Method of and system for generating a weather forecast

1. A method of generating a weather forecast, the method executable on a server, the server including a processor and a machine learning module, the method comprising:

receiving, by the machine learning module, at least one current weather measurement parameter, the at least one current weather measurement parameter being a weather parameter at a measurement time;

receiving, by the machine learning module, a first average value of a historical weather parameter for the measurement time,

the first average value of the historical weather parameter having been generated based on an indication of the measurement time;

generating, by the machine learning module, a normalized value of the weather measurement parameter based on a difference between the current weather measurement parameter and the first average value of the historical weather parameter for the measurement time;

training the machine learning module to predict a normalized value of a weather forecasting parameter based on the normalized value of the weather measurement parameter, the normalized value of the weather forecasting parameter being associated with a future forecasting time, the future forecasting time occurring after the measurement time,

the normalized value of the weather forecasting parameter being indicative of a difference between a predicted value of the weather forecasting parameter and a second average value of the historical weather parameter associated with the future forecasting time;

at a given point in the future forecasting time:

receiving, by the machine learning module, a given average value of the historical weather parameter for the given point in the future forecasting time,

the given average value of the historical weather parameter having been generated based on an indication of the given point in the future forecasting time;

predicting, by the machine learning module, the normalized value of the weather forecasting parameter for the given point in the future forecasting time;

generating, based on the normalized value of the weather forecasting parameter and the given average value of the historical parameter for the given point in the future forecasting time, the weather forecast.

2. The method of claim 1 , wherein the first average value of the historical weather parameter is based on a historical weather parameter data received prior to the measurement time.

3. The method of claim 2 , wherein the method further comprises generating the first average value of the historical weather parameter based on the historical weather parameter data using a static model of weather forecasting.

4. The method of claim 2 , wherein the method further comprises generating the first average value of the historical weather parameter based on the historical weather parameter data, the generating executed using a second machine learning algorithm.

5. The method of claim 1 , wherein the weather measurement parameter is at least one of: an air temperature, a water temperature, an atmospheric pressure, a wind velocity, a wind direction, humidity, cloudiness, and precipitation.

6. The method of claim 1 , wherein the method further comprises receiving from a third-party weather forecast service: at least one value of the weather forecasting parameter at the moment for the future forecasting time and the historical weather forecasting data; and wherein

the training of the machine learning module to create the normalized value of the weather forecasting parameter is executed taking into account the value of the weather forecasting parameter and the historical data of the weather forecasts.

7. The method of claim 6 , wherein the third-party weather forecast service is a plurality of third-party weather forecast services, and a value of the weather forecasting parameter for the moment of forecasting is an average value of the forecasting parameters received from the plurality of third-party weather forecast services.

8. The method of claim 7 , wherein the method further comprises setting a maximum deviation parameter for the forecasting parameter value received from the third-party weather forecast services relative to the normalized value of the weather forecasting parameter; and wherein the method further comprises:

responsive to a given forecasting parameter value received from a given third-party weather forecast service exceeding the maximum deviation parameter, disregarding the given forecasting parameter value while creating the second normalized value of the weather measurement parameter.

9. The method of claim 1 , wherein the method further comprises receiving an indication of the future forecasting time.

10. The method of claim 1 , wherein the future forecasting time is a plurality of future forecasting times, and wherein the machine learning module generates a plurality of the normalized values of the weather forecasting parameters for each one of the future forecasting times.

11. The method of claim 10 , wherein each of the plurality of future forecasting times is associated with one of a plurality of related geographic regions for a single moment of time.

12. The method of claim 1 , wherein the method further comprises receiving a request with an indication to a specific object location, and wherein generating the normalized value of the forecast parameter for the indicated object location is executed.

13. The method of claim 1 , wherein the method further comprises receiving, by the machine learning module, from a third-party weather forecast service at least one value of the weather forecasting parameter for the future forecasting time; and wherein

the training of the machine learning module to create the normalized value of the weather forecasting parameter is executed taking into account the value of the weather forecasting parameter and the normalized value of the weather measurement parameter.

14. A method of creating a weather forecast, the method being executed on a server including a processor and a machine learning module, the method comprises:

receiving of a request to create a weather forecast;

receiving by a machine learning module at least one current weather measurement parameter being a weather parameter at a measurement time;

receiving by the machine learning module a first average value of a historical weather parameter for the measurement time;

the first average value of the historical weather parameter having been generated based on an indication of the measurement time;

creating by the machine learning module a normalized value of a weather measurement parameter based on a difference between a current weather measurement parameter and the first average value of the historical weather parameter for the measurement time;

creating by the machine learning module a normalized value of a weather forecasting parameter based on the normalized value of the weather measurement parameter, the normalized value of the weather forecasting parameter is connected to a future forecasting time following after the measurement time,

the normalized value of the weather forecasting parameter being indicative of a difference between a predicted value of the weather forecasting parameter and a second average value of the historical weather parameter associated with the future forecasting time;

at a given point in the future forecasting time:

receiving a given average value of the historical weather parameter for the given point in the future forecasting time,

the given average value of the historical weather parameter having been generated based on an indication of the given point in the future forecasting time;

predicting, based on the normalized value of the weather measurement parameter, the normalized value of the weather forecasting parameter for the given point in the future forecasting time;

based on the normalized value of the weather forecasting parameter and the given average value of the historical parameter for the given point in the future forecasting time, creating the weather forecast.

15. A server for creating a weather forecast, the server comprising:

a machine learning module and a processor operationally connected to the machine learning module,

the processor is configured to execute:

receiving, by the machine learning module, at least one current weather measurement parameter, the at least one current weather measurement parameter being a weather parameter at a measurement time;

receiving, by the machine learning module, a first average value of a historical weather parameter for the measurement time,

the first average value of the historical weather parameter having been generated based on an indication of the measurement time;

generating, by the machine learning module, a normalized value of the weather measurement parameter based on a difference between the current weather measurement parameter and the first average value of the historical weather parameter for the measurement time;

training the machine learning module to create a normalized value of a weather forecasting parameter based on the normalized value of the weather measurement parameter, the normalized value of the weather forecasting parameter being associated with a future forecasting time, the future forecasting time occurring after the measurement time,

the normalized value of the weather forecasting parameter being indicative of a difference between a predicted value of the weather forecasting parameter and a second average value of the historical weather parameter associated with the future forecasting time;

at a given point in the future forecasting time:

receiving, by the machine learning module, a given average value of the historical weather parameter for the given point in the future forecasting time,

the given average value of the historical weather parameter having been generated based on an indication of the given point in the future forecasting time;

predicting, by the machine learning module, the normalized value of the weather forecasting parameter for the given point in the future forecasting time;

generating, based on the normalized value of the weather forecasting parameter and the given average value of the historical parameter for the given point in the future forecasting time, the weather forecast.

16. A method of generating a weather forecast, the method executable on a server, the server including a processor and a machine learning module, the method comprising:

receiving, by the machine learning module, at least one current weather measurement parameter, the at least one current weather measurement parameter being a weather parameter at a measurement time;

receiving, by the machine learning module, a first average value of a historical weather parameter for the measurement time,

the first average value of the historical weather parameter having been generated based on an indication of the measurement time;

generating, by the machine learning module, a normalized value of the weather measurement parameter based on a difference between the current weather measurement parameter and the first average value of the historical weather parameter for the measurement time, wherein the normalized value of the weather measurement parameter is calculated according to a formula:

Δ T=|T 1− T 2|,

where T1 is the current weather measurement parameter, T2 is the first average value of the historical weather parameter;

training the machine learning module to create a normalized value of a weather forecasting parameter based on, at least partially, the normalized value of the weather measuring parameter, the normalized value of the weather forecasting parameter being associated with a future forecasting time, the future forecasting time occurring after the measurement time;

the normalized value of the weather forecasting parameter being indicative of a difference between a predicted value of the weather forecasting parameter and a second average value of the historical weather parameter associated with the future forecasting time;

at a given point in the future forecasting time:

receiving, by the machine learning module, a given average value of the historical weather parameter for the given point in the future forecasting time,

the given average value of the historical weather parameter having been generated based on an indication of the given point in the future forecasting time;

predicting, by the machine learning module, the normalized value of the weather forecasting parameter for the given point in the future forecasting time;

based on the normalized value of the weather forecasting parameter and the given average value of the historical weather parameter, creating the weather forecast.