A short-term and imminent precipitation forecasting method based on TimeUnet and phenology knowledge

Abstract

The present invention discloses a short-term and imminent precipitation forecasting method based on TimeUnet and phenological knowledge, comprising the following steps: (1) collecting meteorological element observation data and bird sound anomaly information samples, and preprocessing the data; (2) extracting features from the preprocessed meteorological element observation data and bird sound anomaly information samples to construct a feature data set; (3) building a deep learning model TimeUnet that integrates TimesNet and Unet and designing a customized loss function; (4) training the TimeUnet model and adjusting the hyperparameters in the model to obtain an optimal model; (5) generating short-term and imminent precipitation forecasting products based on real-time meteorological element observation data and bird sound anomaly information samples; the present invention effectively improves the forecasting skill of heavy rain.

Description

Technical Field

[0001] The present invention relates to the technical field of precipitation forecasting, and particularly to a short-term and imminent precipitation forecasting method based on TimeUnet and phenological knowledge. Background Art

[0002] Extrapolating precipitation conditions in the future for a period of time based on the current weather background is a common short-term and imminent precipitation forecasting method. The most common method among them is the optical flow method, which has been widely used in the operational part. However, due to the chaotic characteristics of the atmosphere, it is difficult for this method to fully characterize the nonlinear characteristics of atmospheric motion. Therefore, the forecasting performance of this method has great limitations. In recent years, deep learning technology has been widely used due to its high nonlinearity and strong robustness. Some scholars have also applied it to short-term and imminent precipitation forecasting, such as algorithms like ConvLSTM and Unet, which have shown higher forecasting skills compared to the traditional optical flow method. However, the current deep learning algorithms are still difficult to characterize the interaction of spatio-temporal information at different scales and are difficult to well forecast and warn extreme values, which to a certain extent limits the forecasting skills of short-term and imminent precipitation (especially heavy rain). At the same time, restricted by the source of predictability, even short-term and imminent precipitation forecasting based on deep learning algorithms also faces the problem of low predictability, and it is urgent to explore additional sources of predictability. Considering the response of bird activities to environmental changes (especially to heavy rain weather), extracting features from abnormal bird sound information can provide an additional opportunity window for short-term and imminent precipitation forecasting, which is still in the initial stage of development. Summary of the Invention

[0003] Object of the Invention: The object of the present invention is to provide a short-term and imminent precipitation forecasting method based on TimeUnet and phenological knowledge, extract features from abnormal bird sound information, and solve the problem of short-term and imminent precipitation forecasting.

[0004] Technical Solution: A short-term and imminent precipitation forecasting method based on TimeUnet and phenological knowledge according to the present invention includes the following steps:

[0005] (1) Collect meteorological element observation data and abnormal bird sound information samples, and preprocess the data;

[0006] (2) Extract features from the preprocessed meteorological element observation data and abnormal bird sound information samples to construct a feature dataset;

[0007] (3) Build a deep learning model TimeUnet that integrates TimesNet and Unet and design a customized loss function;

[0008] (4) Train the TimeUnet model and adjust the hyperparameters in the model to obtain the optimal model;

[0009] (5) Generate short-term precipitation forecast products based on real-time meteorological element observation data and bird sound abnormal information samples.

[0010] Furthermore, in step (1), the meteorological element observation data includes precipitation data, pressure field data, humidity data and wind field data at the current time and in the past 2 hours; the bird sound abnormal information sample includes information at the current time and in the past 2 hours; the preprocessing is as follows:

[0011] Based on the inverse distance weighted interpolation, the station data is interpolated into uniform grid data; the outliers in the grid data are removed; the calculation formula of the inverse distance weighted interpolation is as follows:

[0012] ;

[0013] Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

[0014] Furthermore, step (2) includes the following steps:

[0015] (21) Based on short-time Fourier transform, the bird sound characteristic spectrum containing time-frequency domain characteristic information is obtained; the formula is as follows:

[0016] ;

[0017] in, is the extracted bird sound feature map. is the original sound spectrum at time T, is the analysis window function, is a complex function;

[0018] (22) De-dimensionalize the meteorological element data to obtain the characteristic map of meteorological elements; the formula is as follows:

[0019] ;

[0020] Among them, f is the original meteorological element data, is the average value of meteorological element data, is the standard deviation of meteorological element data.

[0021] Furthermore, in step (3), the TimeUnet network includes two modules, MFCM-Unet and TimesNet, and includes the following steps:

[0022] (31) Input the meteorological element feature map obtained in step (2) into the MFCM-Unet network to extract meteorological information at different spatial scales; the MFCM-Unet network includes an encoder, a multi-feature based channel attention mechanism, and a decoder; among them, the encoder is used to extract features at different spatial scales; the multi-feature based channel attention mechanism is used to assign higher weights to important forecast features to highlight important information; the decoder is used to reconstruct and generate the final forecast; at the same time, the bird sound feature map TimesNet obtained in step (2) captures bird sound anomaly information at different time scales; including: signal reading, decomposing the signal and constructing a two-dimensional signal field, and signal reconstruction;

[0023] (32) Design a customized loss function, the formula is as follows:

[0024] ;

[0025] Among them, , , , respectively represent the root mean square errors of light rain, moderate rain, heavy rain, and rainstorm, , , , respectively represent , , , the weights of; the calculation formula of the weights is as follows:

[0026] ;

[0027] Among them, represents the weight of the i-th type of precipitation, represents the number of samples of the i-th type of precipitation; among them, precipitation includes: light rain, moderate rain, heavy rain, and rainstorm.

[0028] A short-term precipitation forecasting system based on TimeUnet and phenology knowledge according to the present invention includes:

[0029] Collection module: used to collect meteorological element observation data and bird sound anomaly information samples, and preprocess the data;

[0030] Dataset module: used to extract features from the preprocessed meteorological element observation data and bird sound anomaly information samples, and construct a feature dataset;

[0031] TimeUnet module: used to build a deep learning model TimeUnet that integrates TimesNet and Unet and design a customized loss function;

[0032] Training module: used to train the TimeUnet model and adjust the hyperparameters in the model to obtain the optimal model;

[0033] Forecast module: used to generate short-term precipitation forecast products based on real-time meteorological element observation data and bird sound abnormal information samples.

[0034] Furthermore, in the acquisition module, the meteorological element observation data include precipitation data, pressure field data, humidity data and wind field data at the current time and in the past 2 hours; the bird sound abnormal information sample includes the information at the current time and in the past 2 hours; the preprocessing is as follows: interpolating the station data into uniform grid data based on inverse distance weighted interpolation; removing outliers in the grid data; the calculation formula of inverse distance weighted interpolation is as follows:

[0035] ;

[0036] Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

[0037] Furthermore, the dataset module includes the following steps:

[0038] (21) Based on short-time Fourier transform, the bird sound characteristic spectrum containing time-frequency domain characteristic information is obtained; the formula is as follows:

[0039] ;

[0040] in, is the extracted bird sound feature map. is the original sound spectrum at time T, is the analysis window function, is a complex function;

[0041] (22) De-dimensionalize the meteorological element data to obtain the characteristic map of meteorological elements; the formula is as follows:

[0042] ;

[0043] Among them, f is the original meteorological element data, is the average value of meteorological element data, is the standard deviation of meteorological element data.

[0044] Furthermore, in the TimeUnet module, the TimeUnet network includes two modules, MFCM-Unet and TimesNet, including the following steps:

[0045] (31) Input the meteorological element feature map obtained in step (2) into the MFCM-Unet network to extract meteorological information at different spatial scales; the MFCM-Unet network includes an encoder, a multi-feature based channel attention mechanism, and a decoder; among them, the encoder is used to extract features at different spatial scales; the multi-feature based channel attention mechanism is used to assign higher weights to important forecasting features to highlight important information; the decoder is used to reconstruct and generate the final forecast; at the same time, the bird sound feature map TimesNet obtained in step (2) captures bird sound anomaly information at different time scales; including: signal reading, decomposing the signal and constructing a two-dimensional signal field, and signal reconstruction;

[0046] (32) Design a customized loss function, the formula is as follows:

[0047] ;

[0048] Among them, , , , respectively represent the root mean square errors of light rain, moderate rain, heavy rain, and rainstorm, , , , respectively represent , , , of the weights; the calculation formula of the weights is as follows:

[0049] ;

[0050] Among them, represents the weight of the i-th type of precipitation, represents the number of samples of the i-th type of precipitation; among them, precipitation includes: light rain, moderate rain, heavy rain, and rainstorm.

[0051] An electronic device according to the present invention includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is loaded into the processor, it implements any one of the short-term precipitation forecasting methods based on TimeUnet and phenology knowledge.

[0052] A storage medium according to the present invention stores a computer program, and when the computer program is executed by a processor, it implements any one of the short-term precipitation forecasting methods based on TimeUnet and phenology knowledge.

[0053] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: based on phenological knowledge, by extracting abnormal information of bird sounds, additional forecasting factors are provided for short-term precipitation forecasting, thereby effectively improving the forecasting skills of short-term precipitation; the TimeUnet neural network based on the combination of TimesNet and MFCM-Unet can effectively extract effective information at different time and space scales, thereby achieving high-quality short-term precipitation prediction; the introduction of a customized loss function effectively improves the forecasting skills of heavy rain, thereby improving the application value of the model in extreme scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of the present invention;

[0055] Figure 2 It is a schematic diagram of the model structure of the present invention. DETAILED DESCRIPTION

[0056] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a short-term precipitation forecasting method based on TimeUnet and phenological knowledge, comprising the following steps:

[0058] (1) Collect meteorological element observation data and bird sound abnormal information samples, and pre-process the data; meteorological element observation data include precipitation data, pressure field data, humidity data and wind field data at the current time and in the past 2 hours; bird sound abnormal information samples include information at the current time and in the past 2 hours; the pre-processing is as follows:

[0059] Based on the inverse distance weighted interpolation, the station data is interpolated into uniform grid data; the outliers in the grid data are removed; the calculation formula of the inverse distance weighted interpolation is as follows:

[0060] Based on the inverse distance weighted interpolation, the station data is interpolated into uniform grid data; the outliers in the grid data are removed; the calculation formula of the inverse distance weighted interpolation is as follows:

[0061] ;

[0062] Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

[0063] (2) Extract features from the preprocessed meteorological element observation data and bird sound abnormal information samples to construct a feature data set; the following steps are included:

[0064] (21) Obtain the bird sound feature spectrogram containing time-frequency domain feature information based on the short-time Fourier transform; the formula is as follows:

[0065] ;

[0066] Among them, is the extracted bird sound feature spectrogram, is the original sound spectrum at time T, is the analysis window function, is a complex function;

[0067] (22) Dimensionalize the meteorological element data to obtain the feature map of meteorological elements; the formula is as follows:

[0068] ;

[0069] Among them, f is the original meteorological element data, is the average value of the meteorological element data, is the standard deviation of the meteorological element data.

[0070] (3) Build a deep learning model TimeUnet that integrates TimesNet and Unet and design a customized loss function; the TimeUnet network includes two modules, MFCM-Unet and TimesNet, as Figure 2 shown, including the following steps:

[0071] (31) Input the meteorological element feature map obtained in step (2) into the MFCM-Unet network to extract meteorological information at different spatial scales; the MFCM-Unet network includes an encoder, a multi-feature-based channel attention mechanism, and a decoder; among them, the encoder is used to extract features at different spatial scales; the multi-feature-based channel attention mechanism is used to assign higher weights to important prediction features to highlight important information; the decoder is used to reconstruct and generate the final prediction; at the same time, the bird sound feature spectrogram obtained in step (2) is used by TimesNet to capture bird sound anomaly information at different time scales; including: signal reading, decomposing the signal and constructing a two-dimensional signal field, and signal reconstruction;

[0072] (32) Design a customized loss function, the formula is as follows:

[0073] ;

[0074] Among them, , , , respectively represent the root mean square errors of light rain, moderate rain, heavy rain, and rainstorm, , , , Respectively , , , The weight of is as follows:

[0075] ;

[0076] in, represents the weight of the i-th precipitation, Represents the number of samples of the i-th type of precipitation; precipitation includes: light rain, moderate rain, heavy rain, and rainstorm.

[0077] (4) Train the TimeUnet model and adjust the hyperparameters in the model to obtain the optimal model; specifically, the hyperparameters that can be adjusted in the model mainly include: learning rate, number of network layers, number of convolution kernels, etc., which can be adjusted according to the actual training results. Generally, a smaller learning rate, a larger number of network layers, and a larger number of convolution kernels means a more complex model, which usually leads to higher prediction skills, but also increases the computational requirements of the model. When the complexity of the model reaches a certain level, the skill improvement brought by a more complex model is very limited. Therefore, it is necessary to set the optimal hyperparameters according to the actual training results to ensure the performance and computational requirements of the model.

[0078] (5) Generate short-term precipitation forecast products based on real-time meteorological element observation data and bird sound abnormal information samples.

[0079] The embodiment of the present invention further provides a short-term precipitation forecasting system based on TimeUnet and phenological knowledge, including:

[0080] Acquisition module: used to collect meteorological element observation data and bird sound abnormal information samples, and pre-process the data; meteorological element observation data include precipitation data, pressure field data, humidity data and wind field data at the current time and in the past 2 hours; bird sound abnormal information samples include information at the current time and in the past 2 hours; pre-processing is as follows: interpolate the station data into uniform grid data based on inverse distance weighted interpolation; remove outliers in the grid data; the calculation formula of inverse distance weighted interpolation is as follows:

[0081] ;

[0082] Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

[0083] Dataset module: used to extract features from the preprocessed meteorological element observation data and bird sound anomaly information samples, and construct a feature dataset; including the following steps:

[0084] (21) Obtain a bird sound feature spectrogram containing time-frequency domain feature information based on the short-time Fourier transform; the formula is as follows:

[0085] ;

[0086] Among them, is the extracted bird sound feature spectrogram, is the original sound spectrum at time T, is the analysis window function, is a complex function;

[0087] (22) Dimensionality reduction of the meteorological element data to obtain a feature map of the meteorological elements; the formula is as follows:

[0088] ;

[0089] Among them, f is the original meteorological element data, is the average value of the meteorological element data, is the standard deviation of the meteorological element data.

[0090] TimeUnet module: used to build a deep learning model TimeUnet that integrates TimesNet and Unet and design a customized loss function; in the TimeUnet module, the TimeUnet network includes two modules, MFCM-Unet and TimesNet, including the following steps:

[0091] (31) Input the meteorological element feature map obtained in step (2) into the MFCM-Unet network to extract meteorological information at different spatial scales; the MFCM-Unet network includes an encoder, a multi-feature-based channel attention mechanism, and a decoder; among them, the encoder is used to extract features at different spatial scales; the multi-feature-based channel attention mechanism is used to assign higher weights to important prediction features to highlight important information; the decoder is used to reconstruct and generate the final prediction; at the same time, the bird sound feature spectrogram obtained in step (2) is used by TimesNet to capture bird sound anomaly information at different time scales; including: signal reading, decomposing the signal and constructing a two-dimensional signal field, and signal reconstruction;

[0092] (32) Design a customized loss function, the formula is as follows:

[0093] ;

[0094] Among them, 、 、 , respectively represent the root mean square errors of light rain, moderate rain, heavy rain, and rainstorm, , , , respectively represent , , , ; the calculation formula of the weight is as follows:

[0095] ;

[0096] wherein, represents the weight of the i-th type of precipitation, represents the sample quantity of the i-th type of precipitation; wherein, precipitation includes: light rain, moderate rain, heavy rain, and rainstorm.

[0097] Training module: used to train the TimeUnet model, and adjust the hyperparameters in the model to obtain the optimal model;

[0098] Forecasting module: used to generate short-term and nowcasting precipitation forecast products based on real-time meteorological element observation data and bird sound anomaly information samples.

[0099] An embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is loaded into the processor, it implements any one of the short-term and nowcasting precipitation forecasting methods based on TimeUnet and phenology knowledge.

[0100] An embodiment of the present invention further provides a storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, it implements any one of the short-term and nowcasting precipitation forecasting methods based on TimeUnet and phenology knowledge.

Claims

1. A short-term precipitation forecasting method based on TimeUnet and phenological knowledge, comprising the following steps: (1) Collect meteorological element observation data and bird sound abnormality information samples, and pre-process the data; (2) Extract features from the preprocessed meteorological element observation data and bird sound abnormal information samples to construct a feature data set; (3) Build a deep learning model TimeUnet that combines TimesNet and Unet and design a customized loss function; the TimeUnet network includes two modules: MFCM-Unet and TimesNet: (31) Inputting the meteorological element characteristic map obtained in step (2) into the MFCM-Unet network to extract meteorological information at different spatial scales; The MFCM-Unet network includes an encoder, a channel attention mechanism based on multiple features, and a decoder; wherein the encoder is used to extract features of different spatial scales; the channel attention mechanism based on multiple features is used to give higher weights to important prediction features to highlight important information; the decoder is used to reconstruct and generate the final prediction; at the same time, the bird sound feature map TimesNet obtained in step (2) captures abnormal bird sound information at different time scales; including: signal reading, signal decomposition and construction of a two-dimensional signal field, and signal reconstruction; (32) Design a customized loss function, the formula is as follows: ； in, , , , They represent the root mean square error of light rain, moderate rain, heavy rain and rainstorm respectively, , , , Respectively , , , The weight of is as follows: ； in, represents the weight of the i-th precipitation, represents the number of samples of the i-th precipitation; (4) Train the TimeUnet model and adjust the hyperparameters in the model to obtain the optimal model; (5) Generate short-term precipitation forecast products based on real-time meteorological element observation data and bird sound abnormal information samples.

2. A method for short-term precipitation forecasting based on TimeUnet and phenological knowledge according to claim 1, characterized in that: In step (1), the meteorological element observation data includes the precipitation data, pressure field data, humidity data and wind field data at the current time and the past 2 hours; the bird sound abnormal information sample includes the information at the current time and the past 2 hours; the preprocessing is as follows: Based on the inverse distance weighted interpolation, the station data is interpolated into uniform grid data; the outliers in the grid data are removed; the calculation formula of the inverse distance weighted interpolation is as follows: ； Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

3. The method for short-term precipitation forecasting based on TimeUnet and phenological knowledge according to claim 1, characterized in that: Step (2) includes the following steps: (21) Based on short-time Fourier transform, the bird sound characteristic spectrum containing time-frequency domain characteristic information is obtained; the formula is as follows: ； in, is the extracted bird sound feature map. is the original sound spectrum at time T, is the analysis window function, is a complex function; (22) De-dimensionalize the meteorological element data to obtain the characteristic map of meteorological elements; the formula is as follows: ； Among them, f is the original meteorological element data, is the average value of meteorological element data, is the standard deviation of meteorological element data.

4. A short-term precipitation forecast system based on TimeUnet and phenological knowledge, characterized in that: include: Collection module: used to collect meteorological element observation data and bird sound abnormal information samples, and pre-process the data; Dataset module: used to extract features from preprocessed meteorological element observation data and bird sound abnormal information samples to construct feature datasets; TimeUnet module: used to build the deep learning model TimeUnet that integrates TimesNet and Unet and design a customized loss function; the TimeUnet network includes two modules, MFCM-Unet and TimesNet, and includes the following steps: input the obtained meteorological element feature map into the MFCM-Unet network to extract meteorological information of different spatial scales; the MFCM-Unet network includes an encoder, a channel attention mechanism based on multiple features, and a decoder; wherein the encoder is used to extract features of different spatial scales; the channel attention mechanism based on multiple features is used to give higher weights to important forecast features to highlight important information; the decoder is used to reconstruct and generate the final forecast; at the same time, the bird sound feature map TimesNet obtained in step (2) captures abnormal bird sound information of different time scales; including: signal reading, signal decomposition and construction of two-dimensional signal field, signal reconstruction; Design a customized loss function, the formula is as follows: ； in, , , , They represent the root mean square error of light rain, moderate rain, heavy rain and rainstorm respectively, , , , Respectively , , , The weight of is as follows: ； in, represents the weight of the i-th precipitation, represents the number of samples of the i-th precipitation; Training module: used to train the TimeUnet model and adjust the hyperparameters in the model to obtain the optimal model; Forecast module: used to generate short-term precipitation forecast products based on real-time meteorological element observation data and bird sound abnormal information samples.

5. The short-term precipitation forecast system based on TimeUnet and phenological knowledge according to claim 4 is characterized in that: In the acquisition module, meteorological element observation data include precipitation data, pressure field data, humidity data and wind field data at the current time and in the past 2 hours; bird sound abnormal information samples include information at the current time and in the past 2 hours; preprocessing is as follows: interpolate the station data into uniform grid data based on inverse distance weighted interpolation; remove outliers in the grid data; the calculation formula of inverse distance weighted interpolation is as follows: ； Where n represents the total number of sites around the target grid point, represents the observation data of the ith station, represents the distance from the i-th station to the target grid point, Represents the interpolated grid data.

6. The short-term precipitation forecast system based on TimeUnet and phenological knowledge according to claim 4 is characterized in that: The dataset module includes: The bird sound characteristic spectrum containing time-frequency domain characteristic information is obtained based on short-time Fourier transform; the formula is as follows: ； in, is the extracted bird sound feature map. is the original sound spectrum at time T, is the analysis window function, is a complex function; De-dimensionalize the meteorological element data to obtain the characteristic map of meteorological elements; the formula is as follows: ； Among them, f is the original meteorological element data, is the average value of meteorological element data, is the standard deviation of meteorological element data.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is loaded into a processor, a method for forecasting short-term precipitation based on TimeUnet and phenological knowledge according to any one of claims 1 to 3 is implemented.

8. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a method for forecasting short-term precipitation based on TimeUnet and phenological knowledge according to any one of claims 1 to 3 is implemented.

Images