Reservoir level prediction method and device based on multi-modal feature fusion

Abstract

The invention relates to a reservoir level prediction method and device based on multi-modal feature fusion, and belongs to the technical field of hydrological prediction. The method comprises the following steps: acquiring meteorological data, hydrological data and image data of an area where a reservoir is located; constructing a feature extraction and conversion module, and processing the meteorological data through the feature extraction and conversion module to obtain evaporation capacity, reservoir precipitation and water flow; constructing a feature fusion module, wherein the feature fusion module comprises a mapping unit and a gating attention module; the evaporation capacity, the water flow and the reservoir precipitation are mapped to the same dimension through a mapping unit, and then fusion features are obtained through a gating attention module; the fused features are subjected to water level prediction through a reservoir water level prediction module to obtain a water level prediction value. According to the method, multi-source features such as evaporation capacity, water flow and precipitation are dynamically fused through the improved gating attention unit, the information redundancy and loss risk of high-dimensional features can be effectively reduced, and the prediction precision and the model robustness are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of hydrological prediction, and in particular relates to a reservoir water level prediction method and device based on multi-modal feature fusion. Background Art

[0002] Changes in reservoir water levels directly affect water resource management, flood scheduling, power generation efficiency, etc. Therefore, accurate prediction of reservoir water levels is of great significance for water resource scheduling, risk warning, ecological protection, etc. Traditional water level prediction methods mostly rely on a single data source or model, and often face the problem of low accuracy or limited scope of application. Existing water level prediction methods mainly include statistical time series analysis, machine learning-based prediction models, and physical models. Although these methods can provide relatively accurate prediction results to a certain extent, they usually rely on a single data source (such as precipitation, flow, etc.) or have difficulty in modeling complex nonlinear relationships. The limitations of traditional methods make the prediction accuracy unstable in complex and changing environments. With the development of information technology, modern hydrological and meteorological observation methods can provide various types of data (such as meteorological data, remote sensing data, hydrological data, etc.). These data sources and information forms vary, covering multi-dimensional influencing factors. By fusing these multimodal data, the influencing factors of reservoir water level changes can be captured more comprehensively, making up for the shortcomings of the single data source method. Multimodal feature fusion technology can combine the characteristics of different types of data to improve the accuracy and stability of the prediction model. In recent years, multimodal feature fusion methods have been widely used in various prediction tasks, especially in the fields of natural disaster warning, intelligent transportation, environmental monitoring, etc. Through deep learning, ensemble learning and other technologies, heterogeneous data from different modalities can be effectively processed, more representative features can be extracted, and prediction performance can be further improved.

[0003] This paper proposes a reservoir water level prediction method based on multimodal feature fusion, which integrates the features of multiple data sources such as meteorology, remote sensing, and hydrology, and combines advanced machine learning algorithms to build a more accurate and stable water level prediction model. This method can better handle the uncertainty and complexity of multi-source data, thereby improving the accuracy of water level prediction and providing important support for the scientific scheduling of reservoirs. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a reservoir water level prediction method and device based on multimodal feature fusion.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions: The present invention provides a reservoir water level prediction method based on multimodal feature fusion, comprising the following steps: S1. Obtain meteorological data, hydrological data and image data of the reservoir area; S2. Construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation and water flow; S3. construct a feature fusion module, the feature fusion module includes a mapping unit and a gated attention module; the evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain an evaporation feature vector, a water flow feature vector and a reservoir precipitation feature vector, and then pass through the gated attention module to obtain a fusion feature; S4. The fused features are used for water level prediction by a reservoir water level prediction module to obtain a water level prediction value.

[0006] Furthermore, step S1 specifically includes: Weather data including air temperature , relative air humidity , wind speed , daily total solar radiation, daily ground reflected radiation, and precipitation per unit area ; Hydrological data including soil moisture , maximum soil water capacity ; Image data includes reservoir area and vegetation coverage .

[0007] Furthermore, step S2 specifically includes: Evaporation characteristics Affected by temperature T, net radiation Rn, wind speed u2, water vapor pressure qa, and relative humidity α, E is expressed as ,in Represent the above-mentioned influencing factors respectively. Indicates the calculated evaporation ; In the evaporation extraction and conversion unit, the evaporation is obtained The formula is as follows: , in, represents the slope of the saturated water vapor pressure curve, represents the multiplication operation, represents the net radiation, represents the air density, represents the specific heat capacity, Indicates wind speed, represents the saturated water vapor pressure, Indicates the actual water vapor pressure, represents the latent heat of water, represents the air pressure constant, represents the normalized wind speed; Evaporation In the formula representation, the specific settings of each parameter are as follows: , , , , , , , in, Indicates the air temperature, is the total solar radiation, is the amount of radiation reflected from the ground. Indicates air pressure, is the gas constant, Relative air humidity, Indicates wind speed correction value; Reservoir precipitation characteristics Affected by the reservoir area and local precipitation, ,in represents the reservoir area and precipitation, is the reservoir precipitation calculated by the formula; In the reservoir precipitation extraction and conversion unit, the reservoir precipitation is obtained The formula is as follows: , in, It represents the precipitation per unit area. represents the reservoir area; Water flow characteristics Affected by wind speed ,temperature , vegetation coverage , soil relative humidity Influence, Expressed as ,in For the above factors, is the water flow rate calculated by the formula; In the water flow extraction and conversion unit, the water flow is obtained The formula is as follows: , , in, Indicates the evaporation rate, Indicates soil moisture, represents the maximum water capacity of the soil, represent wind speed and vegetation coverage, respectively. It represents the water input (precipitation) of the reservoir minus the evaporation, which is the net change in the water content of the reservoir excluding the evaporation. Represents the effect of soil moisture. When soil moisture is close to maximum capacity, the flow of water will be restricted to a certain extent, so the water flow will decrease as soil moisture increases. It indicates the regulating effect of wind speed, temperature and vegetation coverage on water flow. Indicates the influence of wind speed. Generally, the greater the wind speed, the faster the water evaporates. They respectively represent the first empirical coefficient, the second empirical coefficient, the third empirical coefficient and the fourth empirical coefficient, which are automatically learned using a support vector machine supervised learning algorithm based on historical data. The historical data are the daily maximum, minimum and average wind speeds, temperatures in the reservoir area and the vegetation coverage in the area.

[0008] Furthermore, step S3 specifically includes: The evaporation characteristics , water flow characteristics and reservoir precipitation characteristics After the mapping unit is mapped to the same dimension, the evaporation feature vector is obtained , water flow characteristic vector And the reservoir precipitation characteristic vector , the formula is as follows: , , , in, They are 6×6, 5×6 and 3×6 in dimension, representing the first weight matrix, the second weight matrix and the third weight matrix. Respectively represent the first bias term, the second bias term, and the third bias term; The evaporation characteristic vector , water flow characteristic vector And the reservoir precipitation characteristic vector After the gated attention module performs feature fusion, the fused feature is obtained .

[0009] Furthermore, the gated attention module adopts an improved gated attention mechanism and uses an M-layer gated attention mechanism for feature fusion. The specific operation steps of the layer-gated attention mechanism are: Gated Attention Neural Network Layer accepts The output feature vector of the layer is expressed as follows: , in, The characteristic vectors representing evaporation, water flow and reservoir precipitation respectively.

[0010] Through linear transformation, each input feature vector is mapped into a query vector Query, a key vector Key, and a value vector Value. The formula is as follows: , , , in, represents the i-th feature vector in the l-th layer input feature set, Respectively expressed in Tier The query vector, key vector, and value vector of each feature, Respectively represent The weight matrix corresponding to the query vector, key vector, and value vector of the layer, Respectively represent Bias terms corresponding to the query vector, key vector, and value vector of the layer.

[0011] In the Layer, by calculating the similarity between the query vector and the key vector, the attention weights between different features are obtained: , in, represents the attention weight between the i-th feature and the j-th feature, represents the dimensions of the query vector and key vector, They are The query vector of the i-th feature and the key vector of the j-th feature of the layer, The function is used to normalize the weights to a probability distribution to ensure that the weight values ​​are between 0 and 1; according to the attention weights, the value vector is weighted summed to obtain the updated feature vector: , in, Indicates that the i-th feature is in The representation of the layer after fusion by the attention mechanism; calculate the similarity between the updated feature vector and the input data: in, Indicates similarity; Based on similarity The size of the next layer is dynamically adjusted to fusion mode: Among them, ξ=0.7 is the set similarity threshold. When , the updated feature vector is directly used as the input of the next layer; when When , the original feature vector and the updated feature vector are weightedly fused and used as the input of the next layer; After M layers of gated attention mechanism, all modal features are gradually fused, and the fused features are obtained by weighted summation of the value vector of the last layer: , in, It represents the fusion feature, which means the comprehensive representation of all modal features after fusion through M layers of gated attention mechanism. represents the global attention weight of the j-th feature in the M-th layer, The value vector representing the j-th feature of the M-th layer.

[0012] Furthermore, step S4 specifically includes: The reservoir water level prediction module includes an LSTM module and a fully connected layer; Historical water level data , fusion features .

[0013] The final hidden state is generated by the LSTM module, and the formula is as follows: , , , , , , in, represents the forget gate, represents the input gate, represents the candidate cell state, Indicates updating the cell status. represents the output gate, Represent the weight matrices of the forget gate, input gate, candidate cell state, and output gate respectively, Respectively represent the bias items of the forget gate, input gate, candidate cell state, and output gate, represents the hidden state at the previous moment, represents the fusion feature at the current time t, Represents the hidden state at the current time t; the final hidden state is mapped through the fully connected layer to obtain the water level prediction value , the formula is as follows: , in, represents the final hidden state, represents the time series length of the fused features, represents the weight matrix of the fully connected layer, Represents the bias term of the fully connected layer.

[0014] The present invention also provides a reservoir water level prediction device based on multimodal feature fusion, which executes a reservoir water level prediction method based on multimodal feature fusion, including: Data acquisition unit: used to obtain meteorological data, hydrological data and image data of the reservoir area; A feature extraction and conversion module construction unit is used to construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation, and water flow; A feature fusion module construction unit is used to construct a feature fusion module, which includes a mapping unit and a gated attention module; the evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain an evaporation feature vector, a water flow feature vector and a reservoir precipitation feature vector, and then pass through the gated attention module to obtain a fusion feature; Water level prediction unit: used to input the fusion features into the reservoir water level prediction module for water level prediction to obtain the water level prediction value.

[0015] The advantages of the present invention are: The present invention proposes a reservoir water level prediction method based on multimodal feature fusion, which combines the gated attention mechanism with the LSTM model and has the following advantages: ① The multimodal features such as evaporation, water flow, precipitation, etc. are dynamically weighted and fused through the improved gated attention mechanism, which significantly reduces the risk of high-dimensional feature information loss; ② The similarity threshold is introduced to dynamically adjust the weight ratio of the original feature and the updated feature, further improving the robustness of feature fusion; ③ The short-term and long-term dependencies of the time series are captured by LSTM, and efficient nonlinear mapping is achieved in combination with the fully connected layer, thereby improving the accuracy and stability of reservoir water level prediction, and providing a scientific decision-making basis for reservoir scheduling, flood warning and ecological protection. ④ Prediction based on evaporation, precipitation and water flow directly reflects the key hydrological process of reservoir water level changes, has a stronger physical correlation and explanatory power with water level changes, and is more intuitive and easy to quantify than climate characteristics, hydrological characteristics and image characteristics. At the same time, they do not rely on complex environmental monitoring networks or high-precision image processing technology, so they have lower data acquisition costs and computational complexity, and are suitable for real-time prediction and reservoir management applications.

[0016] The present invention organizes meteorological data, hydrological data and image data and converts them into three categories: evaporation, water flow and reservoir precipitation. In order to reduce the loss between high-dimensional features and original features, the gated attention network is improved. In each layer output, the similarity between the output features and the original features is calculated. , if the similarity is less than the threshold The output of each layer of the gated attention neural network is weightedly fused with the original features, and the fusion weight of the features of this layer is , as the input data of the next layer of gating; the fused features are integrated in time series and input into LSTM for reservoir water level prediction. The experimental results show that the reservoir water level prediction method based on multimodal feature fusion shows excellent prediction performance in multiple experimental groups, which can significantly reduce the loss of water level prediction. Compared with a single data source or a single model, it has better robustness and generalization ability. The reservoir water level prediction method of the present invention is suitable for fields such as reservoir management, flood warning, and drought monitoring, and provides effective technical support for water resources management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0018] Figure 1 The figure is a flow chart of the steps of the method of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1 In this embodiment, Figure 1 As shown, the present invention provides a reservoir water level prediction method based on multimodal feature fusion, and the specific steps include: S1. Obtain meteorological data, hydrological data and image data of the reservoir area; Specifically, meteorological data includes air temperature , relative air humidity , wind speed , daily total solar radiation, daily ground reflected radiation, and precipitation per unit area ; Hydrological data including soil moisture , maximum soil water capacity ; Image data includes reservoir area and vegetation coverage .

[0021] S2. Construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation and water flow; Specifically, the evaporation characteristics Affected by temperature T, net radiation Rn, wind speed u2, water vapor pressure qa, and relative humidity α, E is expressed as ,in Represent the above-mentioned influencing factors respectively. Indicates the calculated evaporation ; In the evaporation extraction and conversion unit, the evaporation is obtained The formula is as follows: , in, represents the slope of the saturated water vapor pressure curve, represents the multiplication operation, represents the net radiation, represents the air density, represents the specific heat capacity, Indicates wind speed, represents the saturated water vapor pressure, Indicates the actual water vapor pressure, represents the latent heat of water, represents the air pressure constant, represents the normalized wind speed; Evaporation In the formula representation, the specific settings of each parameter are as follows: , , , , , , , in, Indicates the air temperature, is the total solar radiation, is the amount of radiation reflected from the ground. Indicates air pressure, is the gas constant, Relative air humidity, Indicates wind speed correction value; Reservoir precipitation characteristics Affected by the reservoir area and local precipitation, ,in represents the reservoir area and precipitation, is the reservoir precipitation calculated by the formula; In the reservoir precipitation extraction and conversion unit, the reservoir precipitation is obtained The formula is as follows: , in, It represents the precipitation per unit area. represents the reservoir area; Water flow characteristics Affected by wind speed ,temperature , vegetation coverage , soil relative humidity Influence, Expressed as ,in For the above factors, is the water flow rate calculated by the formula; In the water flow extraction and conversion unit, the water flow is obtained The formula is as follows: , , in, Indicates the evaporation rate, Indicates soil moisture, represents the maximum water capacity of the soil, represent wind speed and vegetation coverage, respectively. It represents the water input (precipitation) of the reservoir minus the evaporation, which is the net change in the water content of the reservoir excluding the evaporation. Represents the effect of soil moisture. When soil moisture is close to maximum capacity, the flow of water will be restricted to a certain extent, so the water flow will decrease as soil moisture increases. It indicates the regulating effect of wind speed, temperature and vegetation coverage on water flow. Indicates the influence of wind speed. Generally, the greater the wind speed, the faster the water evaporates. They respectively represent the first empirical coefficient, the second empirical coefficient, the third empirical coefficient and the fourth empirical coefficient, which are automatically learned using a support vector machine supervised learning algorithm based on historical data. The historical data are the daily maximum, minimum and average wind speeds, temperatures in the reservoir area and the vegetation coverage in the area.

[0022] S3. construct a feature fusion module, the feature fusion module includes a mapping unit and a gated attention module; the evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain an evaporation feature vector, a water flow feature vector and a reservoir precipitation feature vector, and then pass through the gated attention module to obtain a fusion feature; Specifically, the evaporation characteristic , water flow characteristics and reservoir precipitation characteristics After the mapping unit is mapped to the same dimension, the evaporation feature vector is obtained , water flow characteristic vector And the reservoir precipitation characteristic vector , the formula is as follows: , , , in, They are 6×6, 5×6 and 3×6 in dimension, representing the first weight matrix, the second weight matrix and the third weight matrix. Respectively represent the first bias term, the second bias term, and the third bias term; The evaporation characteristic vector , water flow characteristic vector And the reservoir precipitation characteristic vector After the gated attention module performs feature fusion, the fused feature is obtained .

[0023] Specifically, the gated attention module adopts an improved gated attention mechanism and uses an M-layer gated attention mechanism for feature fusion. The specific operation steps of the layer-gated attention mechanism are: Gated Attention Neural Network Layer accepts The output feature vector of the layer is expressed as follows: , in, The characteristic vectors representing evaporation, water flow and reservoir precipitation respectively.

[0024] Through linear transformation, each input feature vector is mapped into a query vector Query, a key vector Key, and a value vector Value. The formula is as follows: , , , in, represents the i-th feature vector in the l-th layer input feature set, Respectively expressed in Tier The query vector, key vector, and value vector of each feature, Respectively represent The weight matrix corresponding to the query vector, key vector, and value vector of the layer, Respectively represent Bias terms corresponding to the query vector, key vector, and value vector of the layer.

[0025] In the Layer, by calculating the similarity between the query vector and the key vector, the attention weights between different features are obtained: , in, represents the attention weight between the i-th feature and the j-th feature, represents the dimensions of the query vector and key vector, They are The query vector of the i-th feature and the key vector of the j-th feature of the layer, The function is used to normalize the weights to a probability distribution to ensure that the weight values ​​are between 0 and 1; according to the attention weights, the value vector is weighted summed to obtain the updated feature vector: , in, Indicates that the i-th feature is in The representation of the layer after fusion by the attention mechanism; calculate the similarity between the updated feature vector and the input data: in, Indicates similarity; Based on similarity The size of the next layer is dynamically adjusted to fusion mode: Among them, ξ=0.7 is the set similarity threshold. When , the updated feature vector is directly used as the input of the next layer; when When , the original feature vector and the updated feature vector are weightedly fused and used as the input of the next layer; After M layers of gated attention mechanism, all modal features are gradually fused, and the fused features are obtained by weighted summation of the value vector of the last layer: , in, It represents the fusion feature, which means the comprehensive representation of all modal features after fusion through M layers of gated attention mechanism. represents the global attention weight of the j-th feature in the M-th layer, The value vector representing the j-th feature of the M-th layer.

[0026] S4. The fused features are used for water level prediction by a reservoir water level prediction module to obtain a water level prediction value.

[0027] Specifically, the reservoir water level prediction module includes an LSTM module and a fully connected layer; Historical water level data , fusion features .

[0028] The final hidden state is generated by the LSTM module, and the formula is as follows: , , , , , , in, represents the forget gate, represents the input gate, represents the candidate cell state, Indicates updating the cell status. represents the output gate, Represent the weight matrices of the forget gate, input gate, candidate cell state, and output gate respectively, Respectively represent the bias items of the forget gate, input gate, candidate cell state, and output gate, represents the hidden state at the previous moment, represents the fusion feature at the current time t, Represents the hidden state at the current time t; the final hidden state is mapped through the fully connected layer to obtain the water level prediction value , the formula is as follows: , in, represents the final hidden state, represents the time series length of the fused features, represents the weight matrix of the fully connected layer, Represents the bias term of the fully connected layer.

[0029] Example 2 In this embodiment, the meteorological data of Huangdao District, Qingdao City for 180 days is obtained from the National Meteorological Information Center-China Meteorological Data Network in units of days, including: temperature, humidity, wind speed, precipitation, soil moisture, solar radiation, ground reflected solar radiation, air pressure, relative air humidity, maximum soil moisture capacity, etc. The corresponding reservoir area and reservoir water level data of XXX Reservoir in Huangdao District are obtained by sensor measurement every day and stored in the database together. The data set is divided into a training set and a test set at a ratio of 3:1.

[0030] Through these data, the daily evaporation, water flow and reservoir precipitation are calculated, and the change in reservoir water level can be obtained. Evaporation, water flow and reservoir precipitation are mapped to the same dimension (feature vectors of the same length 1×32) to obtain vectors R1, R2, and R3.

[0031] The number of layers of the improved gated attention network is set to 6, the similarity threshold ξ is set to 0.7, the gated activation function uses softmax, and the fusion weight is calculated according to the similarity to ensure that the loss between features is reduced by weighted fusion; the LSTM hidden unit is set to 64, the input feature dimension is 3×32, the Adam optimizer is used, the learning rate is set to 0.001, the dynamic attenuation coefficient is set to 0.9, the accelerated attenuation coefficient is set to 0.99, the prediction loss is calculated using mean square error, the training batch is set to 64, and the training cycle is set to 200.

[0032] In order to verify the effectiveness of the reservoir water level prediction method based on multimodal feature fusion proposed in the present invention, the following experimental verification was carried out.

[0033] In order to verify the effectiveness of the feature fusion method proposed in this invention, the following experiments are conducted: Table 1 Experimental comparison of feature fusion and direct concatenation features From Table 1, we can see that compared with single type data and directly splicing various features, the fusion features obtained by the feature fusion method based on gated attention proposed in this paper have more complete information and more accurate prediction results. On the other hand, it also shows that the reservoir water level prediction method based on evaporation, precipitation and water flow proposed in this invention has better prediction performance than directly splicing historical data.

[0034] In order to verify the effectiveness of the method of the present invention, the following experiments were performed: Table 2 Experimental comparison between the method of the present invention and traditional machine learning methods It can be seen from Table 2 that the prediction module of the reservoir water level prediction method proposed in the present invention uses LSTM, which has certain improvements in indicators such as mean square error, root mean square error, determination coefficient and mean absolute error compared with the traditional machine learning method, indicating that the method of the present invention can significantly improve the accuracy of water level prediction and has better robustness and generalization ability than the traditional machine learning method.

[0035] Example 3 This embodiment provides a reservoir water level prediction device based on multimodal feature fusion, which executes the reservoir water level prediction method based on multimodal feature fusion as described in Example 1, including: Data acquisition unit: used to obtain meteorological data, hydrological data and image data of the reservoir area; A feature extraction and conversion module construction unit is used to construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation, and water flow; A feature fusion module construction unit is used to construct a feature fusion module, which includes a mapping unit and a gated attention module; the evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain an evaporation feature vector, a water flow feature vector and a reservoir precipitation feature vector, and then pass through the gated attention module to obtain a fusion feature; Water level prediction unit: used to input the fusion features into the reservoir water level prediction module for water level prediction to obtain the water level prediction value.

[0036] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A reservoir water level prediction method based on multimodal feature fusion, characterized in that: The following steps are involved: S1. Obtain meteorological data, hydrological data and image data of the reservoir area; S2. Construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation and water flow; S3. construct a feature fusion module, the feature fusion module includes a mapping unit and a gated attention module; the evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain an evaporation feature vector, a water flow feature vector and a reservoir precipitation feature vector, and then pass through the gated attention module to obtain a fusion feature; S4. The fused features are used for water level prediction by a reservoir water level prediction module to obtain a water level prediction value.

2. The reservoir water level prediction method based on multimodal feature fusion according to claim 1 is characterized in that: Step S1 specifically includes: Weather data including air temperature , relative air humidity , wind speed , daily total solar radiation, daily ground reflected radiation, and precipitation per unit area ; Hydrological data including soil moisture , maximum soil water capacity ; Image data includes reservoir area and vegetation coverage .

3. The reservoir water level prediction method based on multimodal feature fusion according to claim 2 is characterized in that: Step S2 specifically includes: Evaporation characteristics Affected by temperature T, net radiation Rn, wind speed u2, water vapor pressure qa, and relative humidity α, E is expressed as ,in Represent the above-mentioned influencing factors respectively. Indicates the calculated evaporation ; In the evaporation extraction and conversion unit, the evaporation is obtained The formula is as follows: ， in, represents the slope of the saturated water vapor pressure curve, represents the multiplication operation, represents the net radiation, represents the air density, represents the specific heat capacity, Indicates wind speed, represents the saturated water vapor pressure, Indicates the actual water vapor pressure, represents the latent heat of water, represents the air pressure constant, represents the normalized wind speed; Evaporation In the formula representation, the specific settings of each parameter are as follows: ， ， ， ， ， ， ， in, Indicates the air temperature, is the total solar radiation, is the amount of radiation reflected from the ground. Indicates air pressure, is the gas constant, Relative air humidity, Indicates wind speed correction value; Reservoir precipitation characteristics Affected by the reservoir area and local precipitation, ,in represents the reservoir area and precipitation, is the reservoir precipitation calculated by the formula; In the reservoir precipitation extraction and conversion unit, the reservoir precipitation is obtained The formula is as follows: ， in, It represents the precipitation per unit area. represents the reservoir area; Water flow characteristics Affected by wind speed ,temperature , vegetation coverage , soil relative humidity Influence, Expressed as ,in For the above factors, is the water flow rate calculated by the formula; In the water flow extraction and conversion unit, the water flow is obtained The formula is as follows: ， ， in, Indicates the evaporation rate, Indicates soil moisture, represents the maximum water capacity of the soil, represent wind speed and vegetation coverage, respectively. It represents the water input (precipitation) of the reservoir minus the evaporation, which is the net change in the water content of the reservoir excluding the evaporation. Represents the influence of soil moisture; when soil moisture is close to maximum capacity, the flow of water will be restricted to a certain extent, so the water flow will decrease as soil moisture increases. It indicates the regulating effect of wind speed, temperature and vegetation coverage on water flow. Indicates the influence of wind speed. Generally, the greater the wind speed, the faster the water evaporates. They respectively represent the first empirical coefficient, the second empirical coefficient, the third empirical coefficient and the fourth empirical coefficient, which are automatically learned using a support vector machine supervised learning algorithm based on historical data. The historical data are the daily maximum, minimum and average wind speeds, temperatures in the reservoir area and the vegetation coverage in the area.

4. The reservoir water level prediction method based on multimodal feature fusion according to claim 3 is characterized in that: Step S3 specifically includes: The evaporation characteristics , water flow characteristics and reservoir precipitation characteristics After the mapping unit is mapped to the same dimension, the evaporation feature vector is obtained , water flow characteristic vector And the reservoir precipitation characteristic vector , the formula is as follows: ， ， ， in, They are 6×6, 5×6 and 3×6 in dimension, representing the first weight matrix, the second weight matrix and the third weight matrix. Respectively represent the first bias term, the second bias term, and the third bias term; The evaporation characteristic vector , water flow characteristic vector And the reservoir precipitation characteristic vector After the gated attention module performs feature fusion, the fused feature is obtained .

5. The reservoir water level prediction method based on multimodal feature fusion according to claim 4 is characterized in that: The gated attention module adopts an improved gated attention mechanism and uses M layers of gated attention mechanism for feature fusion. The specific operation steps of the layer-gated attention mechanism are: Gated Attention Neural Network Layer accepts The output feature vector of the layer is expressed as follows: ， in, eigenvectors representing evaporation, water flow and reservoir precipitation, respectively; Through linear transformation, each input feature vector is mapped into a query vector Query, a key vector Key, and a value vector Value. The formula is as follows: ， ， ， in, Represents the first feature set in the input feature set of the first layer feature vectors, Respectively expressed in Tier The query vector, key vector, and value vector of each feature, Respectively represent The weight matrix corresponding to the query vector, key vector, and value vector of the layer, Respectively represent The bias terms corresponding to the query vector, key vector, and value vector of the layer; In the Layer, by calculating the similarity between the query vector and the key vector, the attention weights between different features are obtained: ， in, Indicates Features and The attention weights between features, represents the dimensions of the query vector and key vector, Respectively represent Tier The query vector of the feature and the The key vector of features, The function is used to normalize the weights to a probability distribution to ensure that the weight values ​​are between 0 and 1; according to the attention weights, the value vector is weighted summed to obtain the updated feature vector: ， in, Indicates The feature in The representation of the layer after fusion by the attention mechanism; calculate the similarity between the updated feature vector and the input data: in, Indicates similarity; Based on similarity The size of the next layer is dynamically adjusted to fusion mode: Among them, ξ=0.7 is the set similarity threshold. When , the updated feature vector is directly used as the input of the next layer; when When , the original feature vector and the updated feature vector are weightedly fused and used as the input of the next layer; After M layers of gated attention mechanism, all modal features are gradually fused, and the fused features are obtained by weighted summation of the value vector of the last layer: ， in, represents the fusion feature, which means the comprehensive representation of all modal features after fusion through the M-layer gated attention mechanism; represents the global attention weight of the j-th feature in the M-th layer, The value vector representing the j-th feature of the M-th layer.

6. The reservoir water level prediction method based on multimodal feature fusion according to claim 5 is characterized in that: Step S4 specifically includes: The reservoir water level prediction module includes an LSTM module and a fully connected layer; Historical water level data , fusion features ; The final hidden state is generated by the LSTM module, and the formula is as follows: ， ， ， ， ， ， in, represents the forget gate, represents the input gate, represents the candidate cell state, Indicates updating the cell status. represents the output gate, Represent the weight matrices of the forget gate, input gate, candidate cell state, and output gate respectively, Respectively represent the bias items of the forget gate, input gate, candidate cell state, and output gate, represents the hidden state at the previous moment, represents the fusion feature at the current time t, Represents the hidden state at the current time t; the final hidden state is mapped through the fully connected layer to obtain the water level prediction value , the formula is as follows: ， in, represents the final hidden state, represents the time series length of the fused features, represents the weight matrix of the fully connected layer, Represents the bias term of the fully connected layer.

7. A reservoir water level prediction device based on multimodal feature fusion, executing the reservoir water level prediction method based on multimodal feature fusion as claimed in claim 1, characterized in that: include: Data acquisition unit: used to obtain meteorological data, hydrological data and image data of the reservoir area; A feature extraction and conversion module construction unit is used to construct a feature extraction and conversion module, which includes an evaporation extraction and conversion unit, a reservoir precipitation extraction and conversion unit, and a water flow extraction and conversion unit; the meteorological data of the reservoir area is processed by the feature extraction and conversion module to obtain evaporation, reservoir precipitation, and water flow; A feature fusion module construction unit, used to construct a feature fusion module, the feature fusion module includes a mapping unit and a gated attention module; Evaporation, water flow and reservoir precipitation are mapped to the same dimension by the mapping unit to obtain evaporation feature vector, water flow feature vector and reservoir precipitation feature vector, and then pass through the gated attention module to obtain the fusion feature; Water level prediction unit: used to input the fusion features into the reservoir water level prediction module for water level prediction to obtain the water level prediction value.

Images