An ecological environment monitoring data processing method

Abstract

The present invention relates to the field of data processing, and particularly to a method for processing ecological environment monitoring data. The content includes: collecting ecological environment monitoring data in real time and performing fusion processing, purifying the fused signal through convolution operation to obtain a purified signal; performing signal reconstruction based on the purified signal; dynamically adjusting the adaptive weights of sensors based on the ecological environment monitoring data and the reconstructed signal; constructing a spatio-temporal model based on the adaptive weights of sensors and the reconstructed signal to obtain a spatio-temporal modeling result, and predicting the future ecological environment state. It solves the problems that the traditional method for processing ecological environment monitoring data lacks effective purification processing of signals, resulting in obvious external interference to environmental monitoring data; ignores the adaptability of sensors, resulting in excessive amplification or reduction of errors of some sensors; and does not consider the comprehensive influence of spatio-temporal changes, resulting in low prediction accuracy, slow response speed, and inability to effectively cope with complex environmental changes.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method for processing ecological environment monitoring data. Background Art

[0002] With the increasingly serious global climate change and ecological environment problems, ecological environment monitoring has become an important means to protect natural resources and achieve sustainable development. In order to timely understand and predict the changes in the ecological environment, many fields rely on sensor networks to monitor multiple environmental factors such as air quality, water quality, soil humidity, temperature, and light in real time. These sensors can provide a large amount of high-frequency data, helping scientific researchers, governments, and environmental protection organizations understand the current environmental conditions and make decisions. However, due to the complex and multi-dimensional nature of environmental changes, and the differences in measurement accuracy, response time, and sensitivity among different sensors, traditional monitoring methods often have difficulty effectively integrating and processing data from different sensors, resulting in environmental monitoring data being often affected by noise, outliers, and the synergistic effects between different sensors.

[0003] Therefore, how to effectively fuse environmental monitoring data from multi-source sensors, eliminate noise interference, and improve the reliability and accuracy of data has become a key issue in the current ecological environment monitoring system. In addition, with the rapid increase in the amount of environmental monitoring data, how to effectively mine the potential laws in the data through intelligent data processing methods, predict future environmental states, and provide timely feedback and decision support has become an urgent need to improve the efficiency of environmental monitoring.

[0004] The above technologies have the following technical problems: lack of effective purification processing of sensor signals, resulting in obvious external interference to environmental monitoring data and affecting the reliability of subsequent analysis; ignoring the adaptability of sensors and failing to fully utilize the monitoring capabilities of each sensor at a specific moment, which may lead to the over-amplification or reduction of errors of some sensors; not considering the comprehensive impact of spatio-temporal changes and being unable to accurately capture the complex relationships and dynamic changes between environmental variables, resulting in low prediction accuracy, slow response speed, and inability to effectively cope with complex environmental changes. Summary of the Invention

[0005] The present invention provides a method for processing ecological environment monitoring data to solve the problems of the traditional method for processing ecological environment monitoring data, which lacks effective purification processing of signals, resulting in obvious external interference to environmental monitoring data and affecting the reliability of subsequent analysis; ignores the adaptability of sensors and fails to fully utilize the monitoring capabilities of each sensor at a specific moment, which may lead to the over-amplification or reduction of errors of some sensors; does not consider the comprehensive impact of spatio-temporal changes and is unable to accurately capture the complex relationships and dynamic changes between environmental variables, resulting in low prediction accuracy, slow response speed, and inability to effectively cope with complex environmental changes.

[0006] A method for processing ecological environment monitoring data according to the present invention specifically includes the following technical solutions:

[0007] A method for processing ecological environment monitoring data includes the following steps:

[0008] S1. Real-time collect ecological environment monitoring data, perform fusion processing to obtain a fused signal; purify the fused signal through convolution operation to obtain a purified signal; based on the purified signal, perform signal reconstruction to generate a reconstructed signal;

[0009] S2. Dynamically adjust the adaptive weight of the sensor based on the ecological environment monitoring data and the reconstructed signal; construct a spatio-temporal model based on the adaptive weight of the sensor and the reconstructed signal to obtain a spatio-temporal modeling result; predict the future ecological environment state based on the spatio-temporal modeling result to obtain a predicted result of the environmental state at a future moment.

[0010] Preferably, S1 specifically includes:

[0011] Based on the sensitivity and reliability of environmental changes, introduce the contribution coefficient of sensor data in the fusion process, and perform weighted fusion processing on the ecological environment monitoring data to obtain a fused signal.

[0012] Preferably, S1 specifically includes:

[0013] Perform sliding window processing on the fused signal through convolution operation to remove high-frequency noise in the fused signal to obtain a purified signal.

[0014] Preferably, S1 specifically includes:

[0015] Combine the purified signal with the normal signal, and adjust the contribution degrees of the purified signal and the normal signal through a weighting method to generate a reconstructed signal.

[0016] Preferably, S2 specifically includes:

[0017] Dynamically adjust the adaptive weight of the sensor based on the error between the ecological environment monitoring data and the reconstructed signal, and the signal change trend. The specific formula is:

[0018] ,

[0019] where is the adaptive weight of the th sensor; is a regulation factor used to control the sensitivity of the error; is the ecological environment monitoring data collected by the th sensor; is the reconstructed signal; is the mean square error between the ecological environment monitoring data collected by the -th sensor and the reconstructed signal; is the number of sensors; is the influence relationship between the reconstructed signal and the ecological environment monitoring data collected by the -th sensor, which is used to reflect the signal change trend; is the correlation coefficient.

[0020] Preferably, the S2 specifically includes:

[0021] Integrate the ecological environment monitoring data collected by the sensors at the same moment and the adaptive weights of the sensors, combine with the reconstructed signal, and introduce the time change factor to construct a spatio-temporal model to obtain the spatio-temporal modeling result.

[0022] Preferably, the S2 specifically includes:

[0023] Based on the spatio-temporal modeling result, combine with the ecological environment monitoring data and the reconstructed signal to predict the future ecological environment change.

[0024] Preferably, the S2 specifically includes:

[0025] In the process of predicting the future ecological environment change, introduce the spatio-temporal feedback factor and the cumulative factor, combine the spatio-temporal feedback with the spatio-temporal integration to obtain the prediction result of the environmental state at the future moment, and the prediction formula is:

[0026] ,

[0027] where, represents the prediction result of the environmental state at the future moment ; is the -th weighting coefficient, which is used to adjust the contribution degree of each sensor to the prediction result of the environmental state at the future moment; is the ecological environment monitoring data collected by the -th sensor at the moment; is the spatio-temporal feedback factor; is the prediction result of the environmental state at the moment; is the cumulative factor; is the reconstructed signal at the moment; is the weighting coefficient, which is used to adjust the influence of the spatio-temporal modeling result on the prediction result of the environmental state at the future moment; is the spatio-temporal modeling result at the

[0028] The beneficial effects of the technical solution of the present invention are as follows:

[0029] 1. Through the weighted fusion of multiple sensor data, it is possible to effectively integrate the ecological environment monitoring data collected by different sensors under different environmental conditions, ensuring that the contribution of each sensor in the data processing process is reasonably reflected; the convolution operation is used to purify the fused signal, effectively removing high-frequency noise while retaining the low-frequency components in the fused signal, making the purified signal more representative; the introduction of the convolution operation can not only improve the smoothness of the purified signal, but also ensure the accuracy of subsequent signal reconstruction by eliminating interference, providing high-quality input for subsequent data processing steps.

[0030] 2. By weighted combination of the purified signal and the normal signal for signal reconstruction, it is possible to remove abnormal fluctuations in the data while maintaining the environmental change trend, making the reconstructed signal closer to the real environmental state, improving the response ability of the ecological environment monitoring system. Especially in the face of complex environmental changes, it can effectively restore the true characteristics of the ecological environment monitoring data, providing an accurate basis for subsequent spatio-temporal modeling and prediction.

[0031] 3. The present invention introduces the concept of adaptive weights, dynamically adjusting the contribution of sensors according to the error between the ecological environment monitoring data collected by the sensors and the reconstructed signal, optimizing the role of each sensor in the monitoring process; the application of adaptive weights enables the ecological environment monitoring system to more accurately reflect the actual state of the ecological environment according to changes in different time points and environmental conditions, avoiding deviations or distortions that may occur in a single sensor.

[0032] 4. Through spatio-temporal modeling technology, the present invention can accurately predict the environmental state at future moments based on the data of different sensors and environmental change trends; spatio-temporal modeling not only considers the influence of historical environmental state prediction results, but also combines adaptive weights and time factors, improving the accuracy and timeliness of prediction. The predicted environmental state at future moments can provide strong support for environmental monitoring and management, helping decision-makers better respond to environmental changes and formulate reasonable countermeasures. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flowchart of a method for processing ecological environment monitoring data according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0034] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0036] The following specifically describes the specific solution of a method for processing ecological environment monitoring data provided by the present invention with reference to the accompanying drawings.

[0037] Refer to the attached Figure 1 , which shows a flowchart of a method for processing ecological environment monitoring data provided by an embodiment of the present invention. The method includes the following steps:

[0038] S1. Real-time collect ecological environment monitoring data, perform fusion processing to obtain a fused signal; purify the fused signal through convolution operation to obtain a purified signal; based on the purified signal, perform signal reconstruction to generate a reconstructed signal;

[0039] During the ecological environment monitoring process, real-time collect ecological environment monitoring data through multiple sensors; the sensors include temperature sensors, humidity sensors, air pressure sensors, light sensors, etc. Each sensor collects ecological environment monitoring data with different characteristics under different environmental conditions.

[0040] Since the measurement accuracies and reliabilities of each sensor are different, based on the sensitivity and reliability to environmental changes, the ecological environment monitoring data collected by each sensor can be weighted and fused to ensure that each sensor can reasonably reflect its role in the overall monitoring according to its actual contribution degree during the data fusion process, effectively reducing the influence of the measurement error of a certain sensor on the overall result, so as to finally generate a more stable and accurate comprehensive signal, that is, the fused signal, thereby providing more reliable monitoring data; the specific fusion formula is:

[0041] ,

[0042] wherein, is the fused signal at moment; is the ecological environment monitoring data collected by the th sensor at moment; is the number of sensors; is the acquisition period; is the contribution coefficient of the data of the th sensor in the fusion process, which determines the proportion of each sensor data in the fused signal and is obtained through experiments;

[0043] In the data processing process, ecological environment monitoring data is often affected by noise, outliers, and external disturbances. To eliminate noise, the fused signal input is processed with a sliding window through a convolution operation, gradually removing the high-frequency noise in the fused signal and retaining the important low-frequency components to reduce the data volatility, thereby effectively suppressing noise interference, making the purified signal obtained after the convolution operation more representative, and providing a clear and reliable input for the subsequent signal reconstruction step. The formula is as follows:

[0044] ,

[0045] where, represents the purified signal obtained after the convolution operation at time ; is the th convolution kernel, which is used to filter the fused signal during the convolution process; is the number of convolution kernels; represents the convolution operation; is the residual term, which represents the error or noise existing in the convolution process. The convolution kernel is dynamically adjusted according to the characteristics of the ecological environment and the change pattern of the fused signal to ensure that the signal within each time window can remove interference to the greatest extent and retain effective information.

[0046] After signal purification, the purified signal is combined with the normal signal, and through a weighting method, the contribution degrees of the purified signal and the normal signal are adjusted to generate a reconstructed signal that best conforms to the actual ecological environment changes; the normal signal represents the normal data state of the ecological environment, and the range of the normal signal is determined by comparing with ecological environment standards (such as regulations or reference values); the reconstructed signal can restore the trend of the normal signal while retaining the abnormal changes in the purified signal as much as possible to ensure the accuracy of ecological environment monitoring data; in addition, the reconstructed signal will contain more ecological environment information, especially when facing complex environmental changes, it can effectively improve the detection and prediction capabilities of the ecological environment monitoring system. The formula for generating the reconstructed signal is:

[0047] ,

[0048] where, is the reconstructed signal at a moment; is a weighting coefficient used to adjust the contribution of the purified signal and the normal signal to the reconstructed signal at a moment, and is obtained through experiments; is the normal signal at a moment, which is used to represent the normal data state of the ecological environment, without noise or abnormality. By comparing with ecological environment standards (such as regulations or benchmark values), the range of the normal signal is determined; is a weighting coefficient used to adjust the influence of the normal signal on the reconstructed signal at a moment, and is obtained through experiments. The combination of the purified signal and the normal signal can effectively remove the irregularities in the ecological environment monitoring data while maintaining a reasonable trend of ecological environment changes, so that the reconstructed signal is closer to the real environmental state.

[0049] S2. Based on the ecological environment monitoring data and the reconstructed signal, dynamically adjust the adaptive weight of the sensor; based on the adaptive weight of the sensor and the reconstructed signal, construct a spatio-temporal model to obtain the spatio-temporal modeling result; based on the spatio-temporal modeling result, predict the future ecological environment state to obtain the environmental state prediction result at a future moment.

[0050] Since the accuracy and environmental adaptability of the sensor may change over time, therefore, an adaptive weight needs to be assigned to each sensor at each time point to correct the contribution degree of the ecological environment monitoring data collected by each sensor to the comprehensive environmental state; the adaptive weight of the sensor is dynamically adjusted according to the error between the ecological environment monitoring data collected by the sensor and the reconstructed signal and the signal change trend. The greater the error, the smaller its adaptive weight, so as to reduce the influence of the current sensor on the overall data processing result. The specific formula is:

[0051] ,

[0052] where, is the adaptive weight of the th sensor; is a regulation factor used to control the sensitivity of the error and is obtained through experiments; is the ecological environment monitoring data collected by the th sensor; is the reconstructed signal; is the number of sensors; is the square error between the ecological environment monitoring data collected by the th sensor and the reconstructed signal, which is used to measure the size of the error; is the difference between the reconstructed signal and the The influence relationship between the ecological environment monitoring data collected by sensors, which is used to reflect the signal change trend; is the correlation coefficient, obtained through experiments.

[0053] Integrate the ecological environment monitoring data collected by sensors at the same moment and the adaptation weights of the sensors to reflect the changes in the ecological environment state in the spatial and temporal dimensions, and combine the reconstructed signal to more truly reflect the trend of ecological environment changes. At the same time, introduce the time change factor (such as time interval ), construct a spatio-temporal model to obtain the spatio-temporal modeling result; through the adjustment of the adaptation weights, the response ability of each sensor to the changes in the ecological environment at different time points can be more accurately reflected; the basic formula of the spatio-temporal model is as follows:

[0054] ,

[0055] Among them, is the spatio-temporal modeling result at time , representing the comprehensive environmental state at time ; is the adaptation weight of the th sensor at time ; is the adjustment factor, used to control the influence of the reconstructed signal on the spatio-temporal modeling result, obtained through experiments; is the time interval, reflecting the dynamic changes of the time series data; is the ecological environment monitoring data collected by the th sensor at time ;

[0056] Based on the ecological environment monitoring data and the spatio-temporal modeling result, effectively predict the future ecological environment changes to obtain the environmental state prediction result at the future moment, so as to improve the intelligent level of ecological environment monitoring; the prediction formula is:

[0057] ,

[0058] Among them, represents the environmental state prediction result at the future moment ; is the th weighting coefficient, used to adjust the contribution degree of each sensor to the environmental state prediction result at the future moment, obtained through experiments; is the ecological environment monitoring data collected by the th sensor at time ; is a spatio-temporal feedback factor, which is used to represent the correlation between the predicted results of the environmental state at future moments and the predicted results of the historical environmental state, and is obtained through experiments; is the predicted result of the environmental state at the is an accumulation factor, which reflects the influence of environmental changes within a time interval and is obtained through experiments; is a time integration variable; is the reconstructed signal at the is a weighting coefficient, which is used to adjust the influence of the spatio-temporal modeling result on the predicted result of the environmental state at future moments and is obtained through experiments; is the spatio-temporal modeling result at the moment, representing the comprehensive environmental state at the

[0059] By spatio-temporal modeling and predicting the environmental change trend at future moments, the comprehensive monitoring and prediction of the ecological environment state are realized, which helps decision-makers make effective responses. Finally, not only the accuracy and sensitivity of the ecological environment monitoring process are improved, but also more accurate support and basis are provided for environmental protection, resource management and policy-making.

[0060] In summary, a method for processing ecological environment monitoring data is completed.

[0061] The sequence of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0063] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for processing ecological environment monitoring data, characterized in that: The following steps are involved: S1. Collect ecological environment monitoring data in real time, and based on the sensitivity and reliability of environmental changes, introduce the contribution coefficient of sensor data in the fusion process, perform weighted fusion processing on the ecological environment monitoring data, and obtain a fused signal; purify the fused signal through convolution operation to obtain a purified signal; reconstruct the signal based on the purified signal to generate a reconstructed signal; S2. Based on the ecological environment monitoring data and the reconstructed signal, dynamically adjust the adaptability weight of the sensor. The specific formula is as follows: ， in, For the The adaptability weight of each sensor; is the adjustment factor used to control the sensitivity of the error; It is Ecological environment monitoring data collected by sensors; is the reconstruction signal; It is The square error between the ecological environment monitoring data collected by the sensor and the reconstructed signal; is the number of sensors; is the reconstructed signal and The influence relationship between the ecological environment monitoring data collected by the sensors is used to reflect the signal change trend; is the correlation coefficient; Based on the adaptive weights and reconstructed signals of the sensors, a spatiotemporal model is constructed to obtain spatiotemporal modeling results. Based on the spatiotemporal modeling results, the future ecological environment state is predicted to obtain the environmental state prediction results at future moments.

2. The method for processing ecological environment monitoring data according to claim 1, characterized in that: The S1 specifically includes: The fused signal is processed by sliding window through convolution operation to remove high-frequency noise in the fused signal and obtain a purified signal.

3. The method for processing ecological environment monitoring data according to claim 2, characterized in that: The S1 specifically includes: The purified signal is combined with the normal signal, and the contribution of the purified signal and the normal signal is adjusted through a weighted method to generate a reconstructed signal.

4. The method for processing ecological environment monitoring data according to claim 1, characterized in that: The S2 specifically includes: The ecological environment monitoring data collected by the sensor at the same time and the sensor's adaptive weight are integrated, combined with the reconstructed signal, and the time change factor is introduced to build a spatiotemporal model to obtain the spatiotemporal modeling results.

5. The method for processing ecological environment monitoring data according to claim 4, characterized in that: The S2 specifically includes: Based on the results of spatiotemporal modeling, combined with ecological environmental monitoring data and reconstructed signals, future ecological environmental changes are predicted.

6. The method for processing ecological environment monitoring data according to claim 5, characterized in that: The S2 specifically includes: In the process of predicting future ecological environment changes, the spatiotemporal feedback factor and the cumulative factor are introduced, and the spatiotemporal feedback is combined with the spatiotemporal integration to obtain the environmental state prediction results at future moments. The prediction formula is: ， in, Indicates future time The environmental status prediction results; It is A weighting coefficient is used to adjust the contribution of each sensor to the prediction result of the environmental state at the future moment; For the The sensors in Ecological environment monitoring data collected at all times; is the spatiotemporal feedback factor; yes The prediction result of the environmental status at the moment; is the accumulation factor; is the time-integrated variable; yes Reconstruction signal at the moment; is a weighting coefficient used to adjust the impact of spatiotemporal modeling results on the environmental state prediction results at future moments; yes The spatiotemporal modeling results at each moment.

Images