Landscape protection and intelligent application based on AI technology

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

The creation of contemporary cities relies heavily on modern landscape protection, which is increasingly informed by AI, thereby enhancing both the natural environment and the perception of cities. Human comprehension of artificial intelligence is growing as a result of society’s and technology’s ongoing advancements, and intelligent technology is progressively permeating every facet of daily life. It will be easier to utilise network means for landscape protection because media technology can implement rich design structures and offer a wide range of design features. Thus, to meet people’s demands for diversification in contemporary urban gardening construction, this study thoroughly examines the current state and issues of landscape design and attempts to investigate efficient ways to apply artificial intelligence technology to landscape design, thereby encouraging the integration of landscape design and AI design. In addition to encouraging creativity and optimisation in landscape design, artificial intelligence successfully boosts the efficiency of contemporary landscape design while guaranteeing its quality. From 2012 to 2024, at five-year intervals, we calculated the landscape ecological risk to 510 of China’s nature reserves across levels, climate zones, and ecosystem types using the Landscape Ecological Risk Index. We also investigated the effects of climate change and human activity on the temporal variation and spatial heterogeneity of landscape ecological risk in China’s nature reserves. According to our findings, there has been a general decline in the environmental danger to China’s nature reserves over the past thirty years, with the most noticeable drop occurring between 2012 and 2024. With a maximum accuracy of 97.2%, a precision of 96.2%, a recall of 96.8%, and an F1-score of 97.1%, the proposed fmodel is the most effective. The recommended technique performs better at minimising absolute errors than RMSE and MAE. However, whilst the landscape ecological risk to other ecosystem types has declined, the landscape ecological risk to coastline nature reserves has grown.

Article activity feed