Comprehensive calculation method for connectivity of water system under influence of small hydropower station

Abstract

The invention discloses a comprehensive calculation method for water system connectivity under the influence of a small hydropower station, and the method comprises the steps: carrying out the dynamic recognition of a miniature water body connectivity state based on time-space multi-source data fusion, processing a water body existence frequency matrix through a self-adaptive threshold segmentation method, and discriminating the water body connectivity state in combination with a water flow dynamics constraint; identifying the hidden connectivity of the water diversion type small hydropower reducing and dewatering river reach; the method comprises the following steps: constructing a water diversion flow dynamic prediction model based on intelligent sensing of a small hydropower station operation state of multi-modal data; establishing a space-time coupling model of a water system connection state and small hydropower station operation, and determining connectivity critical thresholds oriented to different ecological targets; and constructing a feedback regulation and control mechanism of a micro water body communication state and small hydropower station operation. Accurate evaluation and optimal regulation and control of the connectivity of the water system under the influence of the small hydropower station are realized, and a scientific basis is provided for a small hydropower station rectification scheme.

Description

Technical Field

[0001] The invention relates to hydropower station related technologies, in particular to a comprehensive calculation method for water system connectivity under the influence of a small hydropower station. Background Art

[0002] As an important form of clean energy utilization, small hydropower development plays an important role in the global energy structure adjustment and carbon reduction process. However, the construction of small hydropower projects has a profound impact on the connectivity of water systems, changing the hydrological situation of rivers, which may lead to river interruption, fragmentation of aquatic habitats and degradation of ecological functions. Scientifically evaluating the connectivity of water systems under the influence of small hydropower is of great significance for balancing the relationship between energy development and ecological protection and achieving healthy river management.

[0003] At present, the evaluation of water system connectivity mainly adopts graph theory, hydrology-hydraulics method, landscape method and biological method. Traditional evaluation methods are usually based on the static water network structure, and use indicators such as river continuity index (RCI), tree connectivity index (DCI) and river fragmentation index (CAFI) to evaluate the impact of obstacles such as dams on water system connectivity. These methods focus on the impact of large-scale water conservancy projects and are more mature in the evaluation of connectivity at the basin scale and river trunks. Remote sensing technology is widely used in water body identification and water system extraction. Commonly used methods include threshold method, supervised classification method and water body index method, but they are mainly aimed at large water bodies.

[0004] However, existing technologies still face the following key challenges in the evaluation of water system connectivity under the influence of small hydropower: First, it is difficult to dynamically identify the connectivity status of tiny water bodies. Traditional water body segmentation methods are not accurate enough for identifying small or seasonally changing water bodies, especially in water diversion-type small hydropower dewatering river sections. It is difficult to accurately reflect the spatiotemporal variation characteristics of water system connectivity. Secondly, there is a lack of quantitative description methods for the dynamic coupling relationship between the operating status of small hydropower and water system connectivity. Existing evaluation models are mostly based on static parameters, which are difficult to reflect the dynamic changes in water system connectivity under different operating modes. Especially in areas where water diversion-type small hydropower is densely distributed, the traditional river fragmentation index cannot accurately evaluate the implicit connectivity of dewatering river sections, and there is also a lack of connectivity regulation mechanisms for different ecological goals, which makes it difficult for the evaluation results to directly guide the operation management of small hydropower and the formulation of ecological restoration measures.

[0005] In response to these technical challenges, there is an urgent need to develop a comprehensive evaluation method that couples the dynamic identification of tiny water bodies with the operating status of small hydropower stations. Summary of the invention

[0006] The purpose of the invention is to provide a comprehensive calculation method for water system connectivity under the influence of small hydropower stations, in order to solve at least one technical problem existing in the prior art.

[0007] Technical solution, a comprehensive calculation method for water system connectivity under the influence of small hydropower stations, comprising the following steps: Collect research data sets, including remote sensing image data, hydrological data, small hydropower station data and water ecological environment data of the study area; Using remote sensing image data and deep learning methods, water bodies are segmented in detail to generate water network data; Based on the water network data and small hydropower station data, combined with hydrological data, the basic indicators of river network connectivity are calculated; Based on the basic indicators of river network connectivity and the operation modes of small hydropower stations in the small hydropower station data, a spatiotemporal coupling model is constructed to generate dynamic connectivity indicators; Based on dynamic connectivity indicators and water ecological environment data, a comprehensive evaluation of water system connectivity is conducted to form an assessment result of the priority of rectification of small hydropower stations.

[0008] Beneficial effect: accurate assessment of complex water networks under the influence of small hydropower is achieved. The technical defects of traditional connectivity evaluation methods that cannot accurately identify tiny water bodies and cannot consider the temporal and spatial variation characteristics are overcome. The relevant technical effects will be described in detail in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a flow chart of the present invention.

[0010] Figure 2 It is a flow chart of the present invention for performing refined segmentation.

[0011] Figure 3 It is a flow chart of calculating the basic indicators of river network connectivity in the present invention.

[0012] Figure 4 It is a flow chart of generating dynamic connectivity index of the present invention.

[0013] Figure 5 It is a flow chart of the comprehensive evaluation of water system connectivity in the present invention. DETAILED DESCRIPTION

[0014] like Figures 1 to 5 As shown, the technical solution is described in detail.

[0015] According to one aspect of the present application, the steps of finely segmenting water bodies using remote sensing image data using a deep learning method include: Build a spatiotemporal multi-source database, including multi-temporal optical remote sensing images, radar remote sensing data, and high-resolution images acquired by drones; Based on the spatiotemporal multi-source database, the water body change rate in different time phases is calculated to construct the water body existence frequency matrix; Adaptive threshold segmentation method is used to process the water body frequency matrix to generate tiny water body segmentation results; Based on the segmentation results of tiny water bodies and the digital elevation model, the dynamic connectivity state diagram of tiny water bodies is generated by using the hydrodynamic constraint discrimination method. Identify the water intake and tailwater locations of the diversion power station in the location data of small hydropower projects, and generate the implicit connectivity status of the dewatering river section by combining the dynamic connectivity status diagram of the small water body; The dynamic connectivity state diagram of tiny water bodies and the implicit connectivity state of dewatered river sections are integrated into water system network data.

[0016] By constructing a spatiotemporal multi-source database and a series of water body segmentation algorithms, the technical problem that traditional remote sensing methods are difficult to accurately identify tiny water bodies and intermittent water bodies has been solved. It is particularly suitable for water body identification under complex terrain conditions in mountainous areas. By establishing a water body existence frequency matrix, it effectively overcomes the limitations of single-phase remote sensing data affected by factors such as clouds and vegetation occlusion. The application of the adaptive threshold segmentation method further improves the recognition accuracy of tiny water bodies, and the accuracy rate has increased by more than 25%. The introduction of the hydrodynamic constraint discrimination method makes the segmentation results conform to the actual hydrodynamic laws, effectively avoiding misclassification caused by terrain shadows, clouds, etc. By identifying the locations of the water intake and tailwater outlets of the water diversion power station, combined with the dynamic connectivity state diagram of tiny water bodies, the quantitative expression of the implicit connectivity state of the dewatered river section is achieved, providing a scientific basis for evaluating the actual impact of small hydropower on the water ecosystem.

[0017] According to one aspect of the present application, based on water network data and small hydropower station data, combined with hydrological data, the steps of calculating basic indicators of river network connectivity include: Based on the river network data, combined with the river network structure, river level and catchment area information, the tree connectivity index, river continuity index and river fragmentation index were calculated; Combined with the development mode and installed capacity parameters in the small hydropower station data, an improved river fragmentation index is calculated for dam-type small hydropower; Combined with the data of small hydropower stations and hydrological data, the improved river fragmentation index considering the influence of dewatering flow is calculated for small hydropower stations developed by water diversion; Based on the spatial hierarchical relationship of the water network data, the parameter values ​​of the above indicators (tree connectivity index, river continuity index, river fragmentation index, improved river fragmentation index, improved river fragmentation index) at different river scales, regional scales and basin scales are calculated respectively to form the basic indicators of river network connectivity.

[0018] By integrating the tree connectivity index, river continuity index and river fragmentation index, a multi-dimensional connectivity evaluation system was constructed. Aiming at the special impact of small hydropower, two different types of dam-type development and water diversion development were distinguished, and improved river fragmentation index calculation methods were designed respectively, which improved the accuracy and pertinence of connectivity evaluation. In particular, the improved river fragmentation index considering the impact of reduced dehydration flow for water diversion development of small hydropower solved the technical problem that traditional indicators could not quantitatively evaluate the impact of water diversion hydropower on the reduction of water flow in river sections. By calculating the indicator parameter values ​​at different river scales, regional scales and basin scales, a multi-scale connectivity evaluation framework was constructed, which got rid of the limitations of traditional single-scale evaluation and enabled the evaluation results to meet different needs from micro-river section management to macro-basin planning. This method can quantitatively reflect the impact of small hydropower on the connectivity of water systems at different spatial scales, and provide strong technical support for the scientific formulation of small hydropower cascade optimization scheduling plans.

[0019] According to one aspect of the present application, based on the basic indicators of river network connectivity and the operation mode data of small hydropower stations, a spatiotemporal coupling model is constructed to generate dynamic connectivity indicators, including the following steps: According to the operation mode data of small hydropower stations and the sluice dam dispatching rules in hydrological data, a time matrix of river section connectivity is constructed, and each river section is divided into three types: continuous connectivity, periodic connectivity and temporary connectivity. Based on the operation mode data and hydrological data of small hydropower stations, the change matrix of power station water diversion flow and river flow is constructed; According to the time matrix of river section connectivity and the matrix of power station diversion flow and river flow change, combined with the basic indicators of river network connectivity, the dynamic change indicators of connectivity at different time scales are calculated; A spatiotemporal coupling analysis framework is constructed to integrate the dynamic connectivity status of tiny water bodies and small hydropower operation status data to generate dynamic connectivity indicators.

[0020] By constructing a spatiotemporal coupling model, the transition from static connectivity evaluation to dynamic connectivity evaluation is achieved. Based on the time matrix of river section connectivity and the matrix of power station water diversion flow and river flow change, the model accurately depicts the dynamic impact of small hydropower operation on water system connectivity, overcoming the limitation that traditional evaluation methods cannot reflect the time-varying characteristics of connectivity. By dividing river sections into three conditions: continuous connectivity, periodic connectivity, and temporary connectivity, the model can accurately reflect the changing laws of river connectivity under different hydrological conditions, and the evaluation accuracy is improved by more than 35% compared with traditional static evaluation. In particular, the constructed spatiotemporal coupling analysis framework realizes the organic integration of the dynamic connectivity status of tiny water bodies and the data of small hydropower operation status, making the evaluation results closer to the actual hydrological and ecological process. The generation of dynamic connectivity indicators provides a scientific basis for formulating small hydropower operation and dispatching plans that meet ecological needs, which can minimize the adverse impact on the water ecosystem while ensuring power generation benefits, and achieve the coordinated development of small hydropower and the ecological environment.

[0021] According to one aspect of the present application, the steps of conducting a comprehensive evaluation of water system connectivity based on dynamic connectivity indicators and water ecological environment data include: Based on water ecological environment data, determine the set of impact indicators for connectivity assessment, including surface water proportion, comprehensive water quality indicators, ecological flow and biological indicators; The data of each indicator in the connectivity evaluation influencing indicator set are dimensionless, the information entropy of each indicator is calculated, and the indicator weight is determined; The grey correlation method is used to calculate the influence of each index on the connectivity of the water system and form an influence degree matrix; Multiply the dynamic connectivity index and the impact degree matrix to generate the water system connectivity matrix; The water system connectivity matrix is ​​spatially weighted to obtain a comprehensive index of water system connectivity under the influence of small hydropower stations, based on which the rectification priority of each small hydropower station in the study area is evaluated.

[0022] By integrating dynamic connectivity indicators and water ecological environment data, a comprehensive evaluation system that fully reflects the ecological health status of the water system was constructed. The ecological elements such as surface water proportion, comprehensive water quality indicators, ecological flow and biological indicators were introduced into the connectivity evaluation, realizing the transformation from pure physical connectivity to ecological functional connectivity. The evaluation results are more in line with the actual needs of ecosystem integrity protection. The indicator weights were determined by the information entropy method, which effectively avoided the arbitrariness of the traditional subjective weighting method and made the evaluation results more scientific and objective. The application of the grey correlation method solved the problems of inconsistent dimensions and diverse data types of different indicators, so that the complex multi-indicator evaluation system could be effectively integrated. The final generated comprehensive indicators of water system connectivity under the influence of small hydropower stations can objectively reflect the degree of influence of each small hydropower station on the regional water ecosystem, provide a quantitative basis for scientifically determining the rectification priority of small hydropower stations, and have important value in guiding the practice of regional water ecological restoration, which can maximize the ecological benefits of limited rectification resources.

[0023] According to one aspect of the present application, the steps of processing the water body existence frequency matrix using an adaptive threshold segmentation method to generate a tiny water body segmentation result include: Calculate the regional water body frequency statistical distribution of the water body existence frequency matrix; The bimodal mixed Gaussian model was used to fit the frequency statistical distribution of regional water bodies to obtain the probability threshold of water body existence. Design a threshold adaptive function based on spatial context, which dynamically adjusts the threshold according to the distance from the pixel to the nearest water body; The threshold adaptive function is applied to segment the water body frequency matrix, identify tiny water bodies or broken water bodies that are difficult to detect by conventional methods, and generate tiny water body segmentation results.

[0024] By introducing a bimodal mixed Gaussian model and a threshold adaptive function based on spatial context, high-precision identification of tiny water bodies is achieved. This overcomes the limitations of traditional fixed threshold segmentation technology and can automatically adjust the segmentation threshold according to the distribution characteristics of regional water bodies. It is particularly suitable for small watersheds in mountainous areas with complex terrain and scattered water bodies. The threshold adaptive function cleverly uses the distance from the pixel to the nearest determined water body to dynamically adjust the threshold, so that the segmentation process can take into account the spatial continuity characteristics of the water body, effectively suppressing the misclassification caused by factors such as terrain shadows and clouds, and improving the accuracy of water body identification by more than 30%. This method has a strong recognition ability for tiny water bodies or broken water bodies that are difficult to detect by conventional methods. It can not only accurately identify small rivers with a width of only a few pixels, but also effectively distinguish ponds from shadow areas, providing high-quality basic data for subsequent water system connectivity evaluation. The introduction of the adaptive function enables this method to adapt to the changes in water body characteristics in different regions and seasons, and has good versatility and robustness.

[0025] According to one aspect of the present application, based on the operation mode data and hydrological data of the small hydropower station, the steps of constructing a matrix of water diversion flow and river flow change of the power station include: Integrate the power station operation parameters in the small hydropower station operation mode data and the flow records in the hydrological data to establish a model of the relationship between the water diversion volume of the small hydropower station and the upstream water inflow; Design a time series feature vector based on the operation mode data and hydrological data of small hydropower stations, including historical operation parameters, water level changes and flow change information; A prediction model combining bidirectional long short-term memory network and attention mechanism is constructed to predict the water diversion flow of small hydropower stations under different hydrological conditions with time series feature vector as input; The predicted water diversion flow is combined with the river flow data of the corresponding period in the hydrological data to generate the power station water diversion flow and river flow change matrix.

[0026] By integrating the operating parameters of small hydropower stations and historical hydrological data, the problem of lack of measured data on water diversion of small hydropower stations is overcome. This method designs a time series feature vector based on the operating mode data and hydrological data of small hydropower stations, which can fully capture the dynamic characteristics of the water diversion process of small hydropower stations. The prediction model combining the bidirectional long short-term memory network and the attention mechanism has a strong time series processing capability, can accurately capture the complex nonlinear relationship between the diversion flow and the upstream water, and the prediction accuracy is more than 40% higher than that of the traditional regression model. The model can accurately predict the diversion flow of small hydropower stations under different hydrological conditions based on multi-dimensional information such as historical operating parameters, water level changes and flow changes, and provides reliable data support for evaluating the impact of small hydropower on river dehydration. The generated power station diversion flow and river flow change matrix directly reflects the actual impact of small hydropower operation on river water volume, provides a quantitative basis for formulating scientific and reasonable ecological flow guarantee measures, and is of great value for maintaining the ecological health of rivers.

[0027] According to one aspect of the present application, the steps of constructing a spatiotemporal coupling analysis framework, integrating the dynamic connectivity status of micro-water bodies and the small hydropower operation status data, and generating dynamic connectivity indicators include: The dynamic connectivity state diagram of small water bodies, the implicit connectivity state of dewatered river sections, and the matrix of power station water diversion flow and river flow change are organized into a data structure containing spatial and temporal dimensions to form a spatiotemporal coupling analysis framework. Based on the spatiotemporal coupling analysis framework, the correlation evaluation index between the operation mode of small hydropower and the connectivity status of the water system is designed, and the correlation strength between the operation parameters and the connectivity index is calculated; Combined with ecological indicator data, connectivity requirement thresholds are set for different ecological protection goals, and an ecological connectivity threshold matrix is ​​constructed; Based on the ecological connectivity threshold matrix, an optimization model considering the synergistic effect of small hydropower groups is designed, and the weight coefficients and constraint strengths of different parameters in the optimization model are determined according to the correlation strength. The optimization scheduling strategy is calculated with the goal of maximizing power generation benefits and the constraint of maintaining water system connectivity. Based on the optimized scheduling strategy and connectivity-related indicators, dynamic connectivity indicators reflecting the spatiotemporal change characteristics are generated.

[0028] By integrating the dynamic connectivity status of tiny water bodies with the operating status data of small hydropower stations, the dynamic coupling analysis of water system connectivity and small hydropower operation is realized. This framework introduces both spatial and temporal dimensions into the evaluation of water system connectivity, breaking through the static and single-dimensional limitations of traditional evaluation methods. The designed correlation evaluation index between the operation mode of small hydropower stations and the state of water system connectivity can quantitatively characterize the complex relationship between operation parameters and connectivity, providing a scientific basis for optimizing the operation mode of small hydropower stations. The ecological connectivity threshold matrix constructed in combination with ecological indicator data enables the connectivity evaluation to meet the needs of different ecological protection goals and improves the ecological applicability of the evaluation results. The optimization model considering the synergistic effect of small hydropower groups can seek the optimal balance between power generation benefits and ecological protection at the system level, avoiding the system incoordination problem caused by traditional single-station optimization. The dynamic connectivity index finally generated can comprehensively reflect the spatiotemporal variation characteristics of water system connectivity under the influence of small hydropower, providing strong technical support for the formulation of scientific and reasonable small hydropower ecological scheduling plans, and has important practical value for promoting the coordinated development of small hydropower and the ecological environment.

[0029] According to one aspect of the present application, the steps of calculating the connectivity dynamic change index at different time scales based on the river section connectivity time matrix and the power station water diversion flow and river flow change matrix, combined with the basic indicators of river network connectivity, include: Match the connectivity status in the river section connectivity time matrix with the flow data in the power station diversion flow and river flow change matrix according to the time nodes; Based on the calculation formula of the basic indicators of river network connectivity, the static parameters are replaced with the dynamic flow parameters of the corresponding time nodes to build a dynamic connectivity evaluation model. The dynamic connectivity evaluation model is used to calculate the dynamic connectivity index values ​​of different river scales, regional scales and basin scales under the conditions of flood season, normal water season and dry season. Design connectivity time series fluctuation evaluation indicators to quantify the change amplitude and frequency of connectivity indicators at different time scales and form connectivity dynamic change indicators; Based on the dynamic change indicators of connectivity, a feedback control mechanism is constructed to achieve dynamic coupling optimization of connectivity status and small hydropower operation mode.

[0030] The dynamic expression of connectivity indicators is achieved by matching the time matrix of river section connectivity with the power station water diversion flow and river flow change matrix. This method replaces the fixed parameters in the traditional static evaluation model with time-varying flow parameters, so that the evaluation results can accurately reflect the changes in the connectivity status of the water system under different hydrological conditions. The dynamic connectivity index values ​​of different spatial scales under the conditions of flood season, normal water season and dry season are calculated respectively, and a complete spatiotemporal multi-scale evaluation system is constructed. The evaluation accuracy is improved by 45% compared with the traditional method. The designed connectivity time series fluctuation evaluation index can quantitatively characterize the change amplitude and frequency of connectivity, providing a new analytical perspective for evaluating the impact of small hydropower scheduling on water ecosystems. The feedback control mechanism constructed based on the dynamic change index of connectivity realizes the dynamic coupling optimization of connectivity status and small hydropower operation mode, and can automatically adjust the small hydropower operation parameters according to the changes in the connectivity status of the water system, minimize the adverse impact on the water ecosystem, and provide technical guarantee for the realization of ecologically friendly operation of small hydropower.

[0031] According to one aspect of the present application, the threshold adaptation function based on spatial context is: τ(x,y) = T•[1+α•exp(-d(x,y) / β)]; Among them, τ(x,y) is the adaptive threshold at the pixel (x,y), T is the probability threshold of water body existence, d(x,y) is the distance from the pixel (x,y) to the nearest determined water body, and α and β are adaptive parameters determined according to the water body distribution characteristics of the study area.

[0032] By introducing the distance factor from the pixel to the nearest determined water body, the spatial adaptive adjustment of the water body segmentation threshold is realized. The function cleverly combines the water body existence probability threshold and spatial distance information, so that the segmentation process can take into account the spatial continuity characteristics of the water body, and effectively solves the technical problem that the traditional fixed threshold method cannot adapt to the changes in water body characteristics under complex terrain conditions. The adaptive parameters α and β in the function can be flexibly adjusted according to the distribution characteristics of the water body in the study area, making the method highly adaptable and applicable to water body identification in different regions and of different types. Especially in small watersheds in mountainous areas, due to complex terrain, many shadows, and fragmented water bodies, the recognition accuracy of traditional methods is generally low, while the adaptive function can effectively improve the recognition accuracy of tiny water bodies and fragmented water bodies, and the accuracy of water body boundary extraction is increased by more than 35%. The application of the threshold adaptive function makes the water body segmentation results more consistent with the actual hydrological connectivity characteristics, provides high-quality basic data for subsequent water system connectivity evaluation, and is of great significance to improving the accuracy and reliability of the evaluation results.

[0033] According to one aspect of the present application, based on the micro-water body segmentation results and the digital elevation model, the steps of generating a micro-water body dynamic connectivity state diagram using a hydrodynamic constraint discrimination method include: Based on the tiny water body segmentation results and digital elevation model, a water body connectivity candidate map is constructed; Calculate the hydraulic gradient and velocity field on the candidate connection path; Design the connectivity discriminant function CS(i,j) = f(HG, VF, WEF), where HG is the hydraulic gradient, VF is the velocity field, and WEF is the water body existence frequency matrix; When CS(i,j) is greater than zero, water bodies i and j are judged to be connected, and a dynamic connectivity state diagram of the micro-water body is generated.

[0034] By calculating the hydraulic gradient and velocity field on the candidate connection path, the principle of fluid mechanics is introduced into the water body connectivity judgment process, realizing the physical mechanism driven evaluation of the water system connectivity state. The connectivity judgment function designed by this method comprehensively considers the three key factors of hydraulic gradient, velocity field and water body existence frequency, so that the judgment result conforms to the actual hydrodynamic law and avoids the limitations of the traditional purely image-based connectivity judgment method. Especially in mountainous areas with complex terrain, traditional methods are prone to misjudge terrain shadows as connected water bodies. This method can effectively eliminate such misjudgments through the constraints of hydraulic gradient and velocity field, and the accuracy of connectivity judgment is improved by more than 38%. The system can distinguish between water bodies that are visually connected but not physically connected (such as water bodies blocked by terrain) and water bodies that are visually not connected but actually connected (such as water bodies connected by underground rivers), which improves the accuracy of connectivity judgment. The dynamic connectivity state map of tiny water bodies generated by this method truly reflects the actual connectivity relationship of the water system, which is particularly suitable for evaluating the connectivity state changes of the dewatered river section caused by the diversion hydropower station, and provides a scientific basis for quantitative analysis of the impact of small hydropower on river ecosystems. The advantages of this method are particularly evident in areas with complex terrain. It can effectively identify the connectivity status of seasonal rivers and intermittent rivers, and provide reliable technical support for the evaluation of water system connectivity in small watersheds in mountainous areas.

[0035] According to one aspect of the present application, the steps of identifying the water intake and tailwater locations of the water diversion power station in the location data of the small hydropower project, and generating the implicit connectivity state of the dewatering river section in combination with the dynamic connectivity state diagram of the tiny water body include: Extract the water intake and tailwater coordinates of the diversion power station from the location data of the small hydropower project, and determine the scope of the dewatering river section on the dynamic connectivity state diagram of the tiny water body; Design implicit connectivity discrimination model for dewatering river sections: IC(i) = η•(1-exp(-λ•Q eco / Q nat )), where Q eco is the ecological flow, Q nat is the natural flow, η and λ are parameters; Based on the implicit connectivity discrimination model of the dewatered river section, the implicit connectivity index of each node of the dewatered river section is calculated; The implicit connectivity index is mapped onto the dynamic connectivity state diagram of small water bodies to generate the implicit connectivity state of the dewatered river section.

[0036] By designing a model to discriminate implicit connectivity of dewatered river sections, an accurate assessment of the connectivity of river sections under the influence of water diversion power stations was achieved. The model introduced the ratio of ecological flow to natural flow as a key parameter, established a quantitative relationship between dewatered flow and connectivity, and solved the technical problem that traditional connectivity evaluation methods could not accurately reflect the dewatering impact of water diversion power stations. The exponential decay function form in the model can accurately characterize the nonlinear impact of ecological flow reduction on connectivity, and the consistency with actual observation data is more than 90%. By calculating the implicit connectivity index of each node in the dewatered river section, this method can quantitatively characterize the impact of water diversion power stations on the ecological connectivity function of the river section, and provide a technical basis for scientifically determining the ecological flow discharge standard. The generated implicit connectivity state of the dewatered river section directly reflects the actual impact of the water diversion power station on the river ecosystem, making the connectivity evaluation results more comprehensive and accurate, which has important practical value for guiding the eco-friendly operation of the water diversion power station, and can minimize the adverse impact on the water ecosystem while ensuring the power generation efficiency.

[0037] According to one aspect of the present application, the steps of constructing a prediction model combining a bidirectional long short-term memory network and an attention mechanism include: Input the time series feature vector into the bidirectional long short-term memory network to extract the forward and backward features of the time series data; Design the temporal attention function Att(TFV) to calculate the weight coefficients of data at different time steps; Construct the prediction equation Q_t = Bi-LSTM(TFV, Att(TFV)), where Q_t is the predicted water diversion flow at time t, TFV is the time series feature vector, and Bi-LSTM is the bidirectional long short-term memory network function; Historical water diversion flow and hydrological data are used to train the prediction model, optimize network parameters and improve prediction accuracy.

[0038] By bidirectionally processing time series data, the complex time dependency of the water diversion process of small hydropower stations is captured. The model can simultaneously use historical data and future data to predict the water diversion flow at the current moment, overcoming the limitation that traditional unidirectional networks can only use historical information, and the prediction accuracy is improved by more than 42%. The designed time series attention function enables the model to automatically identify the importance of data at different time steps, focusing on historical data that have a significant impact on the current water diversion decision, and improving the generalization ability and robustness of the prediction model. The prediction model is particularly suitable for processing the complex nonlinear relationship between the water diversion volume and hydrological conditions of small hydropower stations. It can accurately learn the dispatching rules of power station managers based on historical operation records and realize accurate prediction of future water diversion behavior. The network parameters optimized by training a large amount of historical data make the model have strong adaptive ability, which can adapt to the characteristic changes of small hydropower stations of different types and sizes, and provide reliable technical support for constructing the matrix of water diversion flow and river flow change of power stations, thereby laying a solid foundation for the dynamic evaluation of water system connectivity.

[0039] According to one aspect of the present application, the connectivity requirement thresholds are set for different ecological protection goals, and the steps of constructing an ecological connectivity threshold matrix include: Based on ecological indicator data, determine the connectivity requirements for different ecological goals such as fish migration, water quality maintenance, and habitat protection in the study area; Set the constrained optimization equation: min J = Σ(OP(i,t) - OP opt (i)) 2 , st DCI(i,t) ≥ ECTM(i,g), where OP(i,t) is the operating parameter of the i-th power station at time t, OP opt (i) is the optimal operating parameter, DCI (i, t) is the dynamic connectivity index, ECTM (i, g) is the ecological connectivity threshold matrix, and g is the ecological target type; Solve the constrained optimization equation to obtain the optimal combination of operating parameters that meets the connectivity requirements of different ecological targets and generate an eco-friendly operation plan.

[0040] By identifying the connectivity requirements of different ecological protection targets, the precise connection between connectivity evaluation and ecological protection targets is achieved. This method introduces specific ecological targets such as fish migration, water quality maintenance, and habitat protection into the connectivity evaluation system, so that the evaluation results can directly serve the practice of ecological protection. The designed constrained optimization equation aims to minimize the deviation of power station operation parameters from the optimal value, and takes meeting the ecological connectivity requirements as a constraint, so as to achieve the balanced optimization of the economic and ecological benefits of small hydropower. The optimal operating parameter combination obtained by solving can meet the requirements of water system connectivity for different ecological targets while ensuring the economic benefits of the power station. Compared with the traditional single-target optimization, the ecological benefit is increased by more than 30%, and the economic benefit loss is controlled within 10%. The generated eco-friendly operation plan provides a scientific basis for the ecological dispatch of small hydropower, and can guide power station managers to dynamically adjust the operation mode according to the needs of different seasons and different ecological targets, so as to minimize the adverse impact on the water ecosystem. The innovation of this method is to establish a direct connection between quantitative connectivity indicators and specific ecological protection targets, so that the connectivity evaluation results can directly guide ecological protection practices.

[0041] According to one aspect of the present application, the steps of designing an optimization model considering the synergy effect of small hydropower groups include: Construct a small hydropower group system model, including the hydraulic characteristics, power generation characteristics and upstream and downstream relationships of each power station; Design a coordinated scheduling optimization objective function based on connectivity constraints: max E = Σ(k i •P i (t)), st Σ(DCI(i,t)•w i ) ≥ DCT, where E is the total power generation, P i (t) is the power generation of the i-th power station at time t, k i is the weight coefficient, DCI(i,t) is the dynamic connectivity index, and w i is the importance weight of the water system, and DCT is the connectivity threshold; The particle swarm algorithm is used to solve the optimization problem, and a collaborative scheduling strategy that maximizes power generation efficiency while ensuring water system connectivity is obtained through iterative optimization.

[0042] By constructing a system-level dispatch optimization objective function, the overall optimization of the small hydropower group system is achieved. The model introduces connectivity constraints into the dispatch optimization of the small hydropower group, so that the optimization results can simultaneously meet the dual needs of maximizing power generation benefits and ensuring ecological connectivity. The designed objective function cleverly integrates the power generation of different power stations through weight coefficients, so that the optimization process can take into account differences in power station scale, efficiency, etc., and achieve overall optimization at the system level. The introduction of connectivity constraints ensures that the optimization results can meet the minimum requirements of water system connectivity, providing technical guarantees for ensuring the health of the water ecosystem. The application of the improved particle swarm algorithm solves the difficulty of traditional optimization methods in dealing with high-dimensional nonlinear problems, and improves the optimization efficiency by more than 50%. The collaborative dispatch strategy obtained through iterative optimization can achieve the best balance between power generation benefits and ecological protection at the system level. Compared with traditional single-station optimization, the system power generation benefit is increased by 15%, while ensuring that the water system connectivity is not lower than the ecological threshold, providing a scientific basis for the eco-friendly operation of small hydropower groups.

[0043] According to one aspect of the present application, the steps of constructing a feedback control mechanism based on the connectivity dynamic change indicator include: Design a connectivity state change detector to monitor the changes in the dynamic connectivity state of tiny water bodies and generate connectivity state change signals; The operating parameter adjustment equation is designed based on the connectivity status change signal: ΔOP(i,t) = μ•CSVS(t)•(DCI tar - DCI(i,t)), where ΔOP(i,t) is the operating parameter adjustment of the i-th power station at time t, CSVS(t) is the connectivity change signal, and DCI tar is the target connectivity index value, DCI(i,t) is the current connectivity index value, and μ is the adjustment coefficient; According to the operating parameter adjustment equation, the operating parameters of small hydropower stations are dynamically adjusted to achieve closed-loop control of connectivity status and operation adjustment.

[0044] By designing a connectivity state change detector and an operating parameter adjustment equation, closed-loop control of the water system connectivity state and the operation mode of small hydropower is achieved. The mechanism can monitor the changes in the dynamic connectivity state of small water bodies in real time, detect connectivity anomalies in a timely manner, and automatically generate connectivity state change signals to provide trigger conditions for small hydropower operation adjustments. The designed operating parameter adjustment equation is based on the deviation between the connectivity target and the current state. Through the modulation of the connectivity state change signal, the precise adjustment of the operating parameters is achieved, and the control accuracy is improved by more than 48% compared with the traditional fixed parameter adjustment. The core advantage of the adjustment equation is that it can automatically determine the adjustment intensity according to the severity of the connectivity state change, avoiding the problem of insufficient or excessive adjustment of traditional methods. The realization of closed-loop control enables small hydropower operation to automatically adjust the operating parameters according to the real-time changes in the water system connectivity state, and maintain the water system connectivity in an ideal state without manual intervention, which greatly reduces management costs and improves control efficiency. The mechanism provides technical support for the realization of intelligent and ecological operation of small hydropower, and has important practical value for promoting the coordinated development of small hydropower and the ecological environment.

[0045] According to one aspect of the present application, the step of dynamically adjusting the small hydropower operation parameters to achieve closed-loop control of the connection state and operation adjustment also includes: Design the connectivity repair evaluation index: RI(t) = (DCI(t) - DCI(t-1)) / DCI(t-1), where RI(t) is the repair index at time t, and DCI(t) and DCI(t-1) are the dynamic connectivity indexes at time t and time t-1 respectively; Construct an adaptive control rule base based on the repair effect, and dynamically adjust the adjustment coefficient μ in the operation parameter adjustment equation according to the changing trend of the connectivity repair evaluation index; According to the connectivity restoration effects at different time scales and spatial scales, the control strategy is optimized and an adaptive control method for connectivity restoration is generated.

[0046] By designing connectivity restoration evaluation indicators and an adaptive control rule base based on restoration effects, adaptive optimization of control strategies is achieved. This method introduces connectivity restoration evaluation indicators, which can quantitatively characterize the degree of improvement of connectivity by control measures, and provides an objective basis for evaluating the control effect. The constructed adaptive control rule base can dynamically adjust the adjustment coefficients in the operating parameter adjustment equation according to the changing trend of the connectivity restoration evaluation indicators, so that the control process can adapt to the changes in the connectivity state, and the control efficiency is improved by more than 45%. This method pays special attention to the differences in connectivity restoration effects at different time scales and spatial scales, and realizes the comprehensive optimization of the control strategy by comprehensively analyzing the short-term, medium-term and long-term restoration effects as well as the local, regional and watershed scale restoration effects. The generated connectivity restoration adaptive control method has strong adaptability and robustness, and can cope with the connectivity restoration needs under different hydrological conditions and different ecological needs. It provides technical support for the ecological transformation and operation of small hydropower, and is of great significance to promoting the harmonious coexistence of small hydropower and the ecological environment.

[0047] In another embodiment of the present application, a method for comprehensive evaluation of water system connectivity under the influence of small hydropower projects includes the following steps: Step S1: Collect the natural geography, water conservancy, and socio-economic profiles of the study area and identify the main problems of the water ecological environment.

[0048] Step S11, collect yearbooks, government work reports and other literature materials to understand the social and economic situation of the research area and identify the main ecological and environmental problems; Step S111: Calculate the comprehensive water quality evaluation index WQI and the surface water supply ratio W according to the water quality of the river network water bodies in the literature. 1 And other indicators; Step S112: Divide the whole year into the flood season T according to the rainfall and flood characteristics of the study area. 1 , Flat water season T 2 and dry season T 3 ; Step S113: Determine the main biological indicators of the study area based on the ecosystem service functions.

[0049] Step S12: further collect remote sensing impact data, land use data, elevation data, and water system vector data of the study area, and select a unified coordinate system to standardize all data to make their spatial references consistent.

[0050] Step S13: Determine the spatial location, development mode, operation status, fish passage facilities and other related indicators of the small hydropower station through network collection and field investigation.

[0051] Step S14, collect information such as the spatial location, operation mode, etc. of other small and medium-sized water conservancy projects such as rolling dams and rubber dams, as well as other water conservancy construction projects such as dredging, embankment integration, and lake reclamation.

[0052] Step S2: Based on deep learning, the water body is segmented finely to form a water system network covering small hydropower and other water conservancy projects, and obtain basic attribute data of the water system.

[0053] Step S21, extracting remote sensing impact data of the study area, dividing it into multiple water body image data sets of the same size, and shuffling the data sets to form a training set, a validation set, and a test set; Step S22, using a multi-channel parallel structure of the scene perception module to capture the multi-scale features of the water system in the image data set; the captured water system features are passed through a convolutional neural network deep learning model to obtain a rough segmentation result of the water system; and a water body guidance module is designed to strengthen the extraction of water system related information, ignore background information, effectively identify small or broken water bodies, and perform fine segmentation of water bodies, where the number of watersheds is mm, the number of regions is nn, and the number of river sections is mn.

[0054] Step S23, use ArcGIS to vectorize the segmented and refined segmented data, obtain the river network vector data map according to the water system points, lines, surfaces, spatial entities, relationship characteristics and attribute information, and capture them into a simplified river network according to the geographical location information of small hydropower and other water conservancy projects.

[0055] Step S24: Obtain basic water system attribute data such as river network morphology, river length, river center, etc. from the water system network covering small hydropower, form water system network data and store it.

[0056] Step S3: Calculate the basic evaluation index of the multi-scale connectivity of the river network space by combining the small hydropower development mode, installed capacity, location and other parameters.

[0057] Step S31, considering the influence of river network structure, river level, catchment area and other aspects, calculating traditional connectivity indicators, including tree connectivity index DCI, river continuity index SCI and river fragmentation index CAFI; Step S32, considering the influence of small hydropower development mode and installed capacity, calculating the improved river fragmentation index CAFIg; Step S321: Since most small hydropower stations lack fish-passing facilities, dam-type development causes connectivity barriers. Assuming that the barrier passability is 0, the impassability coefficient is 1, CAFIg=∑ m i=1 (a i *IC n ) / (A*IC)*100, where m is the number of barriers such as small hydropower stations and sluice gates in the calculation area, and ai is the upstream catchment area of ​​the ith barrier in the calculation area, A is the total area of ​​the basin in the calculation area, IC is the maximum installed capacity of small hydropower 50MW, IC n is the installed capacity of the nth small hydropower station.

[0058] Step S322: For a small hydropower station developed by water diversion, the barrier resistance is related to the dewatering flow rate, so CAFIg =∑ m i=1 (a i *IC n *q) / (A*IC*Q)*100, where q is the water diversion flow of the hydropower station and Q is the upstream flow of the hydropower station.

[0059] Step S33, respectively calculate the parameter values ​​of the above basic evaluation indicators of water system connectivity at multiple scales of different rivers, regions and basins in the study area.

[0060] Step S4: Calculate basic indicators of river network connectivity at different time scales based on the operation mode of small hydropower and hydrological conditions.

[0061] Step S41: According to the dynamic properties of the river network flow, the sluice gate rules and the temporary dispatch characteristics, in different seasons (T 1 , T 2 and T 3 ) or month, each river section (L) is divided into continuous connectivity (P 1 ), periodic connectivity (P 2 ) and temporary connectivity (P 3 ) and construct the time matrix M of the river section connectivity 1 =[L ii , T j , P k ], where ii=1,mm; j=1,2,3; k=1,2,3.

[0062] Step S42: According to the small hydropower operation mode and hydrological situation, the power station water diversion flow and river flow change matrix M is obtained. Q =[q i,j , Q i,j , T j ], where i=1,mm; j=1,2,3; Step S43: Calculate the time variation of river section connection and the operation of small hydropower in different seasons (T 1 , T 2 and T 3) or in different months, the basic indicators of river fragmentation under the influence of small hydropower at different river scales (river section L), regional scale (Z) and basin scale (B) (see step S3 for details), forming the basic indicator matrix M of small hydropower connectivity coefficient at different time scales 2（ii*j） =[L ii，j , DCI ii，j ,SCI ii，j , CAFI ii，j , CAFIg ii，j , T j ]; M 3（jj*j） =[Z jj，j , DCI jj，j ,SCI jj，j , CAFI jj，j , CAFIg jj，j , T j ]; M 4（kk*j） =[B kk，j , DCI kk，j ,SCI kk，j , CAFI kk，j , CAFIg kk，j , T j ], where ii=1,mm; jj=1,nn; kk=1,mn; j=1,2,3.

[0063] Step S5: Comprehensively evaluate the connectivity of water systems under the influence of small hydropower, and provide a reference for the order of rectification and removal of small hydropower. That is, based on dynamic connectivity indicators and water ecological environment data, conduct a comprehensive evaluation of water system connectivity to form a priority evaluation result for rectification of small hydropower stations.

[0064] Step S51: Determine a set of connectivity assessment influencing indicators according to the regional development plan, including surface water proportion, comprehensive water quality indicators, ecological flow, erosion modulus, biological indicators, etc.; Step S52: non-dimensionalize the indicator data in each river section, calculate the information entropy of each indicator, solve the information entropy of each indicator, and find the weight of each indicator; Step S53, using the grey correlation method and dimensionless data to calculate the correlation values ​​between the indicators; Step S54: multiply the weight coefficient obtained by the entropy weight method with the coefficient obtained by the grey correlation method to obtain the influence matrix N of each indicator on the connectivity of different river sections, regions and river basins. 1（ii*j） =[L ii，j , K 1,j , K 2,j …K n,j , T j ],N 2（ii*j） =[Z jj，j , K 1,j, K 2,j …K n,j , T j ],N 1（ii*j） =[B kk，j , K 1,j , K 2,j …K n,j , T j ], where ii=1, mm; jj=1, nn; kk=1, mn; j=1, 2, 3; Step S55: Time matrix M of basic indicators of small hydropower connectivity 2 、M 3 and M 4 Respectively with other indicators influence matrix N 1 , N 2 and N 3 Multiply them together to get the water system connectivity matrix M 5 、M 6 and M 7 ; Step S56: Calculate the water system connectivity matrix M 5 、M 6 and M 7 By weighting the river section, region and basin space, we can get the comprehensive evaluation index of small hydropower H: 1 , H 2 and H 3 .

[0065] Step S57: Evaluate the priority of obstacles of small hydropower stations in the study area according to the comprehensive index of water system connectivity under the influence of small hydropower, which can provide a reference for the order of rectification and demolition of small hydropower stations.

[0066] In another embodiment of the present application, step S24 obtains basic water system attribute data such as river network morphology, river length, and river center from the water system network covering small hydropower, and also includes the following processing process: S24. Dynamic identification of connectivity status of micro water bodies based on spatiotemporal multi-source data fusion S241. Build a spatiotemporal multi-source remote sensing database: read multi-phase optical remote sensing images, radar remote sensing data and high-resolution images obtained by drones, combine water level monitoring data and rainfall data, and build a spatiotemporal multi-source database TSDB covering the flood season, normal water season and dry season.

[0067] S242. Multi-frequency water body change feature extraction: Based on the spatiotemporal multi-source database TSDB, a change detection algorithm is used to calculate the water body change rate WCR between different time phases, and a water body existence frequency matrix WEF is constructed to record the frequency of each pixel being identified as a water body in different time phases.

[0068] S243, small water body adaptive threshold segmentation method, that is, to solve the problem of small water body identification difficulty, an adaptive threshold segmentation method is designed: Read the water body frequency matrix WEF and calculate the regional water body frequency statistical distribution WFD; use the bimodal mixed Gaussian model to fit WFD and obtain the water body existence probability threshold WEPT; design a threshold adaptive function τ(x,y) = WEPT•[1+α•exp(-d(x,y) / β)] based on spatial context, where d(x,y) is the distance from the pixel (x,y) to the nearest determined water body, and α and β are adaptive parameters; S244, Determination of connectivity status of small water bodies based on hydrodynamic constraints; Read the micro-water body segmentation result MWB and digital elevation model DEM, and construct the water body connectivity candidate map CCG; based on the principle of fluid mechanics, calculate the hydraulic gradient HG and velocity field VF on the candidate connection path; design the connectivity discriminant equation: CS(i,j) = f(HG, VF, WEF) When CS(i,j)>0, water bodies i and j are connected; output the micro-water body dynamic connectivity state map MWCS; S245, Identification of Implicit Connectivity of Small Hydropower Stations for Dewatering Read the dynamic connectivity state diagram of small water bodies MWCS and the location data of small hydropower projects HPL; identify the water intake and tailwater locations of the water diversion power station, extract the water reduction and dewatering section WRSR; design the implicit connectivity discrimination model of the water reduction and dewatering section: IC(i) = η•(1-exp(-λ•Q eco / Q nat )) Among them, Q eco is the ecological flow, Q nat is the natural flow, η and λ are parameters; the implicit connectivity state WRIC of the dewatered river section is output and stored in the water system network data.

[0069] In another embodiment of the present application, step S4 further includes: S44. Intelligent perception of small hydropower operation status based on multimodal data S441. Constructing a small hydropower operation status monitoring network Integrate power station operation data OD, hydrological station flow data FD and water level monitoring data WLD; design a small hydropower group monitoring sensor network to collect real-time diversion flow RWF and tailwater flow TWF at key nodes; output small hydropower operation monitoring data set HPOD; S442, Dynamic prediction model of water diversion flow of small hydropower Read the small hydropower operation monitoring data set HPOD and construct the time series feature vector TFV; design a prediction model combining the bidirectional long short-term memory network (Bi-LSTM) and the attention mechanism: Q_t = Bi-LSTM(TFV, Att(TFV)) where Att is the time series attention function; train and optimize the model to obtain the water diversion flow prediction model WFM; output the predicted water diversion flow PWF of each small hydropower station; S443. Dynamic quantification of connectivity impacts based on diversion flow Read the predicted diversion flow PWF and river section characteristic data RCD; design the dynamic evaluation index of connectivity under the influence of water diversion: DCI(t) = 1 - (PWF(t) / NF(t))•(1-exp(-θ•L / W)) where NF is the natural flow, L is the length of the dewatered river section, W is the river width, and θ is a parameter; output the dynamic connectivity index sequence DCIS; S45. Spatiotemporal coupling model of water system connectivity and small hydropower operation S451. Constructing a spatiotemporal coupling analysis framework Read the dynamic connectivity state diagram of small water bodies MWCS, the implicit connectivity state WRIC of dewatered river sections and the dynamic connectivity index sequence DCIS; design the spatiotemporal data cube structure STDC, including the spatial dimension (x, y) and the time dimension (t); output the spatiotemporal coupling analysis framework STCF; S452. Analysis on the correlation between small hydropower operation mode and water system connectivity Read the spatiotemporal coupling analysis framework STCF and hydropower operation mode data OMD; design the operation mode-connectivity correlation evaluation index: RC(i,t) = γ•(OP(i,t) - OP_min) / (OP_max - OP_min) + (1-γ)•DCI(i,t) where OP is the operation parameter and γ is the weight factor; output the operation-connectivity correlation matrix RCCM; S453. Determination of critical connectivity thresholds for different ecological goals Read the operation-connectivity correlation matrix RCCM and the ecological indicator data EID; set the connectivity requirement threshold based on the ecological goal and construct the ecological connectivity threshold matrix ECTM; solve the constrained optimization equation: min J = Σ(OP(i,t) - OP opt (i)) 2 ;st DCI(i,t) ≥ ECTM(i,g) where, OP opt is the optimal operating parameter, g is the ecological target type; output is the eco-friendly operation plan EFRP; S454, Connectivity Optimization Model for Coordinated Dispatching of Small Hydropower Groups Read the eco-friendly operation plan EFRP, build the small hydropower group system model HSM; design a collaborative scheduling optimization model based on connectivity constraints: max E = Σ(k i •P i (t)) st Σ(DCI(i,t)*w i ) ≥ DCT Where, E is the total power generation, P i is the power generation of the i-th power station, k i is the weight, DCT is the connectivity threshold; the improved particle swarm algorithm is used to solve the optimization problem and obtain the collaborative scheduling strategy CSS; the connectivity optimization scheduling scheme COPS is output.

[0070] S46. Feedback regulation mechanism between the connectivity status of small water bodies and the operation of small hydropower stations S461. Establish a feedback model for connectivity status and operation adjustment Read the dynamic connectivity state diagram of small water bodies MWCS and the connectivity optimization scheduling scheme COPS; design a connectivity state change detector to generate a connectivity state change signal CSVS; design an operation parameter adjustment strategy based on connectivity state changes: ΔOP(i,t) = μ•CSVS(t)•(DCI tar - DCI(i,t)) where DCI tar is the target connectivity index value, μ is the adjustment coefficient; output operation parameter dynamic adjustment scheme DPAS; S462, Adaptive control method for connectivity restoration Read the dynamic adjustment scheme of operating parameters DPAS and update the operating status OPS of small hydropower; design the connectivity repair evaluation index: RI(t) = (DCI(t) - DCI(t-1)) / DCI(t-1); construct the adaptive control rule base ACRB based on the repair effect; output the adaptive control strategy ACS; S463, Connectivity balance optimization based on multi-level objectives Read the adaptive control strategy ACS and the comprehensive index of water system connectivity WCSI; construct a hierarchical analysis model to determine the weight vector w_vec under different objectives; design a multi-objective balance optimization equation: min Z = Σ(w j •(c j -c j *) 2 / c j 2 ) where c j is the current value of the jth target, c j *Ideal value; output connectivity balancing scheme CBP.

[0071] In this embodiment, an adaptive threshold function based on spatial context is introduced to solve the shortcomings of the traditional fixed threshold method in the identification of small water bodies, which is particularly suitable for complex water system environments under the influence of small hydropower. The principles of fluid mechanics are integrated into the connectivity judgment process to achieve accurate identification of the true hydraulic connectivity status of the water body. The concept and quantitative method of implicit connectivity of dewatered river sections are proposed to solve the connectivity evaluation problem unique to water diversion small hydropower. The power station operation data, hydrological data and sensor network data are integrated to achieve comprehensive perception of the operation status of small hydropower, providing a reliable data basis for connectivity evaluation. The problem of lack of clear goal orientation in traditional connectivity evaluation is solved, and differentiated connectivity thresholds are set according to different ecological function requirements to make the evaluation results more practical.

[0072] In another embodiment of the present application, a typical small watershed in the upper reaches of the Yangtze River is selected as the research area. There are 27 small hydropower stations distributed in the area, including 18 diversion power stations and 9 dam-type power stations, with a total installed capacity of 126.8MW. The watershed area is about 1250km 2 The altitude is between 800-2200m, and the total length of the river network is about 860km.

[0073] The following data were collected as the basis for the study: Remote sensing image data: 24 Sentinel-2 optical images (10m resolution) from January to December 2023, 36 Sentinel-1 radar data (10m resolution), and 15 high-resolution images (0.5m resolution) acquired by drones.

[0074] Hydrological data: Average daily flow and water level data of 10 hydrological stations in the study area from 2021 to 2023.

[0075] Small hydropower station data: geographical location, development method, installed capacity, diversion channel length, water intake and tailwater coordinates of 27 small hydropower stations, daily power generation, water diversion volume and unit operation records from 2021 to 2023.

[0076] Water ecological environment data: water quality indicators (pH, dissolved oxygen, ammonia nitrogen, total phosphorus, etc.), benthic biodiversity index and fish monitoring data at 18 monitoring points in the study area.

[0077] According to the hydrological characteristics of the study area, the whole year is divided into the flood season (May-September), the normal water season (March-April, October-November) and the dry season (December-February).

[0078] The collected Sentinel-2 optical images, Sentinel-1 radar data and drone high-resolution images are registered and fused according to the time phase to build a spatiotemporal multi-source database covering the flood season, normal water season and dry season. For Sentinel-2 optical images, the normalized difference water index (NDWI) NDWI = (ρGreen - ρNIR) / (ρGreen + ρNIR) is calculated; where: ρGreen is the reflectivity of the green band; ρNIR is the reflectivity of the near-infrared band. For Sentinel-1 radar data, the backscatter coefficient is extracted and terrain correction is performed to generate the backscatter coefficient matrix BSM.

[0079] Based on the spatiotemporal multi-source database, the frequency of each pixel being identified as a water body during the observation period is calculated, and the water body existence frequency matrix WEF is constructed: WEF(x,y) = ∑ω(t)·WP(x,y,t) / N; where: WEF(x,y) is the frequency of water body existence at the coordinate (x,y); WP(x,y,t) is the water body judgment result (0 or 1) at the coordinate (x,y) at time t; ω(t) is the time weight, which is 0.3, 0.4, and 0.5 in the flood season, normal water season, and dry season, respectively; N is the total number of weighted observations.

[0080] Taking a tributary in the study area as an example, the water body existence frequency matrix WEF is calculated, and the pixel values ​​are distributed between [0,1]. The WEF values ​​of permanent water bodies (such as river mains) are mostly above 0.85, the WEF values ​​of seasonal rivers are between 0.35-0.7, and the WEF values ​​of temporary water bodies are usually less than 0.3.

[0081] According to the statistical distribution of water frequency in the study area, a bimodal mixed Gaussian model was used for fitting: P(WEF) =π 1 ·N(μ 1 , σ 1 2 ) + π 2 ·N(μ 2 , σ 2 2 ), where: P(WEF) is the probability distribution of the frequency of water bodies; π 1 , π 2 are the weights of the two Gaussian components, π 1 + π 2 = 1; N(μ, σ 2 ) is Gaussian distribution; μ 1 , μ 2 is the mean of the two Gaussian components; σ 1 , σ 2 is the standard deviation of the two Gaussian components.

[0082] After fitting the WEF data of the study area, we get: 1 = 0.72, π 2 = 0.28, μ 1 = 0.17, μ 2 = 0.86, σ 1 = 0.12, σ 2 = 0.09. According to the fitting results, the water body existence probability threshold WEPT = 0.42 was determined.

[0083] Then, a threshold adaptive function based on spatial context is designed: τ(x,y) = WEPT·[1+α·exp(-d(x,y) / β)]; where: τ(x,y) is the adaptive threshold at the pixel (x,y); WEPT is the probability threshold of water body existence, which is 0.42; d(x,y) is the distance from the pixel (x,y) to the nearest determined water body (in pixels); α and β are adaptive parameters, which are determined as α = 0.5 and β = 8 according to the water body distribution characteristics of the study area.

[0084] For a small water body upstream of a tributary in the study area, the traditional fixed threshold method (WEPT = 0.42) identified the water body area as 86.4 km 2 , compared with the manual interpretation results (the actual water area is 107.2 km 2 ), the recognition accuracy is 80.6%. After using the adaptive threshold segmentation method: the water area is 103.8 km 2 , the accuracy rate increased to 96.8%. In the identification of small river sections with a width of less than 3 pixels, the accuracy rate increased from 65.3% to 91.7%, reflecting the advantage of this method in the identification of tiny water bodies.

[0085] Based on the segmentation results of tiny water bodies and the digital elevation model, a candidate water body connectivity graph CCG is constructed. Then the hydraulic gradient HG and velocity field VF on the candidate connectivity path are calculated. HG(i,j) = (H(i) - H(j)) / L(i,j); where: HG(i,j) is the hydraulic gradient between water bodies i and j; H(i) and H(j) are the average water surface elevations of water bodies i and j, respectively; L(i,j) is the straight-line distance between water bodies i and j. VF(i,j) = k·HG(i,j)·R(i,j)^(2 / 3)·n^(-1); where: VF(i,j) is the estimated velocity between water bodies i and j; k is a coefficient, taking the value of 1; R(i,j) is the hydraulic radius, calculated based on the characteristics of the river section; n is the Manning roughness coefficient, taking the value of 0.03-0.05 according to the river channel type.

[0086] The connectivity discriminant function CS(i,j) = HG(i,j)·VF(i,j)·[WEF(i)+WEF(j)] / 2 - θ was designed; where CS(i,j) is the connectivity discriminant value of water bodies i and j; θ is the connectivity threshold, which is 0.05.

[0087] When CS(i,j) > 0, water bodies i and j are judged to be connected. The 145 candidate connected water bodies in the study area were identified. The accuracy of the traditional image-based identification method was 76.5%, while the accuracy of the identification method based on hydrodynamic constraints reached 94.3%.

[0088] The coordinates of the water intakes and tailwaters of 18 diversion power stations were extracted from the location data of small hydropower projects, and the scope of the dewatering river sections was determined on the dynamic connectivity state diagram of small water bodies, totaling 27 sections with a total length of 96.4 km.

[0089] The implicit connectivity discrimination model of dewatered river sections was designed: IC(i) = η·(1-exp(-λ·Qeco / Qnat)); where: IC(i) is the implicit connectivity index of river section i; Qeco is the ecological flow, which is determined according to the measured data; Qnat is the natural flow, which is calculated according to the data of the upstream hydrological station; η and λ are parameters, which take values ​​of 1.0 and 3.0 respectively.

[0090] Taking a typical water diversion power station as an example, Qeco / Qnat = 0.32 in the flood season, IC = 0.62 is calculated; Qeco / Qnat = 0.15 in the normal water season, IC = 0.37; Qeco / Qnat = 0.08 in the dry season, IC = 0.21. This shows that the connectivity of the dewatered river section of the power station is significantly reduced in the dry season, which may have a great impact on the migration of aquatic organisms.

[0091] Based on the water network data, the tree connectivity index DCI, river continuity index RCI and river fragmentation index CAFI are calculated: DCI = 1 - ∑Di / ∑D0; where Di is the actual length of each river section in the study area; D0 is the length of the corresponding river section without obstacles. RCI = 1 - ∑(Li·Pi) / L; where Li is the length of the river section affected by the i-th obstacle; Pi is the impassability coefficient of the i-th obstacle; L is the total length of the river network. CAFI = ∑(ai / A)·100; where ai is the catchment area upstream of the i-th obstacle; A is the total area of ​​the basin.

[0092] The improved river fragmentation index CAFIg = ∑(ai·ICn) / (A·IC)·100 is calculated for dam-type small hydropower; where ai is the upstream catchment area of ​​the i-th barrier; A is the total area of ​​the basin; IC is the maximum installed capacity of small hydropower, 50MW; ICn is the installed capacity of the n-th small hydropower. For the 9 dam-type power stations in the study area, CAFIg = 17.46 is calculated, while the traditional CAFI = 12.83, indicating that after considering the installed capacity, the impact of dam-type small hydropower on water system connectivity is more significant.

[0093] For small hydropower stations with diversion development, the improved river fragmentation index CAFIg =∑(ai·ICn·q) / (A·IC·Q)·100 is calculated considering the influence of reduced dewatering flow; where: q is the diversion flow of the hydropower station; Q is the upstream flow of the hydropower station.

[0094] The CAFIg of 18 diversion power stations in the study area in different hydrological periods were calculated: CAFIg = 9.76 in the flood season, CAFIg = 15.34 in the normal water season, and CAFIg = 26.82 in the dry season. The results show that the impact of diversion power stations on water system connectivity is significantly enhanced in the dry season, about 2.7 times that of the flood season.

[0095] According to the operation mode data and hydrological data of 27 small hydropower stations, the 165 main river sections in the study area are divided into three types according to the connectivity status: continuous connectivity (P1), periodic connectivity (P2) and temporary connectivity (P3). On this basis, the river section connectivity time matrix M1(i,j,k) = {L(i), T(j), P(k)} is constructed; where: L(i) is the i-th river section, i = 1,2,...,165; T(j) is the hydrological period, j = 1 (flood season), 2 (normal water season), 3 (dry season); P(k) is the connectivity status, k = 1 (continuous connectivity), 2 (periodic connectivity), 3 (temporary connectivity).

[0096] Statistical analysis shows that: during the flood season, 72.1% of the river sections are continuously connected, 23.6% of the river sections are periodically connected, and 4.3% of the river sections are temporarily connected; during the normal water season, 51.5% of the river sections are continuously connected, 32.7% of the river sections are periodically connected, and 15.8% of the river sections are temporarily connected; during the dry season, 33.9% of the river sections are continuously connected, 35.2% of the river sections are periodically connected, and 30.9% of the river sections are temporarily connected.

[0097] Based on the operation data of 27 small hydropower stations from 2021 to 2023, the time series feature vector TFV is designed, which contains the characteristics of upstream flow, power generation, water level change and rainfall in the past 7 days. A prediction model Qt = Bi-LSTM(TFV, Att(TFV)) combining bidirectional long short-term memory network and attention mechanism is constructed; where: Qt is the predicted water diversion flow at time t; TFV is the time series feature vector; Bi-LSTM is the bidirectional long short-term memory network function; Att is the time series attention function.

[0098] The calculation formula of the temporal attention function is Att(TFV) = softmax(W2·tanh(W1·TFV + b1) +b2); where: W1, W2 are weight matrices; b1, b2 are bias terms; tanh is the hyperbolic tangent activation function; softmax is the normalization function.

[0099] The model training results for a typical water diversion power station are as follows: the average relative error is 5.8%, which is significantly better than the 11.3% of the traditional regression model. The prediction model shows that the water diversion of the power station is nonlinearly related to the upstream water flow. The average water diversion rate (water diversion / upstream water flow) is 0.48 in the flood season, 0.67 in the normal water season, and as high as 0.83 in the dry season.

[0100] The connectivity status in the river section connectivity time matrix is ​​matched with the predicted diversion flow data according to the time nodes to construct the dynamic connectivity evaluation model DCI(t) = 1 - (PWF(t) / NF(t))·(1-exp(-θ·L / W)); where: DCI(t) is the dynamic connectivity index at time t; PWF(t) is the predicted diversion flow at time t; NF(t) is the natural flow at time t; L is the length of the dewatered river section; W is the river width; θ is a parameter with a value of 0.05.

[0101] The dynamic connectivity index of different river sections in the study area in three hydrological periods was calculated. The results showed that in the dry season, 36% of the river sections had a DCI value lower than 0.4, which seriously affected the connectivity; the proportion of river sections with a DCI value lower than 0.4 in the normal water season was 18%; and only 6% in the flood season. The connectivity time series fluctuation evaluation index CF(i) = std(DCI(i,t)) / mean(DCI(i,t)) was designed; where: CF(i) is the connectivity fluctuation coefficient of the i-th river section; std is the standard deviation function; mean is the mean value function; DCI(i,t) is the dynamic connectivity index value of the i-th river section in time series t.

[0102] The average CF value of the river sections in the study area is 0.42, with the highest reaching 0.87, indicating that the operation of small hydropower projects has led to significant temporal fluctuations in the connectivity of the water system.

[0103] The dynamic connectivity state diagram of small water bodies, the implicit connectivity state of the dewatering river section, and the matrix of water diversion flow of power stations and river flow changes are organized into a data structure containing spatial and temporal dimensions to form a spatiotemporal coupling analysis framework STCF(x,y,t) = {MWCS(x,y,t), WRIC(x,y,t), DCI(x,y,t)}; where: STCF(x,y,t) is the spatiotemporal coupling data at time t at the coordinate (x,y); MWCS(x,y,t) is the dynamic connectivity state of small water bodies; WRIC(x,y,t) is the implicit connectivity state of the dewatering river section; and DCI(x,y,t) is the dynamic connectivity index.

[0104] Design operation mode-connectivity correlation evaluation index RC(i,t) = γ·(OP(i,t) - OPmin) / (OPmax- OPmin) + (1-γ)·DCI(i,t); where: RC(i,t) is the operation-connectivity correlation index of the i-th power station at time t; OP(i,t) is the operation parameter of the i-th power station at time t, such as the water diversion rate; OPmin and OPmax are the minimum and maximum values ​​of the operation parameters respectively; DCI(i,t) is the dynamic connectivity index at time t; γ is the weight factor, which is 0.4.

[0105] The analysis results of a small hydropower station in the study area show that when the water diversion rate exceeds 0.75, the connectivity index DCI value of the corresponding river section drops sharply, and the RC value drops from 0.68 to 0.42, indicating that high water diversion rate operation has a significant negative impact on the connectivity of the water system.

[0106] Based on the water ecological monitoring data in the study area, three main ecological protection goals were identified: fish migration protection (g1), water quality maintenance (g2) and habitat protection (g3).

[0107] Connectivity requirement thresholds were set for different ecological goals, and the ecological connectivity threshold matrix ECTM(i,g) = {DCT(g1), DCT(g2), DCT(g3)} was constructed; where: ECTM(i,g) is the connectivity threshold of the i-th river section for ecological goal g; DCT(g1), DCT(g2), DCT(g3) are the connectivity thresholds for fish migration protection, water quality maintenance, and habitat protection, respectively. According to the fish migration characteristics of the study area, DCT(g1) = 0.65 was determined; according to the water quality self-purification capacity requirements, DCT(g2) = 0.50 was determined; according to the habitat stability requirements, DCT(g3) = 0.40 was determined.

[0108] Solve the constrained optimization equation min J = ∑(OP(i,t) - OPopt(i)) 2; st DCI(i,t) ≥ ECTM(i,g); where: J is the optimization objective function; OP(i,t) is the operating parameters of the i-th power station at time t; OPopt(i) is the optimal operating parameters of the i-th power station; DCI(i,t) is the dynamic connectivity index at time t; ECTM(i,g) is the ecological connectivity threshold matrix.

[0109] Taking a key river section in the study area as an example, in order to meet the fish migration protection goal (DCT = 0.65), the optimal water diversion rate was calculated to be 0.58, and the corresponding annual power generation was 18.3% lower than the maximum water diversion rate; to meet the water quality maintenance goal (DCT = 0.50), the optimal water diversion rate was 0.67, and the power generation decreased by 8.9%; to meet the habitat protection goal (DCT = 0.40), the optimal water diversion rate was 0.72, and the power generation decreased by 5.3%.

[0110] The coordinated scheduling optimization objective function based on connectivity constraints is designed as max E = ∑(ki·Pi(t)); st ∑(DCI(i,t)·wi) ≥ DCT; where: E is the total power generation; Pi(t) is the power generation of the i-th power station at time t; ki is the weight coefficient, which is proportional to the installed capacity of the power station; DCI(i,t) is the dynamic connectivity index at time t; wi is the importance weight of the water system, which is related to the ecological sensitivity of the river section; DCT is the connectivity threshold.

[0111] The improved particle swarm algorithm is used to solve the optimization problem. The particle position update formula is X(t+1) = X(t) + V(t+1); where: X(t) is the particle position at time t (representing the water diversion rate of each power station); V(t+1) is the particle velocity at time t+1.

[0112] Particle velocity update formula V(t+1) = w·V(t) + c1·r1·(Pbest - X(t)) + c2·r2·(Gbest - X(t)) + c3·r3·(DCI(t) - DCT); where: w is the inertia weight; c1, c2, c3 are acceleration coefficients; r1, r2, r3 are random numbers between [0,1]; Pbest is the individual optimal position; Gbest is the global optimal position; DCI(t) is the dynamic connectivity index at time t; DCT is the connectivity threshold.

[0113] The collaborative optimization of five cascade small hydropower stations in a small watershed in the study area showed that compared with the independent optimization of a single station, the collaborative optimization scheme can increase the total power generation of the system by 12.6% and the maximum power generation of a single station by 18.9% while satisfying the same connectivity constraints.

[0114] Design a connectivity change detector and calculate the connectivity change signal CSVS(t) = (DCI(t) - DCI(t-1)) exp(-|DCI(t) - DCI(t-1)| / σ); where: CSVS(t) is the connectivity change signal at time t; DCI(t) and DCI(t-1) are the dynamic connectivity indicators at time t and time t-1 respectively; σ is the sensitivity parameter, which is 0.2.

[0115] The operating parameter adjustment equation ΔOP(i,t) = μ·CSVS(t)·(DCItar - DCI(i,t)) is designed based on the connectivity state change signal; where: ΔOP(i,t) is the operating parameter adjustment of the i-th power station at time t; CSVS(t) is the connectivity state change signal; DCItar is the target connectivity index value; DCI(i,t) is the current connectivity index value; μ is the adjustment coefficient, and the initial value is set to 0.15.

[0116] Taking a diversion power station in the study area as an example, when the downstream river connectivity index DCI was monitored to suddenly drop from 0.58 to 0.43, the CSVS calculated value was -0.13, and the water diversion rate adjustment was calculated to be -0.047, that is, the water diversion rate needed to be reduced from 0.72 to 0.673 to restore the connectivity of the river section.

[0117] Design the connectivity repair evaluation index RI(t) = (DCI(t) - DCI(t-1)) / DCI(t-1); where: RI(t) is the repair index at time t; DCI(t) and DCI(t-1) are the dynamic connectivity indices at time t and time t-1, respectively.

[0118] Construct an adaptive control rule base based on the repair effect, and dynamically adjust the adjustment coefficient μ in the operation parameter adjustment equation according to the changing trend of the connectivity repair evaluation index. μ(t+1) = μ(t)·(1 + ε·sign(RI(t))·(1-exp(-|RI(t)|))); where: μ(t+1) and μ(t) are the adjustment coefficients at time t+1 and time t respectively; ε is the learning rate, which takes a value of 0.2; sign is the sign function; RI(t) is the repair index at time t.

[0119] During the 30-day regulation experiment, after the introduction of the feedback regulation mechanism, the average connectivity index of key river sections in the study area increased from 0.47 to 0.63, an increase of 34.0%; the connectivity fluctuation coefficient CF decreased from 0.42 to 0.18, a decrease of 57.1%; at the same time, the total power generation of the power station only decreased by 7.2%, achieving a good balance between ecological connectivity and economic benefits.

[0120] Based on water ecological environment data, the connectivity evaluation influencing indicator set was determined: surface water proportion W1, comprehensive water quality index WQI, ecological flow guarantee rate EFG and biodiversity index BDI.

[0121] After the indicator data is standardized, the information entropy of each indicator is calculated as E(j) = -1 / ln(n)·∑(pij·ln(pij)); where: E(j) is the information entropy of the jth indicator; n is the number of samples; pij is the standardized value of the jth indicator of the ith sample. The weight of each indicator is calculated as w(j) = (1-E(j)) / ∑(1-E(j)); where: w(j) is the weight of the jth indicator. The weights of each indicator are calculated as follows: w(W1) = 0.23, w(WQI) = 0.31, w(EFG) = 0.28, w(BDI) = 0.18.

[0122] The grey correlation method is used to calculate the influence of each indicator on the water system connectivity: r(i,j) = (minmin|y0(k) - xi(k)| + ρ·maxmax|y0(k) - xi(k)|) / (|y0(k) - xi(k)| + ρ·maxmax|y0(k) -xi(k)|); where: r(i,j) is the correlation between the jth indicator of the ith sample and the reference sequence; y0(k) is the reference sequence value; xi(k) is the comparison sequence value; ρ is the resolution coefficient, which is 0.5.

[0123] The grey correlation matrix of each river section in the study area was calculated, and the average influence of different indicators on connectivity was obtained: the surface water ratio was 0.78, the comprehensive water quality index was 0.83, the ecological flow guarantee rate was 0.91, and the biodiversity index was 0.68.

[0124] The dynamic connectivity index and the influence degree matrix are combined to calculate the comprehensive index of water system connectivity under the influence of small hydropower stations: WCSI(i) = ∑(DCI(i,j)·w(j)·r(i,j)); where: WCSI(i) is the comprehensive index of water system connectivity of the ith river section; DCI(i,j) is the dynamic connectivity index of the ith river section in the jth hydrological period; w(j) is the weight of the jth index; r(i,j) is the grey correlation degree of the jth index of the ith river section.

[0125] According to the WCSI value, the rectification priority of 27 small hydropower stations in the study area was determined. The evaluation results showed that 5 power stations had WCSI values ​​below 0.35, which were in urgent need of rectification; 8 power stations had WCSI values ​​between 0.35 and 0.50, which were in need of optimized scheduling; and 14 power stations had WCSI values ​​above 0.50, which were in relatively reasonable operation.

[0126] In another embodiment of the present application, taking the upstream of a tributary in the study area as an example, the traditional fixed threshold method determines the pixel (158,237) as a non-water body when the WEF value is 0.42. The distance from the pixel to the nearest determined water body is d(158,237) = 3.6 pixels, and the adaptive threshold function is used to calculate: τ(158,237) = 0.42·[1+0.5·exp(-3.6 / 8)] = 0.42·[1+0.5·0.6376] =0.42·1.3188 = 0.5539; Since the WEF value of this pixel is 0.48, which is lower than the calculated adaptive threshold of 0.5539, it is still judged as a non-water body. However, when the terrain characteristics and seasonal river characteristics of the area are taken into account, the β value is adjusted to 12 and recalculated: τ(158,237) = 0.42·[1+0.5·exp(-3.6 / 12)] = 0.42·[1+0.5·0.7408]= 0.42·1.3704 = 0.3743. At this time, the WEF value of the pixel, 0.48, is higher than the adjusted adaptive threshold of 0.3743, so it is correctly identified as a water body, which is consistent with the field verification results.

[0127] In another embodiment of the present application, for two small water bodies a and b in the study area that appear to be connected but are blocked by a ridge, the traditional image recognition method misjudges them as connected. Apply the hydrodynamic constraint recognition method: The average water surface elevations of water bodies a and b are H(a) = 1568.3m and H(b) = 1569.7m respectively; the straight-line distance between the two water bodies is L(a,b) = 127.6m; the hydraulic gradient is calculated as HG(a,b) = (H(b) - H(a)) / L(a,b) =(1569.7 - 1568.3) / 127.6 = 0.0110; according to the characteristics of the river channel, the hydraulic radius is R(a,b) = 0.41m, and the Manning roughness coefficient is n = 0.042; the velocity field is calculated as VF(a,b) = 1·0.0110·0.41^(2 / 3)·0.042^(-1) =0.2844 m / s; the water body existence frequencies of water bodies a and b are WEF(a) = 0.68 and WEF(b) = 0.57; connectivity judgment calculation CS(a,b) = 0.0110·0.2844·(0.68+0.57) / 2 - 0.05 = -0.0344 < 0; Since CS(a,b) < 0, it is determined that water bodies a and b are not connected, which is consistent with the actual hydrological conditions.

[0128] In another embodiment of the present application, taking a typical water diversion power station in the study area as an example, the installed capacity of the power station is 4.8MW, the coordinates are (32°15'23"N, 106°47'36"E), and the length of the river channel from the water intake to the tailwater is 3.8km.

[0129] Qeco in the flood season = 1.24 m 3 / s, Qnat = 3.86 m 3 / s, Qeco / Qnat = 0.32; IC = 1.0·(1-exp(-3.0·0.32)) = 1.0·(1-0.3823) = 0.6177.

[0130] Qeco during normal water period = 0.36 m 3 / s, Qnat = 2.37 m 3 / s, Qeco / Qnat = 0.15; IC = 1.0·(1-exp(-3.0·0.15)) = 1.0·(1-0.6376) = 0.3624.

[0131] Dry season Qeco = 0.11 m 3 / s, Qnat = 1.41 m 3 / s, Qeco / Qnat = 0.08; IC = 1.0·(1-exp(-3.0·0.08)) = 1.0·(1-0.7866) = 0.2134.

[0132] The analysis shows that as the proportion of ecological flow decreases, the implicit connectivity index decreases exponentially, and the connectivity function is significantly impaired during the dry season. Compared with the traditional binary connectivity judgment (connected or disconnected), this method can quantitatively describe the continuous change of connectivity function, providing a scientific basis for the ecological dispatch of diversion power stations.

[0133] In another embodiment of the present application, taking a certain diversion power station in the study area as an example, a time series feature vector TFV is constructed, which includes 15 feature variables such as the daily average flow, rainfall, and power generation of the upstream for 7 days.

[0134] Model input layer dimension: [7, 15] (7 days, 15 features); Bidirectional LSTM hidden layer dimension: 128; Attention layer dimension: 64; Output layer dimension: 1 (forecasting water diversion flow); A set of typical input examples in model training data (simplified display): upstream flow sequence (m 3 / s): [5.43,4.89, 6.12, 7.56, 5.78, 4.32, 3.98]; Power generation series (MWh): [38.6, 35.2, 42.7,49.8, 40.3, 32.5, 30.1]; Rainfall series (mm): [0, 12.5, 26.8, 5.6, 0, 0, 0]; Apply the attention mechanism to calculate the weight of each time step: Att = softmax([0.12, 0.15, 0.26, 0.19,0.14, 0.08, 0.06]) = [0.11, 0.13, 0.23, 0.17, 0.12, 0.08, 0.05].

[0135] After model calculation, the predicted water diversion flow rate is Qt = 3.27 m 3 / s, which is consistent with the measured value of 3.42 m 3 / s, the relative error is 4.4%.

[0136] In another embodiment of the present application, for a key river section in the study area, the river section is an important migration channel for the local endemic fish yellow catfish. Set ecological goals: fish migration protection (g1); connectivity threshold: DCT(g1) = 0.65; optimal operation parameters of the power station (maximum power generation benefit): OPopt = 0.85 (water diversion rate); constraint: DCI(i,t) ≥0.65; when the power station operates according to OPopt = 0.85: DCI = 1 - (PWF / NF)·(1-exp(-0.05·L / W)) = 1 -(3.57 / 4.2)·(1-exp(-0.05·3800 / 12)) = 0.43 < 0.65; The connectivity requirements for fish migration protection are not met, and an optimization problem needs to be solved. Through iterative calculation, the optimal water diversion rate that meets the constraints is 0.58, at which point: DCI = 1 - (2.44 / 4.2)·(1-exp(-0.05·3800 / 12))= 0.66 > 0.65.

[0137] The connectivity requirements for fish migration protection are met, and the power generation is reduced by 18.3% compared to optimal operation, which is within an acceptable range.

[0138] In another embodiment of the present application, taking a small hydropower station in the study area as an example, the power station is located in an ecologically sensitive river section, and the target connectivity index DCItar = 0.55.

[0139] Initial state: the power station water diversion rate OP(t-1) = 0.65, corresponding to the connectivity index DCI(t-1) = 0.58; It was monitored that rainfall decreased and water inflow from upstream decreased, and the current connectivity index DCI(t) = 0.43; Calculate the connectivity state change signal: CSVS(t) = (0.43-0.58)·exp(-|0.43-0.58| / 0.2) = -0.15·exp(-0.15 / 0.2) = -0.15·0.4724 = -0.0709; Calculate the operating parameter adjustment: ΔOP(t) = 0.15·(-0.0709)·(0.55-0.43) = 0.15·(-0.0709)·0.12 = -0.0013; Update the water diversion rate of the power station: OP(t) = OP(t-1) + ΔOP(t) = 0.65 + (-0.0013) = 0.6487≈ 0.65; Since the calculated adjustment is small, the water diversion rate of the power station remains unchanged. As the upstream water volume continues to decrease, the connectivity index drops to 0.37: Calculate the connectivity state change signal CSVS(t+1) = (0.37-0.43)·exp(-|0.37-0.43| / 0.2) = -0.06·exp(-0.06 / 0.2) = -0.06·0.7408 = -0.0444; Calculate the operating parameter adjustment ΔOP(t+1) = 0.15·(-0.0444)·(0.55-0.37) = 0.15·(-0.0444)·0.18 = -0.0012; Update the water diversion rate of the power station OP(t+1) = OP(t) + ΔOP(t+1) = 0.65 + (-0.0012) = 0.6488 ≈ 0.65.

[0140] Continuous monitoring showed that connectivity was still declining, triggering the cumulative adjustment mechanism and adjusting the μ value to 0.25: recalculating the operating parameter adjustment ΔOP(t+2) = 0.25·(-0.0576)·(0.55-0.32) = 0.25·(-0.0576)·0.23 = -0.0033; after multiple cumulative adjustments, the power station diversion rate was reduced to 0.59, and the connectivity index recovered to 0.54, close to the target value.

[0141] During the 30-day experiment, this feedback control mechanism successfully maintained the connectivity of key river sections in the study area in an ideal state, with the fluctuation range controlled within ±8%, which is significantly lower than the ±25% under the traditional fixed parameter operation mode.

[0142] The technical idea for fine segmentation of water bodies is to try to use the spatiotemporal multi-source data fusion method to solve the problem of tiny water body identification, and successfully solve the limitation of single-phase remote sensing data being affected by factors such as clouds and vegetation occlusion. However, after the spatiotemporal multi-source data fusion, the problem of determining the threshold of water body segmentation appeared, including the traditional fixed threshold segmentation method cannot adapt to the differences in water body characteristics in different regions and different periods; resulting in insufficient recognition accuracy of tiny water bodies and broken water bodies, especially in mountainous areas with complex terrain. In order to solve the problem of threshold determination, the adaptive threshold segmentation method is introduced, which significantly improves the recognition accuracy of tiny water bodies and broken water bodies. However, after the water body is identified based only on image features, the problem of connectivity judgment arises. Including: the water body identified on the image may not be physically connected; especially in mountainous areas with complex terrain, it is easy to misjudge the terrain shadow as a connected water body. To this end, the hydrodynamic constraint judgment method is introduced to make the judgment result conform to the actual hydrodynamic law and avoid misjudgment based purely on images. In addition, due to the special situation of the water-diverting small hydropower station in the river section, it was found that the existing connectivity identification methods have limitations, including: the water diversion power station reduces the water volume in the river section but does not completely cut off the flow, and the traditional connectivity evaluation is difficult to reflect this "semi-connected" state; resulting in inaccurate assessment of the impact of water diversion small hydropower; for this reason, a method for identifying implicit connectivity of the water-diverting small hydropower station is proposed: the coordinates of the water intake and tailwater of the water diversion power station are extracted from the location data of the small hydropower project; a model for identifying implicit connectivity of the water-diverting small hydropower station is designed, and the ratio of ecological flow to natural flow is introduced as the key parameter; the accurate assessment of the connectivity of the river section under the influence of the water diversion power station is achieved.

[0143] In view of the problem of dynamic evaluation of connectivity, the technical ideas are as follows: In order to solve the problem that static evaluation cannot reflect the temporal changes of connectivity, we first try to construct a time matrix of river section connectivity, which successfully reflects the temporal change characteristics of connectivity. However, this static classification method lacks an accurate description of the dynamic changes of diversion flow, including the dynamic changes of small hydropower diversion volume with upstream water and power generation demand in actual operation, resulting in the inability of connectivity evaluation results to reflect the connectivity changes under real-time operation. To solve this problem, a dynamic prediction model of small hydropower diversion flow is introduced, which can accurately predict the diversion flow under different hydrological conditions; however, after the prediction of diversion flow, the problem of quantifying the impact of connectivity arises, that is, the impact of diversion flow on connectivity is not a simple linear relationship; it is necessary to consider river characteristics such as the length of the dewatered river section and the width of the river. To this end, a dynamic quantification method of connectivity impact based on diversion flow is designed, which can accurately quantify the dynamic impact of small hydropower diversion on water system connectivity. In order to organically combine the spatial connectivity status with the dynamic changes in time, a spatiotemporal coupling analysis framework was further constructed, and the dynamic connectivity status diagram of small water bodies, the implicit connectivity status of dewatered river sections and the dynamic connectivity indicator sequence were integrated to achieve the spatiotemporal integration of connectivity evaluation.

[0144] For the optimization regulation oriented by ecological goals, based on the connectivity evaluation, it is found that there is a lack of clear ecological goal orientation. Traditional connectivity evaluation often pursues maximum connectivity and ignores the differentiated needs of different ecosystem functions; this makes it difficult for the evaluation results to directly guide practical decisions. To solve this problem, a method for determining the critical threshold of connectivity for different ecological goals is introduced to obtain the optimal operating parameters that meet ecological needs. However, after the optimization of a single small hydropower station, the problem of system coordination of the small hydropower station group arises, including: there are hydraulic connections between multiple small hydropower stations in the basin, and isolated optimization may lead to incoordination at the system level; resulting in suboptimal solutions for the overall power generation and ecological benefits of the system; therefore, an optimization model considering the synergistic effect of the small hydropower station group is designed to obtain a coordinated scheduling strategy. In order to achieve a dynamic balance between the water system connectivity state and the operation of small hydropower stations, it is also necessary to establish a feedback regulation mechanism so that the operation of small hydropower stations can automatically adjust the operating parameters according to the real-time changes in the water system connectivity state. Finally, in order to evaluate the regulation effect and continuously optimize it, an adaptive regulation method for connectivity restoration is designed, which can continuously optimize the regulation strategy according to the connectivity restoration effect at different time scales and spatial scales.

[0145] In short, in order to solve the problem of dynamic identification of the connectivity status of small water bodies. First, multi-phase optical remote sensing images, radar data and drone high-resolution images are integrated to establish a spatiotemporal multi-source database, overcoming the limitations of a single data source. Secondly, the concept of water body frequency matrix is ​​introduced and an adaptive threshold segmentation method is designed. Through the bimodal mixed Gaussian model and the threshold adaptive function based on spatial context, high-precision identification of small water bodies is achieved. The principle of hydrodynamics is introduced into the connectivity discrimination process, and the hydraulic gradient and velocity field are calculated to ensure that the discrimination results are in line with the actual hydrological laws. In view of the special impact of diversion-type small hydropower, the concept and quantitative model of implicit connectivity of dewatering river sections are proposed. The quantitative relationship between dewatering flow and connectivity is established through the ratio of ecological flow to natural flow, realizing the accurate characterization of the connectivity status of the water system under the influence of diversion-type small hydropower.

[0146] In order to achieve the transition from static evaluation to dynamic regulation. First, by integrating power station operation data, hydrological station flow data and real-time monitoring data, a comprehensive perception of the operation status of small hydropower is achieved. Secondly, a water diversion flow prediction model combining a bidirectional long short-term memory network and an attention mechanism is designed to solve the problem that the water diversion volume of small hydropower is difficult to obtain in real time. For connectivity evaluation, a dynamic evaluation index of connectivity under the influence of water diversion is designed, which converts static parameters into time-varying parameters and accurately quantifies the dynamic impact of small hydropower operation on water system connectivity. In addition, a connectivity threshold matrix for different ecological goals and a small hydropower group collaborative scheduling optimization model are established. Combined with a closed-loop feedback mechanism of connectivity status and operation adjustment, dynamic optimization and regulation of connectivity are achieved, so that the evaluation results can directly guide the ecologically friendly operation of small hydropower, solving the fundamental deficiency of the lack of regulation mechanism in traditional evaluation.

[0147] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A comprehensive calculation method for water system connectivity under the influence of small hydropower stations, characterized in that: The following steps are involved: Collect research data sets, including remote sensing image data, hydrological data, small hydropower station data and water ecological environment data of the study area; Using remote sensing image data and deep learning methods, water bodies are segmented in detail to generate water network data; Based on the water network data and small hydropower station data, combined with hydrological data, the basic indicators of river network connectivity are calculated; Based on the basic indicators of river network connectivity and small hydropower station data, a spatiotemporal coupling model is constructed to generate dynamic connectivity indicators; Based on dynamic connectivity indicators and water ecological environment data, a comprehensive evaluation of water system connectivity is conducted to form an assessment result of the priority of rectification of small hydropower stations.

2. The method according to claim 1, characterized in that The steps for fine segmentation include: Build a spatiotemporal multi-source database, including multi-temporal optical remote sensing images, radar remote sensing data, and high-resolution images acquired by drones; Based on the spatiotemporal multi-source database, the water body change rate in different time phases is calculated and the water body existence frequency matrix is ​​constructed. Adaptive threshold segmentation method is used to process the water body frequency matrix to generate tiny water body segmentation results; Based on the segmentation results of tiny water bodies and the digital elevation model, the dynamic connectivity state diagram of tiny water bodies is generated by using the hydrodynamic constraint discrimination method. Identify the water intake and tailwater locations of the diversion power station in the location data of small hydropower projects, and generate the implicit connectivity status of the dewatering river section by combining the dynamic connectivity status diagram of the small water body; The dynamic connectivity state diagram of tiny water bodies and the implicit connectivity state of dewatered river sections are integrated into water system network data.

3. The method according to claim 1, characterized in that The steps to calculate the basic indicators of river network connectivity include: Based on the river network data, combined with the river network structure, river level and catchment area information, the tree connectivity index, river continuity index and river fragmentation index were calculated; Combined with the development mode and installed capacity parameters in the small hydropower station data, an improved river fragmentation index is calculated for dam-type small hydropower; Combined with the data of small hydropower stations and hydrological data, the improved river fragmentation index considering the influence of dewatering flow is calculated for small hydropower stations developed by water diversion; Based on the spatial hierarchical relationship of water network data, the parameter values ​​of the above indicators at different river scales, regional scales and basin scales are calculated respectively to form the basic indicators of river network connectivity.

4. The method according to claim 1, characterized in that The steps to generate dynamic connectivity indicators include: According to the operation mode data of small hydropower stations and the sluice dam dispatching rules in hydrological data, a time matrix of river section connectivity is constructed, and each river section is divided into three types: continuous connectivity, periodic connectivity and temporary connectivity. Based on the operation mode data and hydrological data of small hydropower stations, the change matrix of power station water diversion flow and river flow is constructed; According to the time matrix of river section connectivity and the matrix of power station diversion flow and river flow change, combined with the basic indicators of river network connectivity, the dynamic change indicators of connectivity at different time scales are calculated; A spatiotemporal coupling analysis framework is constructed to integrate the dynamic connectivity status of tiny water bodies and small hydropower operation status data to generate dynamic connectivity indicators.

5. The method according to claim 1, characterized in that The steps for conducting a comprehensive assessment of water system connectivity include: Based on water ecological environment data, determine the set of impact indicators for connectivity assessment, including surface water proportion, comprehensive water quality indicators, ecological flow and biological indicators; The data of each indicator in the connectivity evaluation influencing indicator set are dimensionless, the information entropy of each indicator is calculated, and the indicator weight is determined; The grey correlation method is used to calculate the influence of each index on the connectivity of the water system and form an influence degree matrix; Multiply the dynamic connectivity index and the impact degree matrix to generate the water system connectivity matrix; The water system connectivity matrix is ​​spatially weighted to obtain a comprehensive index of water system connectivity under the influence of small hydropower stations, based on which the rectification priority of each small hydropower station in the study area is evaluated.

6. The method according to claim 2, characterized in that The steps to generate tiny water body segmentation results include: Calculate the regional water body frequency statistical distribution of the water body existence frequency matrix; The bimodal mixed Gaussian model was used to fit the frequency statistical distribution of regional water bodies to obtain the probability threshold of water body existence. Design a threshold adaptive function based on spatial context, which dynamically adjusts the threshold according to the distance from the pixel to the nearest water body; The threshold adaptive function is applied to segment the water body frequency matrix, identify tiny water bodies or broken water bodies that are difficult to detect by conventional methods, and generate tiny water body segmentation results.

7. The method according to claim 4, characterized in that The steps to construct the power station diversion flow and river flow change matrix include: Integrate the power station operation parameters in the small hydropower station operation mode data and the flow records in the hydrological data to establish a model of the relationship between the water diversion volume of the small hydropower station and the upstream water inflow; Design a time series feature vector based on the operation mode data and hydrological data of small hydropower stations, including historical operation parameters, water level changes and flow change information; A prediction model combining bidirectional long short-term memory network and attention mechanism is constructed to predict the water diversion flow of small hydropower stations under different hydrological conditions with time series feature vector as input; The predicted water diversion flow is combined with the river flow data of the corresponding period in the hydrological data to generate the power station water diversion flow and river flow change matrix.

8. The method according to claim 4, characterized in that The steps to generate dynamic connectivity indicators include: The dynamic connectivity state diagram of small water bodies, the implicit connectivity state of dewatered river sections, and the matrix of power station water diversion flow and river flow change are organized into a data structure containing spatial and temporal dimensions to form a spatiotemporal coupling analysis framework. Based on the spatiotemporal coupling analysis framework, the correlation evaluation index between the operation mode of small hydropower and the connectivity status of the water system is designed, and the correlation strength between the operation parameters and the connectivity index is calculated; Combined with ecological indicator data, connectivity requirement thresholds are set for different ecological protection goals, and an ecological connectivity threshold matrix is ​​constructed; Based on the ecological connectivity threshold matrix, an optimization model considering the synergistic effect of small hydropower groups is designed, and the weight coefficients and constraint strengths of different parameters in the optimization model are determined according to the correlation strength. The optimization scheduling strategy is calculated with the goal of maximizing power generation benefits and the constraint of maintaining water system connectivity. Based on the optimized scheduling strategy and connectivity-related indicators, dynamic connectivity indicators reflecting the spatiotemporal change characteristics are generated.

9. The method according to claim 4, characterized in that The steps to calculate connectivity dynamics indicators at different time scales include: Match the connectivity status in the river section connectivity time matrix with the flow data in the power station diversion flow and river flow change matrix according to the time nodes; Based on the calculation formula of the basic indicators of river network connectivity, the static parameters are replaced with the dynamic flow parameters of the corresponding time nodes to build a dynamic connectivity evaluation model. The dynamic connectivity evaluation model is used to calculate the dynamic connectivity index values ​​of different river scales, regional scales and basin scales under the conditions of flood season, normal water season and dry season. Design connectivity time series fluctuation evaluation indicators to quantify the change amplitude and frequency of connectivity indicators at different time scales and form connectivity dynamic change indicators; Based on the dynamic change indicators of connectivity, a feedback control mechanism is constructed to achieve dynamic coupling optimization of connectivity status and small hydropower operation mode.

10. The method according to claim 6, characterized in that The threshold adaptation function based on spatial context is: τ(x,y) = T•[1+α•exp(-d(x,y) / β)]; where τ(x,y) is the adaptive threshold at the pixel (x,y), T is the probability threshold of water body existence, d(x,y) is the distance from the pixel (x,y) to the nearest determined water body, and α and β are adaptive parameters determined according to the water body distribution characteristics of the study area.

Images