Landscape ecological design using Elman neural networks and improved Energy Valley optimizer algorithm

Landscape ecology is a multidisciplinary field that examines the connections between spatial patterns and ecological processes. The optimization of spatial patterns is a crucial aspect of landscape ecological design, with the goal of enhancing both the ecological functions and aesthetic values of the landscape. However, achieving spatial pattern optimization is a complex and nonlinear problem that necessitates the use of advanced computational methods. In this study, an innovative design scheme has been presented for landscape construction of ecology and optimization of spatial pattern, utilizing the Elman neural networks and an enhanced version of the Energy Valley optimizer, which is a swarm intelligence algorithm. Visual image processing technique has been employed for analyzing and extracting the characteristics of the space environment of landscape ecology and using visual models of reconstruction for the design of optimization of spatial pattern and landscape construction of ecology. Subsequently, Elman neural networks have been utilized to learn the relationships between the visual features and the ecological indicators, and an improved Energy Valley optimizer has been employed to search for optimal spatial patterns that maximize both ecological functions and aesthetic values. Through simulation tests and analysis, the efficiency of our suggested model has been displayed. The proposed model's efficiency is shown through simulations, revealing a 12% enhancement in ecological functions and a 9% boost in aesthetic values when compared to conventional methods. The outcomes highlight the generation of top-notch landscape ecological spatial patterns that fulfill both ecological and aesthetic standards. Experimental findings demonstrate superior performance in iteration count and running time compared to GA and GA/NN techniques. The algorithm attains a 9.34% higher accuracy than traditional Improved Energy Valley optimizer. The results indicate that the proposed scheme is capable of generating high-quality landscape ecological spatial patterns that meet the criteria for both ecological and aesthetic considerations.