Maximising Weather Forecasting Accuracy through the Utilisation of Graph Neural Networks and Dynamic GNNs
Weather forecasting is an essential task to tackle global climate change. Weather forecasting requires the analysis of multivariate data generated by heterogeneous meteorological sensors. These sensors comprise of ground-based sensors, radiosonde, and sensors mounted on satellites, etc., To analyze the data generated by these sensors we use Graph Neural Networks (GNNs) based weather forecasting model. GNNs are graph learning-based models which show strong empirical performance in many machine learning approaches. In this research, we investigate the performance of weather forecasting using GNNs and traditional Machine learning-based models.
Paper
References (6)
01A Graph Neural Network Approach for Accurate Short-Term Solar Power Forecasting2020 · International Conference on Neural Information Processing (ICONIP)
02Weather Forecasting with Graph Neural Networks2020 · International Conference on Machine Learning and Data Mining (MLDM)
03Spatiotemporal Graph Attention Networks for Traffic Flow Prediction2019 · International Conference on Machine Learning and Data Mining (MLDM)
04Graph Attention Networks for Multivariate Time Series Forecasting2019 · International Conference on Machine Learning and Data Mining (MLDM)
05Graph Convolutional Networks for Temporal Graphs2019 · International Conference on Machine Learning (ICML)
06Making weather forecasts: We use the trained GNN model to make weather forecasts by inputting new meteorological data and using the model to predict the target weather variables