The environmental problem occurring in metropolitan areas in which

 The urban heat island (UHI) effect is a common environmental problem occurring in metropolitan areas in which the air temperature is significantly higher than in suburban areas. The UHI effect also leads to a smoggy climate. The UHI effect mainly results from high-density infrastructures, which not only limit airflow but also emit heat stored from solar energy. In addition, the reduction of vegetation and wetlands further weakens the heat-releasing capacity of cities. It is urgent to mitigate the UHI effect, as it has become a huge threat to the environment and human health (Santamouris, 2007; Santamouris et al., 2011; Stathopoulou, 2008; Mirzaei and Haghighat, 2010).Previous studies indicated that the optical and thermal characteristics of urban structures have a strong relationship with urban climate and temperatures (Chen et al., 2009; White et al., 2010). In many cities, the roofs and pavements comprise about 60% of the total urban area, with roofs contributing about 20–25% and pavements contributing about 40% (Akbari et al., 2003). Cantatindicated that the reflectance of Paris is 16% lower than the surrounding suburban district (Cantat, 1989). Another study claimed that the increase of the solar energy absorption in urban areas is affected by the urban geometrical structures (Aida, 1982; Aida and Gotoh, 1982). Cool pavement is an effective technology to solve the UHI problem. The primary three types of cool pavements are (1) light color aggregates pavement, (2) permeable pavement, and (3) solar-reflective coating pavement. The albedo of normal asphalt pavement is only about 5%. By using white or light color aggregates, the albedo can be increased to about 30% (Doulos et al., 2004). Recent case study results from Portland State University (Oregon, USA) show that if you increase the albedo of the pavement in a bare courtyard from 37% (black) to 91% (white), the mean radiant temperature will increase 2.9 0C, but the air temperature will decrease 1.3 0C (Taleghani, 2014). Cotana et al. (2014) believes that using high solar reflective surfaces is an effective way to mitigate the UHI problem and reduce greenhouse gas emission in urban areas.    Estimating solar radiation gains great attention for researchers in the field of energy. Computer Science, via the (Artificial) Neural Networks (ANN) technique, introduced many ANN models for performing the estimation for either short-term period or a long-term one, as in (Marzo, A. et al,2017) and (Rehman, S. & Mohandes, M., 2008). In china (Ling Z. et al, 2016), for instance, an ANN model-based system is developed for estimating the solar radiation for a long-term period at several sites. Different parameters, collected from weather stations are considered in building the optimal ANN network, namely, humidity, min/max and average temperature, sunshine duration, air and water pressure and the speed of winds. The produced ANN model is evaluated against some empirical models, called IBC and IA–P models. The PB Learning algorithm is used for training the ANN model. Radiation data were collected from different radiation stations at south east China. The results of the estimation systems show a good performance in estimating solar radiation for long-periods (Ling Z. et al, 2016).Additionally, in Saudi Arabia (Abha city), an Artificial Neural Network (ANN) method is applied to estimate the solar radiation for the future (Rehman, S. & Mohandes, M., 2008). Air-temperature and related humidity data between the period 1998 and 2002 is used to train the neural network model. Three data sets are used for training the model and produce the solar radiation as output, namely, a data set that includes the maximum daily air-temperature, a data set that include the mean of daily air-temperature, as well as a data set of the mean of daily air-temperature and its related humidity. The trained ANN model using the mean of daily temperature with relative humidity shows better performance and results than the other two cases.The aim of this project is to develop computational models using Genetic Algorithms (GA) and simulating their results to find the optimal quantities of chemical materials and their reflectivity. The generated results will be applied in the domain of material engineering for manufacturing a special kind of a sun heat reflective paints and coatings using different polymeric particles with a paint carrier and other chemical compounds in our procedures depending on the software algorithm with climate parameters. In order to get a further improve of the thermal reflective paints and coatings with prevent more than 90% of the sun heat and has a low absorption and high diffuse reflection and suit our climate in the Kingdom.