PDF
Full
Outline
Grassland health evaluation is a key technical means to measure the structure and function of grassland ecosystems and to support ecological security and sustainable resource utilization. However, traditional evaluation methods have limitations such as strong subjectivity and insufficient spatio−temporal continuity in index system construction and large−scale dynamic monitoring. This paper proposes an intelligent evaluation method for grassland health based on multi−source spatio−temporal data and machine learning, and constructs an intelligent research framework covering "data collection—feature extraction—index construction—health evaluation—management decision−making." By integrating field sampling data with multi−source remote sensing data, this method introduces expert knowledge to construct the Grassland Health Index (GHI) and utilizes machine learning models to achieve pixel−scale quantitative inversion and dynamic monitoring of long−term sequence grassland health conditions. To verify the effectiveness of this method, Ningxia, which has implemented region−wide grazing exclusion for nearly 20 years, was taken as a typical application scenario. The results show that the machine learning method significantly improved the accuracy of various evaluation indicators, with the R2 of spatial simulation for grass yield reaching 0.88. From 2012 to 2022, the grasslands in Ningxia were generally at a healthy level (GHI>80), remained stable overall, and the ecosystem showed a recovery trend. There was significant spatial heterogeneity in grassland health; due to differences in land use patterns and precipitation gradients in local areas, degradation risks still require continuous attention. The intelligent evaluation method proposed in this study has good operability and extensibility, providing technical support for grassland ecological health diagnosis, degradation risk early warning, and sustainable management in different regions, as well as providing a scientific basis for the optimization of grassland ecological subsidy policies and resource security decision−making.
PDF
235
120
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
