Computer-implemented methods and related hardware and systems for processing mining plans

Abstract

One embodiment of a computer-implemented method for processing a mining plan for mining natural resources from a target environment. The computing system can perform simulation processing for processing the environmental data, the job data, and the plan data to simulate a state of the target environment after an end of a predefined first time period during which the mining plan is simulated to be implemented. The computing system can also perform constraint processing for processing the constraint data and the simulation status of the target environment to determine whether any environmental constraint is simulated violating. If it is simulated that no environmental constraints are violated, the mining plan is marked as compliant. The computing system may also generate a plurality of alternative mining plans and corresponding plan data, and perform simulation processing and constraint processing for each corresponding plan data to mark a plurality of compliant mining plans.

Description

Technical Field

[0001] The present invention relates to methods, related devices and systems for use in the extractive industry. Embodiments of the present invention may be applied to, but not limited to, logging, fishing, terrestrial mining and deep-sea mining. Background Art

[0002] Any reference to documents, acts, materials, devices, articles or the like contained in this specification is for the sole purpose of providing background information for the present invention. It is not to be taken as an admission that any or all of these matters form part of the prior art base or that any or all of these matters were common general knowledge in the field relevant to the present invention as it existed in Australia or elsewhere before the priority date of this application.

[0003] Managing extractive operations often requires striking a delicate balance between inherently conflicting considerations, such as maximizing productivity while keeping environmental impacts within the limits imposed by the regulatory bodies with jurisdiction over the target environment. Generally, achieving this balance is greatly aided by a detailed understanding of the target environment—particularly the ability to predict and quantify the potential environmental impacts of various aspects of proposed extractive activities. However, for many target environments, this information may be incomplete, scarce, or nonexistent. As a non-limiting example, this presents particular difficulties for entities seeking to conduct mining operations in lesser-known target environments, such as the deep sea. Summary of the Invention

[0004] The present invention aims to overcome or substantially ameliorate one or more disadvantages of the prior art, or to provide a useful alternative.

[0005] In one aspect of the present invention, a computer-implemented method is proposed for processing a mining plan for mining natural resources from a target environment, the method comprising configuring a computing system to: access environmental data indicating the target environment; access constraint data indicating multiple environmental constraints applicable to the target environment; access operating data indicating equipment deployed in the target environment; access plan data indicating the mining plan; perform simulation processing for processing the environmental data, operating data, and plan data to simulate the state of the target environment after a predefined first time period, and simulate the implementation of the mining plan within the first time period; perform constraint processing for processing the constraint data and the simulated state of the target environment to determine whether any environmental constraints are simulated to be violated, and if no environmental constraints are simulated to be violated, mark the mining plan as compliant; generate multiple alternative mining plans and corresponding plan data, and perform simulation processing and constraint processing on each corresponding plan data to mark multiple compliant mining plans.

[0006] Preferably, the method includes: defining a metric for quantifying the desirability of a mining plan; calculating a corresponding metric for each compliant mining plan; and submitting the mining plan with the highest metric to a user of the computing system for approval after a predefined second time period, wherein the predefined second time period is shorter than the predefined first time period.

[0007] In one embodiment, if a violation of an environmental constraint is simulated for a mining plan, the computing system is configured to prompt a user of the computing system to select at least one from a plurality of predetermined potential modifications to the mining plan.

[0008] Preferably, the simulation process uses a digital twin configured to simulate the current operating state based on operating data input from sensors, and the digital twin is configured to simulate future operating data during the simulation implementation of the mining plan.

[0009] Preferably, the simulation process processes the operation data and future operation data using probabilistic analysis to model cause-effect relationships for a plurality of environmental impact indicators.

[0010] In one embodiment, the step of generating a plurality of alternative mining plans and corresponding plan data includes: gradually modifying operating variables of the mining plans to generate modified operating variables, and processing the modified operating variables in an optimization algorithm.

[0011] The step of generating a plurality of alternative mining plans and corresponding plan data includes randomly generating starting parameters for the mining plans and processing the randomly generated starting parameters in an optimization algorithm. Examples of such starting parameters include a proposed mining starting location within the target environment, a proposed natural resource extraction rate, a proposed efficiency level, and a proposed power consumption level.

[0012] One embodiment of the computing system maintains a mode indicator for indicating an active adaptive management state or a passive adaptive management state. In this embodiment, when the mode indicator is in the passive adaptive management state, generation of multiple mining alternative plans is limited to a safe region of the operating range, where the mining alternative plans are most likely to meet environmental constraints. When the mode indicator is in the active adaptive management state, generation of multiple mining alternative plans is biased toward a boundary region of the operating range, where the mining alternative plans are close to or violate environmental constraints.

[0013] In one embodiment, the computing system switches the mode indicator between an active adaptive management state and a passive adaptive management state in response to user input. In another embodiment, the computing system is configured to calculate an uncertainty score associated with the probability analysis, and when the uncertainty score is below a threshold, the computing system recommends to the user that the mode indicator be set to the active adaptive management state; when the uncertainty score is above the threshold, the computing system automatically sets the mode indicator to the passive adaptive management state.

[0014] In one embodiment, a mining plan is implemented during a predefined first time period, and a plurality of alternative mining plans and corresponding planning data are generated during the predefined first time period. In such an embodiment, starting operating parameters of at least some of the alternative mining plans correspond to predicted operating parameters of the implemented mining plan at the end of the predefined second time period.

[0015] Some embodiments of the method include defining a third time period, wherein the third time period is longer than the second time period, and the computing system is configured to collate the empirically derived environmental data and the empirically derived operational data at the end of the third time period. Research scientists and / or data analysts apply probabilistic techniques and / or machine learning techniques to the empirically derived environmental data and the empirically derived operational data to update at least one of the following: the probability analysis, the constraint data, the acceptable level of state change, and / or the ecosystem model. The second time period is between five days and six months, and both the first and third time periods are between one month and one year.

[0016] In certain embodiments, the computing system is configured to maintain a portal for access by regulatory agencies and / or the public, the portal providing at least one of the following types of information: environmental data, constraint data, and operational data.

[0017] According to a third aspect of the present invention, a computing system is provided, configured to execute the above method.

[0018] According to another aspect of the present invention, a system for extracting natural resources from a target environment is proposed, the system comprising: a computing system configured to execute the above method; an extraction device disposed in the target environment; and a plurality of sensors disposed on and around the extraction device and in the target environment, the sensors being capable of communicating with the computing system via a telemetry link.

[0019] The features and advantages of the present invention will become more apparent from the following detailed description of preferred embodiments, which are provided by way of example only, and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram showing the architecture of one embodiment of a computing system according to the present invention;

[0021] Figure 2 A schematic diagram showing elements of environmental logic implemented in one embodiment of a computing system according to the present invention is shown;

[0022] Figure 3 A flow chart showing passive adaptive management implemented in one embodiment of the present invention is shown;

[0023] Figure 4 A flow chart showing active adaptive management implemented in one embodiment of the present invention is shown;

[0024] Figure 5 Shows Figure 1 A schematic diagram of the architecture of the digital twin used in the embodiments;

[0025] Figure 6 A flow chart showing active adaptive management implemented in one embodiment of the present invention is shown;

[0026] Figure 7 A flow chart showing a method for generating a mining plan;

[0027] Figure 8 A flow chart showing a method for updating various aspects of system logic using empirically derived data;

[0028] Figure 9 A schematic side view of a system for mining nodules from a seabed target environment is shown. DETAILED DESCRIPTION

[0029] The computing system 1 may be configured to perform Figure 3 、 Figure 4 、 Figure 6 、 Figure 7 and Figure 8 From a schematic point of view, the system architecture includes, for example, Figure 1 Multiple communication and interconnected modules are shown in .

[0030] The computing system 1 can be used in various types of extractive industries, such as logging, fishing, land mining, deep sea mining, etc. A preferred embodiment of the present invention will focus on Figure 9 However, it will be appreciated that one skilled in the art will be able to readily adapt the general concepts of the present invention for application to other types of extractive industries.

[0031] An example of deep sea mining involves mining nodules located on the seabed at a depth of approximately 4,000 to 4,500 meters. The mining system includes a plurality of collectors 4 that travel over the seabed, using jets of water to collect the nodules. Typically, such nodule mining methods involve stirring up surface sediments on the seabed, which may result in a sediment plume moving in the seawater current. This provides a non-limiting example of a computing system 1 that is configured to analyze and predict the types of operational activities and associated environmental impacts. After the nodules are collected by the collectors 4, compressed air bubbles are used to cause the nodules to rise along a generally vertical pipe (referred to as a riser 5), which can transport the nodules to a vessel 6 for subsequent processing.

[0032] In a typical embodiment, the modules of computing system 1 may be implemented in a cloud computing environment. However, as described in more detail below, sensors 3 may be deployed in and around the target environment, and a workstation 21 may be provided onboard vessel 6 to run the software required to implement the telemetry link between sensors 3 and the modules of computing system 1 in the cloud. In a preferred embodiment, some examples of publicly or commercially available software modules that may be used include:

[0033] Kongsberg’s Kognitwin digital twin

[0034] Computational fluid dynamics software provided by DHI Group;

[0035] Open source software for Bayesian networks; and / or

[0036] Database services provided by InfluxData's InfluxDB or Dremio.

[0037] Before the above-mentioned deep-sea mining activities begin, it is necessary to enable the computing system to obtain various data. In some embodiments, some or all of this data is stored in a locally accessible database 24. In other embodiments, some or all of this data is stored in a cloud computing data storage facility, or is made accessible to the computing system 1 by subscribing to a third-party data supply service. This data includes environmental data, which helps to populate the environmental logic module 8 and the ecosystem model 9. Figure 4When the method flow shown first enters step 4.2, environmental data will be collected. This typically includes an environmental baseline, which can be established by collecting samples from the target environment. The samples are sent to a laboratory and analyzed to determine the composition of the ecosystem (including key species). The construction of an ecosystem model 9 supports the modeling of the food web in the target environment. The analysis of the food web includes consideration of nutrient inputs and outputs and the relationships between various species (including predation, scavenging, etc.). This method generates environmental data that represents the target environment accessed by the computing system 1. This provides a baseline for measuring changes in environmental status caused by the human impact of mining activities.

[0038] In some cases, the computing system 1 can obtain various environmental data through public domains or commercial channels (such as subscribing to third-party databases). In deep-sea scenarios, ocean current related data can be obtained in this way.

[0039] Pre-production steps often also involve consulting experts to develop and quantify key ecosystem indicators, such as counting key species. In a deep-sea mining scenario, examples of key ecosystem indicators could include:

[0040] ● Benthic plume deposition;

[0041] ●Definition of protected areas

[0042] Plume diffusion;

[0043] ●Number of key animal species;

[0044] Noise generation;

[0045] ●Number of key microbial species;

[0046] eDNA analysis

[0047] ●Cultural and / or scientific DGM projects;

[0048] Water chemistry;

[0049] Heavy metal content in animals;

[0050] Organic matter flux;

[0051] Nitrification concentration in water column and pore water;

[0052] Pore water chemistry;

[0053] Phytoplankton density / biomass

[0054] Nutrient concentration;

[0055] Water chemistry;

[0056] Plankton community composition;

[0057] ● Sediment characteristics;

[0058] Crustacean density; and

[0059] ●Sediment radiochemistry.

[0060] Figure 2 The various components of the environmental logic module 8 are shown. In addition to the ecosystem model 9, the environmental logic module 8 also provides the computing system 1 with access to constraint data 10, which shows a number of environmental constraints applicable to the target environment. Essentially, this constraint data 10 is a practical manifestation of the environmental regulations applicable to the target environment and the mining activities to be carried out. This can include data indicating environmental elements that must be tracked. The environmental logic can also include data indicating acceptable levels of change in environmental conditions 12. In a deep-sea mining scenario, an example of the type of constraints that can be encoded into the constraint data includes constraints related to suspended sediment and settled sediment caused by the operation of the ore collector 4, as shown below.

[0061]

[0062] Another example of a constraint that is applicable in a deep-sea mining scenario and could be encoded into the constraint data is the noise generated by the mining operations, which propagates through the environment and could potentially disrupt the ecosystem. Such a constraint could state that the noise level caused by the operations of the ore collector 4 and riser 5, measured at a far-field buoy at a certain distance from the operations, must not exceed 75 dB.

[0063] In a land mining scenario, some examples of constraint data that can be encoded into a computing system include:

[0064]

[0065]

[0066] like Figure 5 As shown, the digital twin 2 features a virtual asset representation 17 configured to track the current operational status of physical assets used in the mining system (e.g., collector 4, riser 5, nodule receiving vessel 6, remotely operated underwater vehicle 7, mooring equipment, buoys, environmental monitoring vessels, etc.). This is based on operational data input from sensors 3, which are located on and around the mining equipment and within the target environment. Examples of operational data include equipment location, equipment speed, mining rate, efficiency, power consumption, material handling variables, and logistics variables. Figure 9 Shows some sensors deployed in a deep-sea target environment 3.

[0067] The nodule receiving vessel 6 has the following components:

[0068] ●Return water sampler, which can be used to detect return water quality, turbidity, oxygen content, redox potential, pH value, nitrate concentration and nutrient concentration;

[0069] ●Air pollution sensor, can be used to detect CO, NO x , SO2 and VOC;

[0070] ●Sound level meter, which can be used to measure atmospheric noise levels;

[0071] ●Electromagnetic flow sensor can be used to measure the return water velocity, return water flow, return water CO2 concentration and return water

[0072] Water temperature;

[0073] ●Multi-belt scale, which can be used to measure conveyor belt throughput;

[0074] Global Navigation Satellite Systems, which can be used to monitor heading, speed, x-axis position, and y-axis position; and

[0075] ●Hydrophones, which can be used to measure underwater noise levels.

[0076] The following components are provided in the middle of the riser 5:

[0077] Ultra-short baseline transponder, which can be used to measure x-axis position, y-axis position and depth;

[0078] Hydrophones, which can be used to measure underwater noise levels; and

[0079] ●CTD probe, which can be used to measure conductivity, temperature and depth.

[0080] The riser 5 is provided with the following components at the bottom:

[0081] Underwater acoustic positioning transponders that can measure x-axis position, y-axis position, and depth; and

[0082] Hydrophones, which can be used to measure underwater noise levels.

[0083] Each ore collector 4 may have the following components:

[0084] Underwater particle size analyzers, which can be used to measure turbidity and total suspended solids;

[0085] Light sensors, which can be used to measure light levels;

[0086] Hydrophones, which can be used to measure underwater noise levels;

[0087] A power meter, which can be used to measure power consumption;

[0088] Density meter, which can be used to measure emission density;

[0089] Flow sensor, which can be used to measure discharge flow;

[0090] ● Density meter, which can be used to measure the density of the jumper tube;

[0091] Pressure sensor, which can be used to measure water pressure;

[0092] ●Flow sensor, which can be used to measure the flow across the pipe;

[0093] ●Doppler velocity recorder, which can be used to measure the speed of the ore collector on the seabed;

[0094] An inertial navigation system, which can be used to measure the heading of the ore collector; and

[0095] ●Underwater acoustic positioning transponder, which can be used to measure x-axis position, y-axis position and depth.

[0096] Each remote-controlled underwater robot 7 may have the following components:

[0097] ●Water sample collection bottle, which can be used to measure water quality;

[0098] ●Turbidity sensor, which can be used to measure turbidity;

[0099] An inertial navigation system, which measures heading, roll, and pitch.

[0100] Underwater acoustic positioning transponders, which can be used to measure x-axis position, y-axis position, and depth;

[0101] ●CTD probe, which can be used to measure conductivity, temperature and depth;

[0102] Hydrophones, which can be used to measure underwater noise levels; and

[0103] Light sensors, which can be used to measure light levels.

[0104] Each mooring equipment may have the following components:

[0105] Acoustic Doppler current profilers, which can be used to measure ocean currents, speed, and direction;

[0106] Hydrophones, which can be used to measure underwater noise levels;

[0107] Water samplers that can be used to measure water quality, turbidity, oxygen content, redox potential, pH, nitrate concentration, and nutrient concentration; and

[0108] CTD probe, which can be used to measure conductivity, temperature and depth.

[0109] Each buoy may have the following components:

[0110] Acoustic Doppler current profilers, which can be used to measure ocean currents, speed, and direction.

[0111] The mining system can also use satellite imagery to measure animal migration patterns and emissions from operating fleets.

[0112] The sensors 3 may communicate with the computing system 1 via a telemetry stream 22, wherein each sensor 3 may communicate with a central control station 21 disposed on a vessel 6 floating near the equipment performing the mining operation.

[0113] The digital twin may also utilize the scenario modeler 18 to simulate future operating data that is expected to be applicable to the mining equipment when the mining plan is simulated and implemented.

[0114] Environmental logic module 8 also includes an impact analyzer 11, which is configured to process operational and future operational data using probabilistic analysis to model causal relationships for multiple environmental impact indicators (e.g., key ecosystem indicators). Preferred embodiments utilize a Bayesian network for probabilistic analysis. The Bayesian network is configured to take the current environmental state, the ecosystem model, and the proposed mining plan as inputs and process them to output a range of possible changes in the environmental state. Configuration of the Bayesian network can be performed by one or more research scientists and / or data analysts 28 using known techniques to assign probabilities within the Bayesian network.

[0115] If the initial configuration of the Bayesian network is based entirely or primarily on expert opinion, the output of the Bayesian network may be highly uncertain. That is, the range of changes in environmental states predicted by the Bayesian network may be relatively wide. Therefore, a cautious approach should be taken during the initial operation of the mining system. This requires the adoption of conservative mining plans early in the project life cycle, and may require the initial positioning of initial mining activities in areas with high environmental resilience. The purpose of this system is to support core project personnel in promoting a preventive approach that emphasizes managing risks through proactive decision-making. This approach also advocates postponing potentially harmful decisions until a sufficiently detailed understanding of the relevant causal relationships has been formed. Figure 4As shown, the application of active adaptive management techniques enables the mining system to safely explore operating states for which there is little or no data. Once a history of empirical data has been accumulated through the completion and monitoring of actual mining activities, one or more research scientists and / or data analysts 28 can use this empirical data to optimize the configuration of the Bayesian network. Each time this reconfiguration is performed, the predictions of the probabilistic analysis will typically have reduced uncertainty. That is, within a given confidence interval, the range of environmental state changes predicted by the Bayesian network may become narrower. When this state is reached, the initial cautious approach can be gradually replaced by a more aggressive approach, the extent of which can be based on the certainty predicted by the probabilistic analysis. When the operating state space has been fully explored and the user deems it appropriate, the active adaptive management technique can be replaced by Figure 3 The more traditional reactive adaptive management techniques shown.

[0116] The computing system 1 may maintain a mode indicator that may be used to indicate whether the system currently desires to operate in an active adaptive management state or a passive adaptive management state. Figure 3 Reactive adaptive management, as shown, executes a single management strategy until new data is collected and the management strategy is reassessed to see if it is effective. Figure 4 The active adaptive management presented uses models and data obtained from the implementation of mining activities to compare multiple management strategies with a control group.

[0117] In one embodiment, the computing system switches the mode indicator between an active adaptive management state and a passive adaptive management state in response to user input. In another embodiment, the computing system 1 is configured to calculate an uncertainty score associated with the probability analysis. When the uncertainty score is below a threshold, the computing system recommends to the user that the mode indicator be set to the active adaptive management state. When the uncertainty score is above the threshold, the computing system automatically sets the mode indicator to the passive adaptive management state. Preventing the computing system 1 from automatically setting the mode indicator to the active adaptive management state is a security feature because the mode cannot be switched to the active adaptive management state without the system user's awareness or consent.

[0118] To get started Figure 4 In the method flow shown, a user of the computing system 1 (typically a production manager) will develop an initial proposed extraction plan for extracting natural resources from a target environment. In practice, multiple extraction plans may be implemented simultaneously at different locations within the target environment. Figure 4The example shown includes two mining plans being implemented simultaneously. However, it will be appreciated that other embodiments may implement fewer or more than two mining plans simultaneously. The development of one or more initial mining plans may be done at a number of possible levels of detail. At the highest level, this may simply involve specifying the proposed production targets and the proposed areas to be mined within the target environment. At lower levels, this may include defining more operational details for the proposed mining activities. Optionally, the initial proposed mining plan may also include other desired parameters such as efficiency, power consumption, etc. This may be input into the computing system 1 and stored as plan data for further processing. Figure 4 In the example shown, in step 4.1 the production manager enters planning data for two mining plans that are proposed to be implemented simultaneously.

[0119] The data indicating the two initial proposed mining plans are subject to a "reasonableness check" which includes processing by the physical simulation module of the computing system 1 to check whether the two initial proposed mining plans are physically feasible. If not, the user is prompted to modify the initial proposed mining plans.

[0120] Assuming the "reasonableness check" passes, the data indicating the two initial proposed mining plans will be processed by an optimization algorithm (e.g., a multidisciplinary design optimization (MDO) engine). The MDO engine is configured to process the plan data and the environmental logic module 8 to generate the specific details of the two initial proposed mining plans that meet the specified initial conditions. This may include productivity targets, resource collection rates, detailed proposed trajectories with relevant time stamps for any movable operating equipment (e.g., rigs 4, risers 5, vessels 6, ROVs 7), and operating schedules. It may also include proposed flow rates for riser flows, and other relevant operating data. In some embodiments, as Figure 6 As shown in steps 6.1 to 6.3 of the present invention, an initial compliance check is performed, including simulating the environmental data, operational data, and planning data of the two initial proposed mining plans to determine whether any of the simulated initial proposed mining plans violate any environmental constraints 10. If the simulation predicts that any of the initial proposed mining plans may violate any environmental constraints 10, the computing system 1 is configured to mark the applicable mining plan as invalid in step 6.3 and prompt the user to modify the applicable mining plan in step 6.4 to generate an alternative mining plan for operational implementation. For example, this may involve the user selecting at least one of a plurality of predetermined potential modifications to the mining plan, such as reducing the production target by 10%, or moving the proposed mining site to a less sensitive area, or away from a protected area, etc.

[0121] If a tracked ecosystem variable is predicted to approach but not exceed an acceptable range threshold, enhanced monitoring is triggered. This will improve the system's ability to more accurately predict whether the risk indicator will breach a constraint.

[0122] After the two initially proposed mining plans have passed the aforementioned checks and received approval from the necessary personnel, they are provided to the operations staff for concurrent implementation in the target environment in steps 4.4A and 4.4B. At the start of this concurrent implementation, computing system 1 starts a timer that serves as the starting point for three time periods. The first time period is the time period for the simulation. In a typical embodiment, the first time period may be between approximately one month and approximately one year.

[0123] The second time period is the period during which the two initial mining plans are implemented in parallel in the target environment. This second time period is shorter than both the first and third time periods. Typically, the second time period may be between approximately five days and approximately six months. As will be explained in detail below, multiple alternative mining plans are generated and simulated during this second time period.

[0124] The first time period is longer than the second time period, which allows for the implementation of model predictive control techniques. In other words, the simulation process covers a longer simulation time period than the time period over which the two initial mining plans are actually implemented. This longer timeframe advantageously allows for a more comprehensive calculation of the environmental impacts of the various mining plans. Furthermore, if no compliant alternative mining plans are generated by the end of the second time period, the longer timeframe provides the production manager with greater confidence in deciding whether to proceed with the two initial mining plans. This is because the environmental impacts have been predicted for a period of time beyond the end of the second time period.

[0125] like Figure 4 As shown in Figure 4, six alternative mining plans were generated in step 4.3. Figure 7This generation process is shown in more detail in [ 7 ]. This process utilizes the optimization algorithm described above. However, in this case, in step 7.1, rather than receiving optimization parameters from a user, computing system 1 is configured to automatically generate alternative starting parameters for optimization. At the end of the predefined second time period, two of the six alternative mining plans are selected for implementation. Thus, the starting operating parameters of the first set of three alternative mining plans 4.5A, 4.5B, and 4.5C correspond to the predicted operating parameters of the implemented mining plan 4.4A at the end of the predefined second time period. This means that the operating equipment states of the implemented mining plan 4.4A at the end of the predefined second time period will be consistent with the starting operating equipment states of the three simulated alternative mining plans 4.5A, 4.5B, and 4.5C. Similarly, the starting operating parameters of the second set of three alternative mining plans 4.5D, 4.5E, and 4.5F correspond to the predicted operating parameters of another implemented mining plan 4.4B at the end of the predefined second time period. This means that the state of the working equipment at the end of the predefined second time period of the implemented mining plan 4.4B will be consistent with the starting state of the working equipment of the three simulated alternative mining plans 4.5D, 4.5E and 4.5F.

[0126] One strategy for generating alternative starting parameters (for the MDO engine to process to generate an alternative mining plan) is to configure the computing system 1 to gradually modify the starting parameters (e.g., certain operating variables) of the two user-generated mining plans. Examples of such gradually modifiable operating variables may include: the proposed starting location for mining in the target environment, the proposed rate of extraction of the natural resource, the proposed efficiency level, the proposed power consumption level, the path points (x, y, depth) of the trajectory of each collector, the collection rate associated with each path point, the speed of the collector 4, etc. Another strategy for generating alternative starting parameters for optimization is to configure the computing system 1 to randomly generate the mining plan starting parameters. This random element helps avoid any local minima associated with the user-generated mining plan. However, it should be understood that not all starting parameters can be changed, and the randomly generated starting parameters must be simulated within the physics simulator to ensure that they are achievable within the laws of physics. In general, both of the above strategies can be used to generate multiple sets of alternative optimization starting parameters in step 7.1.

[0127] In step 7.2, computing system 1 adjusts the optimization algorithm based on the current state of the mode indicator. If the mode indicator is in the passive adaptive management state, the optimization algorithm is adjusted to ensure that the multiple alternative mining plans generated are confined to the safe area of the operating range. In other words, the alternative mining plans generated by optimizing the multiple sets of alternative optimization starting parameters using the MDO engine are highly likely to comply with the environmental constraints.

[0128] If the mode indicator is in the active adaptive management state, the optimization algorithm is adjusted to ensure that the multiple alternative mining plans generated are biased toward the boundaries of the operating range. In other words, the alternative mining plans generated by optimizing the MDO engine based on multiple sets of alternative optimization starting parameters are close to violating the environmental constraint 10, or have already violated the environmental constraint 10. In one embodiment, the computing system 1 maintains a variable that defines the degree of this bias. Upon completion of the MDO engine optimization, multiple alternative mining plans and corresponding plan data are generated.

[0129] Thereafter, each of the six alternative mining plans is simulated in steps 4.5A, 4.5B, 4.5C, 4.5D, 4.5E, and 4.5F (see also Figure 7 7.3 of the preceding example). This example shows a total of six alternative mining plans. In practice, however, as many alternative mining plans as are feasible would typically be generated, simulated, and checked for compliance during the second time period. The simulation processes the environmental data, operational data, and planning data for each of the six alternative mining plans to simulate the corresponding state of the target environment at the end of the predefined first time period during which each alternative mining plan was simulated. In other words, the simulation determines, for each alternative mining plan, a range of predicted final states of the target environment after the respective alternative mining plan has been simulated for a period of time equivalent to the first time period.

[0130] The simulation process takes as input a time series history of operational and environmental data, along with the planned data for alternative mining plans generated by the MDO engine optimization, and uses this data to run future simulations. The simulation can be projected into the future to cover a predefined first time period using a world simulator 19 and a series of subsystem simulators 20 (e.g., a materials processing simulator, a biological simulator, and a physics simulator). For example, the computing system 1 can use a physics simulator in conjunction with ocean current forecast data to simulate the spread and deposition of a sediment plume.

[0131] Probabilistic analysis using Bayesian networks can use the final states of the simulation to determine the most likely range of values for key ecosystem indicators at the end of a predefined first time period for each mining alternative. In the deep-sea mining example, the key ecosystem indicators include:

[0132] Primary production

[0133] Sea surface photosynthesis

[0134] ○Phytoplankton density / biomass

[0135] ○Nutrient concentration

[0136] Chemical synthesis

[0137] ○Water Chemistry

[0138] Carbon flux

[0139] ○Plankton community composition

[0140] Bioturbation

[0141] ○ Sediment characteristics

[0142] ○ Cave dweller density

[0143] ○ Sediment radiochemistry

[0144] biodiversity

[0145] Habitat integrity

[0146] ○Plume deposition (seabed)

[0147] ○Integrity of protected areas

[0148] ○Plume diffusion (mid-water layer)

[0149] Fauna characteristics

[0150] ○ Number of key species

[0151] ○ Noise generation

[0152] Microbial diversity

[0153] ○Number of key species

[0154] Nutritional support

[0155] eDNA analysis

[0156] For each mining alternative, a 90% confidence interval is used to determine the likely range of values for each ecosystem indicator. If any part of this likely range falls outside the acceptable range, the corresponding mining alternative is marked as non-compliant.

[0157] The output of the above-described simulation processing can be used to calculate the degree of human impact. The degree of human impact generated by the simulated mining activities for each of the six alternative mining plans can be calculated by subtracting the simulated final environmental state from the simulated initial environmental state. This enables constraint processing, wherein the constraint data for each of the six alternative mining plans and the simulated state of the target environment are processed to determine whether any simulated environmental constraints are violated. If, for an alternative mining plan, no environmental constraints are simulated to be violated, the computing system 1 is configured to mark the mining plan as compliant. If, for an alternative mining plan, at least one environmental constraint is simulated to be violated, the computing system 1 is configured to mark the mining plan as non-compliant. Therefore, at the end of the second time period, the goal is to collect multiple compliant simulated alternative mining plans.

[0158] The above simulation and constraint processing will be carried out in parallel with the implementation of the two mining plans during the predefined second time period. During this implementation, the computing system 1 will continuously monitor the data from the sensor 3 as shown in step 4.6. The computing system 1 will store this empirically derived environmental data and empirically derived operational data for subsequent use (see also Figure 6 Step 6.8 and Figure 8 (Step 8.1).

[0159] At the end of the second time period, the computing system 1 is configured to calculate a metric for each of the six mining alternatives. The metric is intended to quantify the desirability of the mining plan being calculated. Typically, the metric is calculated by taking a weighted average of various criteria. The three metrics for the first set of mining alternatives 4.5A, 4.5B, and 4.5C are compared, and the mining alternative with the highest metric is submitted to the production manager for approval for subsequent implementation (see also Figure 6 Similarly, the three metrics of the second set of alternative mining plans 4.5D, 4.5E and 4.5F are compared and the mining plan with the highest metric is submitted to the production manager for approval for subsequent implementation. Once approved, the process loops through the inner loop 4.7 and restarts the implementation of the two newly approved mining plans (e.g. Figure 6 as shown in steps 6.6 and 6.7).

[0160] The inner loop 4.7 will continue to loop as described above until the third time period ends. In a typical embodiment, the third time period may be between about 1 month and about 1 year. Once the third time period ends, the computing system 1 is configured to sort out the previously stored Figure 4 The environmental and operating data during the inner cycle shown are based on experience (see also Figure 8In step 4.8 (see also step 8.2). Figure 6 Step 6.9 and Figure 8 In step 8.3), one or more research scientists and / or data analysts 28 may apply probabilistic and / or machine learning techniques to these empirically derived environmental and operational data to update any of the following: the probabilistic analysis, the constraint data 10, the acceptable level of state change 12, and / or the ecosystem model 9. The process flow may return to step 4.2 through an outer loop 4.9, where the environmental logic 8 is updated (see also Figure 8 (Step 8.4 of the previous section). Therefore, environmental logic 8 no longer relies on initial expert input. Instead, it has been updated with empirically derived data, so future predictions generated by simulations using environmental logic 8 may be more favorable due to increased certainty. This increased certainty allows computing system 1, when subsequently executing steps 4.3 through 4.7 of the inner loop, to freely generate alternative mining plans that more safely approach the outer boundaries of the operating range.

[0161] like Figure 1 As shown, computing system 1 is configured to maintain a portal 13 accessible to a regulatory body 14. Computing system 1 is also configured to maintain a portal 15 accessible to the public. Users of computing system 1 can customize these portals 13, 15 to select the information available. This information can be selected from environmental data, constraint data, and operational data. Typically, portal 13 accessible to regulatory bodies 14 can contain more detailed information than portal 15 accessible to the public. Furthermore, computing system 1 is configured to maintain a pair of dashboards 23 and 26 that aggregate key information from the digital twin 2 required by operations managers 25 and operators 27 of the mining equipment, respectively.

[0162] Embodiments of the present invention take near-real-time environmental and production data as input and output mining plans, strategies, mitigation measures, actions, data visualizations, and control instructions for operators to execute. This helps advance environmental management strategies that are both adaptive to current operating conditions and projected future states, while remaining sensitive to the system's statistical confidence in the causal relationships defined in the ecosystem model. This approach involves continuously testing hypotheses, collecting data, and updating environmental parameter values to adapt operations to the current and projected future states of the affected environment. Embodiments of the present invention enable key personnel to modify the location, methods, and technical specifications of the mining plan based on changing environmental factors, and such operational changes can be implemented in weeks rather than months or years. Importantly, embodiments of the present invention allow mining plans to be modified dynamically during operations. This contrasts sharply with existing technologies, where such changes are typically only possible before mining activities begin.

[0163] Although a number of preferred embodiments have been described, it will be appreciated by those skilled in the art that many changes and / or modifications may be made to the present invention without departing from the spirit or scope of the invention as broadly described. Therefore, the present embodiments are to be considered in all respects as illustrative and not restrictive.

Claims

1. A computer-implemented method for processing an extraction plan for extracting a natural resource from a target environment, the method comprising configuring a computing system to: accessing environmental data indicative of the target environment; accessing constraint data indicating a plurality of environmental constraints applicable to the target environment; accessing operational data indicative of equipment deployed within the target environment; accessing planning data indicative of the mining plan; Performing simulation processing for processing the environmental data, operating data, and plan data to simulate a state of the target environment after a predefined first time period, and simulating implementation of the mining plan within the first time period; performing constraint processing for processing the constraint data and the simulation state of the target environment to determine whether any environmental constraints are violated by the simulation, and if no environmental constraints are violated by the simulation, marking the mining plan as compliant; Generate multiple alternative mining plans and corresponding planning data, and perform simulation processing and constraint processing on each corresponding planning data to mark multiple compliant mining plans.

2. The computer-implemented method of claim 1 , wherein: include: Define metrics for quantifying the desirability of mining plans; Calculate the appropriate metrics for each compliant mining plan; and submitting the mining plan with the highest metric to a user of the computing system for approval after a predefined second time period, wherein the predefined second time period is shorter than the predefined first time period.

3. The computer-implemented method according to claim 1 or 2, characterized in that If a violation of an environmental constraint is simulated for a mining plan, the computing system is configured to prompt a user of the computing system to select at least one from a plurality of predetermined potential modifications to the mining plan.

4. The computer-implemented method according to any one of claims 1 to 3, wherein: The simulation process utilizes a digital twin configured to simulate a current operating state based on operating data input from sensors, and the digital twin is configured to simulate future operating data during the simulation implementation of a mining plan.

5. The computer-implemented method of claim 4, wherein: The simulation process processes operational data and future operational data using probabilistic analysis to model cause-effect relationships for a plurality of environmental impact indicators.

6. The computer-implemented method according to any one of claims 1 to 5, characterized in that Generating a plurality of alternative mining plans and corresponding plan data includes: gradually modifying operating variables of the mining plans to generate modified operating variables, and processing the modified operating variables in an optimization algorithm.

7. The computer-implemented method according to any one of claims 1 to 6, characterized in that Generating a plurality of alternative mining plans and corresponding plan data includes randomly generating starting parameters of the mining plans and processing the randomly generated starting parameters in an optimization algorithm.

8. The computer-implemented method of claim 7, wherein: The starting parameters include at least one of: a proposed extraction starting location within the target environment, a proposed natural resource extraction rate, a proposed efficiency level, and a proposed power consumption level.

9. The computer-implemented method according to any one of claims 1 to 8, wherein: The computing system has a mode indicator for indicating an active adaptive management state or a passive adaptive management state.

10. The computer-implemented method of claim 9, wherein: When the mode indicator is in the passive adaptive management state, the generation of multiple mining alternative plans is limited to a safe area of the operating range, wherein the mining alternative plans are most likely to meet the environmental constraints.

11. The computer-implemented method according to claim 9 or 10, characterized in that When the mode indicator is in the active adaptive management state, the generation of multiple mining alternative plans is biased towards the boundary area of the operating range, wherein the mining alternative plans are close to violating the environmental constraint condition or violate the environmental constraint condition.

12. The computer-implemented method according to claims 5 and 9, characterized in that The computing system switches the mode indicator between an active adaptive management state and a passive adaptive management state in response to user input.

13. The computer-implemented method of claims 5, 9, 10 and 11, wherein: The computing system is configured to calculate an uncertainty score associated with the probability analysis, and when the uncertainty score is lower than a threshold, the computing system recommends to a user that the mode indicator be set to the active adaptive management state; and when the uncertainty score is higher than the threshold, the computing system automatically sets the mode indicator to the passive adaptive management state.

14. The computer-implemented method according to any one of claims 1 to 13, wherein: The method includes implementing the mining plan within a predefined second time period, and simultaneously generating a plurality of alternative mining plans and corresponding plan data within the predefined second time period.

15. The computer-implemented method of claim 14, wherein: The starting operating parameters of at least some of the alternative production plans correspond to predicted operating parameters of the implemented production plan at the end of the predefined second time period.

16. The computer-implemented method according to any one of claims 1 to 15, wherein: The method includes defining a third time period, wherein the third time period is longer than the second time period, and the computing system is configured to collate the empirically derived environmental data and the empirically derived operational data at the end of the third time period.

17. The computer-implemented method according to claims 5 and 16, characterized in that The Research Scientist and / or Data Analyst applies probabilistic and / or machine learning techniques to empirically derived environmental data and empirically derived operational data to update at least one of the following: Probability analysis; Constraint data; Acceptable levels of status change; and / or Ecosystem model.

18. The computer-implemented method according to claim 16 or 17, wherein: The second time period is between 5 days and 6 months, and the first and third time periods are both between 1 month and 1 year.

19. The computer-implemented method according to any one of claims 1 to 18, wherein: The computing system is configured to maintain a portal for access by regulatory agencies and / or the public, the portal providing at least one of the following types of information: environmental data, constraint data, and operational data.

20. A computing system configured to perform the method according to any one of claims 1 to 19.

21. A system for extracting natural resources from a target environment, the system comprising: A computing system configured to perform the method according to claim 1; mining equipment, the mining equipment being deployed in the target environment; as well as A plurality of sensors are arranged on and around the mining equipment and in the target environment, and the sensors are capable of communicating with the computing system via a telemetry link.

Images