Shuhui Zhang

Dr. Shuhui Zhang


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
16 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SZShuhui Zhang
Shuhui Zhang
Yuke ZhouYuke Zhou
Yuke Zhou
YYYong Yu
Yong Yu
FLFeng Li
Feng Li
RZRuixin Zhang
Ruixin Zhang
WLWenlong Li
Wenlong Li
Understanding the driving mechanisms of vegetation development is critical for maintaining terrestrial ecosystem function in mountain areas, especially under the background of climate change. The Qinba Mountains (QBM), a critical north–south transition zone in China, is an environmentally fragile area that is vulnerable to climate change. It is essential to characterize how its ecological environment has changed. Currently, such a characterization remains unclear in the spatiotemporal patterns of the nonlinear effects and interactions between environmental factors and vegetation changes in the QBM. Here, we utilized the Normalized Difference Vegetation Index (NDVI), obtained from Google Earth Engine (GEE) platform, as an indicator of terrestrial ecosystem conditions. Then, we measured the spatiotemporal heterogeneity for vegetation variation in the QBM from 2003 to 2018. Specifically, the Geodetector method, a new geographically statistical method without linear assumptions, was employed to detect the interaction between vegetation and environmental driving factors. The results indicated that there is a trend of a general increase in vegetation growth amplitude (the average NDVI increased from 0.810 to 0.858). The areas with an NDVI greater than 0.8 are mainly distributed in the Qinling Mountains and the Daba Mountains, which account for more than 76.39% of the QBM area. For the entire region, the global Moran’s index of the NDVI is greater than 0.95, indicating that vegetation is highly concentrated in the spatial domain. The Geodetector identified that landform type was the primary factor in controlling vegetation changes, contributing 24.19% to the total variation, while the explanatory powers of the aridity index and the wetness index for vegetation changes were 22.49% and 21.47%, respectively. Furthermore, the interaction effects between any two factors outperformed the influence of a single environmental variable. The interaction between air temperature and the aridity index was the most significant element, contributing to 47.10% of the vegetation variation. These findings can not only improve our understanding in the interactive effects of environmental forces on vegetation change, but also be a valuable reference for ecosystem management in the QBM area, such as ecological conservation planning and the assessment of ecosystem functions.

2 October 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SHshan He
shan He
HSHuaiyong Shao
Huaiyong Shao
WXWei Xian
Wei Xian
SZShuhui Zhang
Shuhui Zhang
JZJialong Zhong
Jialong Zhong
Jiaguo QiJiaguo Qi
Jiaguo Qi
Hilly areas are important parts of the world’s landscape. A marginal phenomenon can be observed in some hilly areas, leading to serious land abandonment. Extracting the spatio-temporal distribution of abandoned land in such hilly areas can protect food security, improve people’s livelihoods, and serve as a tool for a rational land plan. However, mapping the distribution of abandoned land using a single type of remote sensing image is still challenging and problematic due to the fragmentation of such hilly areas and severe cloud pollution. In this study, a new approach by integrating Linear stretch (Ls), Maximum Value Composite (MVC), and Flexible Spatiotemporal DAta Fusion (FSDAF) was proposed to analyze the time-series changes and extract the spatial distribution of abandoned land. MOD09GA, MOD13Q1, and Sentinel-2 were selected as the basis of remote sensing images to fuse a monthly 10 m spatio-temporal data set. Three pieces of vegetation indices (VIs: ndvi, savi, ndwi) were utilized as the measures to identify the abandoned land. A multiple spatio-temporal scales sample database was established, and the Support Vector Machine (SVM) was used to extract abandoned land from cultivated land and woodland. The best extraction result with an overall accuracy of 88.1% was achieved by integrating Ls, MVC, and FSDAF, with the assistance of an SVM classifier. The fused VIs image set transcended the single source method (Sentinel-2) with greater accuracy by a margin of 10.8–23.6% for abandoned land extraction. On the other hand, VIs appeared to contribute positively to extract abandoned land from cultivated land and woodland. This study not only provides technical guidance for the quick acquirement of abandoned land distribution in hilly areas, but it also provides strong data support for the connection of targeted poverty alleviation to rural revitalization.

30 March 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
RZRuixin Zhang
Ruixin Zhang
Yuke ZhouYuke Zhou
Yuke Zhou
THTianyang Hu
Tianyang Hu
WSWenbin Sun
Wenbin Sun
SZShuhui Zhang
Shuhui Zhang
HWHAN WANG
HAN WANG
Vegetation phenology is a crucial biological indicator for monitoring changes in terrestrial ecosystems and global climate. Currently, there are limitations in using traditional vegetation indices for phenology monitoring (e.g., greenness saturation in high-density vegetation areas). Solar-induced chlorophyll fluorescence (SIF), a novel remote sensing product, has great potential in depicting seasonal vegetation dynamics across various regions with different vegetation covers and latitudes. In this study, based on the GOSIF and MODIS NDVI data from 2001 to 2020, we extracted vegetation phenological parameters in Northeastern China by using Double Logistic (D-L) fitting function and the dynamic threshold method. Then, we analyzed the discrepancy in phenological period and temporal trend derived from SIF and NDVI data at multiple spatiotemporal scales. Furthermore, we explored the response of vegetation phenology to climate change and the persistence of phenological trends (Hurst exponent) in Northeastern China. Generally, there is a significant difference in trends between SIF and NDVI, but with similar spatial patterns of phenology. However, the dates of key phenological parameters are distinct based on SIF and MODIS NDVI data. Specifically, the start of season (SOS) of SIF started later (about 10 days), and the end of season (EOS) ended earlier (about 36 days on average). In contrast, the fall attenuation of SIF showed a lag process compared to NDVI. This implies that the actual period of photosynthesis, that is, length of season (LOS), was shorter (by 46 days on average) than the greenness index. The position of peak (POP) is almost the same between them. The great difference in results from SIF and NDVI products indicated that the vegetation indexes seem to overestimate the time of vegetation photosynthesis in Northeastern China. The Hurst exponent identified that the future trend of SOS, EOS, and POP is dominated by weak inverse sustainability, indicating that the future trend may be opposite to the past. The future trend of LOSSIF and LOSNDVI are opposite; the former is dominated by weak inverse sustainability, and the latter is mainly weak positive sustainability. In addition, we speculate that the difference between SIF and NDVI phenology is closely related to their different responses to climate. The vegetation phenology estimated by SIF is mainly controlled by temperature, while NDVI is mainly controlled by precipitation and relative humidity. Different phenological periods based on SIF and NDVI showed inconsistent responses to pre-season climate. This may be the cause of the difference in the phenology of SIF and NDVI extraction. Our results imply that canopy structure-based vegetation indices overestimate the photosynthetic cycle, and the SIF product can better track the phenological changes. We conclude that the two data products provide a reference for monitoring the phenology of photosynthesis and vegetation greenness, and the results also have a certain significance for the response of plants to climate change.

6 March 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
SZShuhui Zhang
Shuhui Zhang
付李付全 李
付全 李
Yuke ZhouYuke Zhou
Yuke Zhou
ZHZiyuan Hu
Ziyuan Hu
RZruixin zhang
ruixin zhang
YZYali Zhang
Yali Zhang
An ecological footprint is a primary indicator in measuring the sustainability of regional development, especially in resource-based cities. Here, we built an ecological footprint-based framework to assess the sustainability for a resource-based city of Panzhihua, in China. In this framework, a suite of long-term ecological parameters (2000–2020), essentially including Net Primary Productivity (NPP), land cover, as well as social statistical data, was used as the input indices of a provincial hectare ecological footprint model. The model outputs are composed of the ecological footprint (EF), ecological footprint per capita (PEF), ecological capacity (EC), ecological capacity per capita (PEC), ecological deficit/surplus (ED/S), and per capita ecological deficit/surplus (PED/S). Then the sustainable development capability of the city was comprehensively evaluated using a suite of ecological indices, including the ecological pressure index (EPI), ecological footprint per ten thousand GDP (EFG), ecological sustainability index (ESI), and ecological coordination index (ECI). The study reveals that, from 2000–2020, (1) PEC and PED/S presented an increasing trend (0.2401 hm2/person and 2.1421 hm2/person, respectively), while PEF decreased by 1.9 hm2/person. In the case of the ecological deficit, fossil energy land and forest were the dominant land types in controlling the ecological footprint and ecological capacity, (2) EPI and EFG decreased by 6.6381 hm2/person and 2.2462 hm2/person, respectively, and ESI and ECI increased by 0.3436 hm2/person and 0.2897 hm2/person, respectively. These indices also reflect that the utilization rate of natural resources in Panzhihua City has been improved, with enhanced sustainability, as well as a decline in ecological pressure. This ecological footprint-based framework could work as a template for evaluating the sustainability of resource-based cities from positive and negative ecological footprint indices.

23 April 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MJMai Jingjing
Mai Jingjing
QFQisheng Feng
Qisheng Feng
SFShuai Fu
Shuai Fu
RWRuijing Wang
Ruijing Wang
SZShuhui Zhang
Shuhui Zhang
TLTiangang Liang
Tiangang Liang
Timely and accurate crop mapping is crucial for providing essential data support for agricultural production management. Reliable ground truth samples form the foundation for crop mapping using remote sensing imagery, a task that presents significant challenges in regions with limited sample availability. To address this issue, this study evaluates instance-based transfer learning methods, using the Hexi Corridor as a case study to explore crop mapping strategies in areas with scarce samples. High-confidence pixels from the United States Cropland Data Layer (CDL), along with high-density time series data derived from Sentinel-1, Sentinel-2, and Landsat-8 satellite imagery, as well as key vegetation indices, were selected as training samples for the source domain. Various algorithms, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and TrAdaBoost, were employed to transfer knowledge from the source domain to the target domain for crop type mapping. The results demonstrated that during the transfer learning process using only source domain data—without utilizing any target domain data—the overall classification accuracy reached 73.88%, with optimal accuracies for maize and alfalfa at 88.97% and 85.23%, respectively. As target domain data were gradually incorporated, the total accuracy for all models ranged from 0.77 to 0.92, with F1-scores ranging from 0.76 to 0.92, showing a consistent improvement in model performance. This study highlights the feasibility of employing transfer learning for crop mapping in the Hexi Corridor, demonstrating its potential to reduce labeling costs for target domain samples and providing a valuable reference for crop mapping in regions with limited sample availability.