HEAT STRESS MODELING USING NEURAL NETWORKS TECHNIQUE

Rising temperature especially in summer is currently a hot debate. Scientists around the world have raised concerns about Heat Stress Assessment (HSA). It depends on urban geometry, building materials, greenery, environmental factor of region, psychological and behavioral factors inhabitants. Effective accurate heat stress forecasts are useful for managing thermal comfort area. A widely used technique artificial intelligence (AI), neural networks, which can be trained weather variables. In this study, five most important meteorological parameters such as air temperature, global radiation, relative humidity, surface wind speed considered HSA. System dynamic approach new version Gated Recurrent Unit (GRU) method prediction mean radiant predicted vote physiological equivalent temperature. GRU promising technology, results with higher accuracy obtained from algorithm. The model validated output reference software named Rayman. Django's graphical user interface was created allows users to select range scales based their perception age factor, local adaptability, habit tolerating events. also gives warning by color code level discomfort helps them schedule manage outdoor activities. Future work consists coupling greenery analyze impact estimation stress.