Yunjie Shi

Prof. Yunjie Shi

orcid

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
4 December 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JGJianwei Geng
Jianwei Geng
HLHengpeng Li
Hengpeng Li
WLWenfei Luan
Wenfei Luan
YSYunjie Shi
Yunjie Shi
JPJiaping Pang
Jiaping Pang
WZWANGSHOU ZHANG
WANGSHOU ZHANG
The tea plant (Camellia sinensis), as a major, global cash crop providing beverages, is facing major challenges from droughts and water shortages due to climate change. The accurate estimation of the actual evapotranspiration (ETa) of tea plants is essential for improving the water management and crop health of tea plantations. However, an accurate quantification of tea plantations’ ETa is lacking due to the complex and non-linear process that is difficult to measure and estimate accurately. Ensemble learning (EL) is a promising potential algorithm for accurate evapotranspiration prediction, which solves this complexity through the new field of machine learning. In this study, we investigated the potential of three EL algorithms—random forest (RF), bagging, and adaptive boosting (Ad)—for predicting the daily ETa of tea plants, which were then compared with the commonly used k-nearest neighbor (KNN), support vector machine (SVM), and multilayer perceptron (MLP) algorithms, and the experimental model. We used 36 estimation models with six scenarios from available meteorological and evapotranspiration data collected from tea plantations over a period of 12 years (2010–2021). The results show that the combination of Rn (net radiation), Tmean (mean air temperature), and RH (relative humidity) achieved reasonable precision in assessing the daily ETa of tea plantations in the absence of climatic datasets. Compared with other advanced models, the RF model demonstrated superior performance (root mean square error (RMSE): 0.41–0.56 mm day−1, mean absolute error (MAE): 0.32–0.42 mm day−1, R2: 0.84–0.91) in predicting the daily ETa of tea plantations, except in Scenario 6, followed by the bagging, SVM, KNN, Ad, and MLP algorithms. In addition, the RF and bagging models exhibited the highest steadiness with low RMSE values increasing (−15.3~+18.5%) in the validation phase over the testing phase. Considering the high prediction accuracy and stability of the studied models, the RF and bagging models can be recommended for estimating the daily ETa estimation of tea plantations. The importance analysis from the studied models demonstrated that the Rn and Tmean are the most critical influential variables that affect the observed and predicted daily ETa dynamics of tea plantations.

29 December 2023 in Journal of Cleaner Production
Verified
Journal Article
Closed access
YSYunjie Shi
Yunjie Shi
HLHengpeng Li
Hengpeng Li
AAAskar Akida
Askar Akida
JGJianwei Geng
Jianwei Geng
WZWANGSHOU ZHANG
WANGSHOU ZHANG
JPJiaping Pang
Jiaping Pang

17 January 2024 in Forests
Verified
Journal Article
Open access
PDF file
JGJianwei Geng
Jianwei Geng
HLHengpeng Li
Hengpeng Li
YSYunjie Shi
Yunjie Shi
JPJiaping Pang
Jiaping Pang
YSYuyang Shao
Yuyang Shao
The rapid expansion of tea plantations (Camellia sinensis), which replace local natural forests, decreases the water conservation function in the headwater region and threatens regional water security. However, studies focusing on the comprehensive evaluation and improvement of the water conservation function of natural forests and tea plantations are lacking. In this study, we developed a comprehensive evaluation method for the water conservation function by investigating, monitoring, and conducting process model simulations of 221 tea plantation and natural forest (bamboo forest) samples obtained in the field. We also quantified the trade-off between water conservation and carbon sequestration. The results showed that the tea plantations had lower annual water conservation than the bamboo forests. Slope was the most critical influential variable affecting water conservation in tea plantations. Strict control should be exercised in the development of steep slopes above 20° for tea plantations, to enhance the regional water conservation capacity. Water conservation in bamboo forests increased to the maximum level at a planting density (SD) of approximately 2500–2700 tree/ha and then decreased quickly. The optimal SD values of bamboo forests were 2500, 2600, and 2650 trees/ha at slopes of 10°, 15°, and 20°, respectively, which can maintain higher water conservation and adequate carbon sequestration. Overall, water conservation and carbon sequestration increased by approximately 22.6% and 13.7%, respectively, compared with the average values for bamboo forests. However, at slopes >20°, a strong trade-off was observed between water conservation and carbon sequestration, and competing ecosystem services accompanied those, which were hard to balance and which resulted here in disproportionate water conservation at the cost of carbon sequestration loss.

7 August 2024 in Land
Verified
Journal Article
Open access
PDF file
YSYunjie Shi
Yunjie Shi
HLHengpeng Li
Hengpeng Li
JGJianwei Geng
Jianwei Geng
AAAkida Askar
Akida Askar
ZZZhongjing Zhao
Zhongjing Zhao
YSYuyang Shao
Yuyang Shao
Amid unprecedented challenges to protect arable land, China’s permanent capital farmland (PCF) has played a crucial role in grain production. However, a clear legal and physical boundary between PCF and arable land seems to be unable to stop the spread of non-grain production. To address it, an analysis framework for PCF non-grain production was developed to examine the state and drivers of village-scale PCF non-grain production based on the logical relationship between PCF and arable land in the rapid urbanization of Liyang. The results suggested that PCF comprised approximately 70% arable land and 30% adjustable land. Meanwhile, forest land and aquaculture ponds occupied over 25% of PCF, while nearly 20% of PCF is unsuitable for the resumption of crop cultivation. The transition state (scenario SR) offered a realistic representation of PCF non-grain production, with an average non-grain production of 48.88%. This is 14.00% lower than the current state (scenario SD) and 9.65% higher than the future state (scenario ST). Furthermore, PCF area and agricultural income per capita significantly encouraged PCF non-grain production, with explanatory powers of 51.60% and 42.40%, respectively. In contrast, urbanization rate (with an explanatory power of 35.30%) significantly discouraged it. Therefore, this paper proposed PCF redefinition, flexible PCF, and diversified economic incentives to mitigate PCF non-grain production at the village scale.

2 January 2021 in Remote Sensing Letters
Verified
Journal Article
Closed access
WWWenchun Wu
Wenchun Wu
YSYunjie Shi
Yunjie Shi
KCkui cai
kui cai
KLKeyu Li
Keyu Li
LCLhaba Cering
Lhaba Cering
ZGZiling Gong
Ziling Gong
The Qomolangma National Nature Reserve (QNNR) has complex geomorphological characteristics of the high altitude Tibetan Plateau and aunique plateau wetland environment. In order to extract the wetland information effectively and accurately, this research utilizes an explicit decision tree (DT) classification strategy that incorporates multiple feature nodes by using the Landsat-8 OLI imagery as the main data source to interpret the spectral signatures and spatial distribution of the wetlands, and to construct acomprehensive DT classification process for wetland information extraction in QNNR. The multiple feature nodes include snow cover, non-wetland distribution, normalized difference vegetation index (NDVI), normalized difference water index (NDWI), digital elevation model (DEM), land surface temperature (LST) and slope. This strategy produces amore accurate wetland classification in QNNR where there are various interfering factors such as snow, mountain shadows, mineralized regions, grassland and woodland. The method is straightforward and easy to implement. Its classification result has an overall accuracy of 92.75%. This method could be applied to the plateaus with vertical-step ecosystems.