Satellite-based tailings pond risk level determination method and device

Abstract

The disclosure provides a satellite-based tailing pond risk level determination method and device, relating to the technical field of tailing pond monitoring, comprising: obtaining monitoring data fed back by a target satellite, the monitoring data being obtained by monitoring a tailing pond by the target satellite; processing the monitoring data to obtain a plurality of dimensionless indexes; determining a weight coefficient corresponding to each of the dimensionless indexes; and calculating a tailing pond risk comprehensive index based on the weight coefficient, the dimensionless indexes and the monitoring data. The disclosure realizes a fundamental change of tailing pond risk identification from "local, lagging and subjective" to "global, dynamic and quantitative" through a satellite remote sensing driven dimensionless multi-index fusion evaluation mechanism, which not only significantly improves the early discovery and accurate early warning capability of major safety risks, but also provides a feasible and popularized intelligent solution for preventing catastrophic accidents such as dam collapse with a low-cost, high-efficiency and strong expansion technical path.

Description

Technical Field

[0001] This disclosure relates to the field of tailings dam monitoring technology, and in particular to a satellite-based method and apparatus for determining the risk level of a tailings dam. Background Technology

[0002] Tailings dams, as crucial facilities for storing tailings slurry during mineral processing, directly impact the safety and property of downstream residents and the ecological environment. In recent years, with the increasing intensity of mineral resource development, the number of tailings dams has continued to rise. Some tailings dams face risks of dam settlement, displacement deformation, abnormal seepage, and even dam failure, posing significant safety hazards. Therefore, real-time, accurate, and dynamic monitoring and analysis of tailings dam operations are key to achieving risk warning and scientific management.

[0003] Current tailings dam risk assessment methods primarily rely on manual ground inspections, sensor deployment (such as wetting line, displacement, and seepage pressure monitoring), and engineering experience. However, these methods have significant limitations: first, the monitoring coverage is limited, making it difficult to comprehensively reflect the overall deformation and structural state of the tailings dam; second, sensors are susceptible to environmental interference, have high maintenance costs, and are difficult to deploy in remote or complex terrain areas; and third, the assessment process is highly subjective, lacking mechanisms for multi-source heterogeneous data fusion and quantitative analysis, making it difficult to achieve objective and dynamic updates of risk levels. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, one objective of this disclosure is to propose a satellite-based method for determining the risk level of tailings ponds.

[0006] The second objective of this disclosure is to propose a satellite-based device for determining the risk level of tailings ponds.

[0007] The third objective of this disclosure is to propose an electronic device.

[0008] The fourth objective of this disclosure is to provide a non-transitory computer-readable storage medium.

[0009] The fifth objective of this disclosure is to provide a computer program product.

[0010] To achieve the above objectives, the first aspect of this disclosure proposes a satellite-based method for determining the risk level of a tailings dam, comprising: acquiring monitoring data fed back by a target satellite, wherein the monitoring data is obtained by the target satellite monitoring the tailings dam; processing the monitoring data to obtain multiple dimensionless indicators; determining the weight coefficients corresponding to each of the dimensionless indicators; and calculating the comprehensive risk index of the tailings dam based on the weight coefficients, the dimensionless indicators, and the monitoring data.

[0011] According to one embodiment of this disclosure, the step of processing the monitoring data to obtain multiple dimensionless indicators includes: determining target indicator data from the monitoring data based on preset indicators; and standardizing the target indicator data to generate the dimensionless indicators.

[0012] According to one embodiment of this disclosure, the standardization process of the target indicator data to generate the dimensionless indicator includes: for any target indicator data, obtaining the indicator logic corresponding to the target indicator data; and performing extreme value standardization processing on the target indicator data based on the indicator logic to generate the dimensionless indicator corresponding to the target indicator data.

[0013] According to one embodiment of this disclosure, the step of processing the monitoring data to obtain multiple dimensionless indicators includes: acquiring historical monitoring data; for any target indicator data, calculating the key quantile of the target indicator data based on the historical monitoring data, and using the key quantile as the dimensionless indicator corresponding to the target indicator data.

[0014] According to one embodiment of this disclosure, determining the weight coefficients corresponding to each of the dimensionless indicators includes: obtaining safety specification data and / or empirical data corresponding to each of the dimensionless indicators; and calculating the weight coefficients corresponding to each of the dimensionless indicators based on the safety specification data and / or the empirical data.

[0015] According to one embodiment of this disclosure, the method further includes: matching the tailings dam risk comprehensive index with the tailings dam safety level mapping relationship to determine the current safety level of the tailings dam; and issuing a safety warning based on the safety level.

[0016] According to one embodiment of this disclosure, the method further includes: matching the security level with a preset monitoring frequency mapping relationship to determine the target monitoring frequency; and adjusting the monitoring actions of the target satellite based on the target monitoring frequency.

[0017] According to one embodiment of this disclosure, the method further includes: adjusting the current safety level of the tailings dam based on the target event in response to identifying a target event corresponding to the tailings dam.

[0018] To achieve the above objectives, a second aspect of this disclosure provides a satellite-based tailings dam risk level determination device, comprising: an acquisition module for acquiring monitoring data fed back by a target satellite, wherein the monitoring data is the target satellite's monitoring data of the tailings dam; a processing module for processing the monitoring data to obtain multiple dimensionless indicators; a determination module for determining the weight coefficients corresponding to each of the dimensionless indicators; and a calculation module for calculating the tailings dam risk comprehensive index based on the weight coefficients, the dimensionless indicators, and the monitoring data.

[0019] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement the satellite-based tailings dam risk level determination method as described in the first aspect of this disclosure.

[0020] To achieve the above objectives, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the satellite-based tailings dam risk level determination method as described in the first aspect of this disclosure.

[0021] To achieve the above objectives, a fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the satellite-based tailings dam risk level determination method as described in the first aspect of this disclosure.

[0022] This disclosure utilizes a satellite remote sensing-driven dimensionless multi-indicator fusion assessment mechanism to achieve a fundamental shift in tailings dam risk identification from "local, delayed, and subjective" to "comprehensive, dynamic, and quantitative." This not only significantly enhances the early detection and accurate warning capabilities for major safety risks but also provides a practical and scalable intelligent solution for preventing catastrophic accidents such as dam failures through a low-cost, high-efficiency, and highly scalable technical approach. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of a satellite-based method for determining the risk level of a tailings dam, according to one embodiment of this disclosure.

[0024] Figure 2 This is a schematic diagram of another satellite-based method for determining the risk level of a tailings dam, according to one embodiment of this disclosure. Figure 3 This is a schematic diagram of another satellite-based method for determining the risk level of a tailings dam, according to one embodiment of this disclosure. Figure 4 This is a schematic diagram of another satellite-based method for determining the risk level of a tailings dam, according to one embodiment of this disclosure. Figure 5 This is a schematic diagram of a satellite-based tailings dam risk level determination device according to one embodiment of the present disclosure; Figure 6 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure. Detailed Implementation

[0025] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0026] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of relevant laws and regulations.

[0027] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0028] Figure 1 This is a schematic diagram of a satellite-based tailings dam risk level determination method according to one embodiment of this disclosure, as shown below. Figure 1 As shown, the satellite-based method for determining the risk level of tailings dams includes the following steps: S101, acquire monitoring data fed back by the target satellite. The monitoring data is obtained by the target satellite monitoring the tailings dam.

[0029] The satellite-based tailings dam risk level determination method of this application embodiment can be applied to the scenario of tailings dam risk monitoring. The execution subject of the satellite-based tailings dam risk level determination method of this application embodiment can be the satellite-based tailings dam risk level determination device of this application embodiment, which can be installed on an electronic device.

[0030] "Target satellites" can include various types of Earth observation satellites, which can be flexibly selected or combined according to monitoring needs. For example, they can be synthetic aperture radar, high-resolution optical satellites, multispectral / hyperspectral satellites, etc.

[0031] The "monitoring data" in this embodiment includes not only the original remote sensing images, but also the thematic information products generated after preprocessing, such as surface deformation rate maps, digital models, crack distribution maps, and landslide hazard zone identification results.

[0032] Compared to traditional ground-based monitoring methods, satellite remote sensing-based monitoring data offers advantages such as wide coverage, non-contact operation, historical traceability, and multi-dimensional fusion, making it particularly suitable for tailings dam areas that are remote, have complex terrain, or are difficult for humans to access. By continuously acquiring multi-source satellite monitoring data, a foundational data layer can be constructed for an integrated "air-space-ground" perception system for tailings dams, providing objective, comprehensive, and dynamic input for subsequent risk indicator extraction, dimensionless processing, and comprehensive risk index calculation.

[0033] S102 processes the monitoring data to obtain multiple dimensionless indicators.

[0034] Raw remote sensing data is characterized by inconsistent dimensions, large scale differences, and dispersed physical meaning. If used directly for comprehensive assessment, certain high-order indicators (such as area) may dominate the weighted calculation, masking other key but smaller-valued risk signals (such as minor deformations).

[0035] "Processing monitoring data to obtain multiple dimensionless indicators" refers to transforming raw or primary remote sensing monitoring data from multiple satellite sources into standardized numerical indicators that are dimensionless, comparable, and fusionable through feature extraction, physical quantity calculation, and mathematical transformation, for subsequent risk modeling.

[0036] In this embodiment of the disclosure, there are various methods for processing the monitoring data to obtain multiple dimensionless indicators, and no limitation is made here. For example, the monitoring data can be processed using algorithms such as extreme value standardization, quantile standardization, and threshold normalization to obtain multiple dimensionless indicators.

[0037] For example, dimensionless indicators may include, but are not limited to, the water area within the reservoir, the minimum length of the dry beach along the dam direction, the maximum settlement / displacement rate of the dam body, the area of ​​significant vegetation degradation on the dam body and its downstream slope, and the exposure index of newly added population or buildings in the potential inundation area.

[0038] S103, determine the weight coefficients corresponding to each dimensionless index.

[0039] Determining the weight coefficients corresponding to each dimensionless indicator is a scientific way to quantify the relative importance of different risk factors (such as deformation, water level, cracks, etc.) to the overall safety status, so as to reasonably reflect the contribution of each indicator in the comprehensive index calculation.

[0040] In this embodiment of the disclosure, there are various methods for determining the weight coefficients corresponding to each dimensionless index, and no limitation is made here.

[0041] One possible approach is to score the importance of each indicator using expert experience.

[0042] For example, if experts believe that "deformation" is 3 times more important than "water level" and "water level" is 2 times more important than "crack", then the matrix is ​​constructed to obtain the weights as follows: deformation 0.6, water level 0.3, crack 0.1.

[0043] In another possible approach, the weight coefficients of each dimensionless index can be determined using a data-driven method.

[0044] For example, based on historical tailings dam accident / hazard data, the correlation strength between various indicators and risk outcomes can be inferred through statistics or machine learning.

[0045] In another possible approach, the weight coefficients for each dimensionless index can be determined by a combination weighting method.

[0046] For example, we can combine expert experience with data patterns to learn from each other's strengths and make up for our weaknesses.

[0047] S104 calculates the comprehensive risk index of tailings dams based on weighting coefficients, dimensionless indicators, and monitoring data.

[0048] In this embodiment, the acquired multi-source satellite monitoring data, after feature extraction, dimensionless transformation, and weight assignment, are integrated into a unified, quantifiable, and interpretable comprehensive tailings dam risk index. This comprehensive tailings dam risk index has the following advantages: It can be used to uniformly characterize the overall safety status of tailings ponds; It can be used for dynamic early warning; It can be used for horizontal comparison: it supports the ranking of risk levels among different tailings ponds and assists in the priority allocation of resources; It can be used for decision support: providing objective evidence for regulatory authorities and enterprise operations and maintenance, and reducing subjective judgment bias.

[0049] In this embodiment, various methods can be used to calculate the comprehensive risk index of tailings dams, and no limitation is made here. In one possible implementation, a preset index algorithm can be used to calculate the weighting coefficients, dimensionless indicators, and monitoring data to obtain the comprehensive risk index of tailings dams. This index algorithm is pre-designed and can be modified according to actual design needs.

[0050] In this embodiment, monitoring data fed back by the target satellite is first acquired. This monitoring data is obtained by the target satellite monitoring the tailings dam. The monitoring data is then processed to obtain multiple dimensionless indicators. Next, the weight coefficients corresponding to each dimensionless indicator are determined. Finally, the comprehensive risk index of the tailings dam is calculated based on the weight coefficients, the dimensionless indicators, and the monitoring data. This disclosure, through a satellite remote sensing-driven dimensionless multi-indicator fusion evaluation mechanism, achieves a fundamental shift in tailings dam risk identification from "local, delayed, and subjective" to "comprehensive, dynamic, and quantitative." This not only significantly improves the early detection and accurate warning capabilities for major safety risks but also provides a practical and scalable intelligent solution for preventing catastrophic accidents such as dam failures through a low-cost, high-efficiency, and highly scalable technical approach.

[0051] In one possible approach, after acquiring the monitoring data, the data should first be processed, which may include the following steps: radiometric calibration, atmospheric correction, geometric correction, image fusion, image mosaicking and cropping.

[0052] (1) Radiometric calibration: The dimensionless digital quantization values ​​recorded by the sensor are converted into units with actual physical meaning, namely radiance values ​​or apparent reflectance. This step eliminates the errors caused by the sensor itself and is the physical basis for subsequent quantitative remote sensing analysis.

[0053] (2) Atmospheric correction: This step eliminates the effects of atmospheric absorption and scattering of electromagnetic radiation, converting the apparent reflectance received by satellite sensors at the top of the atmosphere into the true reflectance of the Earth's surface. This step is crucial for extracting ground feature information and classifying ground features, as it eliminates image differences caused by changes in atmospheric conditions.

[0054] (3) Geometric correction: Corrects image geometric distortion caused by factors such as Earth's curvature, terrain undulation, and changes in the attitude of remote sensing satellite sensors. Also known as orthorectification. Orthorectification uses digital elevation models to eliminate pixel displacement caused by terrain undulation, giving the image the geometric accuracy of a map and ensuring that the location of ground features on the image is their true geographical location.

[0055] (4) Image fusion: High spatial resolution panchromatic images (e.g., black and white images) acquired at the same time and in the same region are fused with low spatial resolution multispectral images (e.g., color images). This generates a color image that has both high spatial resolution (clearer texture details) and retains rich spectral information. For example, fusing the 2-meter panchromatic band of GF-1 with the 8-meter multispectral band yields a 2-meter spatial resolution multispectral image.

[0056] (5) Image mosaicking and cropping: When the study area is large and a single image cannot completely cover it, multiple images need to be seamlessly stitched into a complete image, i.e., image mosaicking. Conversely, if the study area occupies only a small part of the image, in order to reduce the amount of data processing, the image needs to be cropped according to the boundary of the study area (vector file or coordinate range).

[0057] There are also some innovative methods for processing satellite imagery. Their core idea is to shift from "processing single-scene images" to "processing massive data streams" and to use artificial intelligence to improve the automation and intelligence of the processing.

[0058] First, an innovative trend is the emergence and widespread adoption of Analysis-Ready Data (ARD). Traditionally, users download raw data and then independently complete the entire process from radiometric calibration to geometric correction. ARD, on the other hand, provides standard data products pre-processed by the data provider, with all basic preprocessing already performed and accurately geometrically corrected for surface reflectance calculations. Users can skip the tedious preprocessing steps and focus on information extraction and analysis. This model is tightly integrated with cloud computing platforms, eliminating the need for users to download and store massive amounts of imagery data. Instead, they can directly access pre-processed, spatiotemporally seamless ARD data cubes in the cloud, significantly improving the efficiency of large-area, long-term analysis.

[0059] Secondly, artificial intelligence and deep learning technologies are revolutionizing traditional processing methods. For example, when processing cloud-contaminated images, the traditional approach is to generate cloud masks and remove obscured pixels, which leads to data loss. Innovative methods utilize deep learning models, such as Generative Adversarial Networks (GANs), for cloud removal and image reconstruction. These models can learn spatiotemporal context information and intelligently "fill in" the areas obscured by clouds, generating a complete and clear image. Furthermore, AI super-resolution reconstruction technology offers new avenues for data processing. It can use algorithmic models to upscale low-resolution images to higher spatial resolution, serving as a supplement or enhancement to traditional image fusion techniques and providing a higher-quality data source for subsequent fine-grained interpretation.

[0060] Information extraction from processed satellite imagery mainly includes the following four methods: (1) Visual interpretation: Professionals rely on their expertise and experience to interpret, identify and delineate the features on the image based on interpretation markers such as hue / color, shape, size, texture, shadow, pattern, position and layout. This is the most direct but less efficient method.

[0061] Furthermore, the accuracy and consistency of interpretation can be significantly improved by constructing a systematic workflow. In the initial stages of visual interpretation, a standardized "image interpretation atlas" or "interpretation marker library" can be established. This involves creating a reference guide that includes typical land cover sample images, detailed interpretation marker descriptions, and annotations, tailored to the characteristics of land cover in the study area. During the interpretation process, a hierarchical classification system is adopted, gradually refining from higher-level land cover categories (such as vegetation) to lower-level categories (such as forests and grasslands) to ensure logical consistency. To reduce individual subjective bias, a multi-person independent interpretation and cross-validation mechanism can be introduced. This involves multiple interpreters independently interpreting the same area, comparing the results, discussing and judging inconsistent patches, and ultimately reaching a consensus. Simultaneously, overlaying and analyzing remote sensing imagery with other auxiliary data in a Geographic Information System (GIS) environment (such as topographic maps, planning maps, historical maps, or field survey points) can provide richer contextual information for interpretation, thereby improving the accuracy of the interpretation.

[0062] (2) Pixel-based classification: This is a traditional computer-automated classification method, with a single pixel as its basic unit. It is further divided into supervised and unsupervised classification. In supervised classification, the user first selects "training samples" representing different land cover categories. The computer learns the spectral characteristics of these samples and builds a classification model using methods such as maximum likelihood estimation, support vector machines, and random forests. The model then classifies each pixel in the entire image. Unsupervised classification, on the other hand, does not require manually provided training samples. Based on the similarity of pixel spectral characteristics, the computer automatically aggregates pixels in the image into several clusters. Professionals then identify, define, and adjust these automatically generated clusters to identify the actual land cover information.

[0063] (3) Object-oriented image analysis: This method no longer uses individual pixels as the unit of analysis. It first uses image segmentation algorithms to merge neighboring pixels with similar features (such as color and texture) into meaningful, irregular polygonal objects. The computer not only utilizes the spectral features of these objects, but also uses various features such as the object's shape, size, texture, and relationship with neighboring objects for classification. This method performs particularly well on high-resolution images and can effectively avoid the noise phenomenon in the classification results of traditional pixel-based methods.

[0064] (4) Intelligent interpretation based on deep learning: Using deep neural networks (especially convolutional neural networks CNN), computers can automatically learn abstract features from low to high levels in images, just like the human brain. This method can not only perform pixel-level classification, but also achieve object detection (such as identifying and selecting airplanes, ships, and buildings). This method usually requires a large number of labeled samples for model training, but once the model is trained, its degree of automation and accuracy often surpasses traditional methods.

[0065] Furthermore, for large-scale ground feature extraction, cloud computing platforms can be utilized. These platforms integrate massive online data archives and powerful cloud computing capabilities, enabling efficient multi-source data fusion and time-series analysis. By fusing data from different sensors such as optical and radar sensors, information complementarity can be achieved, improving classification accuracy. Simultaneously, combining pre-trained deep learning models with transfer learning can significantly reduce the workload of sample collection in new areas, achieving large-scale, high-precision automated mapping.

[0066] In the above embodiments, the monitoring data is processed to obtain multiple dimensionless indicators, and can also be obtained through... Figure 2 To further explain, the method includes: S201, determine the target indicator data from the monitoring data based on preset indicators.

[0067] In this embodiment of the disclosure, under the same coordinate reference, monitoring data, such as optical satellite data and digital elevation model data, can be aligned pixel by pixel to construct a tailings dam scene feature cube.

[0068] Then, for each cell / object, the following target metrics data are calculated, including but not limited to: ① Spectral indices: Water body index, vegetation index, bare soil index, etc., used to distinguish between water bodies, dry beaches, and vegetated slopes; ②Texture features: Energy, contrast, entropy, etc. are calculated using the gray-level co-occurrence matrix to distinguish between artificial structures and natural mountains in the dam body; ③ Geometric and topographic features: The slope, aspect, elevation, and local curvature are calculated by the digital elevation model. In particular, the dam area usually presents a combination of "steep slope + regular linear geometry". ④ Synthetic Aperture Radar (SAR) characteristics: backscatter intensity, coherence coefficient, etc., used to stably identify the hard structure of dams and tailings water surface in cloudy and rainy areas.

[0069] In another possible approach, the following key metrics can be extracted from the monitoring data, from the interpretation results and the deformation analysis of Interferometric Synthetic Aperture Radar (InSAR): Aw reservoir water area; Ld is the minimum length of the dry beach along the dam body direction; V s : Maximum settlement / displacement rate of the dam body; A v Area of ​​significantly degraded vegetation on the dam body and its downstream slope; E p Exposure index of newly added population or buildings in the potential flood zone.

[0070] By performing extreme value standardization or quantile standardization based on historical distribution on the above indicators, we obtain the dimensionless indicator I. i (i=1,2,...,5), for example:

[0071] For indicators that are "safer the smaller" (such as dry beach length), reverse standardization is used to ensure that all values ​​are in the direction where the larger the value, the higher the risk.

[0072] S202 standardizes the target indicator data to generate dimensionless indicators.

[0073] It should be noted that standardizing the target indicator data can eliminate the influence of units, make different indicators comparable, and make the data closer to a normal distribution, thereby improving the model performance.

[0074] In this embodiment of the disclosure, the target indicator data is standardized by first obtaining historical detection data, and then, for any target indicator data, calculating the key quantile of the target indicator data based on the historical detection data, and using the key quantile as the dimensionless indicator corresponding to the target indicator data.

[0075] In one possible set of implementations, the above index can be standardized by extreme values ​​or by quantile standardization based on historical distribution to obtain the dimensionless index I. i (i=1,2,...,5), for example:

[0076] For indicators that are "safer the smaller" (such as dry beach length), reverse standardization is used to ensure that all values ​​are in the direction where the larger the value, the higher the risk.

[0077] In the above embodiments, the weight coefficients corresponding to each dimensionless index can also be determined by... Figure 3 To further explain, the method includes: S301, Obtain the safety specification data and / or empirical data corresponding to each dimensionless indicator.

[0078] S302, calculate the weight coefficients corresponding to each dimensionless index based on safety specification data and / or empirical data.

[0079] Combining tailings dam engineering safety regulations and expert experience, the weights of each indicator are determined using the analytic hierarchy process (AHP) or statistical regression methods based on historical accident data. :

[0080] The formula for calculating the comprehensive risk index is:

[0081] The index range is normalized to [0,1], and the larger the value, the higher the overall risk level.

[0082] In this embodiment of the disclosure, the comprehensive risk index of the tailings dam can also be matched with the mapping relationship of the tailings dam safety level to determine the current safety level of the tailings dam, and then a safety warning can be issued based on the safety level.

[0083] The safety level mapping relationship of tailings dams is pre-set and can be changed according to the actual situation of the tailings dam or the actual design needs.

[0084] For example, the safety status of tailings ponds can be classified into four levels based on the TDRI value: 0.00–0.25: Level I (Safe); 0.25–0.50: Level II (Attention); 0.50–0.75: Level III (Higher risk); 0.75–1.00: Level IV (High Risk).

[0085] Furthermore, the Tailings Dam Risk Index (TDRI) is spatially refined to the scale of "dam section / slope section / sub-basin" on the GIS platform, generating a risk zoning map. Each zoning is assigned a corresponding risk level and main contribution indicators (such as "excessive water quality + insufficient dry beach" type, "abnormal deformation + vegetation degradation" type), providing management departments with a visualized and accurate basis for supervision.

[0086] In the time dimension, trend analysis is performed on the TDRI series TDRI(t): If the TDRI increases monotonically over several consecutive periods, or experiences a sudden increase in a short period (such as +0.2 or more), the warning rule will be triggered, and the tailings dam will be automatically marked as "requiring on-site verification". By cross-analyzing TDRI with measured rainfall and reservoir water level data, abnormal coupling events of "meteorology-reservoir water-deformation" can be identified, providing a basis for early intervention under extreme weather conditions.

[0087] Through the aforementioned comprehensive risk index model, this disclosure elevates multi-source monitoring results from "maps + text descriptions" to "calculable, comparable, and automatically predictable" risk quantification results, reflecting a methodological innovation from "monitoring" to "intelligent assessment and early warning".

[0088] In the above embodiments, the detection frequency can also be adjusted according to the security level, which can be achieved through... Figure 4 To further explain, the method includes: S401, matching the security level with the preset monitoring frequency mapping relationship to determine the target monitoring frequency.

[0089] S402 adjusts the monitoring actions of target satellites based on the target monitoring frequency.

[0090] Current technologies for remote sensing monitoring of tailings ponds often employ fixed monitoring frequencies (such as "monthly optical satellite observations and quarterly SAR satellite observations"), making it difficult to flexibly adjust according to changes in risk. This disclosure proposes a risk-level-driven adaptive satellite observation scheduling algorithm based on the Comprehensive Risk Index (TDRI) to achieve dynamic allocation of monitoring resources on demand.

[0091] 1. Risk-Frequency Mapping Rule Design Based on the risk levels obtained above, the risk level L(t) of each tailings dam at any time t is correlated with the optical and SAR observation frequencies:

[0092] The specific cycle can be parameterized based on factors such as the length of the local rainy season and satellite constellation resources.

[0093] 2. Event-driven encrypted observation triggering In response to the identification of a target event corresponding to the tailings dam, the current safety level of the tailings dam is adjusted based on the target event. It should be noted that, in addition to periodic observation, this disclosure also introduces an event triggering mechanism: If the weather forecast issues a "red alert for extreme rainfall / rainstorm", then all tailings ponds at risk level II or above will be automatically subjected to a three-stage intensive observation task: "before rainfall - during rainfall - after rainfall". If the TDRI increases by more than a threshold (e.g., 0.2) between two periods, or if the dam deformation rate Vs suddenly increases by more than the set safety threshold, the risk level of the reservoir will be automatically raised by one level, and the observation period will be shortened accordingly.

[0094] 3. Multi-constellation joint scheduling and priority ordering For satellites from multiple sources both domestically and internationally, this publication maintains information such as transit time, spatial resolution, and imaging costs for each constellation on a cloud platform.

[0095] First, determine the "observation window" and "minimum resolution requirement" based on the risk level of the tailings dam; Then, among the satellites that meet the technical requirements, they are prioritized in the order of "high risk level → sensitive to intervention conditions → cost constraints" to select the most suitable satellite to perform the observation mission; When there are many high-risk tailings ponds and insufficient satellite resources, the algorithm will prioritize the observation needs of Level IV and Level III ponds, and make appropriate concessions to Level I ponds.

[0096] Through this adaptive scheduling algorithm, this disclosure transforms the "pre-fixed monitoring plan" into an "intelligent observation plan that is dynamically updated according to risks," which significantly improves the efficiency of satellite resource utilization and the monitoring and protection level of key risk databases.

[0097] Corresponding to the satellite-based tailings dam risk level determination methods provided in the above embodiments, one embodiment of this disclosure also provides a satellite-based tailings dam risk level determination device. Since the satellite-based tailings dam risk level determination device provided in this disclosure corresponds to the satellite-based tailings dam risk level determination methods provided in the above embodiments, the implementation methods of the above-mentioned satellite-based tailings dam risk level determination methods are also applicable to the satellite-based tailings dam risk level determination device provided in this disclosure, and will not be described in detail in the following embodiments.

[0098] Figure 5 Figure 5 is a schematic diagram of a satellite-based tailings dam risk level determination device according to one embodiment of this disclosure. As shown in Figure 5, the satellite-based tailings dam risk level determination device 500 includes: The acquisition module 510 is used to acquire monitoring data fed back by the target satellite, wherein the monitoring data is obtained by the target satellite monitoring the tailings dam.

[0099] The processing module 520 is used to process the monitoring data to obtain multiple dimensionless indicators.

[0100] The determination module 530 is used to determine the weight coefficients corresponding to each of the dimensionless indicators.

[0101] The calculation module 540 is used to calculate the comprehensive risk index of the tailings dam based on the weighting coefficients, the dimensionless indicators, and the monitoring data.

[0102] According to one embodiment of this disclosure, the step of processing the monitoring data to obtain multiple dimensionless indicators includes: determining target indicator data from the monitoring data based on preset indicators; and standardizing the target indicator data to generate the dimensionless indicators.

[0103] According to one embodiment of this disclosure, the standardization process of the target indicator data to generate the dimensionless indicator includes: for any target indicator data, obtaining the indicator logic corresponding to the target indicator data; and performing extreme value standardization processing on the target indicator data based on the indicator logic to generate the dimensionless indicator corresponding to the target indicator data.

[0104] According to one embodiment of this disclosure, the step of processing the monitoring data to obtain multiple dimensionless indicators includes: acquiring historical monitoring data; for any target indicator data, calculating the key quantile of the target indicator data based on the historical monitoring data, and using the key quantile as the dimensionless indicator corresponding to the target indicator data.

[0105] According to one embodiment of this disclosure, determining the weight coefficients corresponding to each of the dimensionless indicators includes: obtaining safety specification data and / or empirical data corresponding to each of the dimensionless indicators; and calculating the weight coefficients corresponding to each of the dimensionless indicators based on the safety specification data and / or the empirical data.

[0106] According to one embodiment of this disclosure, the method further includes: matching the tailings dam risk comprehensive index with the tailings dam safety level mapping relationship to determine the current safety level of the tailings dam; and issuing a safety warning based on the safety level.

[0107] According to one embodiment of this disclosure, the method further includes: matching the security level with a preset monitoring frequency mapping relationship to determine the target monitoring frequency; and adjusting the monitoring actions of the target satellite based on the target monitoring frequency.

[0108] According to one embodiment of this disclosure, the method further includes: adjusting the current safety level of the tailings dam based on the target event in response to identifying a target event corresponding to the tailings dam.

[0109] This disclosure utilizes a satellite remote sensing-driven dimensionless multi-indicator fusion assessment mechanism to achieve a fundamental shift in tailings dam risk identification from "local, delayed, and subjective" to "comprehensive, dynamic, and quantitative." This not only significantly enhances the early detection and accurate warning capabilities for major safety risks but also provides a practical and scalable intelligent solution for preventing catastrophic accidents such as dam failures through a low-cost, high-efficiency, and highly scalable technical approach.

[0110] To implement the above embodiments, this disclosure also proposes an electronic device 600. Figure 6 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure, such as... Figure 6 As shown, the electronic device 600 includes: a processor 601 and a memory 602 communicatively connected to the processor. The memory 602 stores instructions executable by at least one processor. The instructions are executed by at least one processor 601 to implement the functions described in this disclosure. Figures 1-4 The example describes a satellite-based method for determining the risk level of tailings ponds.

[0111] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to implement the present disclosure. Figures 1-4 The example describes a satellite-based method for determining the risk level of tailings ponds.

[0112] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program, which, when executed by a processor, implements the features of this disclosure. Figures 1-4 The example describes a satellite-based method for determining the risk level of tailings ponds.

[0113] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0114] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0115] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0116] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0117] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that contains, stores, communicates, propagates, or transmits programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0119] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0122] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A satellite-based method for determining the risk level of tailings dams, characterized in that, include: Acquire monitoring data fed back by the target satellite, wherein the monitoring data is obtained by the target satellite monitoring the tailings dam; The monitoring data is processed to obtain multiple dimensionless indicators; Determine the weighting coefficients corresponding to each of the dimensionless indices; The tailings dam risk index is calculated based on the weighting coefficients, the dimensionless indicators, and the monitoring data.

2. The method according to claim 1, characterized in that, The monitoring data is processed to obtain multiple dimensionless indicators, including: Target indicator data is determined from the monitoring data based on preset indicators; The target indicator data is standardized to generate the dimensionless indicator.

3. The method according to claim 2, characterized in that, The standardization process for the target indicator data to generate the dimensionless indicator includes: For any target indicator data, obtain the indicator logic corresponding to the target indicator data; The target indicator data is subjected to extreme value standardization based on the indicator logic to generate a dimensionless indicator corresponding to the target indicator data.

4. The method according to claim 1, characterized in that, The monitoring data is processed to obtain multiple dimensionless indicators, including: Obtain historical testing data; For any target indicator data, the key quantile of the target indicator data is calculated based on the historical detection data, and the key quantile is used as the dimensionless indicator corresponding to the target indicator data.

5. The method according to any one of claims 1-4, characterized in that, Determining the weight coefficients corresponding to each of the dimensionless indices includes: Obtain the safety specification data and / or empirical data corresponding to each of the dimensionless indicators; Calculate the weight coefficients corresponding to each of the dimensionless indicators based on the safety specification data and / or the experience data.

6. The method according to claim 5, characterized in that, The method further includes: The tailings dam risk comprehensive index is matched with the tailings dam safety level mapping relationship to determine the current safety level of the tailings dam; Security warnings are issued based on the aforementioned security level.

7. The method according to claim 6, characterized in that, The method further includes: The target monitoring frequency is determined by matching the security level with the preset monitoring frequency mapping relationship. The monitoring actions of the target satellite are adjusted based on the target monitoring frequency.

8. The method according to claim 6, characterized in that, The method further includes: In response to the identification of a target event corresponding to the tailings dam, the current safety level of the tailings dam is adjusted based on the target event.

9. A satellite-based tailings dam risk level determination device, characterized in that, include: The acquisition module is used to acquire monitoring data fed back by the target satellite, wherein the monitoring data is obtained by the target satellite monitoring the tailings dam; The processing module is used to process the monitoring data to obtain multiple dimensionless indicators; The determination module is used to determine the weight coefficients corresponding to each of the dimensionless indicators; The calculation module is used to calculate the comprehensive risk index of the tailings dam based on the weighting coefficients, the dimensionless indicators, and the monitoring data.

10. An electronic device, characterized in that, Including memory and processor; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method as described in any one of claims 1-8.

Images