Lu Wang

Dr. Lu Wang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Boyi LiangBoyi Liang
Boyi Liang
Hongyan LiuHongyan Liu
Hongyan Liu
ECElizabeth Cressey
Elizabeth Cressey
CXChongyang Xu
Chongyang Xu
SLShi Liang
Shi Liang
JWJia Wang
Jia Wang
As more machine learning and deep learning models are applied in studying the quantitative relationship between the climate and terrestrial vegetation growth, the uncertainty of these advanced models requires clarification. Partial dependence plots (PDPs) are one of the most widely used methods to estimate the marginal effect of independent variables on the predicted outcome of a machine learning model, and it is regarded as the main basis for conclusions in relevant research. As more controversies regarding the reliability of the results of the PDPs emerge, the uncertainty of the PDPs remains unclear. In this paper, we experiment with real, remote sensing data to systematically analyze the uncertainty of partial dependence relationships between four climate variables (temperature, rainfall, radiation, and windspeed) and vegetation growth, with one conventional linear model and six machine learning models. We tested the uncertainty of the PDP curves across different machine learning models from three aspects: variation, whole linear trends, and the trait of change points. Results show that the PDP of the dominant climate factor (mean air temperature) and vegetation growth parameter (indicated by the normalized difference vegetation index, NDVI) has the smallest relative variation and the whole linear trend of the PDP was comparatively stable across the different models. The mean relative variation of change points across the partial dependence curves of the non-dominant climate factors (i.e., radiation, windspeed, and rainfall) and vegetation growth ranged from 8.96% to 23.8%, respectively, which was much higher than those of the dominant climate factor and vegetation growth. Lastly, the model used for creating the PDP, rather than the relative importance of these climate factors, determines the fluctuation of the PDP output of these climate variables and vegetation growth. These findings have significant implications for using remote sensing data and machine learning models to investigate the quantitative relationships between the climate and terrestrial vegetation.

20 February 2021 in Forests
Verified
Journal Article
Open access
PDF file
RLRuoshi Liu
Ruoshi Liu
Yi SongYi Song
Yi Song
Yu LiuYu Liu
Yu Liu
XLXuxiang Li
Xuxiang Li
HSHuiming Song
Huiming Song
LWLu Wang
Lu Wang
Vegetation coverage is very important in terrestrial ecosystems and climate systems. However, the observational record of the normalized difference vegetation index (NDVI), which started in the 1980s when satellites became widely used, is too short to investigate the history of variation in vegetation coverage beyond the modern observation period. Here, we present a 189 y vegetation coverage series based on a total of 349 Mongolian pine (Pinus sylvestris var. mongolica Litv) cores from seven locations from the central–western Da Hinggan Mountains (CW–DHM), northeastern China. We found a significant relationship between tree-ring width and the regional cumulative normalized difference vegetation index (CNDVI). The correlation between the ring-width chronology and the regional June–July CNDVI (CNDVIJJ) was significant, with r = 0.68 (n = 32, p < 0.001) and an explained variance of 45.8% (44.0% after the adjustment for the loss of the degree of freedom). On this basis, we designed a transfer function to reconstruct the CNDVIJJ for the CW–DHM region from 1825 to 2013 CE (Common Era). During the last 189 years, there were 28 years with high CNDVIJJ values, and another 28 years with low values. We also observed CNDVIJJ fluctuations at the inter-annual and decadal time scales, including eight low value periods and nine high value periods. Based on our analysis, the variation in CNDVI is associated with climatic factors, such as temperature, precipitation and the Palmer Drought Severity Index (PDSI), which combines both temperature and precipitation. From 1950 to 2002 CE, the CNDVI showed a noticeable decreasing trend in the CW–DHM region, whereas after 2003 CE, the CNDVI exhibited an apparent increase, which has also been observed in southern Central Siberia, eastern Mongolia and northeastern and eastern China, indicating that the CNDVI change in the CW–DHM is related to climate change in the local region and in some parts of Asia.