Coastal zone wetland ecological safety pattern optimization method and device based on machine learning

Abstract

The invention provides a coastal zone wetland ecological safety pattern optimization method and device based on machine learning, and the method comprises the steps: employing a support vector machineand a random forest method to carry out the supervised classification extraction of a pixel scale of a coastal zone wetland of a target coastal zone, so as to obtain a coastal zone wetland extractionresult; performing shape recognition on each wetland patch in the coastal zone wetland extraction result by adopting a patch shape recognition algorithm based on an information theory; and comparingecological disturbance degree differences of wetland patches with different shapes by utilizing variance analysis to obtain an optimal coastal zone wetland landscape type with statistical significance, thereby obtaining a landscape ecological safety pattern mode capable of maximizing ecological toughness. The method and deice can assist in guiding coastal zone wetland landscape pattern optimization, and landscape planning thought and theoretical basis are provided.

Description

technical field [0001] The invention relates to the field of marine ecology, in particular to a method and device for optimizing the ecological security pattern of coastal wetlands based on machine learning. Background technique [0002] As a unique ecosystem formed by the interaction between land and sea, coastal wetlands have important ecological functions and values, and can provide various ecosystem service values ​​such as carbon sequestration, biodiversity protection, wind and wave protection, and recreation. The ecological security status of coastal wetlands will directly affect the security of the connected terrestrial ecosystems and marine ecosystems, which is an important basis for realizing regional sustainable development. In recent decades, due to the impact of human social and economic activities, the increase of urban population and the rapid expansion of cities have resulted in varying degrees of damage or degradation of wetland resources in terms of quantity...

AI Technical Summary

Problems solved by technology

However, manual extraction of coastlines is time-consuming and laborious, and the extraction accuracy is affected by subjective factors and difficult to unify, so it is difficult to use this method for large-scale coastal wetland extraction.

[0007] 2. It is difficult to avoid human-subjective factors in the process of optimizing the landscape ecological security pattern, and it is impossible to achieve fully automated optimization

For example, in the identification of landscape corridors, existing methods often use the minimum cumulative resistance model, which requires artificially setting the weight of resistance surfaces; in addition, existing methods often use buffer analysis in demarcating research areas or species dispersal areas. The setting of the radius often relies on the qualitative and subjective judgment of the staff, lacking quantitative basis

[0008] 3. Lack of consideration of ecological resilience

When optimizing landscape patterns, the existing methods mostly consider the horizontal migration and diffusion of species, rarely introduce the concept of ecological resilience into the optimization of landscape patterns, and cannot fully understand and exert the resistance and resilience of the ecosystem itself to external disturbances.

Images