A method and system for evaluating the carrying capacity of seaweed

Abstract

The application discloses a seaweed carrying capacity intelligent evaluation method and system, and belongs to the technical field of seaweed intelligent management. The seaweed carrying capacity intelligent evaluation method comprises the following steps: collecting water quality parameters and water samples in real time, wherein the water quality parameters include dissolved inorganic nitrogen concentration, water temperature and light intensity; establishing a seaweed growth dynamic evaluation model coupled with hydrodynamics-ecosystem; dividing the target water area into multiple evaluation units according to the real-time collected data, and online calibrating the key physiological parameters in the established seaweed growth dynamic evaluation model to obtain the calibrated model; based on the calibrated model, setting multiple different seaweed cultivation density scenarios for simulation, predicting the biomass change of seaweed under each scenario and the influence of seaweed on water quality, and evaluating and outputting the seaweed carrying capacity according to the preset ecological threshold and index; and sending the seaweed carrying capacity obtained by evaluation to a remote monitoring center.

Description

Technical Field

[0001] This invention relates to the field of intelligent seaweed management technology, and more specifically to an intelligent assessment method and system for seaweed carrying capacity. Background Technology

[0002] In recent years, with the intensive development of aquaculture, the large-scale cultivation of seaweed (such as kelp and wakame) has brought economic benefits but has also had a significant impact on the nearshore ecological environment. Over-cultivation leads to nutrient depletion, water quality deterioration, and a decline in the quality of cultured organisms in local waters, while excessively low cultivation densities fail to fully utilize the water's productivity. Therefore, scientifically assessing seaweed cultivation capacity and determining reasonable cultivation densities and layouts have become critical issues that urgently need to be addressed in aquaculture management and environmental protection.

[0003] Currently, methods for assessing seaweed aquaculture capacity mainly fall into two categories. One category is based on field surveys and statistical experience models. This involves obtaining water quality and biomass data through manual ship sampling and laboratory analysis, then estimating the aquaculture capacity based on historical data. This method is labor-intensive, lacks timeliness, and struggles to reflect dynamic changes in the aquatic environment. The other category is based on numerical simulation methods using ecological dynamics models. For example, Chinese invention patent 202010455299.5 discloses a dynamic assessment method and application for aquaculture capacity. This method constructs an ecosystem model including modules such as nutrients, phytoplankton, detritus, and cultured organisms, and couples it with a hydrodynamic model to dynamically predict the growth and yield of cultured organisms under different stocking densities. However, this method still has significant shortcomings: firstly, the initial environmental parameters and boundary conditions required by the model mainly rely on offline, static historical survey data or literature values, lacking the ability to respond to real-time environmental changes; secondly, once model parameters (such as maximum growth rate and half-saturation constant) are calibrated, they are fixed and cannot be adaptively calibrated according to actual water quality fluctuations, leading to a significant decrease in model prediction accuracy during long-term operation or cross-regional application.

[0004] In summary, existing technologies have not yet achieved deep coupling between mobile, real-time water quality monitoring platforms and ecological dynamics models, and lack an intelligent method and system that can dynamically calibrate models based on real-time environmental data and quickly assess the carrying capacity of seaweed.

[0005] Therefore, how to provide an intelligent assessment method and system for the carrying capacity of seaweed is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] In view of this, the present invention provides an intelligent assessment method and system for the carrying capacity of seaweed, which solves the problems of existing aquaculture capacity assessment relying on static historical data, lagging model parameter calibration, and inability to adapt to dynamic environmental changes.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: A smart assessment method for seaweed carrying capacity includes: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establish a dynamic assessment model for algal growth that couples hydrodynamics and ecosystem; Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model. Based on the calibrated model, multiple different seaweed culture density scenarios were set up for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating the output seaweed carrying capacity according to the preset ecological thresholds and indicators. The assessed seaweed carrying capacity is sent to the remote monitoring center.

[0008] Furthermore, the seaweed growth dynamic assessment model includes a water proton model and a seaweed growth sub-model constructed based on the dynamic energy budget theory, wherein the growth rate of the seaweed growth sub-model is jointly limited by water temperature, light intensity, nitrogen content in the seaweed, and dissolved inorganic nitrogen concentration in the water.

[0009] Furthermore, the seaweed growth model specifically includes: seaweed biomass change rate = growth rate - respiration rate - decay rate; The growth rate is obtained by multiplying the maximum growth rate by the minimum value of the water temperature limitation function, the light limitation function, and the nutrient limitation function; the nutrient limitation function is calculated using the Michaelis-Menten equation based on the nitrogen content in the algae and the dissolved inorganic nitrogen concentration in the water. Furthermore, the dynamic division of the target water area into multiple evaluation units based on real-time collected data is as follows: Based on real-time collected hydrological environmental data and seaweed farming layout data, combined with geographic information, assessment units are divided according to hydrological environmental parameters and farming density areas.

[0010] Furthermore, the online calibration employs an ensemble Kalman filter algorithm or a particle filter algorithm to assimilate the real-time collected water quality parameters and seaweed biomass sampling data with the simulated values ​​of the seaweed growth dynamic assessment model, so as to update the key physiological parameters of the model in real time.

[0011] Furthermore, the ecological threshold includes: a lower limit for the concentration of dissolved inorganic nitrogen in water or a lower limit for the concentration of dissolved oxygen in water.

[0012] Furthermore, the indicators include the maximum sustainable yield of seaweed per unit area.

[0013] Furthermore, the carrying capacity of the output seaweed is specifically defined as: the range of aquaculture densities that can achieve the maximum sustainable yield of seaweed per unit area or unit of water, provided that the key water quality indicators are not lower than the preset ecological threshold.

[0014] A smart assessment system for seaweed carrying capacity includes: Mobile water quality monitoring device: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establishment Module: Establish a dynamic assessment model for seaweed growth that couples hydrodynamics and ecosystem; Calibration module: Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model; Evaluation module: Based on the calibrated model, multiple different seaweed culture density scenarios are set for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating and outputting the seaweed carrying capacity according to preset ecological thresholds and indicators. Data transmission module: Sends the assessed seaweed carrying capacity to the remote monitoring center.

[0015] As can be seen from the above technical solution, compared with the prior art, the present invention provides an intelligent assessment method and system for seaweed carrying capacity. Through dynamic zoning and online parameter calibration, the model can adapt to the environmental characteristics and seasonal changes of different waters, improving the accuracy and generalization ability of the assessment. It integrates scenario simulation function, which can predict the ecological and yield results under different aquaculture densities, providing quantitative and scientific decision-making basis for aquaculture enterprises and regulatory departments. At the same time, the present invention can operate automatically for a long time without human intervention, which greatly reduces labor costs. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the method flow provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: See Figure 1 Embodiment 1 of the present invention discloses an intelligent assessment method for the carrying capacity of seaweed, comprising: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establish a dynamic assessment model for algal growth that couples hydrodynamics and ecosystem; Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model. Based on the calibrated model, multiple different seaweed culture density scenarios were set up for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating the output seaweed carrying capacity according to the preset ecological thresholds and indicators. The assessed seaweed carrying capacity is sent to the remote monitoring center.

[0020] In one specific embodiment, the seaweed growth dynamic assessment model includes a water proton model and a seaweed growth sub-model constructed based on dynamic energy budget theory, wherein the growth rate of the seaweed growth sub-model is jointly limited by water temperature, light intensity, in vivo nitrogen content, and dissolved inorganic nitrogen concentration in the water.

[0021] In one specific embodiment, the seaweed growth model specifically includes: seaweed biomass change rate = growth rate - respiration rate - decay rate; The growth rate is obtained by multiplying the maximum growth rate by the minimum value of the water temperature limitation function, the light limitation function, and the nutrient limitation function; the nutrient limitation function is calculated using the Michaelis-Menten equation based on the nitrogen content in the algae and the dissolved inorganic nitrogen concentration in the water. In one specific embodiment, the dynamic division of the target water area into multiple evaluation units based on real-time collected data is as follows: Based on real-time collected hydrological environmental data and seaweed farming layout data, combined with geographic information, assessment units are divided according to hydrological environmental parameters and farming density areas.

[0022] In one specific embodiment, the online calibration employs an ensemble Kalman filter algorithm or a particle filter algorithm to assimilate real-time collected water quality parameters and seaweed biomass sampling data with the simulated values ​​of the seaweed growth dynamic assessment model, so as to update the key physiological parameters of the model in real time.

[0023] In one specific embodiment, the ecological threshold includes: a lower limit for the concentration of dissolved inorganic nitrogen in water or a lower limit for the concentration of dissolved oxygen in water.

[0024] In one specific embodiment, the metric includes the maximum sustainable yield of seaweed per unit area.

[0025] In one specific embodiment, the output seaweed carrying capacity is specifically defined as: the range of aquaculture densities that can achieve the maximum sustainable yield of seaweed per unit area or per unit water body, provided that the key water quality indicators are not lower than the preset ecological threshold.

[0026] Traditional models rely on offline, static historical data, while this invention uses real-time acquired data to drive the model and introduces dynamic partitioning, data assimilation, and scenario simulation.

[0027] Example 2: Embodiment 2 of the present invention discloses an intelligent assessment method for the carrying capacity of seaweed, comprising the following steps: Step S1: Deploy at least one mobile water quality monitoring device based on wireless technology. The device is equipped with a microprocessor, a wireless radio frequency transceiver module, a motor drive module, a water quality monitoring module, and a sampling drive module. The device moves within the target water area according to a preset route or remote control command and performs in-situ water sample collection and water quality parameter monitoring at designated sampling points, generating real-time monitoring data. The water quality parameters include at least dissolved inorganic nitrogen concentration, particulate organic carbon concentration, phytoplankton biomass (characterized by chlorophyll a), water temperature, light intensity, and water depth.

[0028] Specifically, in this embodiment, the seaweed (kelp) individual growth sub-model is constructed based on the dynamic energy budget theory. Its biomass (dry weight, B, unit: g / plant) dynamic changes are determined by three processes: growth, respiration, and decay. Its differential equation is:

[0029] in: This is the actual growth rate, not a constant value, but rather limited by the combined effects of water temperature, light intensity, and nitrogen content within the plant, i.e.: For maximum growth rate The temperature constraint function is described using a Gaussian optimal curve:

[0030] in The measured water temperature is in °C. The optimal growth temperature (e.g., 12℃). and These are the upper and lower limits of the growth temperature, respectively.

[0031] Let be the illumination constraint function, described by the Steele equation, and consider the light attenuation at water depth z:

[0032] in, The intensity of light on the water surface is collected in real time by a mobile monitoring device; The extinction coefficient of the water body; For optimal light intensity.

[0033] It is the nitrogen limitation function in vivo. Let be the limiting function for dissolved inorganic nitrogen in water, and take the smaller of the two values ​​as the actual nutrient limitation. The nitrogen limitation in vivo is expressed in the Michaelis-Menten form:

[0034] in This refers to the free nitrogen content within kelp. To maintain the minimum nitrogen content required for growth, It is the half-saturation constant.

[0035] Limitation function of dissolved inorganic nitrogen in water ,in For real-time monitoring of dissolved inorganic nitrogen concentration, It is the half-saturation constant.

[0036] The respiration rate is a function of temperature. ,in The maximum respiratory rate at 20°C. This is an empirical coefficient.

[0037] E is the decay rate, which is set as a function of temperature and increases when the temperature exceeds the optimal range.

[0038] Step S2: Establish a dynamic assessment model for algal growth coupled with hydrodynamics and ecosystem, the model including: The hydrodynamic sub-model is used to simulate the flow field, water exchange, and boundary material flux of the target water area. The water proton model is used to simulate the kinetic mass conservation processes of nutrients, phytoplankton, particulate organic carbon, and dissolved oxygen. The seaweed growth sub-model, based on the dynamic energy budget theory, is used to simulate the biomass changes of individual seaweeds and populations. The seaweed growth sub-model includes the processes of growth, respiration, and decay, and its growth rate is regulated by a joint constraint function of water temperature, light intensity, nitrogen content in the seaweed, and dissolved inorganic nitrogen concentration in the water. Coupling relationship: The seaweed growth sub-model and the water quality sub-model are bidirectionally coupled through source and sink terms of carbon, nitrogen, phosphorus and dissolved oxygen to describe the impact of seaweed growth on water quality and the feedback of water quality changes on seaweed growth.

[0039] Specifically, this invention achieves real-time bidirectional coupling between the algae growth sub-model and the water proton sub-model (such as dissolved inorganic nitrogen (DIN) and particulate organic carbon (POC) modules), as expressed mathematically below: (1) The driving force of the water proton model on the phycosphere model: Actual growth rate of seaweed In , and The item, whose input variables are water temperature (T), water surface illumination (T), etc. water bodies The concentrations were all collected in real time by the mobile water quality monitoring device in step S1 and input into the model. Specifically, the extinction coefficient of the water body... It is calculated from data from the turbidity sensor or underwater photon detector mounted on the monitoring device.

[0040] (2) Feedback from the seaweed seed model to the water proton model: The growth, respiration, and decay processes of seaweed absorb or release nutrients and organic matter, and these feedbacks are added to the source and sink terms of the water proton model: Impact on dissolved inorganic nitrogen (DIN) (summary): Algae absorb DIN from the water during growth. Within the evaluation unit (model box), the following consumption term is added to the DIN change rate equation:

[0041] in The nitrogen-carbon ratio of seaweed tissue. For the volume of the model box, This represents the total number of algae plants in the model chamber. This consumption term is proportional to the algae growth rate μ and biomass B.

[0042] The impact of particulate organic carbon (POC) (source term): Decomposed seaweed and uneaten debris are converted into POC. The following generation term is added to the POC change rate equation:

[0043] in The carbon flux generated by decay. This is a further decomposition of seaweed debris. is the carbon conversion coefficient.

[0044] The effects on dissolved oxygen (DO): oxygen production from algal photosynthesis (source term) and oxygen consumption from respiration (sink term). In the equation for the rate of change of DO:

[0045] in and These are the oxygen production and oxygen consumption coefficients, respectively.

[0046] Step S3: Dynamic Partitioning and Model Parameterization: Based on the real-time hydrological environment and seaweed farming layout data collected by the mobile water quality monitoring device, combined with historical remote sensing or geographic information data, the target water area is dynamically divided into multiple assessment units (model boxes). Within each evaluation unit, key physiological parameters of the seaweed growth dynamic evaluation model are calibrated online or assimilated using real-time monitoring data; the key physiological parameters include at least the maximum growth rate of seaweed, the half-saturation absorption constant, the optimal growth temperature, and the respiration rate.

[0047] Specifically, in this embodiment, dynamic partitioning is not a one-time event, but is automatically executed in each evaluation cycle (e.g., daily). The specific rules are as follows: Partitioning Criteria: The target water area is dynamically partitioned into grids using a multidimensional Euclidean distance clustering algorithm (such as K-means). The feature vector for each grid (100m × 100m) is as follows: X = [water depth, tidal current velocity, current DIN concentration, chlorophyll a concentration, current seaweed cultivation density] The tidal flow velocity is provided by an offline coupled hydrodynamic model (with daily boundary updates), while the remaining parameters are obtained by actual measurements at the grid center point or representative point using a moving monitoring device.

[0048] Specifically, the partitioning process is as follows: S31: Standardize the eigenvectors X of all meshes.

[0049] S32: Set the initial number of partitions k=3 (which can be dynamically adjusted according to the complexity of the water area), and run K-means clustering until the sum of squared errors within each cluster is minimized.

[0050] S33: Outputs the boundary and centroid coordinates for each cluster (i.e., each "model box"). Meshes belonging to the same model box share the same model parameters and water exchange boundary conditions.

[0051] Specifically, the initial environmental variables (such as DIN and phytoplankton concentration) for each model chamber are taken as the average of the measured values ​​of all grids within that chamber. The mass exchange flux between model chambers is determined by the net flow rate at the boundary between the two chambers calculated by the hydrodynamic model.

[0052] Specifically, the specific steps of data assimilation based on ensemble Kalman filtering.

[0053] This embodiment uses Ensemble Kalman Filtering (EnKF) to update the key physiological parameter θ in the algae growth model in real time. The specific steps are as follows: At time t=0, N set members (N=100) of the parameter vector θ are generated, and each member is perturbed by adding a Gaussian perturbation near the reference value in the literature.

[0054] For each set member i, using model M and the parameters θi,t-1a assimilated at the previous time step, predict the model state at the current time step (such as algal biomass B and DIN concentration).

[0055] in This represents the model error.

[0056] When the mobile monitoring device transmits a new measured value dt at time t, calculate the Kalman gain Kt and update the parameters and state of each set member:

[0057] Where H is the observation operator (which maps the model state to the observation space). This represents the observation error.

[0058] The average of all updated set members is taken as the optimal parameter estimate at time t, which is used for the forecast of the next time step and the final scenario simulation.

[0059] Step S4: Scenario Simulation and Capacity Assessment: Based on the current water quality conditions and the calibrated model, several different seaweed farming density scenarios were set. Run the seaweed growth dynamic assessment model to predict the individual growth curve, final biomass, and dynamic impact on key water quality indicators (such as dissolved inorganic nitrogen) of seaweed under various scenarios within a preset cultivation period. Based on preset ecological thresholds (such as minimum dissolved oxygen concentration and maximum allowable nutrient salt decline) and economic benefit indicators (such as maximum sustainable yield), assess and output the seaweed carrying capacity and optimal aquaculture density recommendations for the water area under the current environment.

[0060] Step S5: Wireless transmission and visualization of results: The seaweed carrying capacity, optimal culture density and water quality prediction data obtained from the assessment are sent to the remote monitoring center via a wireless radio frequency transceiver module for real-time display and early warning.

[0061] Example 3: Embodiment 3 of the present invention discloses an intelligent assessment system for seaweed carrying capacity, comprising: Mobile water quality monitoring device: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establishment Module: Establish a dynamic assessment model for seaweed growth that couples hydrodynamics and ecosystem; Calibration module: Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model; Evaluation module: Based on the calibrated model, multiple different seaweed culture density scenarios are set for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating and outputting the seaweed carrying capacity according to preset ecological thresholds and indicators. Data transmission module: Sends the assessed seaweed carrying capacity to the remote monitoring center.

[0062] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0063] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligently assessing the carrying capacity of seaweed, characterized in that, include: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establish a dynamic assessment model for algal growth that couples hydrodynamics and ecosystem; Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model. Based on the calibrated model, multiple different seaweed culture density scenarios were set up for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating the output seaweed carrying capacity according to the preset ecological thresholds and indicators. The assessed seaweed carrying capacity is sent to the remote monitoring center.

2. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The seaweed growth dynamic assessment model includes a water proton model and a seaweed growth sub-model constructed based on dynamic energy budget theory. The growth rate of the seaweed growth sub-model is jointly limited by water temperature, light intensity, nitrogen content in the seaweed, and dissolved inorganic nitrogen concentration in the water.

3. The intelligent assessment method for seaweed carrying capacity according to claim 2, characterized in that, The seaweed growth model specifically includes: seaweed biomass change rate = growth rate - respiration rate - decay rate; The growth rate is obtained by multiplying the maximum growth rate by the minimum value of the water temperature limitation function, the light limitation function, and the nutrient limitation function; the nutrient limitation function is calculated using the Michaelis-Menten equation based on the nitrogen content in the algae and the dissolved inorganic nitrogen concentration in the water.

4. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The process of dynamically dividing the target water area into multiple assessment units based on real-time collected data is as follows: Based on real-time collected hydrological environmental data and seaweed farming layout data, combined with geographic information, assessment units are divided according to hydrological environmental parameters and farming density areas.

5. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The online calibration employs an ensemble Kalman filter algorithm or a particle filter algorithm to assimilate real-time collected water quality parameters and seaweed biomass sampling data with the simulated values ​​of the seaweed growth dynamic assessment model, thereby updating the model's key physiological parameters in real time.

6. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The ecological thresholds include: the lower limit of dissolved inorganic nitrogen concentration in water or the lower limit of dissolved oxygen concentration in water.

7. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The metrics include the maximum sustainable yield of seaweed per unit area.

8. The intelligent assessment method for seaweed carrying capacity according to claim 1, characterized in that, The specific carrying capacity of the output seaweed is: the range of aquaculture density that can achieve the maximum sustainable yield of seaweed per unit area or per unit water body, provided that the key water quality indicators are not lower than the preset ecological threshold.

9. A smart assessment system for seaweed carrying capacity, characterized in that, include: Mobile water quality monitoring device: Real-time collection of water quality parameters and water samples, including dissolved inorganic nitrogen concentration, water temperature, and light intensity; Establishment Module: Establish a dynamic assessment model for seaweed growth that couples hydrodynamics and ecosystem; Calibration module: Based on real-time collected data, the target water area is dynamically divided into multiple assessment units, and the key physiological parameters in the established seaweed growth dynamic assessment model are calibrated online to obtain the calibrated model; Evaluation module: Based on the calibrated model, multiple different seaweed culture density scenarios are set for simulation, predicting the changes in seaweed biomass and its impact on water quality under each scenario, and evaluating and outputting the seaweed carrying capacity according to preset ecological thresholds and indicators. Data transmission module: Sends the assessed seaweed carrying capacity to the remote monitoring center.

Images