Simulation of the spatial pattern of scenic spots combining optimal scale and deep learning

With the development of deep learning and big data technology, artificial neural network methods are used to simulate new areas with high potential develop tourist attractions. They break through limitation lifespan domestic attractions improve credibility results caused by sample size scale effect. This study applied for 906 scenic spots in Northwest China a geographic detector model technology explore dominant factors explaining their spatial distribution under optimal research as The main conclusions this were follows. 1) more reliable 150 km × km. 2) leading affecting normalized difference vegetation index (NDVI), distance from city, population, transportation accessibility. 3) identified that highly suitable attractions, showed regional maturity either natural environment or social development. can act reference further exploration application intelligence spots.