# US 2022/0035073 A1 · Downscaling weather forecasts > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0035073 A1 - Document ID: US20220035073A1 - Status: Published application - Kind: A1 - Application number: 17/298,092 - Filed: 2020-01-31 - Published: 2022-02-03 - Earliest claimed: 2019-01-31 - Assignees: Yara International Asa - Applicants: Yara International Asa - Inventors: Syed MEHTAB; Taewon YEON; Alexander TOPOROV; Navin TWARAKAVI; Ruan BOEZAART - Web page: https://patentgrep.com/patent/US20220035073A1 ## CPC - G01W 1/10: Devices for predicting weather conditions (computers per se G06; display devices G09) - G01W 2001/006: {Main server receiving weather information from several sub-stations} - Y02A 90/10: Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation - G01W: METEOROLOGY (radar, sonar, lidar or analogous systems, designed for meteorological use G01S13/95, G01S15/88, G01S17/95) - Y02A: TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE ## Abstract A method for downscaling a weather forecast including obtaining a sky image and location data indicative of a user location via a mobile computing device; sending the location data to a weather forecast provider; generating, by the weather forecast provider, a local weather forecast for the user location; sending the local weather forecast to a server; determining, by the mobile computing device, cloud cover data and cloud type data based on the sky image, and sending the cloud cover data and cloud type data to the server or sending the sky image to the server and determining cloud cover data and cloud type data based on the sky image; increasing the resolution of the local weather forecast based on the cloud cover data and the cloud type data, thus obtaining a downscaled local weather forecast; and, sending the downscaled local weather forecast to the mobile computing device. ## Claims ### Claim 1 A method for downscaling a weather forecast, comprising the steps of: a) obtaining a sky image and location data indicative of a user location, by means of a mobile computing device; b1) sending, by the mobile computing device, the location data to a weather forecast provider; b2) generating, by the weather forecast provider, a local weather forecast for the user location; b3) sending, by the weather forecast provider, the local weather forecast to a server; c) determining, by the mobile computing device, cloud cover data and cloud type data based on the sky image, and sending the cloud cover data and cloud type data to the server; or, sending the sky image to the server and determining, by the server, cloud cover data and cloud type data based on the sky image; d) increasing resolution of the local weather forecast by the remote server based on the cloud cover data and the cloud type data, thus obtaining a downscaled local weather forecast; and e) sending, by the server, the downscaled local weather forecast to the mobile computing device. ### Claim 2 (depends on 1) The method according to claim 1, wherein the cloud cover data and the cloud type data are determined based on the sky image by means of an artificial neural network. ### Claim 3 (depends on 1) The method according to claim 1, wherein increasing the resolution of the local weather forecast in step d) is performed using Bayesian inference. ### Claim 4 (depends on 1) The method according to claim 1, wherein the mobile computing device comprises one or more environmental sensors; wherein step a) further comprises obtaining, by means of the one or more environmental sensors, environmental information comprising atmospheric pressure, humidity, and/or temperature; wherein step c) comprises sending, by the mobile computing device, the environmental information to the remote server; and wherein the increasing of the resolution in step d) is performed based on the environmental information in addition to the cloud cover data and the cloud type data. ### Claim 5 (depends on 1) The method according to claim 1, wherein determining the cloud cover data and the cloud type data in step c) involves a use of a cloud segmentation algorithm. ### Claim 6 (depends on 1) The method according to claim 1, wherein step b1) comprises sending, by the mobile computing device, the location data to a plurality of weather forecast providers; wherein step b2) comprises generating, by the plurality of weather forecast providers, a plurality of local weather forecasts for the user location; wherein step b3) comprises sending, by the plurality of weather forecast providers, the plurality of local weather forecasts to a remote server; wherein a step d0) is executed between step c) and step d), step d0) comprising comparing the plurality of weather forecasts with the location data, the cloud cover data, and the cloud type data, and based on this comparison, selecting the weather forecast which best corresponds to the location data, the cloud cover data, and the cloud type data as a most accurate weather forecast; and wherein the most accurate weather forecast is downscaled in step d). ### Claim 7 (depends on 1) The method according to claim 1, wherein the sky image or the cloud cover and cloud type data are communicated between the mobile computing device and the remote server by means of a direct data link or via an alternative communication means such as an SMS gateway. ### Claim 8 (depends on 1) The method according to claim 1, wherein the sky image is taken in a direction of a zenith, within a margin of error of 45°. ### Claim 9 (depends on 1) The method according to claim 1, wherein the location data are GPS location data. ### Claim 10 (depends on 1) The method according to claim 1, wherein the mobile computing device is a smartphone. ### Claim 11 A method for downscaling a weather forecast, comprising the steps of: a) receiving, from a mobile computing device, location data indicative of a user location; b) requesting and receiving a local weather forecast for the user location; c) receiving cloud cover data and cloud type data from the mobile computing device, or receiving a sky image from the mobile computing device and determining cloud cover data and cloud type data based on the sky image; d) increasing a resolution of the local weather forecast based on the cloud cover data and the cloud type data, thus obtaining a downscaled local weather forecast; and e) sending the downscaled local weather forecast to the mobile computing device. ### Claim 12 A method for obtaining a downscaled weather forecast, comprising the steps of: a) obtaining a sky image and location data indicative of a user location; b) sending the location data to a weather forecast provider; c) determining cloud cover data and cloud type data based on the sky image, and sending the cloud cover data and cloud type data to a server; or sending the sky image to the server; d) receiving a downscaled local weather forecast from the server. ### Claim 13 (depends on 1) A system configured for executing a method according to claim 1. ### Claim 14 (depends on 11) A server configured for executing a method according to claim 11. ### Claim 15 (depends on 12) A mobile computing device configured for executing a method according to claim 12. ### Claim 16 (depends on 1) The method according to claim 1, wherein the sky image and location data is real-time sky image and location data, and the cloud cover data and cloud type data is real-time cloud cover data and cloud type data. ### Claim 17 (depends on 4) The method according to claim 4, wherein step b1) comprises sending, by the mobile computing device, the location data to a plurality of weather forecast providers; wherein step b2) comprises generating, by the plurality of weather forecast providers, a plurality of local weather forecasts for the user location; wherein step b3) comprises sending, by the plurality of weather forecast providers, the plurality of local weather forecasts to a remote server; wherein a step d0) is executed between step c) and step d), step d0) comprising comparing the plurality of weather forecasts with the location data, the cloud cover data, the cloud type data, and the environmental information, and based on this comparison, selecting the weather forecast which best corresponds to the location data, the cloud cover data, the cloud type data, and the environmental information, as a most accurate weather forecast; and wherein the most accurate weather forecast is downscaled in step d). ### Claim 18 (depends on 11) The method according to claim 11, wherein the location data is real-time location data and the cloud cover data, and the sky image, cloud cover and/or cloud type data is real-time sky image, cloud cover and/or cloud type data. ### Claim 19 (depends on 12) The method according to claim 12, wherein the sky image and location data is real-time sky image and location data, and the cloud cover data and cloud type data is real-time cloud cover data and cloud type data.