The field of environmental and weather forecasting is rapidly advancing with the development of new machine learning models and techniques. Recent research has focused on improving the accuracy and efficiency of forecasting models, particularly in the context of extreme weather events and climate change. One notable trend is the use of graph attention networks and transformer-based models to better capture spatial and temporal dependencies in weather data. Additionally, there is a growing interest in using explainable AI and interpretable models to provide more transparent and trustworthy forecasts. Another area of research is the development of more efficient and effective methods for predicting extreme weather events, such as heat waves and solar flares. Overall, these advancements have the potential to significantly improve our ability to predict and prepare for extreme weather events, ultimately saving lives and reducing economic losses. Noteworthy papers include the proposal of a novel approach to estimate the duration of severe weather-induced power outages through Graph Attention Networks, and the introduction of a unified hybrid Bayesian Deep Learning framework for ensemble weather forecasting.
Advancements in Environmental and Weather Forecasting
Sources
Graph Attention Network for Predicting Duration of Large-Scale Power Outages Induced by Natural Disasters
DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
Power Ensemble Aggregation for Improved Extreme Event AI Prediction
Deep Learning for Short-Term Precipitation Prediction in Four Major Indian Cities: A ConvLSTM Approach with Explainable AI
A Comparison of Lightweight Deep Learning Models for Particulate-Matter Nowcasting in the Indian Subcontinent & Surrounding Regions
A Space-Time Transformer for Precipitation Forecasting
Computationally-efficient deep learning models for nowcasting of precipitation: A solution for the Weather4cast 2025 challenge
ARise: an Augmented Reality Mobile Application to Improve Cultural Heritage Resilience
How many stations are sufficient? Exploring the effect of urban weather station density reduction on imputation accuracy of air temperature and humidity
Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting
Attention-Enhanced Convolutional Autoencoder and Structured Delay Embeddings for Weather Prediction
Global Cross-Time Attention Fusion for Enhanced Solar Flare Prediction from Multivariate Time Series
Coliseum project: Correlating climate change data with the behavior of heritage materials
MMWSTM-ADRAN+: A Novel Hybrid Deep Learning Architecture for Enhanced Climate Time Series Forecasting and Extreme Event Prediction
GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction
Naga: Vedic Encoding for Deep State Space Models
Multi-Horizon Time Series Forecasting of non-parametric CDFs with Deep Lattice Networks
Weather Maps as Tokens: Transformers for Renewable Energy Forecasting
Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts
Unified Multimodal Vessel Trajectory Prediction with Explainable Navigation Intention
Seeing Beyond the Image: ECG and Anatomical Knowledge-Guided Myocardial Scar Segmentation from Late Gadolinium-Enhanced Images
IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics
Interpretable temporal fusion network of multi- and multi-class arrhythmia classification
SWR-Viz: AI-assisted Interactive Visual Analytics Framework for Ship Weather Routing
Connecting the Dots: A Machine Learning Ready Dataset for Ionospheric Forecasting Models
Achieving Skilled and Reliable Daily Probabilistic Forecasts of Wind Power at Subseasonal-to-Seasonal Timescales over France
Spatially Dependent Sampling of Component Failures for Power System Preventive Control Against Hurricane