to combine the initial remediation coefficient and the remediation migration effect to comprehensively evaluate the composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area;

[0013] The global remediation path optimization module is configured to globally plan the heavy metal remediation measures to be implemented in each pollution remediation sub-area based on the composite remediation coefficient when each heavy metal remediation measure is implemented in each pollution remediation sub-area;

[0014] The solution output module is configured to output the remediation path of each heavy metal remediation method in the form of a visual map based on the heavy metal remediation methods implemented in each pollution remediation sub-area.

[0015] Optionally, the evaluating of the initial remediation coefficient of each available heavy metal remediation method for the pollution remediation sub-area based on the land parcel attribute information of the pollution remediation sub-area specifically includes:

[0016] Obtain M heavy metal remediation methods (R1, R2, ..., R j ,..,R M )’s technical parameters, R j is the jth heavy metal remediation method that can be used for the target farmland, and M is the number of types of heavy metal remediation methods that can be used for the target farmland;

[0017] For each of the contaminated repair sub-regions S i and each of the heavy metal remediation means R j (j=1,2,...,M), repair sub-region S based on the pollution i The land property information and heavy metal remediation methods R j The technical parameters are calculated in the pollution remediation sub-area S i Implement heavy metal remediation measures alone j Repair difficulty index D ij and in the pollution repair sub-area S i Implement heavy metal remediation measures alone j The initial repair rate index E that can be achieved ij ;

[0018] The difficulty index D will be repaired ij and the initial repair rate index E ij As the initial remediation coefficient of the jth heavy metal remediation method for the i-th contaminated remediation sub-area.

[0019] Optionally, the evaluation is performed in any pollution remediation sub-area S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l The repair and migration effects generated by (l≠k) specifically include:

[0020] Determining the spatial topological relationship between the N pollution remediation sub-regions;

[0021] Based on the spatial topological relationship and each heavy metal remediation method R j The physical mechanism or chemical migration characteristics of the pollution remediation sub-area S k (k=1,2,...,N) Implement heavy metal remediation measures R j When , all other polluted sub-regions S associated with it are repaired l (l≠k) The repair migration effect T kjl ;

[0022] For each contaminated repair sub-region S k and each heavy metal remediation method R j , summarize and analyze the implementation of this method R j Repair the contaminated sub-region S k All the collateral effects brought by the associated pollution remediation sub-area are evaluated and obtained in the pollution remediation sub-area S k Implementation of heavy metal remediation measures j Factor F affecting the joint restoration effect of the pollution restoration sub-area kj .

[0023] Optionally, the composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area by combining the initial remediation coefficient and the remediation migration effect specifically includes:

[0024] Based on the initial repair rate index E ij Factor F affecting the joint restoration effect of the pollution restoration sub-area ij Perform normalized weighted summation to obtain the composite remediation index when implementing heavy metal remediation measures in the pollution remediation sub-area;

[0025] Based on the TOPSIS method, the composite remediation coefficient of all heavy metal remediation measures implemented in the pollution remediation sub-area is calculated by combining the composite remediation index and remediation difficulty index when all heavy metal remediation measures are implemented in the pollution remediation sub-area.

[0026] Optionally, the global planning of the heavy metal remediation measures to be implemented in each pollution remediation sub-area based on the composite remediation coefficient when each heavy metal remediation measure is implemented in each pollution remediation sub-area specifically includes:

[0027] To be applied to the pollution repair sub-area S k The initial remediation rate index of its own heavy metal remediation means and its application in other pollution remediation sub-areas S l (l≠k) Repair the contaminated sub-region S k The cumulative effect of the repair migration generated exceeds the contaminated repair sub-area Sk The restoration target and the number of heavy metal restoration methods implemented in each pollution restoration sub-area are restricted to no more than n types, where n is the upper limit of heavy metal restoration methods implemented in a single pollution restoration sub-area;

[0028] Construct a scheme evaluation function, take the minimum value of the scheme evaluation function as the goal, and globally search for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area within the constraints.

[0029] Optionally, the construction scheme evaluation function specifically includes:

[0030] The remediation difficulty index of heavy metal remediation measures implemented in all pollution remediation sub-areas in the plan is accumulated to obtain the global difficulty index;

[0031] The global restoration redundancy index is obtained by summing up the initial restoration rate index of the heavy metal restoration means in all pollution restoration sub-areas in the scheme and the ratio of the cumulative restoration migration effect of the restoration means applied to other pollution restoration sub-areas to the restoration target of the pollution restoration sub-area.

[0032] After normalization based on the global difficulty index and the global repair redundancy index, the weighted sum is used as the solution evaluation function.

[0033] Optionally, when taking the minimum value of the scheme evaluation function as the goal and globally searching for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area within the constraints, priority is given to adding heavy metal remediation measures with a large composite remediation coefficient to each pollution remediation sub-area.

[0034] Optionally, the output of the remediation path of each heavy metal remediation method in the form of a visual map based on the heavy metal remediation method implemented in each pollution remediation sub-area specifically includes:

[0035] Based on the heavy metal remediation measures implemented in each pollution remediation sub-area, cluster extraction of the same heavy metal remediation measures is performed to obtain the pollution remediation sub-area corresponding to each heavy metal remediation measure;

[0036] Determine the movable area within the target farmland pollution area based on real-time remote sensing image data of the target farmland pollution area;

[0037] Based on the pollution remediation sub-area corresponding to each heavy metal remediation method, the shortest remediation path is constructed within the movable area within the target farmland pollution area as the optimal remediation path for the heavy metal remediation method;

[0038] Summarize the optimal remediation paths of all heavy metal remediation methods, and output the optimal remediation path of each heavy metal remediation method in the form of a visual map.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention accurately depicts the spatial heterogeneity distribution characteristics of heavy metal pollution in the entire target farmland area and the accompanying land attribute difference information by efficiently acquiring and utilizing UAV remote sensing image data, providing solid and comprehensive spatial data support for subsequent analysis. It realizes the scientific quantification of the spatial collateral impact of remediation measures during implementation. It no longer evaluates the remediation effect of a single sub-region in isolation, but fully considers and quantifies the cross-regional impact of the implementation of heavy metal remediation measures in a specific sub-region, which is either promoted or inhibited by natural migration or conduction on its associated sub-regions. This solution also constructs a comprehensive remediation efficiency evaluation value that integrates the basic remediation efficiency of the region and the cross-regional synergistic effect as the core optimization basis. Based on this evaluation value, the cost input and the expected remediation goals are comprehensively considered, and the optimization algorithm is applied to conduct multi-dimensional collaborative optimization on a global scale. Intelligent decision-making generates a remediation implementation strategy with the best overall cost-effectiveness ratio. The strategy also clarifies the preferred areas and implementation sequence of different heavy metal remediation methods. Finally, the output of a visual specific remediation execution path map combined with the site access conditions greatly improved the on-site guidance and operability of the remediation construction, and provided strong intelligent decision-making support for the efficient, accurate and coordinated remediation of heavy metal pollution in complex farmland. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a block diagram of the farmland heavy metal remediation path planning system based on UAV remote sensing data proposed in Example 1;

[0042] Figure 2 This is a flow chart of evaluating the initial repair coefficient proposed in Example 1;

[0043] Figure 3 This is a flowchart of evaluating the repair migration effect proposed in Example 1;

[0044] Figure 4 Flowchart of constructing the scheme evaluation function for embodiment 1

[0045] Figure 5 This is a block diagram of the farmland heavy metal remediation path planning system based on UAV remote sensing data proposed in Example 2;

[0046] Figure 6 This is a flowchart of the remediation path for each heavy metal remediation method, which is output in the form of a visual map, as proposed in Example 3. DETAILED DESCRIPTION

[0047] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0048] Example 1:

[0049] Reference Figure 1 As shown in the figure, the farmland heavy metal remediation path planning system driven by UAV remote sensing data includes:

[0050] A data acquisition module, the data acquisition module is configured to obtain historical heavy metal pollution basic data of the target farmland pollution area and real-time remote sensing image data covering the target farmland pollution area collected by a multispectral or hyperspectral sensor carried by an unmanned aerial vehicle;

[0051] By integrating historical pollution data with high-resolution, real-time remote sensing data from drones, the limitations of traditional point sampling and static data are overcome, ensuring that the information relied upon for subsequent analysis has the advantages of high timeliness, spatial continuity, and wide coverage.

[0052] The pollution remediation sub-area division module is configured to divide the target farmland pollution area into N pollution remediation sub-areas (S1, S2, ..., S N ), where N is the number of pollution remediation sub-regions divided from the target farmland pollution area. When dividing the pollution remediation sub-regions, a spatial clustering algorithm or a method based on a predefined pollution severity threshold is used to divide the target farmland area;

[0053] Attribute recognition module, the attribute recognition module is configured to combine real-time remote sensing image data to identify each pollution remediation sub-area S i (i=1, 2, ..., N) plot attribute information, the plot attribute information including at least one or more of soil heavy metal pollutant concentration distribution map, soil type, land use status, crop distribution, and surface cover status;

[0054] By extracting key spatial attribute information that affects remediation effectiveness, such as accurate heavy metal distribution maps and soil environmental status, the system can deeply understand the differences in remediation backgrounds and specific constraints within each sub-region, improving the scientific nature and pertinence of subsequent remediation effectiveness evaluations.

[0055] A heavy metal remediation means evaluation module is configured to evaluate the initial remediation coefficient of each available heavy metal remediation means for the contaminated remediation sub-area based on the land attribute information of the contaminated remediation sub-area;

[0056] Objective quantitative evaluation of the effectiveness and difficulty of implementing multiple heavy metal remediation methods in a single sub-area provides a scientific and comparable evaluation basis for selecting the basic heavy metal remediation method that best suits the characteristics of the area;

[0057] The pollution repair sub-region association effect evaluation module is configured to evaluate the pollution repair sub-region association effect evaluation in any pollution repair sub-region S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l (l≠k) The resulting repair migration effect;

[0058] The cross-regional synergistic or interfering effects of heavy metal remediation measures were quantified, enabling a systematic understanding of the environmental impact of a single remediation action at a larger spatial scale, thus avoiding suboptimal or even ineffective planning caused by ignoring regional connections.

[0059] The global remediation path optimization module is configured to globally plan the heavy metal remediation measures to be implemented in each pollution remediation sub-area based on the composite remediation coefficient when each heavy metal remediation measure is implemented in each pollution remediation sub-area;

[0060] Under a unified framework, we comprehensively consider the costs, effectiveness targets, and their mutual impact across all regions, and use a global optimization algorithm to identify the optimal strategy combination for overall benefits. This achieves the coordinated deployment of restoration resources in spatial dimensions and the optimal timing, ensuring the optimality of the solution at the global level.

[0061] The solution output module is configured to output the remediation path of each heavy metal remediation method in the form of a visual map based on the heavy metal remediation methods implemented in each pollution remediation sub-area.

[0062] The abstract and complex optimization results are converted into intuitive and visual spatial path maps, which clearly show the implementation scope and route of each heavy metal remediation method. This greatly enhances the comprehensibility of the plan and the operability of on-site construction, provides strong implementation guidance for engineering personnel, and reduces the risk of implementation deviation.

[0063] Reference Figure 2 As shown in the figure, based on the land attribute information of the pollution remediation sub-area, the initial remediation coefficient of each available heavy metal remediation method for the pollution remediation sub-area is evaluated, including:

[0064] Obtain M heavy metal remediation methods (R1, R2, ..., R j ,..,R M )’s technical parameters, R jis the jth heavy metal remediation method that can be used for the target farmland, and M is the number of types of heavy metal remediation methods that can be used for the target farmland;

[0065] For each contaminated repair sub-region S i and each heavy metal remediation method R j (j=1,2,...,M), repair sub-region S based on the pollution i Land property information and heavy metal remediation methods R j The technical parameters are calculated in the pollution remediation sub-area S i Implement heavy metal remediation measures alone j Repair difficulty index D ij and in the pollution remediation sub-area S i Implement heavy metal remediation measures alone j The initial repair rate index E that can be achieved ij ;

[0066] The difficulty index D will be repaired ij and the initial repair rate index E ij As the initial remediation coefficient of the jth heavy metal remediation method for the i-th contaminated remediation sub-area.

[0067] By integrating the technical characteristics of specific heavy metal remediation methods with the specific environmental attributes of the target sub-area, the remediation difficulty index and the initial remediation rate index are quantitatively generated and used together as the initial remediation coefficient. A set of objective and quantitative evaluation standards has been established, which effectively overcomes the subjectivity and ambiguity of traditional reliance on empirical judgment. By simultaneously considering the actual operational difficulty of implementing the method, reflecting the cost, resource requirements, technical feasibility and the theoretical remediation efficiency that can be achieved in the regional environment, this evaluation method provides a more balanced and comprehensive basic performance measurement method. It lays a scientific basis for the subsequent screening of basic remediation options that are both technically feasible and have remediation benefits in specific areas, avoiding the problem of "effect-only theory" leading to infeasible operation or "cost-only theory" leading to poor results when designing the plan, and significantly improves the scientificity and practicality of the initial remediation strategy matching.

[0068] Reference Figure 3 As shown, the evaluation is performed in any pollution repair sub-area S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l The repair and migration effects generated by (l≠k) specifically include:

[0069] Determine the spatial topological relationship between N pollution remediation sub-areas;

[0070] Based on the spatial topological relationship and each heavy metal remediation method Rj The physical mechanism or chemical migration characteristics of the pollution remediation sub-area S k (k=1,2,...,N) Implement heavy metal remediation measures R j When , all other polluted sub-regions S associated with it are repaired l (l≠k) The repair migration effect T kjl , in evaluating the effect of repair migration T kjl When evaluating the remediation effect, comprehensively consider one or more factors including the spatial distance of the pollution remediation sub-area, hydrological flow direction, groundwater direction, dominant wind direction, soil texture differences, and the physical and chemical migration characteristics of the pollutants themselves. Based on the comprehensive consideration of multiple factors and combined with the experience of heavy metal remediation, comprehensively evaluate the remediation and migration effect;

[0071] For each contaminated repair sub-region S k and each heavy metal remediation method R j , summarize and analyze the implementation of this method R j Repair the contaminated sub-region S k All the collateral effects brought by the associated pollution remediation sub-area are evaluated and obtained in the pollution remediation sub-area S k Implementation of heavy metal remediation measures j Factor F affecting the joint restoration effect of the pollution restoration sub-area kj .

[0072] Specifically, F kj The calculation formula is:

[0073]

[0074] Among them, α l Repair sub-region S for other pollution l For heavy metal remediation means R j The response weight of the repair impact caused, X k Repair sub-region S for pollution k All associated pollution repair sub-areas, l is the pollution repair sub-area S k The lth associated pollution remediation sub-region, where the response weight is determined by the heavy metal remediation means R j and pollution repair sub-area S l The repair adaptability is determined by the response weight. For example, for low permeability areas, it is difficult to achieve a good migration effect by in situ elution. At this time, the response weight is reduced.

[0075] By analyzing the spatial topological relationships between remediation subregions and comprehensively considering the unique physicochemical migration mechanisms of heavy metal remediation measures and various environmental drivers, such as distance, water flow, wind direction, soil properties, and pollutant properties, this study scientifically quantifies the potential transfer of remediation effects to associated subregions when a single remediation action is implemented in a specific subregion. Crucially, the study introduces a dynamic response weight based on "remediation suitability." This weight objectively reflects the conditions of the associated subregion, such as the impact of low-permeability soils on leaching and their receptivity to migration effects, thus avoiding the bias caused by simple linear superposition. Finally, by weighting the migration effects within the associated subregions according to their response weights, a comprehensive impact factor on other subregions when a heavy metal remediation measure is implemented in a specific subregion is derived. This assessment mechanism systematically models and quantifies complex spatial correlation effects with the environmental response characteristics of the recipient region. It captures the complexity of cross-regional remediation impacts in a more realistic and dynamic manner, providing a crucial and reliable quantitative input parameter for balancing local and global effectiveness in subsequent global optimization, avoiding waste of remediation resources or misjudgment of remediation effects due to ignoring specific regional characteristics. This significantly improves the scientific accuracy of restoration planning in the spatial coordination dimension.

[0076] Based on the composite remediation coefficient when implementing each heavy metal remediation method in each pollution remediation sub-area, a global plan is made to implement the heavy metal remediation methods in each pollution remediation sub-area, specifically including:

[0077] To be applied to the pollution repair sub-area S k The initial remediation rate index of its own heavy metal remediation means and its application in other pollution remediation sub-areas S l (l≠k) Repair the contaminated sub-region S k The cumulative effect of the repair migration generated exceeds the contaminated repair sub-area S k The restoration target and the number of heavy metal restoration methods implemented in each pollution restoration sub-area are restricted to no more than n types, where n is the upper limit of heavy metal restoration methods implemented in a single pollution restoration sub-area;

[0078] Construct a scheme evaluation function, take the minimum value of the scheme evaluation function as the goal, and globally search for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area within the constraints.

[0079] Reference Figure 4 As shown in the figure, the construction scheme evaluation function specifically includes:

[0080] The remediation difficulty index of heavy metal remediation measures implemented in all pollution remediation sub-areas in the plan is accumulated to obtain the global difficulty index;

[0081] The global restoration redundancy index is obtained by summing up the initial restoration rate index of the heavy metal restoration means in all pollution restoration sub-areas in the scheme and the ratio of the cumulative restoration migration effect of the restoration means applied to other pollution restoration sub-areas to the restoration target of the pollution restoration sub-area.

[0082] After normalization based on the global difficulty index and the global repair redundancy index, the weighted sum is used as the solution evaluation function.

[0083] This embodiment constructs a two-dimensional quantitative evaluation system that takes into account both the total implementation cost and the redundancy of restoration efficiency. By accumulating the restoration difficulty index of all contaminated restoration sub-areas, the system accurately quantifies the comprehensive resource consumption and operational complexity of the overall project implementation under the selected scheme, such as working hours, equipment requirements, and material costs, providing a core basis for cost control; at the same time, by calculating the ratio of the total actual restoration effect value of each sub-area to its restoration target value and accumulating them, the comprehensive restoration efficiency redundancy level of the entire scheme is innovatively measured. After scientific normalization to eliminate dimensional differences, the two are fused into a single evaluation function value based on preset weights. This function takes minimization as the optimization goal. Under the premise of forcing all areas to meet the restoration standards and the number of means in a single area to be met, it drives the optimization algorithm to automatically screen out the golden balance point plan with the lowest comprehensive cost, the most reasonable restoration efficiency redundancy, and the most balanced global resource allocation. It achieves refined control of the overall cost-effectiveness of the restoration project under strict constraints, significantly improving the economy, reliability and resource utilization efficiency of large-scale farmland restoration projects.

[0084] Example 2:

[0085] Reference Figure 5 As shown, based on the first embodiment, the farmland heavy metal remediation path planning system based on drone remote sensing data driven by this embodiment further includes:

[0086] A composite remediation coefficient calculation module is configured to combine the initial remediation coefficient and the remediation migration effect to comprehensively evaluate the composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area;

[0087] Specifically, the composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area is comprehensively evaluated by combining the initial remediation coefficient and the remediation migration effect. Specifically, it includes:

[0088] Based on the initial repair rate index E ij Factor F affecting the joint restoration effect of the pollution restoration sub-area ij Perform normalized weighted summation to obtain the composite remediation index when implementing heavy metal remediation measures in the pollution remediation sub-area;

[0089] Based on the TOPSIS method, the composite remediation coefficient of all heavy metal remediation measures implemented in the pollution remediation sub-area is calculated by combining the composite remediation index and remediation difficulty index when all heavy metal remediation measures are implemented in the pollution remediation sub-area.

[0090] Specifically, the calculation process of the composite repair coefficient is:

[0091] After normalizing the composite repair index and the repair difficulty index to eliminate the dimension effect;

[0092] The maximum value of the composite repair index and the minimum value of the repair difficulty index are selected as the optimal combination;

[0093] The minimum value of the composite repair index and the maximum value of the repair difficulty index are selected as the worst combination;

[0094] Based on the composite restoration index and restoration difficulty index of each heavy metal restoration method, the composite restoration coefficient is calculated comprehensively with the optimal combination and the worst combination;

[0095]

[0096] Among them, IC ij is the composite remediation coefficient when the jth heavy metal remediation method is implemented in the i-th pollution remediation sub-area, D + is the maximum value of the composite repair index, D - is the minimum value of the composite repair index, FE - The minimum value of the repair difficulty index, FE + The maximum value of the repair difficulty index, FE ij It is the composite remediation index when the jth heavy metal remediation method is implemented in the i-th pollution remediation sub-area.

[0097] In this embodiment, with the goal of minimizing the scheme evaluation function, within the constraints, when globally searching for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area, priority is given to adding heavy metal remediation measures with a large composite remediation coefficient to each pollution remediation sub-area.

[0098] In this embodiment, a composite repair coefficient is introduced to comprehensively reflect the influence of the inter-regional correlation in region S. i Implementation of heavy metal remediation measures j The overall effectiveness of the method is improved, and when performing global optimization, priority is given to adding heavy metal remediation methods with high composite remediation coefficients in each area to ensure that heavy metal remediation methods with high overall effectiveness can be selected first, thereby effectively shortening the calculation time of the global optimization and improving the efficiency of the global optimization algorithm.

[0099] Example 3:

[0100] Reference Figure 6 As shown, based on the first embodiment, this embodiment further proposes:

[0101] Based on the heavy metal remediation measures implemented in each pollution remediation sub-area, the remediation path of each heavy metal remediation measure is output in the form of a visual map, including:

[0102] Based on the heavy metal remediation measures implemented in each pollution remediation sub-area, cluster extraction of the same heavy metal remediation measures is performed to obtain the pollution remediation sub-area corresponding to each heavy metal remediation measure;

[0103] Determine the movable area within the target farmland pollution area based on real-time remote sensing image data of the target farmland pollution area;

[0104] Based on the pollution remediation sub-area corresponding to each heavy metal remediation method, the shortest remediation path is constructed within the movable area within the target farmland pollution area as the optimal remediation path for the heavy metal remediation method;

[0105] Summarize the optimal remediation paths of all heavy metal remediation methods, and output the optimal remediation path of each heavy metal remediation method in the form of a visual map. Among them, the optimal remediation paths of different heavy metal remediation methods are output with different labels, and the optimal remediation path of each heavy metal remediation method can be displayed separately.

[0106] By automatically clustering the regional distribution of similar heavy metal remediation methods, fragmented regional decisions are integrated into construction units classified by technology, providing clear goals for equipment scheduling. Based on real-time remote sensing imagery to identify traversable areas, the shortest moving path is planned for each technical unit under the constraints of the actual site, significantly reducing the equipment's idling distance and time costs. Finally, through multi-dimensional visualization output, the optimal construction route map for various heavy metal remediation methods is intuitively presented, transforming complex global remediation plans into clear operating instructions that can be executed in steps and regions. This not only significantly reduces the coordination difficulty and risk of misoperation at the construction site, but also reduces equipment energy consumption and operation time through precise route planning, comprehensively improving the implementation efficiency and economy of farmland remediation projects from the execution level, and ultimately achieving closed-loop management of the entire process.

[0107] In summary, the advantages of the present invention are: by efficiently acquiring and utilizing UAV remote sensing image data, the spatial heterogeneity distribution characteristics of heavy metal pollution in the entire target farmland area and the accompanying land attribute difference information are accurately portrayed, providing solid and comprehensive spatial data support for subsequent analysis. It realizes the scientific quantification of the spatial joint impact of remediation measures during implementation. Instead of evaluating the remediation effect of a single sub-region in isolation, it fully considers and quantifies the cross-regional impact of the natural migration or conduction effect on its associated sub-regions when implementing heavy metal remediation measures in a specific sub-region. This solution also constructs a comprehensive remediation efficiency evaluation value that integrates the basic remediation efficiency of the region and the cross-regional synergistic effect as the core optimization basis. Based on this evaluation value, the cost input and the expected remediation target are comprehensively considered, and the optimization algorithm is applied to conduct multi-dimensional collaborative optimization on a global scale. Intelligent decision-making generates a remediation implementation strategy with the best overall cost-effectiveness ratio. The strategy also clarifies the preferred areas and implementation order of different heavy metal remediation methods. Finally, the output of a visual specific remediation execution path map combined with the site access conditions greatly improved the on-site guidance and operability of the remediation construction, and provided strong intelligent decision-making support for the efficient, accurate and coordinated remediation of heavy metal pollution in complex farmland.

[0108] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A farmland heavy metal remediation path planning system driven by UAV remote sensing data, characterized by: include: A data acquisition module configured to acquire historical heavy metal pollution basic data of the target farmland pollution area and real-time remote sensing image data covering the target farmland pollution area collected by a multispectral or hyperspectral sensor carried by an unmanned aerial vehicle; The pollution remediation sub-area division module is configured to divide the target farmland pollution area into N pollution remediation sub-areas (S1, S2, ..., S N ), where N is the number of pollution remediation sub-areas divided into target farmland pollution areas; Attribute recognition module, the attribute recognition module is configured to combine the real-time remote sensing image data to identify each of the pollution repair sub-areas S i (i=1, 2, ..., N) plot attribute information, wherein the plot attribute information includes at least one or more of a soil heavy metal pollutant concentration distribution map, soil type, land use status, crop distribution, and surface cover status; A heavy metal remediation means evaluation module is configured to evaluate the initial remediation coefficient of each available heavy metal remediation means for the contaminated remediation sub-area based on the land parcel attribute information of the contaminated remediation sub-area, wherein the initial remediation coefficient includes a remediation difficulty index and an initial remediation rate index; The pollution repair sub-region association effect evaluation module is configured to evaluate the pollution repair sub-region association effect evaluation in any pollution repair sub-region S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l (l≠k) The resulting repair migration effect; A composite remediation coefficient calculation module is configured to combine the initial remediation coefficient and the remediation migration effect to comprehensively evaluate the composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area; The global remediation path optimization module is configured to globally plan the heavy metal remediation measures to be implemented in each pollution remediation sub-area based on the composite remediation coefficient when each heavy metal remediation measure is implemented in each pollution remediation sub-area; A solution output module is configured to output the remediation path of each heavy metal remediation method in the form of a visual map based on the heavy metal remediation methods implemented in each pollution remediation sub-area; Wherein, the evaluation is performed in any pollution remediation sub-area S k When (k=1,2,...,N) implements heavy metal remediation measures, all other polluted remediation sub-areas S associated with it are l The repair and migration effects generated by (l≠k) specifically include: Determining the spatial topological relationship between the N pollution remediation sub-regions; Based on the spatial topological relationship and each heavy metal remediation method R j The physical mechanism of action or chemical migration characteristics, R j is the jth heavy metal remediation method that can be used in the target farmland, and the estimated k (k=1,2,...,N) Implement heavy metal remediation measures R j When , all other polluted sub-regions S associated with it are repaired l (l≠k) The repair migration effect T kjl ; For each contaminated repair sub-region S k and each heavy metal remediation method R j , summarize and analyze the implementation of this method R j Repair the contaminated sub-region S k All the collateral effects brought by the associated pollution remediation sub-area are evaluated and obtained in the pollution remediation sub-area S k Implementation of heavy metal remediation measures j Factor F affecting the joint restoration effect of the pollution restoration sub-area kj ; The above-mentioned heavy metal remediation measures implemented in each pollution remediation sub-area are globally planned based on the composite remediation coefficient when each heavy metal remediation measure is implemented in each pollution remediation sub-area, and specifically include: To be applied to the pollution repair sub-area S k The initial remediation rate index of its own heavy metal remediation means and its application in other pollution remediation sub-areas S l (l≠k) Repair the contaminated sub-region S k The cumulative effect of the repair migration generated exceeds the contaminated repair sub-area S k The restoration target and the number of heavy metal restoration methods implemented in each pollution restoration sub-area are restricted to no more than n types, where n is the upper limit of heavy metal restoration methods implemented in a single pollution restoration sub-area; Construct a scheme evaluation function, take the minimum value of the scheme evaluation function as the goal, and globally search for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area within the constraints.

2. The farmland heavy metal remediation path planning system based on UAV remote sensing data according to claim 1 is characterized in that: The evaluation of the initial remediation coefficient of each available heavy metal remediation method for the pollution remediation sub-area based on the land parcel attribute information of the pollution remediation sub-area specifically includes: Obtain M heavy metal remediation methods (R1, R2, ..., R j ,..,R M ), M is the number of heavy metal remediation methods that can be used in the target farmland; For each of the contaminated repair sub-regions S i and each of the heavy metal remediation means R j (j=1,2,...,M), repair sub-region S based on the pollution i The land property information and heavy metal remediation methods R j The technical parameters are calculated in the pollution remediation sub-area S i Implement heavy metal remediation measures alone j Repair difficulty index D ij and in the pollution repair sub-area S i Implement heavy metal remediation measures alone j The initial repair rate index E that can be achieved ij ; The difficulty index D will be repaired ij and the initial repair rate index E ij As the initial remediation coefficient of the jth heavy metal remediation method for the i-th contaminated remediation sub-area.

3. The farmland heavy metal remediation path planning system based on UAV remote sensing data according to claim 2 is characterized in that: The composite remediation coefficient when implementing heavy metal remediation measures in the pollution remediation sub-area, in combination with the initial remediation coefficient and the remediation migration effect, is comprehensively evaluated, specifically including: Based on the initial repair rate index E ij Factor F affecting the joint restoration effect of the pollution restoration sub-area ij Perform normalized weighted summation to obtain the composite remediation index when implementing heavy metal remediation measures in the pollution remediation sub-area; Based on the TOPSIS method, the composite remediation coefficient of all heavy metal remediation measures implemented in the pollution remediation sub-area is calculated by combining the composite remediation index and remediation difficulty index when all heavy metal remediation measures are implemented in the pollution remediation sub-area.

4. The farmland heavy metal remediation path planning system based on UAV remote sensing data according to claim 3 is characterized in that: The construction scheme evaluation function specifically includes: The remediation difficulty index of heavy metal remediation measures implemented in all pollution remediation sub-areas in the plan is accumulated to obtain the global difficulty index; The global restoration redundancy index is obtained by summing up the initial restoration rate index of the heavy metal restoration means in all pollution restoration sub-areas in the scheme and the ratio of the cumulative restoration migration effect of the restoration means applied to other pollution restoration sub-areas to the restoration target of the pollution restoration sub-area. After normalization based on the global difficulty index and the global repair redundancy index, the weighted sum is used as the solution evaluation function.

5. The farmland heavy metal remediation path planning system based on UAV remote sensing data according to claim 4 is characterized in that: The goal is to minimize the scheme evaluation function. Within the constraints, when globally searching for the optimal scheme for implementing heavy metal remediation measures in each pollution remediation sub-area, priority is given to adding heavy metal remediation measures with a large composite remediation coefficient to each pollution remediation sub-area.

6. The farmland heavy metal remediation path planning system based on UAV remote sensing data according to claim 1 is characterized in that: The heavy metal remediation measures implemented in each pollution remediation sub-area are output in the form of a visual map of the remediation path of each heavy metal remediation measure, specifically including: Based on the heavy metal remediation measures implemented in each pollution remediation sub-area, cluster extraction of the same heavy metal remediation measures is performed to obtain the pollution remediation sub-area corresponding to each heavy metal remediation measure; Determine the movable area within the target farmland pollution area based on real-time remote sensing image data of the target farmland pollution area; Based on the pollution remediation sub-area corresponding to each heavy metal remediation method, the shortest remediation path is constructed within the movable area within the target farmland pollution area as the optimal remediation path for the heavy metal remediation method; Summarize the optimal remediation paths of all heavy metal remediation methods, and output the optimal remediation path of each heavy metal remediation method in the form of a visual map.

Images