EP-4741767-A1 - VEHICLE ROUTE WEATHER FORECASTING AND NAVIGATION

EP4741767A1EP 4741767 A1EP4741767 A1EP 4741767A1EP-4741767-A1

Abstract

According to an aspect of an embodiment, a method may include obtaining first real-time observational data corresponding to current conditions within an operational area of a vehicle, the first real-time observational data corresponding to the operational area of the vehicle. A first forecast of one or more weather conditions associated with the operational area of the vehicle may be generated using an artificial intelligence (AI) forecasting model and based on the first real-time observational data. The first forecast may be tailored for and according to the operational area of the vehicle. The method may include generating navigation routes for the vehicle in the operational area based on the first forecast, the vehicle navigating the operational area according to the navigation routes.

Inventors

HAZARIKA, SUBHASHIS
WONG, Hon Yung

Assignees

Fujitsu Limited

Dates

Publication Date: 20260513
Application Date: 20251105

Claims (20)

A method comprising: obtaining first real-time observational data corresponding to current conditions within an operational area of a vehicle, the first real-time observational data being obtained based on the first real-time observational data corresponding to the operational area of the vehicle; generating, using an artificial intelligence (AI) forecasting model and based on the first real-time observational data, a first forecast of one or more weather conditions associated with the operational area of the vehicle such that the first forecast is tailored for and according to the operational area of the vehicle; and generating one or more navigation routes for the vehicle in the operational area based on the first forecast, the vehicle navigating the operational area according to the one or more navigation routes.
The method of claim 1, further comprising: prior to obtaining the first real-time observational data corresponding to the current conditions within the operational area of the vehicle: training the AI forecasting model to forecast weather conditions using an historical weather conditions dataset.
The method of claim 1, further comprising: obtaining second real-time observational data corresponding to the current conditions within the one or more navigation routes; generating, using the AI forecasting model and based on the second real-time observational data, a second forecast of one or more weather conditions associated with the one or more navigation routes; and generating one or more updated navigation routes for the vehicle in the operational area based on the second forecast, the vehicle navigating the area according to the one or more updated navigation routes.
The method of claim 3, further comprising: prior to obtaining the second real-time observational data: obtaining, via a user interface, a user input indicating a selection to obtain the second real-time observational data.
The method of claim 4, wherein the user input indicates a timestep to feed the second real-time observational data to the AI forecasting model.
The method of claim 1, further comprising: prior to generating the one or more navigation routes: downscaling, using an AI downscaling model, the first set of forecasts.
The method of claim 6, wherein downscaling the first set of forecasts comprises: training the AI downscaling model using a first historical training dataset including weather conditions data with a first resolution and a second historical training dataset including weather conditions data with a second resolution, wherein the first resolution is lower in resolution than the second resolution; obtaining the first set of forecasts in the first resolution from the AI forecasting model; and converting, using the AI downscaling model, the first resolution of the first set of forecasts to the second resolution.
The method of claim 7, wherein the weather conditions data with the first resolution includes data with a grid size equal to or exceeding 20 km 2 .
The method of claim 7, wherein the weather conditions data with the second resolution includes data with a grid size equal to or less than 1 km 2 .
The method of claim 1, wherein the weather conditions include one or more of: wave height, current velocity, wave direction, storms, wind direction, wind velocity, currents and tides, rain, lightning, precipitation, temperature, humidity, or cloud coverage.
A system comprising: one or more processors configured to perform operations comprising: obtaining first real-time observational data corresponding to current conditions within an operational area of a vehicle, the first real-time observational data being obtained based on the first real-time observational data corresponding to the operational area of the vehicle; generating, using an artificial intelligence (AI) forecasting model and based on the first real-time observational data, a first forecast of one or more weather conditions associated with the operational area of the vehicle such that the first forecast is tailored for and according to the operational area of the vehicle; and generating one or more navigation routes for the vehicle in the operational area based on the first forecast, the vehicle navigating the operational area according to the one or more navigation routes.
The system of claim 11, the operations further comprising: prior to obtaining the first real-time observational data corresponding to the current conditions within the operational area of the vehicle: training the AI forecasting model to forecast weather conditions using an historical weather conditions dataset.
The system of claim 11, the operations further comprising: obtaining second real-time observational data corresponding to the current conditions within the one or more navigation routes; generating, using the AI forecasting model and based on the second real-time observational data, a second forecast of one or more weather conditions associated with the one or more navigation routes; and generating one or more updated navigation routes for the vehicle in the operational area based on the second forecast, the vehicle navigating the area according to the one or more updated navigation routes.
The system of claim 13, the operations further comprising: prior to obtaining the second real-time observational data: obtaining, via a user interface, a user input indicating a selection to obtain the second real-time observational data.
The system of claim 14, wherein the user input indicates a particular timestep to feed the second real-time observational data to the AI forecasting model.
The system of claim 11, the operations further comprising: prior to generating the one or more navigation routes: downscaling, using an AI downscaling model, the first set of forecasts.
The system of claim 16, wherein downscaling the first set of forecasts comprises: training the AI downscaling model using a first historical training dataset including weather conditions data with a first resolution and a second historical training dataset including weather conditions data with a second resolution, wherein the first resolution is lower in resolution than the second resolution; obtaining the first set of forecasts in the first resolution from the AI forecasting model; and converting, using the AI downscaling model, the first resolution of the first set of forecasts to the second resolution.
The system of claim 17, wherein the weather conditions data with the first resolution includes data with a grid size equal to or exceeding 20 km 2 .
The system of claim 17, wherein the weather conditions data with the second resolution includes data with a grid size equal to or less than 1 km 2 .
One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a system to perform operations, the operations comprising: obtaining first real-time observational data corresponding to current conditions within an operational area of a vehicle, the first real-time observational data being obtained based on the first real-time observational data corresponding to the operational area of the vehicle; generating, using an artificial intelligence (AI) forecasting model and based on the first real-time observational data, a first forecast of one or more weather conditions associated with the operational area of the vehicle such that the first forecast is tailored for and according to the operational area of the vehicle; and generating one or more navigation routes for the vehicle in the operational area based on the first forecast, the vehicle navigating the operational area according to the one or more navigation routes.

Description

FIELD The embodiments discussed in the present disclosure are related to routing vehicles based on customized weather forecasting. BACKGROUND Vehicle weather routing involves planning a vehicle's course based on current and/or forecasted weather conditions to avoid adverse weather conditions and/or to optimize fuel efficiency. The quality of the forecasted weather for an operational area for the vehicle route planning may greatly affect the efficacy of the resulting route. The subject matter claimed herein is not limited to embodiments that solve any disadvantages or that operate only in environments such as those described above. Rather, this background is only provided to illustrate one example technology area where some embodiments described herein may be practiced. SUMMARY According to an aspect of an embodiment, a method may include obtaining first real-time observational data corresponding to current conditions within an operational area of a vehicle, the first real-time observational data being obtained based on the first real-time observational data corresponding to the operational area of the vehicle. A first forecast of one or more weather conditions associated with the operational area of the vehicle may be generated using an artificial intelligence (AI) forecasting model and based on the first real-time observational data. The first forecast may be tailored for and according to the operational area of the vehicle. The method may further include generating one or more navigation routes for the vehicle in the operational area based on the first forecast, the vehicle navigating the operational area according to the one or more navigation routes. The object and advantages of the embodiments will be realized and achieved at least by the elements, features, and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS Example embodiments will be described and explained with additional specificity and detail through the use of the accompanying drawings in which: FIG. 1 illustrates an example system configured to generate navigational routes for a vessel, in accordance with at least one embodiment of the present disclosure;FIG. 2 a flow diagram of an example method of data assimilation, arranged in accordance with one or more embodiments of the present disclosure;FIG. 3 illustrates a flow chart of an example method of weather forecasting and route determination, arranged in accordance with at least one embodiment of the present disclosure; andFIG. 4 illustrates a block diagram of an example computing system that may be used with a weather forecasting and route determination system, in accordance with one or more embodiments of the present disclosure. DESCRIPTION OF EMBODIMENTS Vehicles may travel along navigational routes to reach a destination. Navigational routes refer to pathways or directions that guide the vehicles or operators of the vehicles from a first location to a second location. Vehicles include any means of transportation that is designed to carry people or goods from one place to another. For example, the vehicles may include various types, such as ships, boats, automobiles, trucks, buses, bicycles, trains, aircraft, motorcycles, off-highway vehicles, etc. The navigational routes may vary depending on the types of the vehicles. For example, the navigational routes may include waterways, roadways, railways, air routes, off-road trails, etc. The navigational routes are determined based on various factors such as weather conditions, traffic conditions, road conditions, vehicle types, etc. As an example, vessels such as ships may navigate water bodies based on navigational routes. The navigational routes may correspond to various routes and/or ways that the vessels may follow to reach a destination location. In some circumstances, the navigational routes may be determined based on weather conditions, such as storms, winds, waves, tides, etc. Determining the navigational routes and other maritime operations based on weather conditions may help the vessels avoid hazardous areas, reduce fuel consumption, and/or minimize risk of delays and/or damages to cargo. Additionally, the navigational routes determined based on the weather conditions may help improve efficiency of the navigational routes such that greenhouse gas emissions may be reduced. The weather conditions for future or upcoming areas and/or times may be forecasted or predicted, such that the navigational routes may be determined considering the weather conditions. For instance, the weather conditions corresponding to the areas between the vessel and the destination location may be forecasted for the times of travel for the vessels. Such forecasted weather conditions may be used in the route planning to identify and/or de