Rainy Conditions Research Articles

A multi-frame fusion video deraining neural network based on depth and luminance features

Rainy weather is a common natural occurrence, but capturing clear and accurate images in rainy conditions can be challenging. Consequently, addressing the effects of rain on video imagery is essential for enhancing visual quality and the accuracy and reliability of computer vision applications. In this work, we introduce a novel rain model accompanied by a multi-frame fusion video rain removal algorithm that exploits depth and luminance features. We present an innovative three-stage video deraining methodology that synergizes multi-frame fusion with advanced neural network design to achieve highly realistic and clear rain removal. Our Option-Flow-Depth-Luminance (OFDL) Derain algorithm propels the research forward by offering a new perspective on rain removal. Incorporating depth and luminance features into image processing, we devise a novel rain model that allows the algorithm to handle complex environments and a variety of rain patterns effectively. Additionally, our model takes into account degradation factors such as rain streaks, accumulation, runoff, and occlusion, leading to the generation of more authentic rain-affected images that improve the training and performance evaluation of the model. Experimental tests conducted on the RainSynLight25, RainSynComplex25, and NTURain datasets demonstrate that our method outperforms current state-of-the-art techniques, achieving increases of 4.3 dB, 2.2 dB, and 2.2 dB in PSNR, and enhancements of 0.062, 0.109, and 0.008 in Structural Similarity Index Measure (SSIM), respectively. Moreover, our approach exhibits superior processing speed, further underscoring its practical advantages.

Cascade contour-enhanced panoptic segmentation for robotic vision perception.

Panoptic segmentation plays a crucial role in enabling robots to comprehend their surroundings, providing fine-grained scene understanding information for robots' intelligent tasks. Although existing methods have made some progress, they are prone to fail in areas with weak textures, small objects, etc. Inspired by biological vision research, we propose a cascaded contour-enhanced panoptic segmentation network called CCPSNet, attempting to enhance the discriminability of instances through structural knowledge. To acquire the scene structure, a cascade contour detection stream is designed, which extracts comprehensive scene contours using channel regulation structural perception module and coarse-to-fine cascade strategy. Furthermore, the contour-guided multi-scale feature enhancement stream is developed to boost the discrimination ability for small objects and weak textures. The stream integrates contour information and multi-scale context features through structural-aware feature modulation module and inverse aggregation technique. Experimental results show that our method improves accuracy on the Cityscapes (61.2 PQ) and COCO (43.5 PQ) datasets while also demonstrating robustness in challenging simulated real-world complex scenarios faced by robots, such as dirty cameras and rainy conditions. The proposed network promises to help the robot perceive the real scene. In future work, an unsupervised training strategy for the network could be explored to reduce the training cost.

Simultaneous lightwave information and power transfer for NLOS ultraviolet communications under different weather conditions

In this work, a power allocation scheme for ultraviolet communication (UVC) with simultaneous lightwave information and power transfer (SLIPT) is proposed. Based on the non-line-of-sight (NLOS) single scattering channel model, the path loss and bit error rate (BER) performance of the UVC system with different geometrical parameters are analyzed. The effects of three types of weather, light rain, fine weather and severe fog conditions are considered. It is proved that the path loss is minimized on foggy days with minimum BER, followed by sunny days. The proposed SLIPT approach that the receiving energy is in turn divided into two parts, one for energy harvesting (EH) and the other for information decoding (ID). The system is designed to optimize energy harvesting for autonomous power supply, while ensuring a specified BER threshold and maintaining spectral efficiency. The effects of three types of weather on the SLIPT system are further investigated. It is demonstrated that under shorter communication distance(r), smaller elevation angle of receiving terminal (βR), larger field of view (FoV) and lower spectral efficiency(η) conditions, a higher percentage of energy is allocated for EH, with foggy days being the most favorable. The extreme geometric parameters of rainy condition can lead to the inability of communication, which needs to be limited to r ≤ 10 m, elevation angle of Rx ≤ 6°, FOV ≥100°, spectral efficiency ≤3, under the preset parameters in this paper.

Genetic variability, character association and path analyses effects on fiber yield and yield attributing morpho-agronomic traits of tossa jute (Corchorus olitorius L.)

Jute (Corchorus spp.) is a natural fiber crop having a lower extent of genetic variability due to its self-pollinating nature. The success of any breeding program for variety development primarily depends on the presence of genetic variation in the parental genotypes. A field experiment was conducted in a randomized complete block design at ManikganjStation of Bangladesh Jute Research Institute (BJRI) during 2019-2020. The genetic divergence of 58 tossa jute (C. olitorius) genotypes including two pre-released standard varieties (O-9897, BJRI Tossa pat 4) and 56 accessions were studied to select genotypes having the most divergence in natural rainy condition. The jute genotypes were categorized into five clusters based on Mahalanobis D2 analysis. Cluster I and IV showed maximum inter-cluster distance (181.44) while the maximum intra-cluster distance (16.15) was recorded in cluster I. Cluster V revealed the highest values for number of nodes, stem mid-diameter, core diameter, green weight with leaves, dry stick weight and dry fiber weight per plant while cluster IV showed higher means for plant height, green bark thickness and leaf area. The highest contribution (47.14%) was wielded by plant height of total deviations. The results recommended that hybridization between genotypes of cluster V, IV and III could provide a wide range of discrepancies in the segregating generation which could offer chance for isolation of good genotypes with high fibre yielding lines.

Spatio-temporal characteristics of rainfall and drought conditions are using the different drought indices with geospatial approaches in Karnataka state

Karnataka state drought conditions are assessed via drought indices. Over the past several decades, several indices of drought (DI) have been developed and presented, although some of them are region-specific and have problems regarding their applicability to other climatic circumstances. Additionally, choosing the best DI time step to illustrate the drought condition is difficult because of the DIs' various time steps. The study compares the Standardized Precipitation Index (SPI), Statistical Z-Score, China Z-Index (CZI), Rainfall Anomaly Index (RAI), and Rainfall Departure (RD) to determine which one is most appropriate for the districts of the Karnataka state that are prone to both dry and rainy conditions. This study has pointed out that the best drought indices are SPI and RD, and the least accountable drought indice is China Z index. Droughts were most common in 22 districts in 2009, which represent around 70.97% of the state's landmass. In comparison with the rest of the districts, the Ramanagara district noticed the worst drought conditions in 2003, with rainfall reaching 92.47 mm and SPI -3.68, RAI-6.04, MCZI -2.39, and Z score −2.62. Overall, the results of the study will aid in the organization and improvement of drought, flood, agriculture, and water resource management approaches in the state.

Weathering words: a virtual reality study of environmental influence on reading dynamics.

Reading is a fundamental cognitive activity that is influenced by both textual and external environmental factors, although the latter has been less thoroughly explored. This study aims to examine the impact of environmental visual conditions on reading performance using Virtual Reality (VR) technology. We conducted two experiments to assess the effects of visual contrast and simulated weather conditions on reading dynamics. In Experiment 1, we measured single-word recognition speed using a lexical decision task under different visual contrasts and weather conditions. In Experiment 2, we assessed reading dynamics during a sentence reading task, analyzing how visual contrast and simulated sunny versus rainy weather conditions affected reading behavior, particularly focusing on reading speed and eye fixations. In Experiment 1, high visual contrast, particularly under sunny conditions, significantly enhanced single-word recognition speed, indicating a notable influence of environmental visual conditions. In Experiment 2, visual contrast had minimal effect on sentence reading; however, sunny weather facilitated faster reading times, while rainy scenarios increased the number of eye fixations. These findings suggest that environmental factors, such as weather conditions, can significantly affect reading behavior. The study contributes to the understanding of key environmental influences on reading in everyday life contexts and has implications for the ergonomic design of reading materials, especially for outdoor settings and VR environments. Additionally, the integration of controlled stimuli within VR increases the ecological validity of reading research, underscoring the potential of VR as a powerful tool for cognitive research.

Could music reduce driver fatigue? An investigation on music effects in various weather conditions

Fatigue impairs drivers’ performance and increases the occurrence likelihood of traffic incidents. This study aims to explore the capability of music as an intervention to reduce driver fatigue under different weather conditions by conducting a driving simulation experiment. The Eysenck Personality Questionnaire-Neuroticism (EPQ-N) scale is used to assess drivers’ personalities. A mixed factorial analysis of variance (ANOVA) is applied to analyze the influence of music on the driving behavior of different drivers under various weather conditions, including sunny, rainy, and foggy scenarios. Results indicated that drivers’ fatigue levels are reduced by the music under less complicated weather conditions, such as sunny and foggy conditions. The results also revealed that drivers with low EPQ-N scores could demonstrate better physical reactions and driving performance in sunny and rainy conditions, whereas those with high EPQ-N scores perform better in foggy conditions. These findings could help prevent traffic accidents caused by driving fatigue in sunny and foggy conditions through the strategic use of music.

Trajectory planning for intelligent vehicle obstacle avoidance in rainy and snowy conditions

Trajectory planning for intelligent vehicle obstacle avoidance in rainy and snowy conditions

Wildlife target detection based on improved YOLOX-s network

To addresse the problem of poor detection accuracy or even false detection of wildlife caused by rainy environment at night. In this paper, a wildlife target detection algorithm based on improved YOLOX-s network is proposed. Our algorithm comprises the MobileViT-Pooling module, the Dynamic Head module, and the Focal-IoU module.First, the MobileViT-Pooling module is introduced.It is based on the MobileViT attention mechanism, which uses a spatial pooling operator with no parameters as a token mixer module to reduce the number of network parameters. This module performs feature extraction on three feature layers of the backbone network output respectively, senses the global information and strengthens the weight of the effective information. Second, the Dynamic Head module is used on the downstream task of network detection, which fuses the information of scale sensing, spatial sensing, and task sensing and improves the representation ability of the target detection head. Lastly, the Focal idea is utilized to improve the IoU loss function, which balances the learning of high and low quality IoU for the network. Experimental results reveal that our algorithm achieves a notable performance boost with mAP@0.5 reaching 87.8% (an improvement of 7.9%) and mAP@0.5:0.95 reaching 62.0% (an improvement of 5.3%). This advancement significantly augments the night-time wildlife detection accuracy under rainy conditions, concurrently diminishing false detections in such challenging environments.

Assembly of WO3-Nb2O5-ZnIn2S4 with embedded quasi-planar heterojunction characteristics and its efficient and stable dark-state photoelectrochemical cathodic protection performance

Constructing a photoanode with both high dark-state protection performance and high stability remains a top priority for photoelectrochemical cathodic protection technology, especially in a marine environment (dark-state or rainy conditions) without hole scavenging agents. In this work, we developed a class of energy-storage quasi-planar heterojunctions (WO3-Nb2O5-ZnIn2S4) with directional paths (low onset potential and well-matched energy band) and embedded morphology. The co-design of embedded and directional paths reduces the carrier transport energy barrier at the composite interface, and increases the interface contact area, thereby achieving highly stable and sensitive dark-state energy storage and photoelectrochemical cathodic protection performance in 3.5 wt.% NaCl solution without hole scavenging agent (Dark-state energy storage efficiency increased by 43%. For carbon steel, the performance retention rate is 99.6% after 500 cycles, the performance retention rate is 89% after 5000 s).

A systematic survey of environmental DNA in Palau's lakes and waterfalls reveals an increase in Leptospira levels after flooding

ObjectiveLeptospirosis is an important bacterial zoonosis which is widespread in tropical and subtropical islands and influences human and animal health which has secondary economic effects. Although leptospirosis is endemic in Palau, an Oceanian Pacific Island country, few systematic surveys of potential risk factors for Leptospira infection, such as weather and host animals, have been conducted in the natural environment. We used environmental DNA metabarcoding to assess the distribution, species diversity, and abundance of pathogenic Leptospira in this endemic region to investigate the potential environmental risks. MethodsForty-two paired water samples, representing fine and rainy weather conditions, were collected from four representative waterfalls and lakes on Babeldaob Island, the largest island in Palau. High-throughput sequencing analysis was conducted for polymerase chain reaction products of leptospiral 16S rRNA and vertebrate animal mitochondrial 12S rRNA genes. ResultsWe revealed greater Leptospira diversity and abundance in samples collected after continuous rain, particularly in the presence of flooding, compared with samples collected under typhoon, monsoon, or fine weather conditions. From same samples, six mammalian species including cats (Felis catus), mice (Mus musculus), Yap flying fox (Pteropus yapensis), rats (Rattus spp.), and pigs (Sus scrofa) were repeatedly detected. These may be candidates of host animals of Leptospira in Palau; however, their detection was not clearly correlated with that of Leptospira. ConclusionWe repeatedly detected several species of pathogenic Leptospira from water samples of a wide region of Babeldaob Island. We confirmed that Leptospira contamination in freshwater environments increased under rainy conditions, particularly in the presence of flooding. This information could be used to improve public health control measures in this region.

Enhanced intrusion detection with fiber optic sensors in rainy weather conditions: a comparative study of phase parameter matching and cross rebuilding algorithms for higher end communication

Enhanced intrusion detection with fiber optic sensors in rainy weather conditions: a comparative study of phase parameter matching and cross rebuilding algorithms for higher end communication

Evaluating 4G Network Performance at UTeM Campus to Facilitate 5G Implementation in Malaysia

As Malaysia transitions to 5G technology, evaluating 4G coverage performance is essential for preparing the groundwork for advanced networks. This project focuses on assessing the radio communication link performance of 4G systems at the University Technical Malaysia Malacca (UTeM) campus. The goal is to assist Mobile Broadband (MBB) service providers in developing efficient long-term strategies for Malaysian university campuses and enhancing 4G coverage. The study conducted measurement campaigns and real-time performance analysis using the G-Net Track app, recording key metrics such as minimum RSRP (-115 dBm off-peak, -117 dBm peak), RSRQ (-18 dB off-peak, -17 dB peak), and average SNR (11.178 dB off-peak, 11.003 dB peak). Signal quality varied with 25.3% excellent and 4.5% poor in normal weather, and 21.8% excellent and 5.8% poor in rainy conditions. Proximity to the base station showed the best RSRP of -68 dBm at 56m and the worst at -110 dBm around 915m away. The study concludes that mobile network operator (MNO) performance is influenced by traffic load, weather conditions, and distance from the base station. Understanding these dynamics can help MBB service providers enhance coverage, reliability, and overall user experience on university campuses and beyond. Future research considering additional KPIs and environmental factors will further enrich these insights, supporting robust network planning and management.

Style Optimization Networks for real-time semantic segmentation of rainy and foggy weather

Semantic segmentation is an essential task in the field of computer vision. Existing semantic segmentation models can achieve good results under good weather and lighting conditions. However, when the external environment changes, the effectiveness of these models are seriously affected. Therefore, we focus on the task of semantic segmentation in rainy and foggy weather. Fog is a common phenomenon in rainy weather conditions and has a negative impact on image visibility. Besides, to make the algorithm satisfy the application requirements of mobile devices, the computational cost and the real-time requirement of the model have become one of the major points of our research. In this paper, we propose a novel Style Optimization Network (SONet) architecture, containing a Style Optimization Module (SOM) that can dynamically learn style information, and a Key information Extraction Module (KEM) that extracts important spatial and contextual information. This can improve the learning ability and robustness of the model for rainy and foggy conditions. Meanwhile, we achieve real-time performance by using lightweight modules and a backbone network with low computational complexity. To validate the effectiveness of our SONet, we synthesized CityScapes dataset for rainy and foggy weather and evaluated the accuracy and complexity of our model. Our model achieves a segmentation accuracy of 75.29% MIoU and 83.62% MPA on a NVIDIA TITAN Xp GPU. Several comparative experiments have shown that our SONet can achieve good performance in semantic segmentation tasks under rainy and foggy weather, and due to the lightweight design of the model we have a good advantage in both accuracy and model complexity.

Deep learning for the super resolution of Mediterranean sea surface temperature fields

Abstract. Sea surface temperature (SST) is one of the essential variables of the Earth's climate system. Being at the air–sea interface, SST modulates heat fluxes in and out of the ocean, provides insight into several upper and interior ocean dynamical processes, and is a fundamental indicator of climate variability potentially impacting the health of marine ecosystems. Its accurate estimation and regular monitoring from space is therefore crucial. However, even if satellite infrared/microwave measurements provide much better coverage than what is achievable from in situ platforms, they cannot sense the sea surface under cloudy and rainy conditions. Large gaps are present even in merged multi-sensor satellite products, and different statistical strategies, mostly based on optimal interpolation (OI) algorithms, have thus been proposed to obtain gap-free (L4) images. These techniques, however, filter out the signals below the space–time decorrelation scales considered, significantly smoothing most of the small mesoscale and submesoscale features. Here, deep learning models, originally designed for single-image super resolution (SR), are applied to enhance the effective resolution of SST products and the accuracy of SST gradients. SR schemes include a set of computer vision techniques leveraging convolutional neural networks to retrieve high-resolution data from low-resolution images. A dilated convolutional multi-scale learning network, which includes an adaptive residual strategy and implements a channel attention mechanism, is used to reconstruct features in SST data at 1/100° spatial resolution starting from 1/16° data over the Mediterranean Sea. The application of this technique shows an improvement in the high-resolution reconstruction, capturing small-scale features and providing a root-mean-squared-difference improvement of 0.02 °C with respect to the L3 ground-truth data.

Machine Learning Approaches for Short-Term Photovoltaic Power Forecasting

A photovoltaic (PV) power forecasting prediction is a crucial stage to utilize the stability, quality, and management of a hybrid power grid due to its dependency on weather conditions. In this paper, a short-term PV forecasting prediction model based on actual operational data collected from the PV experimental prototype installed at the engineering college of Misan University in Iraq is designed using various machine learning techniques. The collected data are initially classified into three diverse groups of atmosphere conditions—sunny, cloudy, and rainy meteorological cases—for various seasons. The data are taken for 3 min intervals to monitor the swift variations in PV power generation caused by atmospheric changes such as cloud movement or sudden changes in sunlight intensity. Then, an artificial neural network (ANN) technique is used based on the gray wolf optimization (GWO) and genetic algorithm (GA) as learning methods to enhance the prediction of PV energy by optimizing the number of hidden layers and neurons of the ANN model. The Python approach is used to design the forecasting prediction models based on four fitness functions: R2, MAE, RMSE, and MSE. The results suggest that the ANN model based on the GA algorithm accommodates the most accurate PV generation pattern in three different climatic condition tests, outperforming the conventional ANN and GWO-ANN forecasting models, as evidenced by the highest Pearson correlation coefficient values of 0.9574, 0.9347, and 0.8965 under sunny, cloudy, and rainy conditions, respectively.

A Biogeochemical Comparison of three Representative Lakes of Costa Rica

ABSTRACT Lakes are widely distributed across Costa Rica, from coasts to the highest elevation regions, and located in the main terrestrial biomes. However, updated biogeochemical information about the main types of lakes is still lacking. We present comparative biogeochemistry (water chemistry, stable isotopes, and picoplankton) for a coastal lake (Lake Madre de Dios, LMD), a volcanic lake (Lake Barva, LB), and a glacial lake (Lake Ditkevi, LD). Sampling was conducted between February-November 2022 including dry and rainy seasonal conditions. Hydrological and chemical conditions were evaluated using water and carbon stable isotopes, dissolved organic matter (DOM), major ions, and microbiota analysis. Isotopic data (δ18O, δ13CDIC) confirmed lower evaporative losses for the maar and tarn lakes and productivity response to precipitation inputs. Excitation/Emission matrices confirmed the prevalence of fulvic and humic acids in the coastal and glacial lakes, mainly aromatic proteins and soluble microbial by-products in the volcanic lake. Picophytoplankton (PPP, ∼0.2 to 10 μm) was mainly represented by phycocyanin-rich picocyanobacteria (PC-Pcy) events in the three lakes, but maar and tarn lakes had more representation of phycoerythrin (PE-Pcy) events. We confirmed fluctuations in PPP cell abundance in the lakes lower than in temperate lakes. Like in other eutrophic lakes, Pcy also dominated over picoeukaryotes (Peuk) algae abundance. This work seeks to promote adopting an ecosystem approach to study the biogeochemical functioning of tropical lakes using the combination of chemical, hydrological, and biological data and to provide baseline information for future studies (e.g., climate change and pollution impacts) on tropical lakes of Costa Rica.

Evaluation of Scikit-Learn Machine Learning Algorithms for Improving CMA-WSP v2.0 Solar Radiation Prediction

This article aims to evaluate the performance of solar radiation forecasts produced by CMA-WSP v2.0 (version 2 of the China Meteorological Administration Wind and Solar Energy Prediction System) and to explore the application of machine learning algorithms from the scikit-learn Python library to improve the solar radiation prediction made by the CMA-WSP v2.0. It is found that the performance of the solar radiation forecasting from the CMA-WSP v2.0 is closely related to the weather conditions, with notable diurnal fluctuations. The mean absolute percentage error (MAPE) produced by the CMA-WSP v2.0 is approximately 74% between 11:00 and 13:00. However, the MAPE ranges from 193% to 242% at 07:00–08:00 and 17:00–18:00, which is greater than that observed at other daytime periods. The MAPE is relatively low (high) for both sunny and cloudy (overcast and rainy) conditions, with a high probability of an absolute percentage error below 25% (above 100%). The forecasts tend to underestimate (overestimate) the observed solar radiation in sunny and cloudy (overcast and rainy) conditions. By applying machine learning models (such as linear regression, decision trees, K-nearest neighbors, random forests regression, adaptive boosting, and gradient boosting regression) to revise the solar radiation forecasts, the MAPE produced by the CMA-WSP v2.0 is significantly reduced. The reduction in the MAPE is closely connected to the weather conditions. The models of K-nearest neighbors, random forests regression, and decision trees can reduce the MAPE in all weather conditions. The K-nearest neighbor model exhibits the most optimal performance among these models, particularly in rainy conditions. The random forest regression model demonstrates the second-best performance compared to that of the K-nearest neighbor model. The gradient boosting regression model has been observed to reduce the MAPE of the CMA-WSP v2.0 in all weather conditions except rainy. In contrast, the adaptive boosting (linear regression) model exhibited a diminished capacity to improve the CMA-WSP v2.0 solar radiation prediction, with a slight reduction in MAPE observed only in sunny (sunny and cloudy) conditions. In addition, the input feature selection has a considerable influence on the performance of the machine learning model. The incorporation of the time series data associated with the diurnal variation of solar radiation as an input feature can further improve the model’s performance.

Differential growth rate, water use efficiency and climate sensitivity between males and females of Ilex aquifolium in north-western Spain.

Dioecious plant species, i.e., those in which male and female functions are housed in different individuals, are particularly vulnerable to global environmental changes. For long-lived plant species, such as trees, long-term studies are imperative to understand how growth patterns and their sensitivity to climate variability differentially affect the sexes. Here, we explore long-term intersexual differences in wood traits, namely radial growth rates, water use efficiency quantified as stable carbon isotope abundance of wood cellulose, and their climate sensitivity in Ilex aquifolium trees growing in a natural population in NW Spain. We found that sex differences in secondary growth rates were variable over time, with males outperforming females in both radial growth rates and water use efficiency in recent decades. Summer water stress significantly reduced the growth of female trees in the following growing season, while the growth of male trees was primarily favoured by cloudy and rainy conditions the previous fall and winter combined with low cloud cover and warm conditions in summer. Sex-dependent lagged correlations between radial growth and water availability were found, with a strong association between tree growth and cumulative water availability in females at 30 months and in males at 10 months. Overall, our results point to greater vulnerability of female tress to increasing drought, which could lead to sex-ratio biases threatening population viability in the future.

An XAI Framework for Predicting Wind Turbine Power under Rainy Conditions Developed Using CFD Simulations

Renewable energy sources are essential to address climate change, fossil fuel depletion, and stringent environmental regulations in the subsequent decades. Horizontal-axis wind turbines (HAWTs) are particularly suited to meet this demand. However, their efficiency is affected by environmental factors because they operate in open areas. Adverse weather conditions like rain reduce their aerodynamic performance. This study investigates wind turbine power prediction under rainy conditions by integrating Blade Element Momentum (BEM) theory with explainable artificial intelligence (XAI). The S809 airfoil’s aerodynamic characteristics, used in NREL wind turbines, were analyzed using ANSYS FLUENT and symbolic regression under varying rain intensities. Simulations at a Reynolds number (Re) of 1 × 106 were performed using the Discrete Phase Model (DPM) and k–ω SST turbulence model, with liquid water content (LWC) values of 0 (dry), 10, 25, and 39 g/m3. The lift and drag coefficients were calculated at various angles of attack for all the conditions. The results indicated that rain led to reduced lift and increased drag. The innovative aspect of this research is the development of machine learning models predicting changes in the airfoil coefficients under rain with an R2 value of 0.97. The proposed XAI framework models rain effects at a lower computational time, enabling efficient wind farm performance assessment in rainy conditions compared to conventional CFD simulations. It was found that a heavy rain LWC of 39 g/m3 could reduce power output by 5.7% to 7%. These findings highlight the impact of rain on aerodynamic performance and the importance of advanced predictive models for optimizing renewable energy generation.