Rainfall forecast method and device combining meteorological satellite brightness temperature data and GNSS-PWV

Abstract

The present invention discloses a rainfall forecasting method and device that combines meteorological satellite brightness temperature data with GNSS-PWV data. The method comprises: obtaining channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV rate for several preceding time periods at the location where rainfall is to be predicted; then, after matching these channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV rate by time, inputting them into a trained multi-layer neural network model to output a predicted rainfall level for a preset future time period. By combining brightness temperature and GNSS-PWV data, the present invention reduces the false alarm and under-reporting rates of rainfall forecasts based solely on brightness temperature data from meteorological satellites, thereby improving the accuracy of rainfall forecasts.

Description

Technical Field

[0001] The present invention relates to the field of rainfall prediction, and in particular to a rainfall forecasting method and device combining meteorological satellite brightness temperature data and GNSS-PWV. Background Art

[0002] Brightness Temperature (BT) data from meteorological satellites plays a crucial role in traditional rainfall forecasting. These data, which reflect the cloud layer's response to microwave radiation emitted by satellite sensors, can be used to identify cloud structure and estimate rainfall intensity. However, BT primarily reflects cloud surface characteristics and lacks detailed information about the total amount of water vapor in the atmosphere. This leads to false and underreported rainfall forecasts based solely on BT data from meteorological satellites, reducing the accuracy of rainfall forecasts. Summary of the Invention

[0003] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a method and apparatus for rainfall forecasting that combines brightness temperature data from meteorological satellites and GNSS-PWV data. By combining brightness temperature data and GNSS-PWV data, the false alarm rate and missed alarm rate of rainfall forecasts based on single brightness temperature data from meteorological satellites are reduced, thereby improving the accuracy of rainfall forecasts.

[0004] According to one aspect of the present invention, a method for rainfall forecasting combining meteorological satellite brightness temperature data and GNSS-PWV is provided, comprising:

[0005] Obtain the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for the previous several time periods at the location where rainfall is to be forecast;

[0006] After matching the channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV increase rate according to time, the results are input into a trained multi-layer neural network model to output a predicted rainfall level for a preset future period. The training of the multi-layer neural network model includes:

[0007] Acquire remote sensing data from meteorological satellites in real time, and extract long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be predicted from the remote sensing data;

[0008] Acquire GNSS data and extract the long-term PWV, PWV increment and PWV increase rate at the location of the rainfall to be forecast from the GNSS data;

[0009] Obtaining long-term rainfall data at the location where rainfall is to be forecast, and dividing the rainfall data into several rainfall levels;

[0010] The rainfall level during the rainfall period is matched with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several periods before the rainfall period in time to obtain a sample data set;

[0011] Construct a multi-layer neural network model, the input layer of which is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for several time periods before different times, and the output layer is the rainfall level for a preset time period in the future corresponding to the time;

[0012] The constructed multi-layer neural network model is trained using the sample data set to obtain a trained multi-layer neural network model.

[0013] As a further technical solution, after obtaining the sample data set, the following is also included:

[0014] The sample dataset is divided into rainfall dataset and non-rainfall dataset according to the standard of whether there is rainfall or not;

[0015] The random downsampling method is used to select the same number of samples from the non-rainfall dataset as from the rainfall dataset to form the modeling dataset.

[0016] As a further technical solution, after obtaining the modeling data set, it also includes:

[0017] Randomly select a part of the modeling data set as the training set, and the remaining data as the test set;

[0018] The training set and the test set are input into the constructed multi-layer neural network model, the model is trained until convergence, and the model parameters are saved.

[0019] As a further technical solution, the rainfall levels are divided into no rain, light rain, moderate rain, heavy rain and extremely heavy rain.

[0020] As a further technical solution, the multi-layer neural network model is constructed using a back-propagation neural network including three hidden layers.

[0021] As a further technical solution, the channels used to extract brightness temperature include BT11.2 and BT13.3, and the channels used to calculate brightness temperature difference include BTD6.2-11.2, BTD7.3-12.4, BTD10.4-12.4, BTD7.3-10.4, BTD8.6-11.2 and BTD11.2-12.4; among them, BT11.2 and BT13.3 represent the channel brightness temperatures of 11.2μm and 13.3μm respectively; BTD6.2-11.2 represents the brightness temperature difference between BT6.2-BT11.2, and the others are the same.

[0022] According to one aspect of the present invention, a rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV is provided, comprising:

[0023] A data acquisition module is used to obtain the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of the previous several time periods at the location of the rainfall to be forecast;

[0024] A rainfall forecast module is configured to match the channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV increase rate according to time, input the data into a trained multi-layer neural network model, and output a predicted rainfall level for a preset time period in the future. The training of the multi-layer neural network model includes:

[0025] Acquire remote sensing data from meteorological satellites in real time, and extract long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be predicted from the remote sensing data;

[0026] Acquire GNSS data and extract the long-term PWV, PWV increment and PWV increase rate at the location of the rainfall to be forecast from the GNSS data;

[0027] Obtaining long-term rainfall data at the location where rainfall is to be forecast, and dividing the rainfall data into several rainfall levels;

[0028] The rainfall level during the rainfall period is matched with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several periods before the rainfall period in time to obtain a sample data set;

[0029] Construct a multi-layer neural network model, the input layer of which is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for several time periods before different times, and the output layer is the rainfall level for a preset time period in the future corresponding to the time;

[0030] The constructed multi-layer neural network model is trained using the sample data set to obtain a trained multi-layer neural network model.

[0031] According to one aspect of the present invention, a ground observation device is provided, comprising a processor and a memory, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV.

[0032] According to one aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the steps of the rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention utilizes brightness temperature data from meteorological satellites, combined with the GNSS-PWV correlation factor, and uses a neural network (NN) model to predict rainfall. This reduces the false alarm rate and missed alarm rate of rainfall forecasts based on single brightness temperature data from meteorological satellites, and improves the accuracy of rainfall forecasts.

[0035] 2. The present invention constructs a multi-layer neural network model and, through data fusion technology, combines brightness temperature data and GNSS-PWV data. This reduces the false alarm rate and missed alarm rate of rainfall forecasts based on single brightness temperature data from meteorological satellites, and improves the overall accuracy of rainfall forecasts. Especially in areas with complex terrain or scarce observation data, the model can more effectively capture and analyze the dynamics of water vapor in the atmosphere, thereby providing more accurate single-point short-term rainfall forecasts and can respond to possible extreme rainfall events. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction will be given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic flow chart of a rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV is provided in an embodiment of the present invention.

[0038] Figure 2 A schematic diagram of the structure of a rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention addresses the problems of false alarms and missed reports in existing rainfall forecasts based on single brightness temperature data from meteorological satellites. Considering that GNSS atmospheric precipitable water volume (PWV) is an important meteorological parameter that can be used for rainfall forecasting, a rainfall forecasting method combining brightness temperature data from meteorological satellites and GNSS-PWV is provided. By combining brightness temperature data with GNSS-PWV data, the false alarm rate and missed report rate of rainfall forecasts based on single brightness temperature data from meteorological satellites are reduced, thereby improving the accuracy of rainfall forecasts.

[0040] It should be noted that, unless otherwise specified, the technologies involved in the specification of the present invention are all well-known technologies.

[0041] The terms "including" and "having" and any variations thereof in the description and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 making creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or structural composition mode, but must be based on the ability of ordinary technicians in this field to implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0043] The embodiment of the present invention provides a rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV, such as Figure 1 As shown, the method includes: obtaining channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV rate of increase for the previous several time periods at the location where rainfall is to be forecasted; matching the channel brightness temperature, brightness temperature difference, PWV, PWV increment, and PWV rate by time, inputting these data into a trained multi-layer neural network model, and outputting a predicted rainfall level for a preset time period in the future. This embodiment of the present invention combines brightness temperature data with GNSS-PWV data to reduce the false alarm and underreporting rates of rainfall forecasts based solely on brightness temperature data from meteorological satellites, thereby improving the accuracy of rainfall forecasts.

[0044] The training of the multi-layer neural network model described in the embodiment of the present invention includes data acquisition, data processing, and building and training the multi-layer neural network model.

[0045] The data acquisition steps include:

[0046] (1) Real-time acquisition of remote sensing data from meteorological satellites, usually with a temporal resolution of 10 minutes. The long-term channel brightness temperature (BT) at the location of the rainfall forecast is extracted from the remote sensing data from meteorological satellites, and the corresponding brightness temperature difference (BTD) is calculated.

[0047] (2) The long-term PWV, PWV increment and PWV rate data are collected at the GNSS station at the location where the rainfall is to be forecast, usually with a time resolution of 10 minutes.

[0048] (3) Obtain long-term rainfall data at the location where rainfall is to be forecast from ERA5 data, with an original time resolution of 1 hour.

[0049] The data processing steps include:

[0050] (1) The rainfall is divided into the following rainfall levels according to the World Meteorological Organization's classification standards for different rainfall levels: no rain (<0.1 mm / h), light rain (0.1-2.5 mm / h), moderate rain (2.5-9.9 mm / h), heavy rain (10.0-49.9 mm / h), and extremely heavy rain (≥50.0 mm / h).

[0051] (2) The rainfall level during the rainfall period is matched with the forecast factors (PWV, PWV increment, PWV increase rate, BT, BTD) of a certain period of time (e.g., 6 hours) before the rainfall period to obtain a sample data set.

[0052] (3) The sample data set is divided into rainfall data set and non-rainfall data set according to the standard of whether there is rainfall or not.

[0053] (4) Using the random downsampling method, the same number of samples as the rainfall data are selected from the non-rainfall data to form the modeling data set.

[0054] The steps of constructing and training a multi-layer neural network model include:

[0055] (1) The forecast factors (PWV, PWV increment, PWV rate, BT, BTD) of a period of time before different moments (e.g., 6 hours) are used as input features, and the rainfall level of a period of time after the corresponding moment (e.g., 1 hour) is used as the output result.

[0056] (2) During the model training process, a portion of the modeling data set (e.g., 70% or 80%) is randomly selected as the training set, and the remaining data (e.g., 30% or 20%) is used as the test set.

[0057] (3) Input the training set and test set into the model, train the model until convergence, and save the model parameters.

[0058] After model training is complete, rainfall forecasting is performed using the trained model. First, the data acquisition step collects forecast factors (PWV, PWV increment, PWV rate of increase, BT, and BTD) for the preceding several hours at the location where rainfall is to be predicted. Next, the data is processed according to the data processing step and input into the trained model to obtain the predicted rainfall level for a period of time in the future (e.g., one hour).

[0059] As a preferred embodiment, the present invention introduces an embodiment of rainfall forecasting for a certain GNSS station based on the Japanese meteorological remote sensing satellite Himawari-8 and a back-propagation neural network model.

[0060] (1) Data acquisition:

[0061] i. Download multi-band Himawari-8 data from 2020-2021 with a temporal resolution of 10 minutes. Extract long-term channel brightness temperature data at a specific GNSS station from the Himawari-8 remote sensing data and calculate the corresponding brightness temperature differences. These include BT11.2, BT13.3, BTD6.2-11.2, BTD7.3-12.4, BTD10.4-12.4, BTD7.3-10.4, BTD8.6-11.2, and BTD11.2-12.4 (BT11.2 represents the brightness temperature of the 11.2 μm channel; BTD6.2-11.2 represents the brightness temperature difference between BT6.2 and BT11.2; all other values ​​remain the same).

[0062] ii. Calculate the PWV, PWV increment, and PWV rate of increase for a given GNSS station from 2020 to 2021, with a temporal resolution of 10 minutes.

[0063] iii. Download the 2020-2021 ERA5 data (the fifth-generation global atmospheric reanalysis dataset released by the European Centre for Medium-Range Weather Forecasts) and obtain rainfall data at a specific GNSS station. The original time resolution is 1 hour.

[0064] (2) Data processing:

[0065] i. The rainfall is divided into the following rainfall levels according to the World Meteorological Organization's classification standards for different rainfall levels: no rain (<0.1mm / h), light rain (0.1-2.5mm / h), moderate rain (2.5-9.9mm / h), heavy rain (10.0-49.9mm / h), and extremely heavy rain (≧50.0mm / h).

[0066] ii. Match the rainfall level during the rainfall period with the forecast factors (PWV, PWV increment, PWV increase rate, brightness temperature BT, brightness temperature difference BTD) in the first 6 hours of the rainfall period to obtain a sample data set.

[0067] iii. Divide the sample dataset into a rainfall dataset and a non-rainfall dataset based on the presence or absence of rainfall. Using random downsampling, select the same number of samples from the non-rainfall dataset as from the rainfall dataset to form the modeling dataset.

[0068] (3) Construct a backward neural network (BPNN) model with three hidden layers:

[0069] i. Use the forecast factors (PWV, PWV increment, PWV growth rate, the above-mentioned BT, the above-mentioned BTD) of the six hours before different moments as the input layer, and the rainfall level of the next hour at the corresponding moment as the output layer, outputting no rain (0), light rain (1), moderate rain (2), heavy rain (3), and extremely heavy rain (4).

[0070] ii. During the model training process, 80% of the modeling dataset is randomly selected as the training set, and the remaining 20% ​​is used as the test set.

[0071] iii. Input the training set and test set into BPNN, train the model until convergence, and save the model parameters.

[0072] (4) Using the trained model for rainfall forecasting. First, the prediction factors (PWV, PWV increment, PWV rate of increase, BT, BTD) for the previous six hours at a GNSS station are collected according to the data acquisition steps. Then, the data is processed according to the data processing steps and input into the trained model to obtain the predicted rainfall level within the next hour at that time.

[0073] The various embodiments of the present invention are implemented through programmed processing by a device with processor functionality. Therefore, in practical engineering applications, the technical solutions and functionalities of the various embodiments of the present invention are packaged into various modules. Based on this reality, and in addition to the aforementioned embodiments, an embodiment of the present invention provides a rainfall forecasting device that combines meteorological satellite brightness temperature data with GNSS-PWV data. This device is used to implement the rainfall forecasting method for combining meteorological satellite brightness temperature data with GNSS-PWV data, as described in the aforementioned method embodiments.

[0074] See also Figure 2The device includes: a data acquisition module for acquiring channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for the previous several time periods at the location of rainfall to be forecasted; a rainfall forecast module for matching the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate according to time, inputting the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate into a trained multi-layer neural network model, and outputting a predicted rainfall level for a preset time period in the future; the training of the multi-layer neural network model includes: acquiring remote sensing data from meteorological satellites in real time, and extracting a long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be forecasted from the remote sensing data; acquiring GNSS data, and extracting a long-term series of PWV at the location of rainfall to be forecasted from the GNSS data , PWV increment and PWV increase rate; obtain long-term rainfall data at the rainfall location to be forecast, and divide the rainfall data into several rainfall levels; match the rainfall level of a rainfall period with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several time periods before the rainfall period in time to obtain a sample data set; construct a multi-layer neural network model, the input layer of the multi-layer neural network model is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several time periods before different moments, and the output layer is the rainfall level of a preset time period in the future corresponding to the moment; use the sample data set to train the constructed multi-layer neural network model to obtain a trained multi-layer neural network model.

[0075] The embodiment of the present invention provides a rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV, which adopts Figure 2 By combining brightness temperature data with GNSS-PWV data, the several modules in the system can reduce the false alarm rate and missed alarm rate of rainfall forecast based on single brightness temperature data of meteorological satellites and improve the accuracy of rainfall forecast.

[0076] It should be noted that the device embodiments provided by the present invention are not only used to implement the methods in the above-mentioned method embodiments, but also used to implement the methods in other method embodiments provided by the present invention. The only difference is the setting of corresponding functional modules. The principles thereof are basically the same as those of the above-mentioned device embodiments provided by the present invention. As long as those skilled in the art refer to the specific technical solutions in other method embodiments on the basis of the above-mentioned device embodiments, obtain corresponding technical means and technical solutions composed of these technical means by combining technical features, and on the premise of ensuring the practicality of the technical solutions, improve the modules in the above-mentioned device embodiments to obtain corresponding device-type embodiments, which are used to implement the methods in other method-type embodiments. For example:

[0077] Based on the content of the above device embodiment, as a preferred embodiment, the rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV provided in the embodiment of the present invention, after obtaining the sample data set, further includes:

[0078] The sample dataset is divided into rainfall dataset and non-rainfall dataset according to the standard of whether there is rainfall or not;

[0079] The random downsampling method is used to select the same number of samples from the non-rainfall dataset as from the rainfall dataset to form the modeling dataset.

[0080] Based on the contents of the above device embodiments, as a preferred embodiment, the rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV provided in the embodiments of the present invention, after obtaining the modeling data set, further includes:

[0081] Randomly select a part of the modeling data set as the training set, and the remaining data as the test set;

[0082] The training set and the test set are input into the constructed multi-layer neural network model, the model is trained until convergence, and the model parameters are saved.

[0083] Based on the contents of the above-mentioned device embodiments, as a preferred embodiment, the rainfall forecasting device provided in the embodiments of the present invention that combines meteorological satellite brightness temperature data and GNSS-PWV also includes: dividing the rainfall levels into no rain, light rain, moderate rain, heavy rain and extremely heavy rain in turn.

[0084] Based on the contents of the above-mentioned device embodiment, as a preferred embodiment, in the rainfall forecast device of combining meteorological satellite brightness temperature data and GNSS-PWV provided in the embodiment of the present invention, the multi-layer neural network model is constructed using a back-propagation neural network including three hidden layers.

[0085] Based on the contents of the above-mentioned device embodiment, as a preferred embodiment, in the rainfall forecasting device combining meteorological satellite brightness temperature data and GNSS-PWV provided in the embodiment of the present invention, the channels for extracting brightness temperature include BT11.2 and BT13.3, and the channels for calculating brightness temperature difference include BTD6.2-11.2, BTD7.3-12.4, BTD10.4-12.4, BTD7.3-10.4, BTD8.6-11.2 and BTD11.2-12.4 (BT11.2 represents the brightness temperature of the 11.2μm channel; BTD6.2-11.2 represents the brightness temperature difference between BT6.2 and BT11.2, and the others are the same).

[0086] Based on the same inventive concept as the above embodiment, an embodiment of the present invention also provides a ground observation device, including a processor and a memory, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV.

[0087] When using the ground observation equipment provided by the embodiment of the present invention to make rainfall forecasts, the false alarm rate and missed alarm rate of rainfall forecasts based on single brightness temperature data of meteorological satellites can be reduced by combining brightness temperature data and GNSS-PWV data, thereby improving the accuracy of rainfall forecasts.

[0088] Based on the same inventive concept as the above embodiment, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions cause the computer to execute the steps of the above-described method for rainfall forecasting using combined meteorological satellite brightness temperature data and GNSS-PWV, including:

[0089] Obtain the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for the previous several time periods at the location where rainfall is to be forecast;

[0090] After matching the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate according to time, they are input into the trained multi-layer neural network model to output the predicted rainfall level for a preset period in the future; wherein, the training of the multi-layer neural network model includes: acquiring remote sensing data from meteorological satellites in real time, and extracting the long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be forecasted from the remote sensing data; acquiring GNSS data, and extracting the long-term series of PWV, PWV increment and PWV increase rate at the location of rainfall to be forecasted from the GNSS data; acquiring the long-term series of rainfall at the location of rainfall to be forecasted The method comprises the following steps: collecting rainfall data and dividing the rainfall data into several rainfall levels; matching the rainfall level in a rainfall period with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate in several time periods before the rainfall period in time to obtain a sample data set; constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate in several time periods before different moments, and the output layer is the rainfall level in a preset time period in the future of the corresponding moment; and using the sample data set to train the constructed multi-layer neural network model to obtain a trained multi-layer neural network model.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV, characterized in that: include: Obtain the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for the previous several time periods at the location where rainfall is to be forecast; After matching the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate according to time, the results are input into the trained multi-layer neural network model to output the predicted rainfall level for a preset period in the future; The training of the multi-layer neural network model includes: Acquire remote sensing data from meteorological satellites in real time, and extract long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be predicted from the remote sensing data; Acquire GNSS data and extract the long-term PWV, PWV increment and PWV increase rate at the location of the rainfall to be forecast from the GNSS data; Obtaining long-term rainfall data at the location where rainfall is to be forecast, and dividing the rainfall data into several rainfall levels; The rainfall level during the rainfall period is matched with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several periods before the rainfall period in time to obtain a sample data set; Construct a multi-layer neural network model, the input layer of which is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for several time periods before different times, and the output layer is the rainfall level for a preset time period in the future corresponding to the time; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained multi-layer neural network model.

2. The rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV according to claim 1 is characterized in that: After obtaining the sample data set, it also includes: The sample dataset is divided into rainfall dataset and non-rainfall dataset according to the standard of whether there is rainfall or not; The random downsampling method is used to select the same number of samples from the non-rainfall dataset as from the rainfall dataset to form the modeling dataset.

3. The rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV according to claim 1 is characterized in that: After obtaining the modeling dataset, it also includes: Randomly select a part of the modeling data set as the training set, and the remaining data as the test set; The training set and the test set are input into the constructed multi-layer neural network model, the model is trained until convergence, and the model parameters are saved.

4. The rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV according to claim 1 is characterized in that: The rainfall levels are divided into no rain, light rain, moderate rain, heavy rain and extremely heavy rain.

5. The rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV according to claim 1 is characterized in that: The multi-layer neural network model is constructed using a back-propagation neural network comprising three hidden layers.

6. The rainfall forecast method combining meteorological satellite brightness temperature data and GNSS-PWV according to claim 1, characterized in that: The channels used to extract brightness temperature include BT11.2 and BT13.3, and the channels used to calculate brightness temperature difference include BTD6.2-11.2, BTD7.3-12.4, BTD10.4-12.4, BTD7.3-10.4, BTD8.6-11.2 and BTD11.2-12.4; among them, BT11.2 and BT13.3 represent the channel brightness temperatures of 11.2μm and 13.3μm respectively; BTD6.2-11.2 represents the brightness temperature difference between BT6.2 and BT11.2, and the others are the same.

7. A rainfall forecast device combining meteorological satellite brightness temperature data and GNSS-PWV, characterized in that: include: A data acquisition module is used to obtain the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of the previous several time periods at the location of the rainfall to be forecast; A rainfall forecast module is used to match the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate according to time, input them into a trained multi-layer neural network model, and output the predicted rainfall level for a preset time period in the future; The training of the multi-layer neural network model includes: Acquire remote sensing data from meteorological satellites in real time, and extract long-term series of channel brightness temperature and brightness temperature difference at the location of rainfall to be predicted from the remote sensing data; Acquire GNSS data and extract the long-term PWV, PWV increment and PWV increase rate at the location of the rainfall to be forecast from the GNSS data; Obtaining long-term rainfall data at the location where rainfall is to be forecast, and dividing the rainfall data into several rainfall levels; The rainfall level during the rainfall period is matched with the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate of several periods before the rainfall period in time to obtain a sample data set; Construct a multi-layer neural network model, the input layer of which is the channel brightness temperature, brightness temperature difference, PWV, PWV increment and PWV increase rate for several time periods before different times, and the output layer is the rainfall level for a preset time period in the future corresponding to the time; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained multi-layer neural network model.

8. A ground observation device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the steps of the rainfall forecasting method combining meteorological satellite brightness temperature data and GNSS-PWV according to any one of claims 1 to 6.

Images