Simulation of Sentinel-2 and Landsat Data with ST-Vision Net

Escalating urban growth aligns with rising constraints on cities due to rapid and unplanned urbanization by expeditious development of urban metropolises. It is necessary for urban planners and administrators to have a prior understanding of the connections and interactions between various elements of the urban environment to construct environmentally suitable urban and regional plans. This study proposes a unique insight of Sentinel-2 satellite and Landsat pictography on Google Cloud AI with convolutional neural networks (CNNs) and recurrent neural network (RNN) hybrid model ST-Vision Net (spatial and temporal vision network) for multispectral AI analysis and effective urban planning particularly analyzing urban heat island effect, which provides perfect exposure to all urban indices within the framework of Industry 5.0. A variety of datasets are made available by combining Sentinel-2 and Landsat-8 missions to assist our research. Being the intersection of environmental consequences and urbanization, urban heat islands (UHIs) provide a connecting framework for smart urban planning, aligning with global sustainable development. It combines ground-based IoT sensor data with satellite imagery to enhance the accuracy of UHI predictions, helping in developing mitigation strategies, which are crucial to address issues such as climate change, urban effects, green roofs, and natural vegetation.