Solar Variations Research Articles

Effect of Solar Irradiation Inter-Annual Variability on PV and CSP Power Plants Production Capacity: Portugal Case-Study

The sizing of solar energy power plants is usually made using typical meteorological years, which disregards the inter-annual variability of the solar resource. Nevertheless, such variability is crucial for the bankability of these projects because it impacts on the production goals set at the time of the supply agreement. For that reason, this study aims to fill the gap in the existing literature and analyse the impact that solar resource variability has on solar power plant production as applied to the case of Portugal (southern Europe). To that end, 17 years (2003–2019) of meteorological data from a network of 90 ground stations hosted by the Portuguese Meteorological Service is examined. Annual capacity factor regarding photovoltaic (PV) and concentrating solar power (CSP) plants is computed using the System Advisor Model, used here for solar power performance simulations. In terms of results, while a long-term trend for increase in annual irradiation is found for Global Horizontal Irradiance (GHI) and Direct Normal Irradiance (DNI), 0.4148 and 3.2711 kWh/m2/year, respectively, consistent with a solar brightening period, no corresponding trend is found for PV or CSP production. The latter is attributed to the long-term upward trend of 0.0231 °C/year in annual average ambient temperature, which contributes to PV and CSP efficiency reduction. Spatial analysis of inter-annual relative variability for GHI and DNI shows a reduction in variability from the north to the south of the country, as well as for the respective power plant productions. Particularly, for PV, inter-annual variability ranges between 2.45% and 12.07% in Faro and Santarém, respectively, while higher values are generally found for CSP, 3.71% in Faro and 16.04% in São Pedro de Moel. These results are a contribution to future instalments of PV and CSP systems in southern Portugal, a region with very favourable conditions for solar energy harvesting, due to the combination of high production capacity and low inter-annual variability.

Reconstruction of the Total Solar Irradiance During the Last Millennium

Solar irradiance variations across various timescales, from minutes to centuries, represent a potential natural driver of past regional and global climate cold phases. To accurately assess the Sun’s effect on climate, particularly during periods of exceptionally low solar activity, known as grand minima, an accurate reconstruction of solar forcing is essential. While direct measurements of the total solar irradiance (TSI) only began in the late 1970s, with the advent of space radiometers, indirect evidence from various historical proxies suggests that the Sun’s magnetic activity has undergone possible significant fluctuations over much longer timescales. Employing diverse and independent methods for TSI reconstruction is essential to gaining a comprehensive understanding of this issue. This study employs a semi-empirical model to reconstruct TSI over the past millennium. Our approach uses an estimated open solar magnetic field (F o ), derived from cosmogenic isotope data, as a proxy for solar activity. We reconstruct the cyclic variations of TSI, due to the solar surface magnetic features, by correlating F o with the parameter of active region functional form. We obtain the long-term TSI trend by applying the empirical mode decomposition algorithm to the reconstructed F o to filter out the 11 yr and 22 yr solar variability. We prepare a reconstructed TSI record, spanning 971 to 2020 CE. The estimated departure from modern TSI values occurred during the Spörer minimum (around 1400 CE), with a decrease of approximately 2.3 Wm−2. A slightly smaller decline of 2.2 Wm−2 is reported during the Maunder minimum, between 1645 and 1715 CE.

Correlation analysis of the long-term interplay of cosmic rays, solar activity, and solar irradiance

Abstract This study presents a comprehensive analysis of the interplay between solar irradiance variability, solar activity, and cosmic rays over an extensive period from 1950 to 2023, well beyond the scope of previous research that focused on fewer solar cycles. Besides, using a robust dataset, we investigated the correlation between solar activity, represented by sunspot numbers, and the total solar irradiance, alongside the influence of cosmic rays. In this respect, our methodology incorporated sophisticated statistical techniques, including correlation analysis and linear regression, in order to elucidate the complex relationships among these variables. We identified a strong positive correlation between solar activity and total solar irradiance r ≈ + 0.95 , together with a significant anti-correlation between solar activity and cosmic rays r ≈ − 0.72 as well as cosmic rays and total solar irradiance r ≈ − 0.67 . As a consequence, the results of this study offer new insights into the long-term solar influence on climate through cosmic rays, enhancing our understanding of the Sun-Earth dynamic over prolonged periods. Likewise, the extended time series and the analytical framework developed in this study pave the way for further research into related phenomena, including the effects of cloud cover and potential links between cosmic rays and climate change.

Multiple New or Updated Satellite Total Solar Irradiance (TSI) Composites (1978–2023)

Several total solar irradiance (TSI) satellite missions have been carried out since 1978. None of these missions have lasted more than one to two solar cycles (SCs), and each mission implies a slightly different absolute TSI baseline. Nonetheless, several satellite composites have been developed by compositing satellite data from different missions to form an almost continuous daily record for the satellite era. However, disconcertingly, each mission has implied slightly different changes in TSI between consecutive solar minima and solar maxima. Some groups have developed adjustments to individual missions that have substantially reduced these differences. Others prefer to use the original data published by the satellite science teams. Some TSI composites average together conflicting records, while others prioritize specific records over others. Here, we compare four existing composites to 17 new alternative series based on the available satellite data. These 21 TSI series are statistically sorted into six groups of three to four series each. We found that the six groups suggest different intercycle trends between solar minima. We compare the groups to eight daily resolved solar proxy-based TSI reconstructions and to daily sunspot numbers. Excellent agreement is obtained over one to two SCs, but significant differences are observed over longer timescales for each group. Therefore, we have assembled all these time series (old and new) into a large and new TSI data set for use by the scientific community. Versions scaled to 1 au (for studying solar variability) or in situ values at Earth (for studying solar/terrestrial interactions) are provided at daily, monthly, and yearly resolutions.

Detrimental impact of solar and geomagnetic activity on plasma B-complex vitamins in the VA normative aging study cohort

It has been hypothesized that ultraviolet (UV) radiation can lead to depletion of plasma folate and B12 vitamin, but few studies have investigated effects of other parameters of solar and geomagnetic activity (SGA). We investigated the association between four SGA parameters—interplanetary magnetic field (IMF), sunspot number (SSN), Kp index, and ground shortwave solar radiation (SWR)—and three plasma B-complex vitamins—folate, B6, and B12—in 910 participants from the Normative Aging Study (NAS) between 1998 and 2017. Mixed-effects regression models were used for 1- to 28-moving day averages of SGA exposure, adjusted for covariates. We compared the impact of SGA in individuals under higher and lower B-complex supplementation (> or < 50th quartile). Our findings show that increases in solar activity variables IMF and SSN were found to be significantly associated with decreases in B12 vitamin. IMF and SSN were associated with decrease in folate levels, especially in individuals under higher levels of B-complex supplementation. No associations were found for SWR and Kp index. To our knowledge, this is the first study that demonstrated the detrimental impact of solar activity on plasma B12 and folate in a large cohort. These findings have clinical implications during periods of high solar activity.

An explainable hybrid framework for estimating daily reference evapotranspiration: Combining extreme gradient boosting with Nelder-Mead method

Accurate estimation of reference evapotranspiration (ETo) is essential for effective water resources management, irrigation system design, and various hydrological and agricultural applications. This study employed extreme gradient boosting (XGBoost) model, signal decomposition techniques, and XGBoost coupled with Nelder–Mead (NM) method to enhance ETo prediction across two meteorological stations in Iran. This study proposed a novel framework which lies in its comprehensive integration of advanced techniques to create a model that is both interpretable and highly accurate for ETo estimation. For this aim, sixty meteorological variables were categorized into solar and cloud-based, temperature-based, wind and humidity-based, and pressure-based groups to analyze their effect on ETo estimation. Feature selection methods, including the Gradient Boosting Machine, Kendall’s Tau, and Relief Algorithm, were employed to identify the most influential predictors. Variables with normalized weights equal to or greater than 0.9 were selected for model input, resulting in the top 10% of variables being utilized. The XGBoost models were then developed using these selected inputs (level 1), a wavelet-based hybrid was developed according to the most effective features (level 2), and the XGBoost model was coupled by NM algorithm (level 3) for ETo estimation. Results of estimated ETo by levels 1 to 3 were compared with four common empirical approaches. The results indicated that Kendall’s Tau-based feature selection provided the most accurate predictions in Shiraz, achieving an RMSE of 0.721 (mm/day) for solar and cloud-based variables during the test phase. Additionally, the application of wavelet analysis further refined the model inputs, which enhanced ETo estimation in most variable groups. Integrating the NM algorithm with XGBoost demonstrated significant improvements in ETo estimation, where it could improve RMSE to 0.091 and 0.155 (mm/day) for testing section in Fasa and Shiraz, respectively.

On the long-term stability of the association between foF2 and EUV solar proxies

Solar extreme ultraviolet (EUV) radiation is the main source of heating and ionization of the Earth's upper atmosphere, forcing most of this system's time variability, which in annual scales corresponds to the solar activity ∼11-year cycle. Due to the difficulties in obtaining solar EUV time series covering extended periods of time or during periods without measurements available, the use of solar EUV proxies became a solution. In the case of the ionosphere, and in particular the F2-layer critical frequency (foF2), in addition to the solar activity cycle variation, it may also exhibit the effect of long-term trend forcings, like the monotonous increasing greenhouse gas concentration since the industrial revolution. To accurately detect and measure this weak trend against the solar activity variability, it is crucial to account for the solar forced variation. Traditionally, it is modeled as a linear association between foF2 and a given solar EUV proxy. However, the stability of this association has become a controversial issue. It would be reasonable to assume, in turn, that if the ionospheric environment is undergoing a trend forced by a non-solar diver, like the greenhouse gas concentration increase, the relationship between foF2 and solar proxies may be affected, ceasing to be stable if this additional driver is not introduced in the modeled association. Using rolling regressions over the period 1960–2023 to analyze this stability, our results suggest that the issue may not only lie in the steady trend expected in foF2 from a non-solar source or the need to include terms in the simple linear regression commonly used, but also in the possible deviation of the different proxies from the 'true' EUV solar flux, which is the ultimate main driver of F2 region ionization, a deviation that has been intensifying over the last two decades. We assert that it is a deviation from the actual EUV behavior because the indices diverge from one another, something that should not occur if they all reflect the same solar EUV.

A review of global long-term changes in the mesosphere, thermosphere and ionosphere: A starting point for inclusion in (semi-) empirical models

The climate of the upper atmosphere, including the mesosphere, thermosphere and ionosphere, is changing. As data records are much more limited than in the lower atmosphere and solar variability becomes increasingly dominant at higher altitudes, accurate trend detection and attribution is not straightforward. Nonetheless, observations reliably indicate that, on average, the mesosphere has been cooling, the density in the thermosphere has been decreasing, and ionospheric layers have been shifting down. These global mean changes can be largely attributed to the increase in CO2 concentration, which causes cooling and thermal contraction in the middle and upper atmosphere. The decline in thermosphere density is particularly relevant from a practical viewpoint, as this reduces atmospheric drag and thereby increases orbital lifetimes and the build-up of space debris. Long-term changes in the ionosphere can have further practical implications and are not only driven by the increase in CO2 concentration, but also by changes in the Earth’s magnetic field. The empirical models that are mostly used to inform applications in industry on the state of the upper atmosphere, as well as being widely used in science, do not yet properly account for long-term trends in the mesosphere, thermosphere and ionosphere. This is problematic when long-term future projections are needed or models rely strongly on older data. This review provides an overview of the main evidence of long-term trends observed in the mesosphere, thermosphere and ionosphere, together with the latest insights on what causes these trends. It is hoped that this may serve as a starting point to include long-term trends in (semi-) empirical models to benefit all users of these models. We also offer some thoughts on how this could be approached.

Long-term geomagnetic activities and stratospheric winter temperature

In this research, impact of long term solar forcing on stratospheric winter temperature is checked. The 11- year sunspot activity and geomagnetic indices (AE, Kp, Dst) are used as an indicator for solar forcing, as geomagnetic activity indices show good correlation with solar variability. To understand the impact of solar forcing through high latitude, stratospheric winter (November to March) time North Polar Region (60N–90N) temperature anomalies are considered. The findings showed that temperature changes in the stratosphere are significantly correlated with solar activity, as evidenced by a significant positive correlation between the 11-year moving mean of stratospheric (10 hPa) temperature anomalies and sunspot number. Approximately from 1970 to 2000, the North Polar Region saw positive anomalous stratospheric winter temperatures. During the same time, the geomagnetic activity also showed a substantial increase. The year-to-year correlation between stratospheric pole temperature and geomagnetic activity is significant (about 0.5). The Empirical Mode Decomposition analysis reveals a highly significant correlation (around 0.9) between the long-term component of stratospheric winter temperature (IMF-4) and the long-term component of geomagnetic activity (IMF-3 and IMF-4). One of the reasons for the increase in lower stratospheric temperature is an increase in ozone concentration during the same period when geomagnetic activity is higher. Empirical orthogonal function (EOF) and correlation analysis of stratospheric winter temperature with large-scale circulation patterns are also carried out. The spatial correlation is checked for stratospheric winter temperature at North Pole and lower atmospheric levels (250 hPa and 850 hPa) followed by pre-monsoon and monsoon season. This study includes statistical analysis, however, also highlights the necessity of in-depth dynamical analysis to improve our understanding of how solar activity impacts Earth's atmospheric layers, which may be helpful in predicting the weather and climate.

Variation in the Quanta-to-Energy Ratio of Photosynthetically Active Radiation under the Cloudless Atmosphere

The quanta-to-energy ratio plays a crucial role in converting energy units to quantum units in the context of photosynthetically active radiation (PAR). Despite its widespread use, the effects of atmospheric particles and solar zenith angle (SZA) on the quanta-to-energy ratio remain unclear. In this study, both simulation and observation data revealed that the principal wavelength, which can be transformed into the quanta-to-energy ratio using a constant, exhibits a slow initial growth, followed by a rapid increase beyond 60° solar zenith angles and a subsequent dramatic decrease after reaching its maximum value. The measured quanta-to-energy ratio demonstrates a variable range of less than 3% for SZA under 70° in a cloudless atmosphere, with significant changes only occurring at zenith angles above 80°. Simulation data indicate that ozone, wind speed, surface-level pressure, surface air temperature, and relative humidity have negligible effects on the quanta-to-energy ratio. The Ångstrom exponent exerts a minor influence on the quanta-to-energy ratio by affecting diffuse radiation. Visibility, however, is found to have a substantial impact on the quanta-to-energy ratio. As a result, two relationships are established, linking the principal wavelength to visibility and the diffuse fraction of PAR. The principal wavelength serves as an effective measure of solar spectrum variability, remaining unaffected by radiation energy. This implies that atmospheric parameters which do not alter the solar spectrum will not influence the principal wavelength. The strong correlations between the principal wavelength, visibility, and the diffuse fraction of PAR suggest a broader range of applications for the principal wavelength in various research domains, opening up new avenues for exploration and potential contributions to numerous fields.

Extreme solar storms and the quest for exact dating with radiocarbon.

Radiocarbon (14C) is essential for creating chronologies to study the timings and drivers of pivotal events in human history and the Earth system over the past 55,000 years. It is also a fundamental proxy for investigating solar processes, including the potential of the Sun for extreme activity. Until now, fluctuations in past atmospheric 14C levels have limited the dating precision possible using radiocarbon. However, the discovery of solar super-storms known as extreme solar particle events (ESPEs) has driven a series of advances with the potential to transform the calendar-age precision of radiocarbon dating. Organic materials containing unique 14C ESPE signatures can now be dated to annual precision. In parallel, the search for further storms using high-precision annual 14C measurements has revealed fine-scaled variations that can be used toimprove calendar-age precision, even in periods that lack ESPEs. Furthermore, the newly identified 14C fluctuations provide unprecedented insight into solar variability and the carbon cycle. Here, we review the current state of knowledge and share our insights into these rapidly developing, diverse research fields. We identify links between radiocarbon, archaeology, solar physics and Earth science to stimulate transdisciplinary collaboration, and we propose how researchers can take advantage of these recent developments.

Deep learning performance prediction for solar-thermal-driven hydrogen production membrane reactor via bayesian optimized LSTM

The random fluctuation of solar energy poses significant challenges for direct solar utilization systems. Solar-driven membrane reactors (SMMR) are efficient devices for energy conversion and pure hydrogen production, featuring thermal inertia and complex physicochemical processes. To realize advance control of SMMR under solar variations to promote their practical application, accurate performance prediction is essential. This study develops a deep learning-assisted performance prediction model for SMMR using Bayesian optimized long short-term memory (BO-LSTM) network and weather classification. Time-series datasets with similar environmental features are generated through SMMR multi-physics modeling and trained by BO-LSTM. The BO-LSTM demonstrates high accuracy in both short-time (1-day) and long-time (40-day) predictions, with a correlation coefficient exceeding 0.997 and a deviation of ±0.0016 in long-term predictions. Weather classification ensures consistent prediction accuracy across different weather. Compared to RF, SVM, BPNN, and CNN models, BO-LSTM provides smoother prediction curves and significantly improves accuracy and stability, reducing RMSE by 44.6% on sunny days and 53.3% on cloudy days in short-time predictions, and by 56.7% and 68.0% in long-time predictions, respectively. The BO-LSTM proposed in this study accurately predicts SMMR performance under various weather, guiding practical applications and offering a reference for prediction and control in solar thermal utilization systems.

Toward a Live Homogeneous Database of Solar Active Regions Based on SOHO/MDI and SDO/HMI Synoptic Magnetograms. II. Parameters for Solar Cycle Variability

Solar active regions (ARs) determine solar polar fields and cause solar cycle variability within the framework of the Babcock–Leighton dynamo. The contribution of an AR to the polar field is measured by its dipole field, which results from flux emergence and subsequent flux transport over the solar surface. The dipole fields contributed by an AR before and after the flux transport are referred to as the initial and final dipole fields, respectively. For a better understanding and prediction of solar cycles, in this paper, we provide a database including AR's initial and final dipole fields and the corresponding results of their bipolar magnetic region (BMR) approximation from 1996 onward. We also identify the repeated ARs and provide the optimized transport parameters. Based on our database, we find that although the commonly used BMR approximation performs well for the initial dipole field, it exhibits a significant deviation for the final dipole field. To accurately assess an AR’s contribution to the polar field, the final dipole field with its real configuration should be applied. Despite the notable contributions of a few rogue ARs, approximately the top 500 ARs ordered by their final dipole fields are necessary to derive the polar field at the cycle minimum. While flux transport may increase or decrease the dipole field for an individual AR, its collective impact over all ARs in a cycle is a reduction in their total dipole field.

Modeling and performance analysis of a new integrated solid oxide fuel cell and photovoltaic‐thermal energy supply system by heat current method

AbstractEfficient and reliable utilization of renewable energy at the user's end is the key to achieving a low‐carbon life. This paper proposed a new distributed energy system around the comprehensive utilization of solar energy by integrating solid oxide fuel cell (SOFC), energy storage equipment, photovoltaic thermal (PVT) collector, and heat pump. By integrating the use of SOFC and PVT, we can further minimize reliance on fossil fuels, while employing the coupling of PVT and heat pump effectively mitigates the inherent challenges of solar energy's variability and intermittency, all while enhancing overall system efficiency. On this basis, we apply the heat current method to construct a cross‐scale heat current model of the components and the system by considering the energy transfer, conversion, and storage characteristics of the system. By employing this model, we simulate the system's operation throughout an entire typical day, assess the COP enhancement of the PVT‐coupled heat pump system, analyze the influence of diverse operating conditions on daily system performance, and evaluate the economy of the energy storage devices in the system.

Mapping solar variability of equatorial sunspots and plasma flows

Mapping solar variability of equatorial sunspots and plasma flows

Energy Conservation in the Cooling and Contracting Upper Mesosphere and Lower Thermosphere

AbstractTime series of radiative cooling of the upper mesosphere and lower thermosphere (UMLT) by carbon dioxide (CO2) are examined for evidence of trends over 20 years. Radiative cooling rates in K day−1 provided by the SABER instrument are converted to time series of infrared power radiated from three distinct layers between 0.1 hPa and 0.0001 hPa (65–105 km). Linear regression against time and a predictor for solar variability provides estimates of the trend in exiting longwave radiation (ELR) from these layers. Trends in ELR are not significantly different from zero at 95% or 99% confidence in each layer. These results demonstrate energy conservation in the UMLT on decadal time scales and show that the UMLT continues to radiate the same amount of energy it receives despite cooling and contracting over two decades. These results are enabled by the long‐term stability of the SABER instrument calibration.

Exoplanet Aeronomy: A Case Study of WASP-69 b’s Variable Thermosphere

Aeronomy, the study of Earth’s upper atmosphere and its interaction with the local space environment, has long traced changes in the thermospheres of Earth and other solar system planets to solar variability in the X-ray and extreme-ultraviolet (collectively, XUV) bands. Extending comparative aeronomy to the short-period extrasolar planets may illuminate whether stellar XUV irradiation powers atmospheric outflows that change planetary radii on astronomical timescales. In recent years, near-IR transit spectroscopy of metastable Hei has been a prolific tracer of high-altitude planetary gas. We present a case study of exoplanet aeronomy using metastable Hei transit observations from Palomar Observatory's Wide Field InfraRed Camera and follow-up high-energy data from the Neil Gehrels Swift Observatory that were taken within 1 month of the WASP-69 system, a K-type main-sequence star with a well-studied hot Jupiter companion. Supplemented by archival data, we find that WASP-69's X-ray flux in 2023 was less than 50% of what was recorded in 2016 and that the metastable Hei absorption from WASP-69 b was lower in 2023 versus past epochs from 2017 to 2019. Via atmospheric modeling, we show that this time-variable metastable Hei signal is in the expected direction given the observed change in stellar XUV, possibly stemming from WASP-69's magnetic activity cycle. Our results underscore the ability of multiepoch, multiwavelength observations to paint a cohesive picture of the interaction between an exoplanet’s atmosphere and its host star.

Mathematical modeling and seasonal solar radiation variability in Nigeria’s geo-political zones: A recurrence and multifractal analysis

This article delves into the seasonal variation of solar radiation patterns across Nigeria’s four geo-political zones, exploring their complex, scale-dependent behaviors. By employing chaotic quantifiers, the study characterizes irregular and self-similar patterns, enhancing our understanding of solar radiation variability and heterogeneity. The research uniquely fits meteorological parameters onto a global solar radiation model and focuses on the underexplored nonlinear aspects within tropical regions, specifically in the Nigerian context. Utilizing daily data from ERA INTERIM satellite archives for representative stations, the study employs nonlinear time series analysis methods like recurrence plots, recurrence qualitative analysis, and multifractal spectral analysis to comprehensively explore the unpredictable behaviors observed. The quantifier spectrums play a key role in revealing intricate scaling behaviors and correlation structures among environmental variables, shedding light on patterns often concealed by conventional statistical methods. For instance, we found that solar radiation variability in the northern region increases more significantly during the dry season compared to the wet season, unlike in the southern region. Additionally, the multifractal spectral analysis revealed a higher degree of complexity in solar radiation patterns during transition periods between seasons. The findings reveal a low recurrence quantitative analysis, long right tail, and truncations at both ends of the spectrum. This suggests instability in solar radiation across different seasons and locations. Nonetheless, the results also demonstrate that solar radiation is consistently available throughout the year, which is typical of tropical regions.

Full Modeling and Practical Parameterization of Cosmogenic 10Be Transport for Cosmic‐Ray Studies: SOCOL‐AERv2‐BE Model

AbstractA new full model of the atmospheric transport of cosmogenic 10Be is presented based on the specialized SOCOL‐AERv2‐BE chemistry‐climate model coupled with the CRAC:10Be isotope production model. The model includes all the relevant atmospheric processes and allows computing the isotope concentration at any given location and time. The full model is directly compared with 10Be isotope measurements in five Antarctic and Greenland ice cores for the period 1980–2007. The model reasonably well reproduces the average concentration and solar‐cycle dependency or the lack of it for most observational sites but does not perfectly catch the interannual variability at sites with complex orography likely due to the coarse model grid. This implies that the model correctly reproduces the large‐scale atmospheric dynamics but effectively averages out synoptic‐scale variability. It is found that the dominant source of 10Be is located in the middle stratosphere (25–40 km), in the tropical (&lt;30° latitudes) and polar (&gt;60°) regions, as produced by galactic cosmic rays and solar energetic particles, respectively. It is shown that &gt;60% (90%) of 10Be produced in the atmosphere reaches the Earth's surface within one (two) years, respectively. For practical purposes, a simple parameterization of the full‐model results is presented which agrees with the full model within 20% in polar regions. This parameterization allows one to make a quick estimate of near‐ground 10Be concentrations based only on production rates without heavy calculations. This practical approach can be applied to studies of solar and geomagnetic variability using cosmogenic isotopes.

Advancing short-term solar irradiance forecasting accuracy through a hybrid deep learning approach with Bayesian optimization

The optimization of solar energy integration into the power grid relies heavily on accurate forecasting of solar irradiance. In this study, a new approach for short-term solar irradiance forecasting is introduced. This method combines Bayesian Optimized Attention-Dilated Long Short-Term Memory and Savitzky-Golay filtering. The methodology is implemented to analyze data obtained from a solar irradiance probe situated in Douala, Cameroon. Initially, the unprocessed data is augmented by integrating distinctive solar irradiation variables, and the Savitzky-Golay filter with Bayesian Optimization is used to enhance its quality. Subsequently, multiple deep learning models, including Long Short-Term Memory, Bidirectional Long Short-Term Memory, Artificial Neural Networks, Bidirectional Long Short-Term Memory with Additive Attention Mechanism, and Bidirectional Long Short-Term Memory with Additive Attention Mechanism and Dilated Convolutional layers, are trained and evaluated. Out of all the models considered, the proposed approach, which combines the attention mechanism and dilated convolutional layers, demonstrates exceptional performance with the best convergence and accuracy in forecasting. Bayesian Optimization is further utilized to fine-tune the polynomial and window size of the Savitzky-Golay filter and optimize the hyperparameters of the deep learning models. The results show a Symmetric Mean Absolute Percentage Error of 0.6564, a Normalized Root Mean Square Error of 0.2250, and a Root Mean Square Error of 22.9445, surpassing previous studies in the literature. Empirical findings highlight the effectiveness of the proposed methodology in enhancing the accuracy of short-term solar irradiance forecasting. This research contributes to the field by introducing novel data pre-processing techniques, a hybrid deep learning architecture, and the development of a benchmark dataset. These advancements benefit both researchers and solar plant managers, improving solar irradiance forecasting capabilities.