weather-forecasting

An Android app that uses your phone's sensors to assist with wilderness treks or survival situations.

Implementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorch

MeteoSwiss' continuosly updated Open Data documentation

A spherical CNN for weather forecasting

AI Challenger 2018 Weather Forecasting - 1st Place Solution

Code for the paper "STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting" (Neurocomputing, Elsevier)

[ICML 2026] U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

Zeus Subnet leverages AI to forecast environmental variables using real-time global data. It incentivizes innovation in climate science by enabling miners and validators to develop and evolve efficient, decentralized prediction models.

A weather app made using OpenWeatherMap API in JavaScript. It tells the current temperature and some additional information like Air Quality Index, Real Feel, Humidity, Highest Temperature, Lowest Temperature, Wind Speed, Wind Direction, Visibility, Pressure, Sunrise and Sunset.

This real-time project integrates flight information from the AviationStack API for DFW Airport and weather data from the National Weather Service API, to provide the latest arrival, departure, and forecast details.

The central point of ongoing research regarding the usefulness of the large-scale atmospheric variability in the Mediterranean for forecasting extreme precipitation in the domain.

Implementation of Convolutional Encoder Decoder Network for short term (0 - 2 hours) weather forecasting.

[NeurIPS 2025] Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting

🐉 AI forecasts of global sea-surface temperature and ENSO, 1–16 months ahead (Advanced Science 2026). Live: canglong.earth · Hugging Face Space

Predicting where India's medium-range weather forecasts will bust, district by district, and explaining why. XGBoost + SHAP + FastAPI + React, served for $0. SIH 2026 PS 26079 (Ministry of Earth Sciences).

Using LSTM model to predict temperature using data of previous 3hours.

Hybrid Maritime Weather Forecaster Using Optimized of Neural Networks and Type-2 Fuzzy Logic

Google DeepMind's WeatherNext 2 at full 0.25° on consumer GPUs. Same model, same results: 6.4 GiB instead of 34 GiB, 7× faster.

Create the Streamlit app that can analyze and forecast the weather for the next days.