Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks

• URL: http://arxiv.org/abs/2604.13455v2
• Date: Fri, 17 Apr 2026 19:33:42 GMT
• Title: Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks
• Abstract summary: We propose a lightweight, Physics-Informed Hybrid CNN-BiLSTM framework that prioritizes domain knowledge over architectural depth.<n>Unlike standard data-driven approaches, our model is explicitly guided by a vector of 15 engineered features including Clear-Sky indices and Solar Zenith Angle.<n> Experimental validation using NASA POWER data in Sudan demonstrates that our physics-guided approach achieves a Root Mean Square Error (RMSE) of 19.53 W/m2, significantly outperforming complex attention-based baselines.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate Global Horizontal Irradiance (GHI) forecasting is critical for grid stability, particularly in arid regions characterized by rapid aerosol fluctuations. While recent trends favor computationally expensive Transformer-based architectures, this paper challenges the prevailing "complexity-first" paradigm. We propose a lightweight, Physics-Informed Hybrid CNN-BiLSTM framework that prioritizes domain knowledge over architectural depth. The model integrates a Convolutional Neural Network (CNN) for spatial feature extraction with a Bi-Directional LSTM for capturing temporal dependencies. Unlike standard data-driven approaches, our model is explicitly guided by a vector of 15 engineered features including Clear-Sky indices and Solar Zenith Angle - rather than relying solely on raw historical data. Hyperparameters are rigorously tuned using Bayesian Optimization to ensure global optimality. Experimental validation using NASA POWER data in Sudan demonstrates that our physics-guided approach achieves a Root Mean Square Error (RMSE) of 19.53 W/m^2, significantly outperforming complex attention-based baselines (RMSE 30.64 W/m^2). These results confirm a "Complexity Paradox": in high-noise meteorological tasks, explicit physical constraints offer a more efficient and accurate alternative to self-attention mechanisms. The findings advocate for a shift towards hybrid, physics-aware AI for real-time renewable energy management.

Related papers

• SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors [48.60897189520386]
  We introduce the JEPA-style model for real-time quadrotor control.<n>We combine a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state.<n>To reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation.
  arXiv  Detail & Related papers  (2026-06-22T15:00:59Z)
• ASTRO: Adaptive Spatio-Temporal Reinforcement Optimization for GNN Powered Anomly Detection in Cyber Physical Systems [0.0]
  This article introduces Adaptive Spatio-Temporal Reinforcement Optimization ASTRO (ASTRO), a novel anomaly detection framework.<n>By integrating a Deep Q-Network (DQN) with Graph Neural Networks (GNNs), temporal modelling and a Multi-Head Attention mechanism, ASTRO continuously adapts its decision boundaries to improve detection accuracy.<n>The ASTRO approach is evaluated on two real world industrial benchmarks: the Secure Water Treatment (SWaT) and Water Distribution (WADI) datasets.
  arXiv  Detail & Related papers  (2026-05-24T15:30:14Z)
• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems [0.0]
  This paper introduces the Physics-Informed State Space Model (PISSM) to bridge the gap between efficiency and physical accuracy for edge-deployed microcontrollers.<n>A Linear State Space Model replaces heavy attention mechanisms, efficiently modeling temporal dependencies for parallel processing.<n> PISSM achieves superior accuracy with fewer than 40,000 parameters, establishing an ultra-lightweight benchmark for real-time off-grid control.
  arXiv  Detail & Related papers  (2026-04-13T17:59:49Z)
• Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis [48.809049043865905]
  Image deraining plays a pivotal role in low-level computer vision.<n>Deep learning paradigms often suffer from severe performance degradation when generalized to unseen Out-of-Distribution scenarios.<n>This paper proposes a pioneering cross-scenario deraining adaptation framework.
  arXiv  Detail & Related papers  (2026-03-23T07:38:55Z)
• Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems [2.7106545070231722]
  textbfAdaptive Physics Transformer (APT)<n>APT is a geometry-, mesh-, and physics-agnostic neural operator.<n>First architecture that directly learns from adaptive mesh refinement simulations.
  arXiv  Detail & Related papers  (2026-02-10T22:48:58Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks [47.413471945080566]
  Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing.<n>In artificial neural networks, the effective receptive field (ERF) serves as a valuable tool for analyzing feature extraction capabilities.<n>We introduce the Spatio-Temporal Effective Receptive Field (ST-ERF) to analyze the ERF distributions across various Transformer-based SNNs.
  arXiv  Detail & Related papers  (2025-10-24T12:46:58Z)
• A Deep Learning Approach for Spatio-Temporal Forecasting of InSAR Ground Deformation in Eastern Ireland [2.840858735842673]
  Monitoring ground displacement is crucial for urban infrastructure and mitigating geological hazards.<n>This paper introduces a novel deep learning framework that transforms sparse point measurements into a dense-temporal tensor.<n>Results demonstrate that the proposed architecture provides more accurate and spatially coherent forecasts.
  arXiv  Detail & Related papers  (2025-09-17T17:10:18Z)
• QGAPHEnsemble : Combining Hybrid QLSTM Network Ensemble via Adaptive Weighting for Short Term Weather Forecasting [0.0]
  This research highlights the practical efficacy of employing advanced machine learning techniques.<n>Our model demonstrates a substantial improvement in the accuracy and reliability of meteorological predictions.<n>The paper highlights the importance of optimized ensemble techniques to improve the performance the given weather forecasting task.
  arXiv  Detail & Related papers  (2025-01-18T20:18:48Z)
• A Scalable Real-Time Data Assimilation Framework for Predicting Turbulent Atmosphere Dynamics [8.012940782999975]
  We introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF) and a vision transformer-based surrogate. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier.
  arXiv  Detail & Related papers  (2024-07-16T20:44:09Z)
• Towards Physically Consistent Deep Learning For Climate Model Parameterizations [46.07009109585047]
  parameterizations are a major source of systematic errors and large uncertainties in climate projections. Deep learning (DL)-based parameterizations, trained on data from computationally expensive short, high-resolution simulations, have shown great promise for improving climate models. We propose an efficient supervised learning framework for DL-based parameterizations that leads to physically consistent models.
  arXiv  Detail & Related papers  (2024-06-06T10:02:49Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• Physics-Driven Turbulence Image Restoration with Stochastic Refinement [80.79900297089176]
  Image distortion by atmospheric turbulence is a critical problem in long-range optical imaging systems. Fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions. This paper proposes the Physics-integrated Restoration Network (PiRN) to help the network to disentangle theity from the degradation and the underlying image.
  arXiv  Detail & Related papers  (2023-07-20T05:49:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.