RAJESH KUMAR MISHRA

https://doi.org/10.64823/ijpcs.2601002

Geomagnetic storms, driven primarily by coronal mass ejections (CMEs) and high-speed solar wind streams interacting with the Earth's magnetosphere, pose significant risks to satellite operations, power grid infrastructure, aviation, and communication systems. Traditional empirical and physics-based models of geomagnetic indices such as Dst and Kp, while physically interpretable, often struggle to capture the highly nonlinear and non-stationary dynamics of solar wind-magnetosphere coupling, particularly during the storm recovery phase. Artificial Intelligence (AI) techniques, including artificial neural networks, ensemble tree-based methods, and multilayer perceptron (MLP) models, have demonstrated considerable promise for improving the accuracy and lead time of geomagnetic storm forecasts. This paper (i) reviews the evolution of AI-based approaches to Dst/Kp prediction; (ii) proposes a consolidated methodological framework for building and validating AI-driven space-weather forecasting systems; and (iii) reports a complete, reproducible experimental case study in which a physically-grounded Burton-McPherron-Russell (BMR) ring-current simulator was used to generate a multi-year hourly solar-wind-driven Dst dataset, on which Random Forest, Gradient Boosting, Multilayer Perceptron, and linear baseline models were trained and evaluated under a chronologically leakage-aware train/validation/test protocol at 1-, 3-, and 6-hour forecast horizons. The best-performing model (MLP) achieved RMSE = 3.82 nT and R² = 0.956 at the 1-hour horizon, degrading to RMSE = 10.27 nT and R² = 0.684 at 6 hours, consistent with the general skill-decay pattern reported in the literature for physically driven Dst forecasting. Feature importance analysis confirmed that the most recent lagged Dst value and the 6-hour rolling mean of the southward IMF component (Bz) dominate predictive skill. Key challenges relating to data leakage, class imbalance for extreme events, multimodal data fusion, and model interpretability are discussed, along with directions for future research including physics-informed machine learning and probabilistic forecasting.

https://doi.org/10.64823/ijpcs.2601001

Artificial intelligence (AI) and machine learning (ML) are increasingly used as general-purpose research instruments across the physical sciences, accelerating tasks that were traditionally limited by trial-and-error experimentation, computational cost, or the sheer dimensionality of the underlying physics. Three areas illustrate this shift with particular clarity: computational materials discovery, nanostructured electrode design for energy storage, and space weather / heliophysics forecasting. Despite substantial progress in each area individually, limited work has examined them together, quantitatively, as expressions of a single underlying trend — the convergence of AI methodology with core physical and chemical science. Methods: This study used a narrative and scoping review methodology, incorporating quantitative benchmarks drawn directly from primary and independent critical sources. Peer-reviewed literature, preprints, direct observational monitoring data, and ResearchGate-hosted scholarly works published primarily between 2023 and 2026 were identified through structured searches combining terms from materials informatics, nanostructured energy-storage materials, and AI-based space weather forecasting. Sources were screened for topical relevance and synthesized thematically, with reported quantitative claims cross-checked against independent critical appraisal where available. Results: The synthesis identifies convergent innovation across three domains, with all three now quantitatively documented: (1) AI-driven inverse design (exemplified by a 2.2-million-structure materials search yielding roughly 380,000 candidate stable materials) is accelerating materials discovery, though independent re-analysis found only a small fraction of these structures met joint criteria of novelty, credibility, and utility; (2) nanostructured graphene–metal oxide composite electrodes span a wide reported performance envelope (specific capacitances from roughly 100 F/g to over 1000 F/g; energy densities up to roughly 100+ Wh/kg), with statistically designed synthesis optimization improving reproducibility; and (3) AI-assisted forecasting achieved approximately one-minute precision in reconstructing a major 2024 geomagnetic superstorm, in contrast to a roughly 40% amplitude error and nine-month timing error in the leading pre-cycle statistical/physical forecast of Solar Cycle 25's overall intensity. Discussion: A common methodological pattern recurs across all three domains: AI is used not to replace physical theory but to navigate high-dimensional parameter spaces that are analytically or computationally intractable by classical means alone, and the strongest, most defensible results are those subjected to independent, domain-expert critical appraisal rather than accepted at face value. Conclusion: Continued progress will depend on higher-quality shared datasets, physics-informed model architectures, standardized benchmarking protocols, and routine independent critical appraisal as a formal part of the AI-for-science publication cycle.