Typical Weather Research Articles

Enhancing climate resilience in buildings using Collective Intelligence: A pilot study on a Norwegian elderly care center

The combined challenge of climate change and population aging requires novel solutions that enhance the resilience of building energy systems and secure indoor comfort for vulnerable occupants in extreme weather conditions. This research investigates the performance of a newly developed Energy Management (EM) system based on Collective Intelligence (CI) and Reinforcement Learning (RL), called CIRLEM, managing the energy performance of an urban complex in Ålesund, Norway, including an elderly care center with decentralized PV generation, EV charging and storage, while connected to a main electricity grid. CIRLEM controls multiple flexibility assets including independent thermal zones (the demand-side agents) and Electric Vehicle (EV) charging stations (the local storage). In a novel approach, CIRLEM coordinates the distributed storage and generation together with the demand side to control energy systems and react collaboratively to environmental variations. Under extreme weather conditions, without applying CIRLEM, the demand can be more than double that of typical weather conditions. The implementation of the double-layer CIRLEM can reduce the total demand by 35 % over a month. Furthermore, the inclusion of photovoltaic (PV) systems allows the system to be independent from the grid for almost 40 % of its operational hours, while adding EV storage can increase it to around 70 %. Finally, the application of CIRLEM reduced overheating hours from 17 h ∙°C to 2 h ∙°C under extreme conditions, while maintaining comfortable conditions even during temperature ramps.

From Local Energy Communities towards National Energy System: A Grid-Aware Techno-Economic Analysis

Energy communities are key actors in the energy transition since they optimally interconnect renewable energy capacities with the consumers. Despite versatile objectives, they usually aim at improving the self-consumption of renewable electricity within low-voltage grids to maximize revenues. In addition, energy communities are an excellent opportunity to supply renewable electricity to regional and national energy systems. However, effective price signals have to be designed to coordinate the needs of the energy infrastructure with the interests of these local stakeholders. The aim of this paper is to demonstrate the integration of energy communities at the national level with a bottom–up approach. District energy systems with a building scale resolution are modeled in a mixed-integer linear programming problem. The Dantzig–Wolfe decomposition is applied to reduce the computational time. The methodology lies within the framework of a renewable energy hub, characterized by a high share of photovoltaic capacities. Both investments into equipment and its operation are considered. The model is applied on a set of five typical districts and weather locations representative of the Swiss building stock. The extrapolation to the national scale reveals a heterogeneous photovoltaic potential throughout the country. Present electricity tariffs promote a maximal investment into photovoltaic panels in every region, reaching an installed capacity of 67.2 GW and generating 80 TWh per year. Placed in perspective with the optimal PV capacity forecast at 15.4 GW peak at the national level, coordinated investment between local and national actors is needed to prevent dispensable expenses. An uncoordinated design is expected to increase the total costs for residential energy systems from 12% to 83% and curtails 48% of local renewable electricity.

Impacts of Climate Change on Teesta River Basin Char Lands: A Study of Livelihood and Ecosystem Dynamics in Bangladesh

This study anticipates identifying how does climate change affect the livelihood and ecosystem of char land of Teesta River basin char land. Structured questionnaire and related documents were used for both primary and secondary data collection. Survey was conducted in two districts (Rangpur and Nilphamari) and four unions (Lakhitari, Topa Madhupur, Shatibari, Gulmund) of four upazilas (Gangachara, Kaunia, Dimla, Jaldhaka). A total of 50 respondents from each selected char union was selected following a multistage random sampling procedure. Thus, there was altogether 200 respondents selected for this study. Data related to age, education level, occupation, knowledge about climate change of char inhabitants and perception of char dwellers regarding climate change was measured. A total number of 93% of the respondents clearly grasp that climate change refers to changes in long-term typical weather. It was observed that ongoing climate change has 78% impact on agriculture followed by health of peoples and other animals that is 20%. In the rainy season they observed increase in lightning from sun as the highest effect of climate change that has a WAI of 1.77. Teesta river basin people perceived dry spell frequency as the second highest extent of climate change that had a WAI of 1.74 followed by timing of rain offset, uneven distribution of rainfall and timing of rain onset. According to their perception it was found that great extent of loss was found in skills of char peoples (48.35%) followed by knowledge of char peoples (44.27%). It was also observed that a third great extent of loss was found in char peoples good health (41.67%) followed by ability to work (39.06%). Out of all the respondents 166 (43.2%) observed that soil is becoming dry day by day due to climate change followed by rivers becoming dry (37.8%) (Table 8). They found that growing trees have become difficult (45.1%), due to drought underground water is decreasing (61.7%) and air became dry due to climate change, and these are small extent of loss. Char inhabitants observed that climate change impact on physical capital and great extent impact was perceived on people's migration to another place (41.4%). Teesta River basin char dwellers opined about 24 adaptation strategies to reduce the impact of climate change on livelihood and ecosystem in that area.

Assessing built microclimate with building group frontal projection maps: A sun-path-dependent deep transfer learning neural network approach

Climate conditions play a pivotal role in estimating buildings' energy consumption. For urban-scale building energy dynamic simulation, the typical meteorological year weather represents a universal climate condition for the entire city. However, the varying terrain roughness, environment conditions, human-built architectures jointly formulate a unique microclimate condition for each building. This study intends to develop flexible and reliable approach to assess a building's microclimate condition based on its surrounding environment morphological features. The proposed approach leverages deep transfer learning neural networks that combines seasonal sun path trajectories and front projection maps of building groups. To validate the proposed method, a case study was conducted on a campus environment with wireless environmental sensing systems. The findings of this study demonstrate that the projection matrices and sun path can improve the assessment methods solely based on the dynamic impacts of urban morphological features and can forecast microclimate dynamics for urban-scale building energy simulation.

Energy savings potential and life cycle costs of deep energy retrofits in buildings with and without habitable style loft attic conversions: A case study of Irelands residential sector

This paper evaluated the potential energy and life cycle cost (LCC) savings arising from the deep energy retrofit of residential buildings. The cost optimal model was determined for material upgrades and the addition of an air-to-water heat pump, where the household level of savings at 2023 energy prices will be dependent on the typical housing characteristics and weather conditions. LCC savings post retrofit for a detached dwelling insulated at the ceiling/rafter including installation of a heat pump amount to a €20,031-€21,370 for an uninsulated dwelling pre-retrofit, rising to €38,448 for dwellings with a habitable loft conversion. Partially insulated dwellings, pre-retrofit did not all incur favourable returns in investment, and in some cases were unviable. Although, the application of a 50% grant results in a viable return on investment for home owners. A sensitivity analysis found high discount rates, fuel prices and increasing capital costs can negate positive returns on investment. Finally, at a national level energy saving of 7.72 TWh by 2030 could be realised if the Irish Climate Action Plan 2023 retrofit targets are adhered to. In addition, total LCC savings could be valued at €1.4 billion. Where only material upgrade are pursued a loss occurs of €0.56 billion.

Cloud type classification using deep learning with cloud images.

Clouds play a pivotal role in determining the weather, impacting the daily lives of everyone. The cloud type can offer insights into whether the weather will be sunny or rainy and even serve as a warning for severe and stormy conditions. Classified into ten distinct classes, clouds provide valuable information about both typical and exceptional weather patterns, whether they are short or long-term in nature. This study aims to anticipate cloud formations and classify them based on their shapes and colors, allowing for preemptive measures against potentially hazardous situations. To address this challenge, a solution is proposed using image processing and deep learning technologies to classify cloud images. Several models, including MobileNet V2, Inception V3, EfficientNetV2L, VGG-16, Xception, ConvNeXtSmall, and ResNet-152 V2, were employed for the classification computations. Among them, Xception yielded the best outcome with an impressive accuracy of 97.66%. By integrating artificial intelligence technologies that can accurately detect and classify cloud types into weather forecasting systems, significant improvements in forecast accuracy can be achieved. This research presents an innovative approach to studying clouds, harnessing the power of image processing and deep learning. The ability to classify clouds based on their visual characteristics opens new avenues for enhanced weather prediction and preparedness, ultimately contributing to the overall accuracy and reliability of weather forecasts.

A TPA-TCN Prediction Model Applied In Photovoltaic Power Generation Field

To solve the problem of large fluctuation and instability of photovoltaic power generation, a deep learning prediction model (TPA-TCN) based on temporal pattern attention mechanism (TPA) and temporal convolutional network (TCN) is proposed, and then applied to photovoltaic power generation. First of all, the k-means clustering algorithm is used to cluster historical data to obtain three typical weather types, and the model is trained by dividing test sets according to the clustering results. After TPA is introduced into the TCN model, which can capture the influence of each variable on the predicted series of the model, help the model pay better attention to the key features in the time series, improve the model’s ability to understand the data, and thus efficiently and accurately predict the short-term photovoltaic power. Combined with the measured data, the experiment results show that the TPA-TCN model has good generalization ability and high precision in different weather types.

Adaptive SPP–CNN–LSTM–ATT wind farm cluster short-term power prediction model based on transitional weather classification

With the expansion of the scale of wind power integration, the safe operation of the grid is challenged. At present, the research mainly focuses on the prediction of a single wind farm, lacking coordinated control of the cluster, and there is a large prediction error in transitional weather. In view of the above problems, this study proposes an adaptive wind farm cluster prediction model based on transitional weather classification, aiming to improve the prediction accuracy of the cluster under transitional weather conditions. First, the reference wind farm is selected, and then the improved snake algorithm is used to optimize the extreme gradient boosting tree (CBAMSO-XGB) to divide the transitional weather, and the sensitive meteorological factors under typical transitional weather conditions are optimized. A convolutional neural network (CNN) with a multi-layer spatial pyramid pooling (SPP) structure is utilized to extract variable dimensional features. Finally, the attention (ATT) mechanism is used to redistribute the weight of the long and short term memory (LSTM) network output to obtain the predicted value, and the cluster wind power prediction value is obtained by upscaling it. The results show that the classification accuracy of the CBAMSO-XGB algorithm in the transitional weather of the two test periods is 99.5833% and 95.4167%, respectively, which is higher than the snake optimization (SO) before the improvement and the other two algorithms; compared to the CNN–LSTM model, the mean absolute error (MAE) of the adaptive prediction model is decreased by approximately 42.49%–72.91% under various transitional weather conditions. The relative root mean square error (RMSE) of the cluster is lower than that of each reference wind farm and the prediction method without upscaling. The results show that the method proposed in this paper effectively improves the prediction accuracy of wind farm clusters during transitional weather.

АГРОБИОЛОГИЧЕСКАЯ ОЦЕНКА МАСЛИЧНЫХ КУЛЬТУР В УСЛОВИЯХ ЛЕСОСТЕПИ ЦФО РФ

This article presents the results of environmental tests of the most promising very early soybean lines of Krasnodar breeding in the conditions of the Forest-steppe of the Central Federal District of the Russian Fed-eration, which were involved in hybridization. In the obtained hybrid populations of F4 in the conditions of Krasnodar, very early elite plants with a growing period of 90-100 days, plant height of at least 70 cm, and increased productivity were isolated. Their offspring in generations F6 and F7 underwent selection evalua-tion in the latitudinal and climatic conditions of the forest–steppe of the Central Black Soil region on the ba-sis of the Lipetsk Rapeseed Research Institute - a branch of the Federal State Budgetary Research Center V.S. Pustovoit All-Russian Research Institute of Oil crops, Lipetsk. As a result of the conducted studies, it was found that in the typical weather conditions of the Central Black Soil region in 2021 and with the dates of soybean sowing in the Lipetsk region in the 2nd decade of May, the earliest genotypes ripened in late August – early September. The duration of their growing seasons was 96-103 days. In the abnormally cold and rainy conditions of 2022, the growing season of these genotypes increased to 110-123 days. The yield of the earliest of the studied soybean genotypes in the conditions of 2021 varied in the range of 2.04-2.46 t/ha, in the condi-tions of 2022 – in the range of 2.07-2.91 t/ha. A two-year analysis of the productivity of the studied soybean genotypes in various weather conditions allowed us to identify 7 breeding lines that form a yield of more than 2.0 t/ha, both in close to optimal and in abnormally cold weather conditions with excessive precipitation.

Defining generation parameters with an adaptable data-driven approach to construct typical meteorological year weather files

Weather files play a critical role in building energy simulation by providing crucial information on the environmental condition. Typical meteorological year (TMY) weather files are often used in building energy simulation to approximate the long-term performance. These files are generated using long-term weather data and are meant to reflect the typical weather conditions within the dataset. Common generation methods used to construct TMY weather files typically rely on expert-defined universal generation parameters. However, the weather parameters and weighting factors used to generate these files, termed generation parameters, often overlook variations in climate and applications. This study introduces a data-driven approach to define the generation parameters used in the Sandia method to produce TMY weather files. The study aims to enhance the generation method by providing a framework to define the generation parameters which considers data availability, climate and application.The proposed methodology employs machine learning and feature importance to define the generation parameters used to construct TMY weather files. The generated TMY weather files are evaluated for a Montreal case study using building energy demand. The results show an improvement in the representativeness of the long-term average building energy demand for the weather file generated using the model-defined generation parameters.

Building for tomorrow: Analyzing ideal thermal transmittances in the face of climate change in Brazil

The climate will become hotter, and buildings will perform differently as outdoor conditions evolve. If the lowest energy demand is desired, it is crucial to determine the ideal thermophysical properties of the envelope over the buildings' life span. However, the scientific literature is still scarce in providing a compelling answer. Therefore, this study (i) determines ideal thermal transmittance values (U-values) for present-day and future climates, (ii) determines to what extent the thermophysical properties will need to change to remain ideal, (iii) identifies different trends of U-values over time, (iv) establishes a relationship between outdoor air temperatures, cooling and heating setpoints, and ideal U-values, and (v) proposes a set of design strategies according to each trend. The EPSAP generative design method was used to create a large dataset of residential buildings with random geometries and U-values to evaluate their energy demand for heating and cooling in EnergyPlus. The thermal performance of each building was evaluated for 30 locations in Brazil for the current period and two future timeframes (2050 and 2080). The Future Weather Generator tool was used to morph today's typical meteorological weather to match the EC-Earth3 data for the SSP5–8.5 scenario. Although climate change has a similar relative impact, its consequences differ over time in each location. The ideal U-values have different trends in different regions: (a) remaining unchanged in the future, (b) changing from being the highest possible to the lowest of the analyzed range in 2050 or 2080, and (c) being mid-range values in the present and with similar or lower values in the future climate. The impact on the thermal loads of maintaining the present-day ideal U-values also varies significantly in the future timeframes, from being nil to representing an increase reaching 30 % in 2050 (∆ 2.94 MW·h ± 0.06 MW·h) and 57 % in 2080 (∆ 6.05 MW·h ± 0.09 MW·h). Therefore, building design professionals need to use different strategies according to each region and consider how climate evolves during the lifetime of the building.

A Novel Approach for Day-Ahead Hourly Building-Integrated Photovoltaic Power Prediction by Using Feature Engineering and Simple Weather Forecasting Service

Although the accuracy of short-term prediction of building-integrated photovoltaics is essential to making an optimal decision on the management of the generated electricity, the weather forecasting service in many countries provides insufficient features for improving the prediction accuracy of the photovoltaics power output. This study suggests a machine learning model incorporated with feature engineering to improve the prediction performance of day-ahead hourly power outputs using a simple weather forecast service. A new synthetic feature, the modified sky condition, is derived to infer onsite sky condition and solar irradiation, which is not supported by the typical weather forecasting services. It evaluated the prediction performance with different training and hyper-parameter conditions for 60 days. By using the derived modified sky condition, the model outperformed other predictor configurations in most daily sky conditions; particularly, the accuracy improved by more than 50% on overcast days compared to when it used the original weather forecasting service data. The result demonstrates the feasibility and ability of the model to enable more efficient energy management of building-integrated photovoltaic power output in buildings without an onsite weather station, thus contributing toward the optimized dispatch of the integrated electricity energy storage system and other distributed energy resources.

Impacts of high-albedo urban surfaces on outdoor thermal environment across morphological contexts: A case of Tianjin, China

The urban heat island (UHI) effect can exacerbate various environmental challenges related to high temperatures in urban areas. Increasing urban surface albedo is an effective strategy to mitigate UHI. However, the efficacy of high-albedo urban surfaces across varying urban contexts remains poorly understood. In this study, we leverage Urban Weather Generator to systematically simulate the effects of high-albedo roads, walls, and roofs on urban microclimate across Tianjin. Our simulation covers a typical meteorological year, representing typical weather conditions from January to December. Our results reveal that increasing road albedo is more effective in mitigating UHI in fringe areas, whereas increasing wall and roof albedo is more effective in mitigating UHI in central areas. Local climate zones with an urban aspect ratio of about 0.5 can obtain a maximum reduction of road surface temperature (-6 °C) and wall surface temperature (-3 °C). The temperature changes induced by albedo changes show evident seasonal characteristics: the road temperature decreases significantly in summer, while the wall temperature decreases significantly in spring and autumn. Our results could help guide UHI mitigation policies and urban planning in cities hoping to enhance urban surface albedo to balance urban growth and climate resilience.

Fast nitrate formation aloft supported by typical synoptic weather patterns and complex terrain in the North China Plain

North China Plain has been suffering from the increasing prominent nitrate pollution. In addition to intensive anthropogenic emissions, typical synoptic weather patterns and complex terrain in this region potentially contribute to fast nitrate formation, which has not been well understood. Focusing on a winter haze episode, we investigate their combined effects on nitrate formation by combining regional observations, weather situation analysis, and model simulations. In addition to the commonly proposed accumulating pollutants, our results indicate that synoptic weather patterns and complex terrain can uplift the precursors from the ground level and transport O3 from the free troposphere, enhancing the nitrate formation in the residual layer, with a faster formation than near the surface. The downward transport of nitrate aloft aggravates the nitrate pollution at the ground level. Our study demonstrates the notable effects of synoptic weather patterns and complex terrain on shaping nitrate production vertically, and highlights the importance of nitrate formation aloft to nitrate pollution at the ground level.

Reconstruction of narrowband solar radiation for enhanced spectral selectivity in building-integrated solar energy simulations

Solar radiation is a critical factor in advanced envelope design and solar energy's building integration, necessitating a shift from broadband solar radiation analyses towards more precise narrowband or spectrum-focused approaches. Understanding the performance potential of spectral-selective materials or structures requires accurate solar spectral information at specified locations, a feature often overlooked by conventional modeling tools. This work presents an innovative solar decomposing model capable of differentiating key solar irradiation components—visible and infrared—from broadband solar irradiance, without the need for expensive spectrum measurements. Our approach employs the extreme boosting regression tree method and leverages existing or easily derivable data from typical weather files. An exploratory analysis of the importance and interaction of different features in predicting solar irradiation components is also conducted. The results show that the proposed algorithm has an R2 of 0.981 and 0.990, RMSE of 18.280 and 18.390, and MAE of 7.989 and 8.011, for predicting VIS and NIR amount in DNI, respectively (for the strongest model using all the predictors within the dataset). This research offers an added layer of practicality by including case studies demonstrating how the solar decomposition models serve in real-world applications, especially in the integration of wavelength-selective devices like window systems and transparent solar cells into advanced envelope designs. Such real-world testing has verified the presence of a disparity between the power output calculation of NIR-selective transparent photovoltaics upon the broadband solar radiation data and the suggested narrowband solar radiation data, potentially resulting in a maximum deviation of 15.7 %. The decomposing models developed empower researchers and designers to generate new weather files comprising narrowband solar irradiance data, thereby enhancing their capacity to examine the influence of spectral-selective materials on a building's solar performance using existing solar simulation programs. The proposed method will be further improved by including more data from different climate zones and weather characteristics in the training model and validating through field measurements.

A novel aging acceleration rate equation for accelerated weather aging test of high viscosity modified asphalt: Theoretical derivation and experimental correction

Accelerated weather aging test is a novel aging method for evaluating the long-term real aging behavior of large-void asphalt pavement (OGFC) and high viscosity modified asphalt (HVMA). However, uncertainties in aging acceleration rate and inconsistencies in selecting weather parameters are the core issues restricting its widespread application. To address these issues, this study proposes a novel approach to construct aging acceleration rate equation for the accelerated weather aging test, considering aging kinetics theory and experimental data correction. First, three representative weather aging combinations were chosen, and a theoretical model for aging acceleration rate was preliminarily constructed based on thermal aging kinetics theory, photoaging kinetics theory, and humidity peak model. Then, by comparing the aging performance between accelerated weather aged HVMA and natural aged HVMA, the experimental aging acceleration rate range (AF1) was determined, and the theoretical model was parameterized to formulate the aging acceleration rate equation at the binder level. Finally, based on the aging performance comparison between accelerated weather aged HVMA and recycled HVMA from field-aged OGFC, the experimental aging acceleration rate range (AF2) was determined, and the mixture-level aging acceleration rate equation after parameter correction was determined. The results show that after theoretical derivation and experimental correction, the aging acceleration rate equation at the binder level incorporates temperature acceleration rate, solar radiation acceleration rate, humidity acceleration rate, and binder correction coefficient Cα (Cα = 1.214). For the mixture level, it also requires considering mixture correction coefficient Cβ (Cβ = 3.731). Under the three typical weather aging combinations in this study, a one-day accelerated weather aging test can simulate the aging effect of 18, 40 and 81-days natural aging for HVMA or 2, 5, and 10-months field aging for OGFC. The aging acceleration rate equations involve real weather parameters, allowing the determination of aging acceleration rates under any combination of weather parameters. This provides a foundation for weather parameter selection and enables accurate simulation of long-term aging of HVMA and OGFC in the laboratory.

Weather pattern conducive to the extreme summer heat in North China and driven by atmospheric teleconnections

Extreme summer heat can have severe socioeconomic impacts and has occurred frequently in North China in recent years, most notably in June–July 2023, when North China experienced the most widespread, persistent, and high-intensity extreme heat on record. Here, typical weather patterns covering North China and its surrounding areas were classified into seven types based on the Cost733class package, and the weather pattern type 4 (T4), characterized by the strengthened ridge and anticyclone anomaly in northeastern China, was found as the most favorable for the occurrence of extreme summer heat in North China (NCSH). Diagnostic and wave activity flux analyses indicate that the Eurasian teleconnection (EAT) pattern from the atmosphere and the Victoria mode (VM) from the ocean are the top two dominant climate drivers of the T4 weather pattern. The empirical models constructed based on the EAT and the VM can effectively simulate the number of days of the T4 weather pattern and the NCSH, respectively. Our results suggest that, with the help of the seasonal forecast from climate models, the EAT and the VM can be used to predict the number of days of the T4 weather pattern and the NCSH for the coming summer, enabling us to protect human health and reduce its socioeconomic impacts through proactive measures in advance.

Traffic flow prediction based on T-GCN in extreme weather: A case study of Beijing

In recent years, frequent extreme weather events have significantly impacted traffic management and urban planning. Consequently, accurate and real-time traffic prediction has become crucial for effective urban traffic planning, management, and control. This study aims to predict road traffic flow in Beijing under extreme weather conditions. To achieve this goal, the study analyses historical weather data of Beijing and identifies four typical extreme weather conditions. Using traffic data collected between 2014 and 2016, the study then employs the time series graph convolutional network (T-GCN) model to predict traffic flow under extreme weather conditions.

A Methodology to Assess the Suitability of Typical Meteorological Year Weather Data for Simulating the Performance of Buildings Conditioned Entirely by Ambient Energy

Abstract This study evaluates for the first time the suitability of typical meteorological year (TMY) weather data for simulating the performance of buildings that are entirely conditioned by ambient energy. A home in Durango, CO, was simulated with TMY data, with real data for 1998–2020 and with extreme meteorological year (XMY) data. For this climate, the indoor temperature in the house designed with TMY data drops below the range of comfortable indoor temperature (20–25 °C) for 16 of 23 years, including as low as 13 °C during 2008. With the thermal time constant of the house adjusted for each data set to maintain comfort, the required time constants for the real data ranged from 1.178 to 7.56 days with a mean of 3.14 and a median of 2.38, while the TMY value was 1.862 for a percentile rank of 0.318. XMY data did not produce significantly better results. The correlation of the time constant to weather parameters showed that the maximum interval during which the 24-h average solar load ratio remains below 1 is a promising index for identifying the most challenging year. Until more representative TMY and XMY weightings are developed for ambient-conditioned buildings across other climates, it is advisable that current TMY data are used only for preliminary design and that multi-year simulations are conducted for final design.

Multi-channel feature fusion attention Dehazing network.

Haze is a typical weather phenomena that has a significant negative impact on transportation safety, particularly in the port, highways, and airport runway areas. A multi-scale U-shaped dehazing network is proposed in this research, which is based on our multi-channel feature fusion attention structure. With the help of the feature fusion attention techniques, the model can focus on the intriguing locations with higher haze concentration area. In conjunction with UNet, it can achieve multi-scale feature reuse and residual learning, allowing it to fully utilize the feature information of each layer for image restoration. Experimental resulsts show that our technique performs well on a variety of test datasets. On highway data sets, the PSNR / SSIM / L∞ error performance over the novel technique is increased by 0.52% / 0.5% / 30.84%, 4.68% / 0.78% / 26.19% and 13.84% / 9.05% / 55.57% respectively, when compared to DehazeFormer, MIRNetv2, and FSDGN methods. The findings suggest that our proposed method performs better on image dehazing, especially in terms of L∞ error performance.