Search

• Machine learning has great potential for assessing vegetation restoration and greenness. • RFR model using meteorological factors explained 80% of NDVI variation • Climate and human activities affect greening in China's ecological engineering zones • Human activity was the most important factor associated with NDVI increase A series of policies and laws have been implemented to address climate change impacts in China since the 1980s. One of the most notable policies is ecological restoration engineering. However, there are many environmental factors that affect vegetation in the ecological restoration engineering zones. The relationships among different factors cannot be explained well by traditional statistical methods due to the existence of hidden non-linear features. Moreover, it is difficult to adopt threshold methods to accurately define vegetation areas fully, or to quantitatively analyze and assess the effects of climate factors and human activities on vegetation changes. The objective of this study was to determine vegetation area and distribution using Landsat TM/ETM/OLI images combined with a support vector machine (SVM) classification model. We analyzed the dynamic characteristics of vegetation area and greenness (NDVI, Normalized Difference Vegetation Index) in China's ecological restoration engineering zones from 1990 to 2015. Based on random forest regression (RFR) with a residual analysis method, the contributions of meteorological factors and human activities to vegetation greenness changes were quantitatively evaluated. Vegetation area and NDVI changed significantly in the study areas, increasing by more than 50% and 40%, respectively, from 1990 to 2015. Temperature, sunshine hours, and precipitation impacted vegetation greenness, which caused NDVI fluctuations in specific years. However, the NDVI increase was difficult to explain fully with meteorological factors. Using cross-validation, we predicted about 80% of the observed NDVI variation occurring from 1984 to 1994. Nine meteorological factors were related to vegetation growth, of which the average temperature, minimum temperature, maximum temperature, and average relative humidity were most critical. The combined effect of the nine climatic factors contributed less to NDVI increase than human activities. Human activity was the most important factor associated with NDVI increase, with contributions of more than 100% in most study areas. Human activities derived from national or local policies had large impacts on vegetation changes. The methods and results of this study can help to understand vegetation changes observed in ecological zones and provide guidance for evaluating ecological restoration policies. [ABSTRACT FROM AUTHOR]

• A decoupled relationship between water storage and vegetation was found under ER. • Widespread ER-driven green up was observed concurrent with large-scale water loss. • ER played the dominant role in freshwater resource loss in YRB among all factors. • ER with more investment and intense land-cover change caused higher water deficit. • Water conservation should be considered in the design of large-scale ER programs. China has implemented some of the world's most ambitious ecological restoration (ER) programs over the past two decades. These large-scale multi-billion-dollar projects have achieved widespread greening across the country. However, the impacts of different ER-driven land cover modifications on total water resources remain largely unknown, particularly over areas characterized by complex environments of coupled human and natural systems. Here we quantified ecohydrological impacts of multiple ER programs applied over various parts of China's Yellow River Basin (YRB), with their lumped effects being partitioned into individual ones. ER-related drivers were disentangled, leading in individual attribution of inter-annual climatic variability and agricultural activity with cross-sensor satellite observations and statistical modelling. Our results showed an ecohydrological decoupling of water storage and vegetation greenness attributed to ER programs. Increases in natural land cover types (e.g. forest and grassland) were found at the expense of human intensive land use, such as farmland, with the combined changes resulting in a concurrent dramatic water storage loss of 3.70 billion tons/year from 2002 to 2021. ER was the dominant driver of water loss (>66 %) among all factors considered, commensurate with areal land-cover change and ER program cost. The entire basin was divided into two regions with opposite water trends by the ER activities with different restoration strategies. This study's framework is applicable to substantial part of the globe like YRB and is encouraged to be applied for more wholistic ER impact evaluations. [ABSTRACT FROM AUTHOR]

[Display omitted] • Building a new assessment BPSR framework to evaluate alpine pastoral ecosystem health. • Entropy method was applied to determine the weights for indicators. • Spatiotemporal dynamics of ecosystem health in Gannan pastoral were analyzed comprehensively. • The spatial distribution of ecosystem health in Gannan pastoral decreased from southwest to northeast. Ecosystem health is the goal of eco-environmental management, and its assessment is necessary for improving regional ecological environments and promoting regional sustainable development. However, previous studies on regional ecosystem health assessment have mainly concentrated on rapidly developing urbanized areas, with very few having been conducted on alpine pastoral regions. Taking the Gannan alpine pastoral region of China as the study area, and based on remote-sensing and GIS technologies, we used entropy methods to calculate the relative weights of several indicators to quantify the uncertainty in the data processing so that the accuracy of the results of the ecosystem health evaluation could be improved. In this study, a new basic-pressure-state-response assessment framework for alpine pastoral ecosystem health assessment is proposed, based on the pressure-state-response. It was found that the levels of ecosystem health of the Gannan pastoral had a spatial distribution pattern that decreased from southwest to northeast, from 2000 to 2015. Notably, the areas of the well and weak health showed a decreasing trend, with more regions tending toward ordinary levels. Among all the assessing indicators, the average value of the pressure indicator was the greatest, with the basic indicator value being the lowest. Our assessment results could be used as a guide for eco-environment managers tasked with taking effective measures to improve the status of the ecosystem health in alpine pastoral regions. [ABSTRACT FROM AUTHOR]