The system as described collects and utilizes weather data sensor information in order to rapidly collect and update weather forecasts using real-time weather data collected at high rates of frequency, and use this collected high frequency weather data to rapidly correct and update the weather forecasts generated by the system.

The system as described collects and utilizes weather data sensor information in order to rapidly collect and update weather forecasts using real-time weather data collected at high rates of frequency, and use this collected high frequency weather data to rapidly correct and update the weather forecasts generated by the system.

The embodiments herein describe a forecasting system that uses captured images or a location to generate a weather forecast for that location. As used herein, a hyper-location is any location where images of that location are available to the forecasting system. For example, a hyper-location can be an airport where a security camera can provide historical images of the weather conditions at the airport. In one embodiment, the forecasting system can extract attributes from the images that indicate the historical weather conditions at the hyper-location. The forecasting system can then use those weather conditions to select which one of a plurality of historical scenarios best matches the weather conditions. The selected scenario can then be used to train a machine learning (ML) model that tunes a weather forecast for that location.

Methods and systems for generating a multi-model ensemble of global climate simulation data from a plurality of pre-existing global climate simulation model (GCM) datasets, are disclosed. The methods and systems perform steps of computing a GCM dataset validation measure based on at least one sample statistic for at least one climate variable from the pre-existing GCM dataset; selecting a validated subset of the plurality of pre-existing GCM datasets; selecting a subset of GCM datasets; generating one or more candidate ensembles of GCM datasets; computing an ensemble forecast skill score for each candidate ensemble of GCM datasets; generating the multi-model ensemble of GCM datasets by selecting a candidate ensemble of GCM datasets with a best ensemble forecast skill score; and training the NN-based climate forecasting model using the multi-model ensemble of GCM datasets. Embodiments of the present invention enable accurate climate forecasting without the need to run new dynamical global climate simulations on supercomputers.

Techniques for evaluating electricity distribution infrastructures include a method comprising: determining, by a computing device, respective positions for individual solar panels included in a plurality of solar panels located within a geographical region; determining, by the computing device based on the respective positions and meteorological data for the geographical region, respective predicted solar power generation levels for the individual solar panels; determining, by the computing device based on the respective predicted solar power generation levels for the individual solar panels, a solar power generation estimate for the geographical region; and determining, by the computing device based on the solar power generation estimate for the geographical region and one or more properties of an electricity distribution infrastructure for the geographical region, one or more infrastructure modifications for the electricity distribution infrastructure.

Systems, devices, and methods for a sensor pair, where the sensor pair comprises: an emissions sensor configured to generate trace gas data; a wind sensor configured to generate wind data, where the wind data comprises wind speed and wind direction; and a position data, where the position data comprises a location corresponding to the generated trace gas data and generated wind data.

A mesoscale modeling system and method that enables meteorologists to adjust forecasts to account for known biases of weather forecasting models and outputs high-resolution images consistent with the adjusted forecasts. The mesoscale modeling system and method may also use a weather forecasting model to forecast future weather events based on one or more adjustments provided by the meteorologists.

A method performed by at least one apparatus is inter alia disclosed, said method comprising: obtaining weather model data indicative of location-specific weather information for a first set of locations (26) on a first grid (28); obtaining an area of interest (30) associated to at least one user (32); obtaining and/or determining a second set of locations (34) based on a second grid (36) within said area of interest (30); obtaining measurement data on location-specific weather information of a measurement device associated to said at least one user located at a measurement location (38) within and/or proximate to said area of interest (30); and determining, based on at least said obtained weather model data and said obtained measurement data, location-specific weather information for said second set of locations (34) based on said second grid (36).

The embodiments herein describe a forecasting system that uses captured images or a location to generate a weather forecast for that location. As used herein, a hyper-location is any location where images of that location are available to the forecasting system. For example, a hyper-location can be an airport where a security camera can provide historical images of the weather conditions at the airport. In one embodiment, the forecasting system can extract attributes from the images that indicate the historical weather conditions at the hyper-location. The forecasting system can then use those weather conditions to select which one of a plurality of historical scenarios best matches the weather conditions. The selected scenario can then be used to train a machine learning (ML) model that tunes a weather forecast for that location.

Improved mechanisms for collecting information from a diverse suite of sensors and systems, calculating the current precipitation, atmospheric water vapor, atmospheric liquid water content, or precipitable water and other atmospheric-based phenomena, for example presence and intensity of fog, based upon these sensor readings, predicting future precipitation and atmospheric-based phenomena, and estimating effects of the atmospheric-based phenomena on visibility, for example by calculating runway visible range (RVR) estimates and forecasts based on the atmospheric-based phenomena.