Changes in grassland vegetation based on spatiotemporal variation in vegetation growth and spatial configuration dynamics of bare lands

Li, Xiaofan; Zhang, Na; Zhang, Anan; Tang, Jiakui; Li, Zhenyu; Nie, Zexu

doi:10.1016/j.ecoinf.2024.102473

Cited by 3 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to those in typical grassland areas, desert grassland resources are more vulnerable to climate change and human disturbance, and pasture degradation and desertification problems are becoming increasingly serious [ 6 ]. Grassland degradation is first manifested as a reduction in the fractional vegetation cover and number of plant species and expansion of the bare soil area, which directly affects the comprehensive utilization level of grassland resources [ 7 , 8 ]. It is very important to study and elucidate the growth status and change trend of vegetation communities in desert grassland for systematic analysis of grassland resource economic characteristics and rational development and utilization.…”

Section: Introductionmentioning

confidence: 99%

Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model

Jin,

Du,

et al. 2024

Sensors

View full text Add to dashboard Cite

Real-time and high-precision land cover classification is the foundation for efficient and quantitative research on grassland degradation using remote sensing techniques. In view of the shortcomings of manual surveying and satellite remote sensing, this study focuses on the identification and classification of grass species indicating grassland degradation. We constructed a UAV-based hyperspectral remote sensing system and collected field data in grassland areas. By applying artificial intelligence technology, we developed a 3D_RNet-O model based on convolutional neural networks, effectively addressing technical challenges in hyperspectral remote sensing identification and classification of grassland degradation indicators, such as low reflectance of vegetation, flat spectral curves, and sparse distribution. The results showed that the model achieved a classification accuracy of 99.05% by optimizing hyperparameter combinations based on improving residual block structures. The establishment of the UAV-based hyperspectral remote sensing system and the proposed 3D_RNet-O classification model provide possibilities for further research on low-altitude hyperspectral remote sensing in grassland ecology.

show abstract

Section: Introductionmentioning

confidence: 99%