Assessing the effects of climate and human activity on vegetation change in Northern China

Fractional vegetation cover (FVC) has changed significantly under various disturbances over northern China in recent decades. This research examines the dynamics of FVC and how it is affected by climate and human activity during the period of 1990-2018 in northern China. The effects of climate change (i.e., temperature, precipitation, solar radiation, and soil moisture) and human activity (socioeconomic data and land use) on vegetation coverage change in northern China from 1990 to 2018 were quantified using the Sen + Mann-Kendall test, partial correlation analysis, and structural equation modelling (SEM) methods. The findings of this research indicate the following: (1) From 1990 to 2018, the overall trend in FVC in northern China was increased. The areas with obvious increases were mainly situated on the northern slope of Tianshan Mountains, Xinjiang, the Loess Plateau, the Northeast China Plain, and the Sanjiang Plain, while the areas with distinct degradation were located in the Inner Mongolia Plateau, the Changbai Mountain and the eastern part of north China. (2) In the past 29 years, the FVC in northern China has been mainly affected by precipitation and soil moisture. (3) Based on structural equation modelling, we discovered that certain variables impacted the main factors influencing the amount of FVC in northern China. Human activity has had a larger impact on FVC than climate change. Our findings can accelerate the comprehension of vegetation dynamics and their underlying mechanisms and provide a theoretical basis for regional ecological environmental protection.

Spatial and temporal variations of vegetation cover and its influencing factors in Shandong Province based on GEE

Economic development has rapidly progressed since the implementation of reform and opening up policies, posing significant challenges to sustainable development, especially to vegetation, which plays a crucial role in maintaining ecosystem service functions and promoting green low-carbon transformations. In this study, we estimated the fractional vegetation cover (FVC) in Shandong Province from 2000 to 2020 using the Google Earth Engine (GEE) platform. The spatial and temporal changes in FVC were analyzed using gravity center migration analysis, trend analysis, and geographic detector, and the vegetation changes of different land use types were analyzed to reveal the internal driving mechanism of FVC changes. Our results indicate that vegetation cover in Shandong Province was in good condition during the period 2000 to 2020. The high vegetation cover classes dominated, and overall changes were relatively small, with the center of gravity of vegetation cover generally shifting towards the southwest. Land use type, soil type, population density, and GDP factors had the most significant impact on vegetation cover change in Shandong Province. The interaction of these factors enhanced the effect on vegetation cover change, with land use type and soil type having the highest degree of influence. The observational results of this study can provide data support for the policy makers to formulate new ecological restoration strategies, and the findings would help facilitate the sustainability management of regional ecosystem and natural resource planning.

Spatial and temporal variation of vegetation cover in the main mining area of Qibaoshan Town, China: Potential impacts from mining damage, solid waste discharge and land reclamation

The increasing frequency of mining activities in the world has led to many environmental pollution problems, such as mine wastewater discharge, mine solid waste dumps, and mine dust dispersion. These problems have negative implications for the environment and the public health of people living nearby the mining areas. Despite this, there are few methods to determine the state of mine pollution on a regional scale. Therefore, we applied remote sensing technologies to assess the mine pollution situation, especially the mine solid waste pollution, of a mining area, taking Qibaoshan Town, Liuyang City, Hunan Province, China, as an example. In our research, we have calculated the vegetation cover change of the Qibaoshan Town over the years (2000-2020), charted the vegetation coverage grade maps, and analysed the tendency of vegetation cover changes, to infer the mine pollution situation, the progress of pollution treatment and the efforts made by the local government and the mines on mine pollution disposal and the land reclamation. Additionally, mining damage can bring about geological hazards such as surface subsidence leading to vegetation destruction, while mining solid waste pollution and discharge can occupy a large amount of land and thus lead to vegetation reduction. As a result, this method of calculating FVC changes in a mining area is particularly suitable for assessing the extent of mining damage, the status of solid waste pollution and discharge, and the progress of land reclamation. In the abstract, we claim that this short communication article serves as a guide to start a conversation, and encourages experts and scholars to engage in this area of research.

Assessment of vegetation change on the Mongolian Plateau over three decades using different remote sensing products

As a major component of temperate steppes in the Eurasian continent, the Mongolian Plateau (MP) plays a pivotal role in the East Asian and global carbon cycles. This paper describes the use of five remote sensing indices derived from satellite data to characterize vegetation cover on MP, namely: gross primary production (GPP), net primary production (NPP), normalized difference vegetation index (NDVI), leaf area index (LAI) and fractional vegetation cover (FVC). It is found that GPP, NPP, and NDVI exhibit increasing trends, whereas LAI and FVC present decreasing trends on the MP since 1982. The different indices highlight discrepancies in the spatial pattern of vegetation growth, with the greatest increase in the southeast of MP. Only 3.4% of the total land area of MP exhibited consistent trends in the indices (0.1% degradation and 3.3% growth, P < 0.01), with the synchronous change of both LAI and NPP exhibiting higher consistency than that of raw NDVI and NPP. Understanding of the characteristics and status of vegetation change on the MP has far-reaching implications for its ecological protection management, and climate change mitigation.

Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features

BACKGROUND

Fractional vegetation cover (FVC) is an important basic parameter for the quantitative monitoring of the alpine grassland ecosystem on the Qinghai-Tibetan Plateau. Based on unmanned aerial vehicle (UAV) acquisition of measured data and matching it with satellite remote sensing images at the pixel scale, the proper selection of driving data and inversion algorithms can be determined and is crucial for generating high-precision alpine grassland FVC products.

METHODS

This study presents estimations of alpine grassland FVC using optimized algorithms and multi-dimensional features. The multi-dimensional feature set (using original spectral bands, 22 vegetation indices, and topographical factors) was constructed from many sources of information, then the optimal feature subset was determined based on different feature selection algorithms as the driving data for optimized machine learning algorithms. Finally, the inversion accuracy, sensitivity to sample size, and computational efficiency of the four machine learning algorithms were evaluated.

RESULTS

(1) The random forest (RF) algorithm (R2: 0.861, RMSE: 9.5%) performed the best for FVC inversion among the four machine learning algorithms driven by the four typical vegetation indices. (2) Compared with the four typical vegetation indices, using multi-dimensional feature sets as driving data obviously improved the FVC inversion accuracy of the four machine learning algorithms (R2 of the RF algorithm increased to 0.890). (3) Among the three variable selection algorithms (Boruta, sequential forward selection [SFS], and permutation importance-recursive feature elimination [PI-RFE]), the constructed PI-RFE feature selection algorithm had the best dimensionality reduction effect on the multi-dimensional feature set. (4) The hyper-parameter optimization of the machine learning algorithms and feature selection of the multi-dimensional feature set further improved FVC inversion accuracy (R2: 0.917 and RMSE: 7.9% in the optimized RF algorithm).

CONCLUSION

This study provides a highly precise, optimized algorithm with an optimal multi-dimensional feature set for FVC inversion, which is vital for the quantitative monitoring of the ecological environment of alpine grassland.