Data-Driven Climate Risk Forecasting Using Hybrid Machine Learning Models

Predicting Thermal Structure in Large Reservoirs Under Climate Change Using Machine Learning

DySCo: Dynamically consistent data-driven downscaling of extremes in climate projections

Regional climate risk assessment is critical for applications such as infrastructure design, disaster forecasting, and insurance resource allocation. However, estimating regional (i.e., high-spatial-resolution) risk with global climate models (GCMs) remains computationally prohibitive, which has driven the development of downscaling methods for coarse GCM outputs. Downscaling is vital for rare events, since quantifying their extreme properties requires high spatial resolution and very long GCM simulations. These methods non-intrusively increase GCM resolution while correcting statistical biases from unresolved fine-scale processes, thereby improving the accuracy of extreme event statistics with long return periods. A key challenge is preserving dynamical consistency, as freely evolving GCM trajectories are not expected to track the observational dataset used for training the correction operator. This is critical for causal extreme event analyses, where storyline-based risk assessment, i.e., extreme event catalogs, is necessary for effective planning. We address this challenge by introducing Dynamically and Statistically Consistent downscaling (DySCo), a non-intrusive framework yielding high-resolution climate projections consistent with coarse GCM dynamics. DySCo relies on a data-driven reformulation of nudging to create dynamically paired training trajectories without intrusive GCM modifications. Using these paired trajectories, we train a dynamically and statistically consistent, two-stage operator. We evaluate the method by downscaling the Community Earth System Model v2 Large Ensemble (LENS2) in time and space towards historical reanalysis. Results show DySCo achieves superior dynamical consistency with the coarse GCM trajectories, essentially applying a minimal, causal correction to the GCM, preserving top statistical performance comparable to state-of-the-art unsupervised models.

Neural Time Series Forecasting: A Problem-Driven Survey from Data Challenges to Model Choice

The literature is organized around five recurring difficulties: nonlinear and nonstationary behavior, contamination and structural breaks, uncertainty, long contexts and cross-variable dependence, and limited target-domain data.

Robust Ensemble Framework for Extrapolation and Uncertainty Quantification across Limited Time-Series Data in Prognostics

Remaining Useful Life (RUL) prediction for turbofan engines is critical for balancing operational safety against maintenance costs and environmental impact from premature replacements. Models must reliably extrapolate beyond training data, yet no single method performs optimally across all operational contexts, making model selection fundamentally heuristic. Rather than demonstrating individual model superiority, this work recognizes that reliable prognostic performance emerges from adaptive model contribution. This work introduces an ensemble framework integrating three components: (1) legacy-representative data splitting that mirrors realistic deployment where models predict for newer assets using historical data, (2) median absolute deviation-based outlier filtering for stability, and (3) WTA³ weighting that dynamically adjusts model influence based on cycle-by-cycle performance. This treats model coordination as a time-varying optimization problem adapting to evolving degradation patterns. The framework is validated on NASA CMAPSS data using six diverse models spanning traditional machine learning (Random Forest, XGBoost, Support Vector Regression) and deep learning (LSTM, CNN, Transformer). We investigate how prediction robustness changes during temporal extrapolation, whether adaptive weighting provides more stable forecasts than individual models or fixed combinations, and how uncertainty quantification supports safer maintenance decisions. Initial validation demonstrates that the WTA³ meta-ensemble achieves approximately 3 cycles RMSE and under 3 cycles MAE, representing over 30% improvement over the best individual model, with particularly strong performance in the critical late-life phase. The ensemble maintains highly stable predictions with well-calibrated confidence intervals and substantially improved coverage compared to individual models. This work reframes prognostics from competitive model selection to adaptive coordination, demonstrating that ensemble stability under extrapolation can be systematically achieved. The approach provides actionable confidence bounds for aerospace maintenance programs, enabling cost-efficient scheduling while reducing environmental waste, directly supporting both economic and sustainability objectives where data scarcity and safety criticality are paramount.

WIRED: Weighted Adaptive Prediction with Structured Dependence for Probabilistic Multiseries Forecasting

This paper presents WIRED, an R package algorithm for joint probabilistic forecasting of multiple related time series. WIRED combines a library of simple marginal predictive distributions, CRPS-based adaptive mixture weights, and a Gaussian or Student t copula for cross-series simulation. We evaluate the implementation in a benchmark with four synthetic data-generating processes (DGPs), three forecast horizons, 30 replicates per DGP-horizon pair, nine ablations and external baselines, and a rolling-origin study on the built-in EuStockMarkets data. The central contribution is architectural and diagnostic. WIRED separates adaptive marginal expert aggregation from dependence reconstruction; the benchmark supports explicit dependence modeling, but shows that the current CRPS-extrapolated softmax weighting is not yet robust enough to dominate simpler bootstrap or equal-weight alternatives. The paper therefore identifies a working layer of the design, a bottleneck in the marginal aggregation layer, and a concrete research path for more regularized probabilistic ensemble construction.

Artificial Intelligence Techniques for Climate Change Prediction and Mitigation: A Systematic Review

Rising global temperatures, stronger hydrological cycles, and an increase in the frequency of extreme weather events are all signs of climate change, which is one of the biggest worldwide issues of the twenty-first century. Computational methods that can process huge heterogeneous datasets and model nonlinear interactions are necessary to address these complicated climate dynamics. Traditional methods of climate modeling, such statistical regression and physics-based numerical simulations, offer significant theoretical insights, but they frequently have issues with high-dimensional data assimilation and computing scalability. New possibilities for improving climate prediction accuracy and enabling data-driven climate analytics have been made possible by recent developments in artificial intelligence (AI), notably machine learning and deep learning. A PRISMA-aligned systematic review of AI methods used for climate change prediction and mitigation between 2020 and 2026 is presented in this work. 120 peer-reviewed publications in all were examined from a variety of angles, including data sources, model architecture, learning paradigm, application domain, and assessment measures. The findings show that AI-driven climate research is expanding quickly, with prediction-oriented applications making up around 70% of the literature and mostly concentrating on extreme weather detection, precipitation modeling, and temperature forecasting. Due to their capacity to capture intricate spatiotemporal climatic patterns, deep learning architectures like Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), transformers, and graph neural networks dominate current research. The paper suggests a four-dimensional taxonomy based on application domain, learning paradigm, data modality, and model architecture to arrange the disjointed research landscape. Critical issues include dataset imbalance, uneven benchmarking procedures, worries about computational sustainability, and a lack of real-world mitigation application are also identified by the review. The results emphasize the need for energy-efficient, scalable, and comprehensible AI systems that can assist realistic approaches to climate adaptation and mitigation.