Climate Change-based Urban Geographical Regions Planning: Sustainable Application Using Artificial Intelligence

From the level of individual creatures to that of ecosystems, where all species are components of intricate webs of interactions in the natural world, climate change can have a cascade impact. Though their full promise for mitigating climate change is still unrealised, artificial intelligence and machine learning are revolutionising scientific fields. Despite making up a small percentage of the planet’s surface, the enormous population of urban areas has a huge impact on climate change. Nevertheless, our understanding of the consequences of urbanisation on ecosystems and the climate is still lacking. This research proposes a novel technique in urban geographical region planning and climate change detection using a machine learning model. Here, the input has been collected as urban region geographical region changes analysis with climate change dataset and processed for noise removal and normalisation. Then this image has been segmented using a region-based graph cut active contour neural network, and features have been extracted using a deep transfer convolutional Gaussian model. Experimental analysis has been carried out in terms of detection accuracy, random precision, AUC, F1-score, and recall. The proposed model attained detection accuracy of 97%, random precision of 94%, AUC of 96%, F1-score of 95%, and recall of 98%.