Application method of arid region decision analysis system under arid region underlying surface condition

Abstract

The invention provides an application method of an arid region decision analysis system under an arid region underlying surface condition. The application method of the decision analysis system for the arid region under the underlying surface condition of the arid region comprises the steps that a, data collection is conducted, specifically, multi-source environment data of the arid region are collected, the data comprise weather, soil, terrain, vegetation and surface water, the timeliness and accuracy of the data are ensured, and the data comprise but not limited to precipitation, air temperature, soil humidity and evaporation key variables; b, data preprocessing: cleaning, de-noising and normalizing the collected multi-dimensional data to ensure the consistency and integrity of the data; according to the application method of the decision analysis system for the arid region under the underlying surface condition of the arid region, the system ensures the timeliness and accuracy of data by collecting multi-source environment data and combining a remote sensing technology and ground monitoring station data. By means of data preprocessing, standardization processing and other methods, the system can effectively remove noise and unify the data format, and the quality and consistency of data are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of decision - making analysis in arid regions, and specifically to an application method of a decision - making analysis system in arid regions under underlying surface conditions. Background Art

[0002] The basic structure of a decision - making analysis system in arid regions includes a data acquisition module, a data processing module, a decision - making support module, and an output module. The data acquisition module is responsible for obtaining basic data such as meteorology, soil, and hydrology in arid regions and conducting real - time monitoring. The data processing module constructs environmental models such as water resources and soil moisture in arid regions by cleaning, analyzing, and modeling these data. The decision - making support module provides specific response plans for decision - makers by using methods such as multi - objective optimization and risk assessment based on the processed data. The output module presents the decision results in a visual way for easy understanding and implementation by decision - makers. Based on the characteristics of the underlying surface conditions in arid regions, the entire system can help decision - makers formulate scientific and reasonable measures to deal with droughts, and promote rational resource allocation and emergency management.

[0003] Although the decision - making analysis system in arid regions provides comprehensive decision - making support, it still has some deficiencies. Existing meteorological and hydrological models cannot fully consider the particularities of arid regions, such as local climate change and extreme weather events, which limits the system's performance in dealing with complex environments. The system's design lacks flexibility and is difficult to quickly adapt to sudden drought events. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides an application method of a decision - making analysis system in arid regions under underlying surface conditions, which solves the problems that existing meteorological and hydrological models cannot fully consider the particularities of arid regions, resulting in limited system performance in dealing with complex environments, and the system's design lacks flexibility and is difficult to quickly adapt to sudden drought events.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An application method of a decision - making analysis system in arid regions under underlying surface conditions, including:

[0006] a. Data acquisition: Collect multi - source environmental data in arid regions, including meteorology, soil, terrain, vegetation, and surface water, ensuring the timeliness and accuracy of the data. The data includes but is not limited to key variables such as precipitation, temperature, soil humidity, and evaporation;

[0007] b. Data pre - processing: Clean, denoise, and normalize the collected multi - dimensional data to ensure the consistency and integrity of the data. Use the following formula to normalize soil moisture:

[0008]

[0009] Among them, θ norm is the standardized soil moisture, θ min and θ max are the minimum and maximum values in the historical data of this area respectively;

[0010] c. Dynamic modeling: Construct a meteorological and hydrological model adapted to the characteristics of arid regions. The model incorporates the influence of local climate change and extreme weather events. The meteorological model uses a spatio-temporal data fusion method to improve the prediction accuracy of local climate change by integrating remote sensing data, satellite images, and ground meteorological station data. The specific formula is as follows:

[0011]

[0012] Among them, T forecast (t) is the predicted air temperature, T i (t) is the air temperature value of the i-th data source at time t, w i is the weighting coefficient corresponding to the data source, and n is the number of data sources;

[0013] d. Hydrological model: Adopt a hydrological model based on physical processes to simulate precipitation, evaporation, and soil moisture flow in arid regions. The model calculates the change in soil moisture through the following formula:

[0014]

[0015] Among them, θ is the soil moisture, Q is the water flow of the soil moisture, S precip (t) is the precipitation at time t, S ET (t) is the evaporation;

[0016] e. Multi-objective optimization and risk assessment: Based on the prediction results, use a multi-objective optimization algorithm to comprehensively consider the goals of water resource utilization, agricultural production, and ecological protection for optimization decisions. The optimization model is:

[0017]

[0018] Among them, f(x) is the optimization goal, c i is the weight of the i-th goal, x i is the decision variable under each goal. The risk assessment model conducts multi-level risk assessment based on historical data and real-time meteorological data according to the probability of drought events occurring, and uses the risk formula:

[0019]

[0020] Among them, R total is the total risk, P j is the occurrence probability of the j-th drought event, I j is the impact degree of the corresponding event;

[0021] f. Emergency response and decision support: Automatically generate emergency response plans for different drought levels according to the prediction results through the emergency response decision-making model:

[0022]

[0023] Among them, E response is the emergency response plan, w k is the weight of the response measure, R k is the effect evaluation value of the response measure, maximizing the comprehensive effect of the response measure.

[0024] Preferably, the meteorological model adopts a spatio-temporal data fusion method, combines remote sensing data, satellite images, and meteorological station data, and can adjust key meteorological parameters such as temperature and precipitation in real time to dynamically optimize the prediction results.

[0025] Preferably, the hydrological model combines physical hydrological calculation formulas with machine learning algorithms, can dynamically adjust hydrological parameters, simulate water resource changes under different climate conditions, and improve the prediction accuracy of soil moisture.

[0026] Preferably, the multi-objective optimization algorithm realizes the optimal decision-making of resource allocation by establishing objective functions for multiple objectives of water resources, agriculture, and ecology and considering emergency response plans under various drought events.

[0027] Preferably, the risk assessment model is based on the joint analysis of historical meteorological data and real-time meteorological data, and provides timely and scientific support for drought decision-making through a multi-level risk assessment model.

[0028] Preferably, the system further includes a data fusion module, which realizes high-precision modeling of the arid area by integrating remote sensing data, geographic information system data, and on-site survey data.

[0029] Preferably, the system supports a distributed architecture based on a cloud computing platform, can realize massive data processing and real-time analysis, and provides support for decision-making in multiple arid areas.

[0030] Preferably, the system combines historical drought data with real-time monitoring data, has an intelligent learning and model adaptive optimization function, and ensures that the system can long-term adapt to the environmental changes in the arid area.

[0031] The present invention provides an application method of a decision analysis system for arid areas under the underlying surface conditions of arid areas. It has the following beneficial effects:

[0032] The application method of the decision - making analysis system in the arid area under the underlying surface conditions of the arid area. The system collects multi - source environmental data, combines remote sensing technology and data from ground monitoring stations, ensuring the timeliness and accuracy of the data. Through methods such as data pre - processing and standardization processing, the system can effectively remove noise and unify the data format, improving the quality and consistency of the data, and ensuring the scientific nature of model training and decision - making. More importantly, the present invention adopts dynamic modeling technology, especially meteorological and hydrological models that integrate local climate change and extreme weather events, greatly improving the accuracy of drought prediction and hydrological changes, and meeting the prediction requirements under the special environment of the arid area.

[0033] The multi - objective optimization and risk assessment module of this technical solution can comprehensively consider multiple objectives such as water resource utilization, agricultural production, and ecological protection to optimize the decision - making plan. Through the joint analysis of historical meteorological data and real - time meteorological data, the risk assessment model can effectively predict the occurrence probability and impact degree of drought events, providing timely and scientific support for emergency response in the arid area. Different from traditional models, the system of the present invention can quickly adapt to sudden drought events, provide flexible and real - time emergency response plans, maximize the comprehensive effect of response measures, and ensure the optimal decision - making of resource allocation. The system also has data fusion, cloud computing support, and intelligent learning functions, making decision - making support more accurate and real - time, being able to continuously adapt to the changing environment of the arid area, and providing long - term sustainable decision - making support. Brief Description of the Drawings

[0034] Figure 1 It is a schematic flowchart of the present invention. Detailed Embodiments

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the 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 of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] As Figure 1 shown, the embodiments of the present invention provide an application method of a decision - making analysis system in the arid area under the underlying surface conditions of the arid area, including: a. Data collection: Collect multi - source environmental data in the arid area, including meteorology, soil, topography, vegetation, and surface water, ensuring the timeliness and accuracy of the data. The data includes but is not limited to key variables such as precipitation, temperature, soil humidity, and evaporation. The meteorological model adopts a spatio - temporal data fusion method, combines remote sensing data, satellite images, and meteorological station data, and can adjust key meteorological parameters such as temperature and precipitation in real - time, dynamically optimizing the prediction results.

[0037] b. Data preprocessing: Clean, denoise, and normalize the multi-dimensional data collected to ensure data consistency and integrity. The following formula is used to normalize soil moisture:

[0038]

[0039] where θ norm is the normalized soil moisture, θ min and θ max are the minimum and maximum values in the historical data of this area respectively. During the data cleaning process, the system will use anomaly detection algorithms such as the isolation forest algorithm based on machine learning to automatically identify and remove abnormal data points, automatically alarm for abnormal fluctuations in precipitation and temperature variables, and mark them as data anomalies to ensure that the processed data is not interfered by error information.

[0040] c. Dynamic modeling: Construct meteorological and hydrological models adapted to the characteristics of arid regions. The models incorporate the influence of local climate change and extreme weather events. The meteorological model uses a spatio-temporal data fusion method to improve the prediction accuracy of local climate change by integrating remote sensing data, satellite images, and ground meteorological station data. The specific formula is as follows:

[0041]

[0042] where T forecast (t) is the predicted air temperature, T i (t) is the air temperature value of the i-th data source at time t, w i is the weighting coefficient corresponding to the data source, n is the number of data sources. The hydrological model combines physical hydrological calculation formulas with machine learning algorithms, can dynamically adjust hydrological parameters, simulate water resource changes under different climate conditions, and improve the prediction accuracy of soil moisture.

[0043] d. Hydrological model: Adopt a hydrological model based on physical processes to simulate precipitation, evaporation, and soil moisture flow in arid regions. The model calculates the change of soil moisture through the following formula:

[0044]

[0045] where θ is the soil moisture, Q is the water flow of the soil moisture, S precip (t) is the precipitation at time t, S ET (t) is the evaporation. The hydrological model is not only based on physical processes but also adopts an adaptive algorithm based on machine learning. The system monitors the changes of precipitation, evaporation, and soil moisture in real time through a feedback mechanism, and automatically adjusts the model parameters according to new environmental data to ensure high adaptability under different climate conditions.

[0046] e. Multi-objective Optimization and Risk Assessment: Based on the prediction results, through a multi-objective optimization algorithm, comprehensively consider the goals of water resource utilization, agricultural production, and ecological protection for optimization decisions. The optimization model is:

[0047]

[0048] Among them, f(x) is the optimization objective, c i is the weight of the i-th objective, x i is the decision variable under each objective. The risk assessment model conducts multi-level risk assessment based on historical data and real-time meteorological data and the probability of drought events occurring. The risk formula is used:

[0049]

[0050] Among them, R total is the total risk, P j is the occurrence probability of the j-th drought event, I j is the impact degree of the corresponding event. The multi-objective optimization algorithm realizes the optimal decision of resource allocation by establishing the objective functions of multiple objectives of water resources, agriculture, and ecology and considering the emergency response plans under various drought events. The risk assessment model is based on the joint analysis of historical meteorological data and real-time meteorological data, and provides timely and scientific support for drought decision-making through a multi-level risk assessment model.

[0051] f. Emergency Response and Decision Support: Automatically generate emergency response plans for different drought levels according to the prediction results through the emergency response decision model:

[0052]

[0053] Among them, E response is the emergency response plan, w k is the weight of the response measure, R k is the effect evaluation value of the response measure. Maximize the comprehensive effect of the response measure. The system further includes a data fusion module, which realizes high-precision modeling of the arid area by integrating remote sensing data, geographic information system data, and on-site survey data. The system supports a distributed architecture based on a cloud computing platform, can realize massive data processing and real-time analysis, and provides support for decision-making in multiple arid areas. The system combines historical drought data and real-time monitoring data, and has the functions of intelligent learning and model adaptive optimization to ensure that the system can adapt to the environmental changes in the arid area in the long term.

[0054] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The application method of the arid area decision analysis system under the underlying surface conditions in the arid area is characterized by: include: a. Data collection: Collect multi-source environmental data in arid areas, including meteorology, soil, topography, vegetation, and surface water, to ensure the timeliness and accuracy of the data. The data include but are not limited to key variables such as precipitation, temperature, soil moisture, and evaporation; b. Data preprocessing: Clean, denoise, and normalize the collected multi-dimensional data to ensure data consistency and integrity. Use the following formula to normalize soil moisture: Among them, θ norm is the standardized soil moisture, θ min and θ max are the minimum and maximum values ​​in the historical data of the region, respectively; c. Dynamic modeling: Construct a meteorological and hydrological model that adapts to the characteristics of arid areas. The model integrates the impact of local climate change and extreme weather events. The meteorological model uses a spatiotemporal data fusion method to improve the prediction accuracy of local climate change by integrating remote sensing data, satellite images and ground meteorological station data. The specific formula is as follows: Among them, T forecast (t) is the predicted temperature, T i (t) is the temperature value of the i-th data source at time t, w i is the weighting coefficient of the corresponding data source, and n is the number of data sources; d. Hydrological model: A hydrological model based on physical processes is used to simulate precipitation, evaporation and soil moisture flow in arid areas. The model calculates soil moisture changes using the following formula: Where θ is soil moisture, Q is the flow of soil moisture, S precip (t) is the precipitation at time t, S ET (t) is the evaporation amount; e. Multi-objective optimization and risk assessment: Based on the prediction results, a multi-objective optimization algorithm is used to comprehensively consider water resource utilization, agricultural production, and ecological protection goals to make optimization decisions. The optimization model is: Among them, f(x) is the optimization target, c i is the weight of the i-th target, x i are decision variables under each objective. The risk assessment model uses historical data and real-time meteorological data to conduct multi-level risk assessment based on the probability of drought events, using the risk formula: Among them, R total is the total risk, P j is the probability of occurrence of the jth drought event, I j is the impact degree of the corresponding event; f. Emergency response and decision support: Automatically generate emergency response plans for different drought levels based on the forecast results, and use the emergency response decision model to: Among them, E response For emergency response plan, w k is the weight of the response measure, R k It is the effectiveness evaluation value of the response measures and maximizes the comprehensive effect of the response measures.

2. The method for applying the arid area decision analysis system according to claim 1 to the underlying surface conditions in arid areas is characterized by: The meteorological model adopts a spatiotemporal data fusion method, combining remote sensing data, satellite images, and weather station data. It can adjust key meteorological parameters such as temperature and precipitation in real time and dynamically optimize the prediction results.

3. The method for applying the arid area decision analysis system according to claim 1 under the underlying surface conditions in arid areas is characterized by: The hydrological model combines physical hydrological calculation formulas with machine learning algorithms, and can dynamically adjust hydrological parameters, simulate water resource changes under different climatic conditions, and improve the prediction accuracy of soil moisture.

4. The method for applying the arid area decision analysis system according to claim 1 under the underlying surface conditions in arid areas is characterized by: The multi-objective optimization algorithm achieves the optimal decision of resource allocation by establishing objective functions of multiple objectives of water resources, agriculture and ecology, taking into account emergency response plans under various drought events.

5. The method for applying the arid area decision analysis system according to claim 1 under the underlying surface conditions in arid areas is characterized by: The risk assessment model is based on the joint analysis of historical meteorological data and real-time meteorological data, and provides timely and scientific support for drought decision-making through a multi-level risk assessment model.

6. The method for applying the arid area decision analysis system according to claim 1 under the underlying surface conditions in arid areas is characterized by: The system further includes a data fusion module, which realizes high-precision modeling of arid areas by integrating remote sensing data, geographic information system data and field survey data.

7. The method for applying the arid area decision analysis system according to claim 1 to the underlying surface conditions in arid areas is characterized by: The system supports a distributed architecture based on a cloud computing platform, can realize massive data processing and real-time analysis, and provide support for decision-making in multiple drought-stricken areas.

8. The method for applying the arid area decision analysis system according to claim 1 to the underlying surface conditions in arid areas is characterized by: The system combines historical drought data with real-time monitoring data, and has intelligent learning and model adaptive optimization functions to ensure that the system can adapt to environmental changes in arid areas in the long term.

Images