Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City

• URL: http://arxiv.org/abs/2512.23898v1
• Date: Mon, 29 Dec 2025 23:22:25 GMT
• Title: Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City
• Abstract summary: This study presents a benchmark of ten deep learning architectures for short-term (1-hour ahead) Global Horizontal Irradiance (GHI) forecasting in Ho Chi Minh City.<n> Experimental results identify the Transformer as the superior architecture, achieving the highest predictive accuracy with an R2 of 0.9696.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable forecasting of Global Horizontal Irradiance (GHI) is essential for mitigating the variability of solar energy in power grids. This study presents a comprehensive benchmark of ten deep learning architectures for short-term (1-hour ahead) GHI time series forecasting in Ho Chi Minh City, leveraging high-resolution NSRDB satellite data (2011-2020) to compare established baselines (e.g. LSTM, TCN) against emerging state-of-the-art architectures, including Transformer, Informer, iTransformer, TSMixer, and Mamba. Experimental results identify the Transformer as the superior architecture, achieving the highest predictive accuracy with an R^2 of 0.9696. The study further utilizes SHAP analysis to contrast the temporal reasoning of these architectures, revealing that Transformers exhibit a strong "recency bias" focused on immediate atmospheric conditions, whereas Mamba explicitly leverages 24-hour periodic dependencies to inform predictions. Furthermore, we demonstrate that Knowledge Distillation can compress the high-performance Transformer by 23.5% while surprisingly reducing error (MAE: 23.78 W/m^2), offering a proven pathway for deploying sophisticated, low-latency forecasting on resource-constrained edge devices.

Related papers

• Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector [0.0]
  The analysis utilizes 134,376 hourly observations from Ioannina, Greece, spanning January 2011 to April 2026, sourced from ERA5 via the OpenMeteo Historical Weather API.<n>The most effective purely recurrent models are a 64-unit LSTM for the 24-hour horizon, with a WQS of 0.816755, and a 1024-unit GRU for the 168-hour horizon, with a WQS of 0.779465.<n>The hybrid CNN-GRU models achieved the highest overall scores of 0.827535 and 0.782863 for the 24-hour and 168-hour horizons, but with additionally more number of units respectively to
  arXiv  Detail & Related papers  (2026-07-11T08:39:20Z)
• t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations [8.965320425114603]
  GPS communications are affected by ionospheric Total Electron Content (TEC) gradients.<n>To address this gap, we introduce an interpretable ML-based model, t-STEP, designed to predict TEC at a 30-second resolution.<n>The model is developed using GPS observations from solar cycle 24 at a station located at 5.49S, 47.49W.
  arXiv  Detail & Related papers  (2026-06-28T23:21:37Z)
• Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption [0.0]
  This paper benchmarks Transformer-based and xLSTM architectures for short-term heat-demand forecasting.<n>We establish a benchmark that tests whether models trained on pooled, heterogeneous building data are able to generalize across diverse building stock.<n>The results show that the xLSTM achieves the lowest RMSE (19.88 kWh for three-hour, 21.47 kWh for 24-hour forecasts), while the Temporal Fusion Transformer attains the best MAE (9.16 kWh for three-hour forecasts)
  arXiv  Detail & Related papers  (2026-05-10T19:40:03Z)
• Forecasting Continuum Intensity for Solar Active Region Emergence Prediction using Transformers [34.25104679311873]
  Early and accurate prediction of solar active region (AR) emergence is crucial for space weather forecasting.<n>We investigate a sliding-window Transformer architecture to forecast continuum intensity evolution up to 12 hours ahead using data from 46 ARs observed by SDO/HMI.<n>Our best-performing model, combining the Early Detection architecture without the Conv1D layer, achieved a Root Mean Square Error (RMSE) of 0.1189.<n>While the Transformer demonstrates superior aggregate timing and accuracy, we note that this high-sensitivity detection comes with increased variance compared to smoother baseline models.
  arXiv  Detail & Related papers  (2026-01-19T15:25:04Z)
• Forecasting Thermospheric Density with Transformers for Multi-Satellite Orbit Management [41.99844472131922]
  This work presents a transformer-based model that forecasts densities up to three days ahead.<n>It avoids spatial reduction and complex input pipelines, operating directly on a compact input set.<n>It is validated on real-world data and shows potential to support mission planning.
  arXiv  Detail & Related papers  (2025-11-08T19:02:14Z)
• 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)
• WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion [3.344876133162209]
  We present WGAST, a Weakly-performing Genedrative Network for Daily 10 m LST resolution via SSupervise-Temporal Fusion of MODIS, Landsat 8, and Sentinel-2.<n>It adopts a conditional generative adversarial architecture with a generator composed of four stages: feature extraction, fusion, LST reconstruction, and noise suppression.<n>Experiments demonstrate that WGAST outperforms existing methods in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-08-08T17:49:46Z)
• Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts [37.09823149373976]
  This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather forecasts.<n>Our method treats forecast lead times as sequential tokens'', enabling the transformer to learn complex temporal relationships.<n>Results demonstrate that the transformer-based post-processing significantly enhances forecast skill compared to dense neural networks.
  arXiv  Detail & Related papers  (2025-05-16T23:22:07Z)
• Forecasting Local Ionospheric Parameters Using Transformers [39.58317527488534]
  We present a novel method for forecasting key ionospheric parameters using transformer-based neural networks.<n>The model provides accurate forecasts and uncertainty quantification of the F2-layer peak plasma frequency (foF2), the F2-layer peak density height (hmF2), and total electron content (TEC) for a given geographic location.
  arXiv  Detail & Related papers  (2025-02-20T23:23:09Z)
• Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting [50.298817606660826]
  We introduce Powerformer, a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay.<n>Our empirical results demonstrate that Powerformer achieves state-of-the-art accuracy on public time-series benchmarks.<n>Our analyses show that the model's locality bias is amplified during training, demonstrating an interplay between time-series data and power-law-based attention.
  arXiv  Detail & Related papers  (2025-02-10T04:42:11Z)
• Wind Speed Forecasting Based on Data Decomposition and Deep Learning Models: A Case Study of a Wind Farm in Saudi Arabia [0.0]
  Wind power generation is always accompanied by uncertainty due to the wind speed's volatility.<n>Wind speed forecasting (WSF) is essential for power grids' dispatch, stability, and controllability.<n>This study proposes a novel WSF framework for stationary data based on a hybrid decomposition method.
  arXiv  Detail & Related papers  (2024-12-17T22:04:46Z)
• Real-time gravitational-wave inference for binary neutron stars using machine learning [71.29593576787549]
  We present a machine learning framework that performs complete BNS inference in just one second without making any approximations. Our approach enhances multi-messenger observations by providing (i) accurate localization even before the merger; (ii) improved localization precision by $sim30%$ compared to approximate low-latency methods; and (iii) detailed information on luminosity distance, inclination, and masses.
  arXiv  Detail & Related papers  (2024-07-12T18:00:02Z)
• Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal [0.15361702135159847]
  The model was evaluated using a leave one year out cross-validation and compared with the climatological benchmark. Results show that the transformer model outperforms the benchmark model for one month forecasting horizon, after which the climatological benchmark is better. Overall, the tested Transformer model is a valid method for FAPAR forecasting, especially when combined with weather data and used for short-term predictions.
  arXiv  Detail & Related papers  (2024-02-08T11:00:51Z)
• Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer [112.12271800369741]
  Wind power is attracting increasing attention around the world due to its renewable, pollution-free, and other advantages. Accurate wind power forecasting (WPF) can effectively reduce power fluctuations in power system operations. Existing methods are mainly designed for short-term predictions and lack effective spatial-temporal feature augmentation.
  arXiv  Detail & Related papers  (2023-05-30T04:03:15Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast [91.9372563527801]
  We present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy. Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast and large-member ensemble forecast in real-time.
  arXiv  Detail & Related papers  (2022-11-03T17:19:43Z)
• Wind Speed Prediction and Visualization Using Long Short-Term Memory Networks (LSTM) [1.8495489370732452]
  This paper proposes the prediction of wind speed that simplifies wind farm planning and feasibility study. The results show a deep learning approach, long short-term memory (LSTM) outperforms other models with the highest accuracy of 97.8%.
  arXiv  Detail & Related papers  (2020-05-22T17:51:13Z)

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.