Corrigendum: An experimental analysis and deep learning model to assess the cooling performance of green walls in humid climates

IntroductionPlease change to: In recent decades, overpopulation and economic growth have significantly accelerated global warming, resulting in numerous serious issues for urban areas and their residents (Buhaug & Urdal, 2013; Chowdhury et al., 2021). The release of greenhouse gases and chemical pollutants into the atmosphere (Hashim et al., 2020) intensifies climate change (Filho et al., 2023; Perera et al., 2020), exacerbates the urban heat island (UHI) effect, and increases heat stress (Chew et al., 2021; Mahdavi Estalkhsari et al., 2023; Mohammad Harmay & Choi, 2022), leading to higher energy demands (Khotbehsara et al., 2018; Mutschler et al., 2021). The construction industry, which addresses essential human needs such as housing, is a significant energy consumer, with building and construction sectors accounting for nearly 40% of total energy usage. This energy is primarily consumed by heating and cooling systems throughout the year (Ghahramani et al., 2018; Rafsanjani et al., 2020).Various scientific reports have concluded that multiple urban elements, including exterior walls (building envelopes), roofs, terrain, pavement and roads, and building materials, can play an essential role in urban design. This design aims to create thermally pleasant outdoor spaces where these elements can influence the environment by controlling heat transfer (Convertino et al., 2019), solar radiation (Vox et al., 2018), albedo (Salata et al., 2015), and airflow (Perini et al., 2011). Materials have notably different heat capacities, thermal conductivity (thermal bulk properties), and surface radiative attributes such as albedo and emissivity (Mohajerani et al., 2017; Mohammad et al., 2021). Using dark surfaces and materials, such as asphalt, cement, concrete, composite, and metal, can lead to higher air temperatures and manifest UHI effects (Stempihar et al., 2012; Zhou et al., 2021). The UHI phenomenon emerges as cities replace natural landscapes with dense arrangements of heat-absorbing surfaces, such as pavement, buildings, and others, resulting in elevated air temperatures (Kardinal Jusuf et al., 2007). Moreover, as noted earlier, the escalating impact of global warming exacerbates the frequency of hot days and nights, heightening the risk of heat stress and associated health concerns. While everyone can be negatively affected by heat waves and extreme heat events, some people, like the elderly, those with chronic illnesses, children, and pregnant women, are at risk of suffering harm during such hot spells (Folkerts et al., 2022; McElroy et al., 2020). There has been extensive research on various aspects of environmental design in different contexts. A broad overlap and cooperation for expected outcomes emerge by carefully studying these strategies. The use of green walls supports processes such as air purification (Abdo & Huynh, 2021), rainwater collection (Prenner et al., 2021), reduction of ambient noise levels (Cardinali et al., 2023), increase in biodiversity (Chen et al., 2020), and enhancement of a building's fire resistance (Kotzen et al., 2023). Green walls are also highly recommended due to their significant impact on ambient air temperature (Afshari, 2017; Olivieri et al., 2014; Shafiee et al., 2020; Susorova et al., 2013).For instance, Alexandri and Jones (2008) found that implementing green wall systems decreased outdoor air temperature by 8°C. Additionally, east-west oriented vegetated walls were shown to lower the average daytime temperature by approximately 2°C. Furthermore, Wong et al. (2010) noted that 0.15 meters from the plant surface resulted in a temperature reduction of roughly 3°C. In a broader context, Kontoleon and Eumorfopoulou (2010) reported that the cooling potential of a green wall on a north-oriented facade is insignificant and negligible. Additionally, they concluded that the reduction is more significant for west-oriented facades at about 3.50°C, while for east- and south-oriented facades, the temperature drop reaches about 2°C and 1°C, respectively. Chen et al. (2013) concluded that the cooling merits of the VGS are more pronounced on the exterior surface than in the indoor environment, which is relatively weaker. This reduction was recorded at about 1.5°C.This study has examined the impact of green walls during warm conditions in Rasht, the largest city along Iran's Caspian Sea. Rasht is classified under Köppen's subtropical humid climate (Cfa) and is a representative sample of similar Cfa climate zones globally. This unique climate makes Rasht particularly susceptible to the UHI effect compared to other large cities. While studies on green walls have been explored in various research articles over the decades, only a limited number have investigated the thermal performance of green walls (specifically, the reduction of outdoor temperature and mitigation of UHI) in humid conditions across the globe (e.g., Ref.: (Alexandri & Jones, 2008; Karimi Zarchi & Shahhoseini, 2019)).In line with that, several research investigations have addressed UHI concerns in the humid climate of Rasht. These studies have elucidated temperature differentials ranging from 5-6.4 °C during the cold season and 3-5.6 °C during the warm season, differentiating between the central part of the city and its surrounding areas (Karimi Zarchi & Shahhoseini, 2019). In research conducted by Bahman and Dokhat Mohammad (2010), UHI in Rasht underwent evaluation by deploying nine environmental sensors for field measurements. The findings indicated 5 to 6.4 °C temperature variances at Sabzeh Meydan Square and Shahrdari stations. The fact that green walls can reduce ambient temperature in humid climates is now evident. However, the extent to which distance matters and how effectively these systems can reduce ambient temperature are still underexplored.This research seeks to assess the influence of SCP on temperature reduction across distinct cardinal directions. By delving into the intricate dynamics of SCP placement, our study aims to provide in-depth insights into the optimal distances that yield the most effective temperature reduction in a humid climate. We used different analysis techniques, such as field measurements and advanced modeling approaches, to quantify the impact of varying SCP distances on temperature mitigation. To achieve the research objectives, the research team has established two scenarios for the study's orientation, including Scenario 1) Field measurement-based analysis (SC 1: FMA), and Scenario 2) Deep Learning Model (SC 2: DLM). As previously described in the literature, this study investigates the impact of SCP in a humid climate, evaluating the thermal performance of SCP and the surrounding conditions when green walls are in use. The present study also offers a novel approach by utilizing a deep learning model to enhance the accuracy of the analysis, utilizing data generated from the experimental scenario. This study provides new knowledge on the impact of green walls in humid climates, a relatively unexplored area with only a few existing studies. This research is also among the first to assess the cooling performance of green walls at different points from the wall surface in a humid climate, offering a detailed analysis of how proximity to the wall affects temperature reduction. By highlighting the benefits of integrating green wall systems, the study supports the development of more effective and sustainable urban design practices.Material and methodsClimate attributes of the study areaThe city of Rasht is situated in the northern region of Iran and falls under the humid subtropical climate category (Cfa) according to the Köppen climate classification. With an average annual rainfall of 1359 mm, Rasht holds the top position for rainfall among the provincial centers in Iran, earning it the nickname "the city of rain." Rasht experiences an average annual temperature of 15.9 °C, with the average annual maximum air temperature at 20.6 °C and the average annual minimum at 11.3 °C. The annual temperature range is reported to be 9.3 °C. Figure 1 depicts the geographical location of the study area, while Figure 2 illustrates its climatic attributes. FIGURE 1. The location of the study area on the map Legend: Above Bottom HumidityDry TemperatureWind DirectionWind VelocityFIGURE 2. Climatic attributes of Rasht include dry-bulb temperature, wind speed and direction, and relative humidity (Plotted by Dview)The latitude of Rasht is 37.280834, and the longitude is 49.583057 which is located in Iran country in the cities place category with the GPS coordinates of 37° 16' 51.0024'' N and 49° 34' 59.0052'' E. According to the Köppen climate classification, Rasht has a humid subtropical climate (Cfa). The city experiences an average annual rainfall of 1,359 mm. The city of Rasht receives an average annual rainfall of 1,359 mm, making it the leading city in rainfall among the provincial capitals of Iran, and earning it the nickname "the city of rain." The average annual temperature in Rasht is 15.9°C, with the average annual maximum temperature being 20.6°C and the average annual minimum temperature at 11.3°C. This results in an annual temperature range of 9.3°C between the maximum and minimum temperatures. Figure 1 depicts the geographical location of the study area, and Figure 2 illustrates the climatic features. Case study selection criteriaBased on the findings reported by Oji (2021), the green spaces in Rasht city underwent significant changes between 1964 and 2013. The total green areas decreased from 7,255 hectares to 5,990 hectares, marking a 17% reduction. Dense green spaces saw an even more dramatic decline, shrinking from 2,855 hectares to 788 hectares, which represents a 72% decrease. The majority of these reductions were observed in the central region of Rasht (see Fig. 3)On this basis, SC 1: FMA includes the selection of 4 case studies, all of which are situated in the central region of Rasht with the same properties as SCP in a dense urban area. These cases have the same leaf area index (LAI) (see Table 1). Moreover, in selecting the samples, extensive care has been taken to ensure consistency in all cases regarding the parameters influencing the UHI effect. These parameters include the number, density, and height of buildings; the window-to-wall ratio; floor height; building function; and pavement characteristics such as material type, albedo, thermal conductivity, thickness, and volumetric heat capacity. Additionally, the level of traffic has been considered to maintain uniformity. SC 1: FMA aims to evaluate whether the SCP orientation effectively reduces UHI. The SCP is covered with a Hedera helix, the common species called ivy. The SCP used in the study features self-clinging plants that attach directly to the wall through adhesive suckers with adventitious roots. These climbers form a self-supporting layer of vegetation on solid surfaces, creating a traditional green wall.a b FIGURE 3. of green spaces in Rasht 2021), and the location of the cases on the 1. This is a be in the the first they are species area self-clinging Hedera self-clinging Hedera self-clinging Hedera self-clinging of the of selecting our case significant on and the of the study was and a role in our to the and of To from the building in a detailed to to Additionally, was a that the case study a and of the environment in which the was among the as the case study to the effects of SCP on ambient We this case of the building's location for implementing data The of the building this Additionally, the analysis when the data was recorded The orientation of the SCP is on the of the experimental the effect of SCP on outdoor cooling among cases across Rasht the research team a potential SCP Case 1 as a case study for field measurements. The essential is that the Case 1 is situated in an urban area to the level where everyone through the the green wall is situated on a broad which from from on its as a potential Additionally, this case study features an of plant The green wall is of self-clinging plants that attach directly to the wall through their adhesive adventitious et al., These climbers form a self-supporting vegetation layer on a solid The was the to the east-west temperature measurements were recorded at The SCP was covered with Hedera helix, a used meters the were used to outdoor temperature data & This height and location were to temperature that the ambient can temperature at a height of approximately meters the which with This height is significant for environmental as it conditions that are directly and by in outdoor The were in of the Table 1 the data The data are on and at 0.15 and from the surface (see Figure Table 2 provides the of experimental 2. The of the et al., with air temperature, and and measurements. in & 1 5 and when is speed temperature data temperature data at throughout the study parameters of outdoor air for days from to in of the green wall the temperature the wall was by two to ensure that the were The experimental analysis was during to assess the cooling effects of the SCP in the ambient the was generated to the cooling effect for the the generated was experimental results to ensure that the new was FIGURE of the study area and of data for ambient air studying the impact of plants on outdoor air temperature, several into While the can be and on various environmental the and for our is the of from and plant surfaces and from plant can be a significant cooling in green The is used to radiation at the surface heat temperature speed at 2 meters the surface of green walls in cooling outdoor air temperature can also be to heat transfer The heat transfer can be to the cooling effect on the of heat and the surface area covered by green transfer transfer area covered by green walls of the green wall surface air temperature deep learning for data research team in field measurements in this due to various These include limited data in data and data By learning techniques, data that the measurements. This to the data and more learning techniques, such as have in modeling and data By on the field were to a model that the intricate dynamics between the distance for temperature reduction by SCP and the humid climate. is a to enhance the performance of when with limited et al., be used to and the temperature reduction at various insights into the By learning into the have a novel approach to data in temperature reduction by SCP under a humid climate. In the of data over from at and on at with a used to the deep learning including a the air temperature, and air temperatures recorded at distances of 0.15 and from the of the data over days air air at air at air at air at air temperature and air temperature of the were recorded at distances of and from the green of this the for the at and to temperatures across different SCP The of the the evaluating the to to data The model two for and air temperature and for temperatures at distances from the The was as the to The of the is shown in Table 3. The and of air temperature at the distance of 0.15 from the temperature at the distance of from the temperature at the distance of from the temperature at the distance of from the the use of a as the Deep Learning of a of called that to a The learning of the the to achieve the which be a of on the being The are at the to across multiple a in deep The used in this research has The of our model is in Figure The layer with two is with the and air temperature, the to the between data and the and the layer of that the air temperature at different distances from the green form the FIGURE The Deep Learning used in our is the a & The performance was by the as the described by In this context, the number of is by the by and the by We our into two data selection to and evaluate the The considered to our model and used the to its this used two for and as shown in Table The deep learning and 1: on the of this the research data at points the The indoor temperature and humidity data for the green wall were compared to those for a The data the indoor temperature and relative humidity highlighting the between the green wall and the wall In building surrounding the was reported to by the Figure 4 the of the this of the the and are the temperature and respectively. As the points 0.15 and from the were and the temperatures were recorded through the data FIGURE temperature SCP the and SCP temperatures during the field in the on the the temperature for all is a significant temperature reduction and between 0.15 and To the temperature Figure provides the performance of are observed in the same range for the other on the the of thermal for all which due to the increase in the FIGURE temperature SCP temperature to Figure the ambient temperature be affected by air SCP is covered by it has the temperature data which air and it can be that at 0.15 from the the air temperature is most affected by the of the The higher and lower temperature data for the are recorded at and The and temperature range of the recorded points are shown in Table of air temperature for 0.15 2: model is used to air temperature at the distances from the SCP A to which is our model is The is on air temperature from to in Figure FIGURE Deep Learning results on air the data generated by deep which and for at the temperature and temperature, including about the air temperature and the recorded temperature of over the first which the performance of the SCP cooling effect in the few the data from the field for and the points and the data generated by the deep learning for conditions are compared with the model data FIGURE measurements were compared with the recorded data for were compared with the deep learning generated data deep the deep learning data and the cooling performance of the it can be that the SCP was to drop the air temperature in a compared with The average reduction was recorded by about The average air temperature was about which that the of temperature reduction in the data from the is to the of the data generated by the deep learning the of the research Figure The SCP air temperature reduction from to which was on an urban investigated the cooling impact of the SCP in a humid climate during the The performance of the SCP was at points located at varying distances from the The measurements were conducted in two In the first experimental measurements were temperature data for distances and conditions over the research team a deep learning model to the performance and data through the While the limited in this the deep learning to from this data to broader conditions was an essential of our Deep learning is a of learning that the use of with to various of data et al., 2023). Deep learning are traditional systems in numerous of our et al., research has on and and by The number of material makes experimental study and are and more are by and their et al., 2022; et al., is a model by the human and from to such as classification, and more 2017; et al., the data collection of our experimental several primarily due to These and which affected the accuracy and consistency of our temperature in conditions in the making it to maintain across all measurements. These the in field where environmental conditions can and impact the data collection the of data collection due to these conditions to maintain the and accuracy of our on the field the average air temperature reductions for points and were and respectively. The and ambient air temperatures were and respectively. this the performance of the results indicated that distance a significant temperature reduction effect compared to The findings of the first that the SCP a impact on temperatures. The maximum average reduction across the points was compared to the temperature of This that the performance in air temperature was approximately resulting in a drop of ambient air temperature by air temperature reductions from to for points and were approximately and respectively. The average air temperature was the points reduce the ambient air temperature by about for for for and for A performance than by about of the present some research studies have been conducted under the same climate with outdoor thermal and investigated that the temperature for the Cfa climate of during is and for the year is et al. concluded that the is °C on the the temperature during are between °C and °C, that the distances of 0.15 and reduce the air temperature to the outdoor thermal the outcomes of regarding the effect of and green walls on the of UHI & 2022; & 2018; et al., et al., 2020), our study a and for the most effective distance for these systems to reduce ambient temperatures. This represents a novel to our research the existing of Moreover, our an a deep learning model to the of our This utilizing data from experimental the of learning into our also provides an for data the of temperature reduction through SCP in a humid and for the primarily due to the of for buildings, particularly their and This effective urban heat and climate change mitigation at the According to the literature, the are environmental and human investigations various including on the thermal performance of in and Moreover, different plant is essential when evaluating the reduction in ambient air this the impact of green walls in the reduction of ambient air However, studies have shown the influence of green walls on indoor ambient temperature and human is the study by et al. which that the green wall significantly reduce wall temperatures and maintain indoor et al. investigated the thermal performance of green walls on indoor thermal study that green walls can indoor temperature and et al. conducted a study on the thermal performance of green walls compared to walls on the northern facade of a building in the humid climate of Rasht during the The results that the green wall significantly indoor temperature and relative the green wall indoor temperature by and relative humidity by the study due to building and plant and data collection for the was the research on only orientation of the building where the green wall was These areas for research and In while this research the significant potential in ambient temperatures and urban these findings be the of these these and more studies be essential in our of like plants and their in creating and urban studies, the findings of this research in several field measurements across urban are to the findings regarding the cooling performance of green it is to the impact of different of green walls on their cooling studies on the impact of such systems on indoor thermal study aims to green cooling effects in a humid climate. To this this research two such as experimental to data of temperature and humidity in different points in of the green including and an model was for data to the The of the plant was This research on the cooling performance of green walls in the orientation of the The findings a relatively significant reduction in ambient air temperatures at various distances from the plant The results that the green wall effectively air temperature, a reduction compared to a distances and were found to to temperature of approximately and respectively.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.