Yuchong Long

Mr. Yuchong Long

Shanghai Jiaotong University, Shanghai, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
10 August 2023 in Forests
Verified
Journal Article
Open access
PDF file
Yuchong LongYuchong Long
Yuchong Long
WZWenwen Zhang
Wenwen Zhang
NSNingxiao Sun
Ningxiao Sun
PZPenghua Zhu
Penghua Zhu
Jingli YanJingli Yan
Jingli Yan
SYShan Yin
Shan Yin
Urban forests play a crucial role in both emitting and absorbing atmospheric pollutants. Understanding the ecological processes of biogenic volatile organic compounds (BVOCs) and secondary organic aerosols (SOAs) and their interactions in urban forests can help to assess how they influence air quality. Additionally, exploring the adaptation and feedback mechanisms between urban forests and their surrounding environments can identify new pollutants and potential risks in urban forests. However, the relationship between BVOC emissions and SOA formation is complex due to the influence of meteorological conditions, photochemical reactions, and other factors. This complexity makes it challenging to accurately describe this relationship. In this study, we used time-of-flight mass spectrometry and aerosol particle size spectrometry to monitor concentrations of BVOCs and particulate matter with a diameter less than 1 µm (PM1; representing SOAs) at a frequency of 10–12 times per min in an urban forest near Shanghai. We then analyzed the temporal changes in concentrations of BVOCs, SOAs, and other chemical pollutants in different periods of the day by using subsequence clustering and causal inference methods. The results showed that after using this method for diurnal segmentation, PM1 prediction accuracy was improved by 26.77%–47.51%, and the interaction rules of BVOCs and SOAs had sequential interaction characteristics. During the day, BVOCs are an important source of SOAs and have a negative feedback relationship with O3. From night to early morning, BVOCs have a positive, balanced relationship with O3, SOAs are affected by wind speed or deposition, BVOCs have no obvious relationship with O3, and SOAs are affected by temperature or humidity. This study is the first to apply Toeplitz inverse covariance-based clustering and causal inference methods for the high-frequency monitoring of BVOCs and SOAs, revealing the temporal effects and characteristics of BVOCs and SOAs and providing a scientific basis and new methods for understanding the dynamic effects of urban forest communities on the environment.

2 February 2025 in Atmosphere
Verified
Journal Article
Open access
PDF file
WXWenkai Xue
Wenkai Xue
YLYongjun Lin
Yongjun Lin
正孙正奇 孙
正奇 孙
Yuchong LongYuchong Long
Yuchong Long
DCDele Chen
Dele Chen
SYShan Yin
Shan Yin
Airborne particulate matter (PM) is one of the most urgent urban environment problems in the world today. The urban ecosystem has been identified as a potentially promising solution to reduce the airborne PM based on the ability of plants to retain PM. Numerous studies have been conducted to explore the process and mechanism of atmospheric PM retention by plant leaves in the past. In this study, in order to better summarize previous research, particularly the impact of leaf traits on PM retention, and to provide guidance for the selection of tree species for nature-based urban PM solutions, a systematic review was carried out using the method recommended in the PRISMA, and a total of 49 articles were selected. It was found that: 1. Asian countries contribute the majority of the proportion (32, 65%). Following behind are European countries (13, 26.5%). The American countries contribute two cases. 2. Among all the tree species, Ginkgo biloba (16), Euonymus japonicus (11), Magnolia denudate (9), Styphnolobium japonicum (9), Magnolia grandiflora (8), and Prunus cerasifera (8) emerged as hot species in research. 3. Leaf area and shape emerged as the two most frequently discussed macro-indicators, while roughness, hairiness, and stomatal characteristics were the top three micro-indicators explored. 4. Roughness and stomata, respectively, play crucial roles in capturing larger PM particles and retaining fine and ultrafine PM through their recessed structures. Trichomes decrease the likelihood of particle resuspension and boosts the efficiency of PM retention. 5. Leaves with high rigidity and complex multi-faceted leaf shapes are typically presumed to exhibit higher PM retention efficiency for higher edge effects and increased interleaf turbulence. Furthermore, with rigidity and edge effects ensured, a larger leaf area is beneficial for retaining PM.

4 December 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
Yuchong LongYuchong Long
Yuchong Long
WSWen Sun
Wen Sun
NSNingxiao Sun
Ningxiao Sun
WWWenxiao Wang
Wenxiao Wang
LLLi Chao Li
Li Chao Li
SYShan Yin
Shan Yin
Automated pollen recognition is a foundational tool for diverse scientific domains, including paleoclimatology, biodiversity monitoring, and agricultural science. However, conventional methods create a critical data bottleneck, limiting the temporal and spatial resolution of ecological analysis. Existing deep learning models often fail to achieve the requisite localization accuracy for microscopic pollen grains, which are characterized by their minute size, indistinct edges, and complex backgrounds. To overcome this, we introduce HieraEdgeNet, a novel object detection framework. The core principle of our architecture is to explicitly extract and hierarchically fuse multi-scale edge information with deep semantic features. This synergistic approach, combined with a computationally efficient large-kernel operator for fine-grained feature refinement, significantly enhances the model’s ability to perceive and precisely delineate object boundaries. On a large-scale dataset comprising 44,471 annotated microscopic images containing 342,706 pollen grains from 120 classes, HieraEdgeNet achieves a mean Average Precision of 0.9501 (mAP@0.5) and 0.8444 (mAP@0.5:0.95), substantially outperforming state-of-the-art models such as YOLOv12n and the Transformer-based RT-DETR family in terms of the accuracy–efficiency trade-off. This work provides a powerful computational tool for generating the high-throughput, high-fidelity data essential for modern ecological research, including tracking phenological shifts, assessing plant biodiversity, and reconstructing paleoenvironments. At the same time, we acknowledge that the current two-dimensional design cannot directly exploit volumetric Z-stack microscopy and that strong domain shifts between training data and real-world deployments may still degrade performance, which we identify as key directions for future work. By also enabling applications in precision agriculture, HieraEdgeNet contributes broadly to advancing ecosystem monitoring and sustainable food security.

20 August 2023 in Land
Verified
Journal Article
Open access
PDF file
Yuchong LongYuchong Long
Yuchong Long
ZCzhengwei CAO
zhengwei CAO
YMYan Mao
Yan Mao
XLXinran Liu
Xinran Liu
YGYan Gao
Yan Gao
XZXin Zheng
Xin Zheng
The construction of agricultural green bases is an important part of sustainable agricultural development. This paper takes urban agriculture green bases in Shanghai as an example, choosing base construction elements, production, and ecological construction elements, as well as status assessment elements as evaluation indicators, in order to construct an evaluation system for urban agriculture green bases. Using a Bayesian network, typical urban agricultural green bases in six agricultural districts of Shanghai were evaluated. The construction of the evaluation system was analyzed by using intervention, counterfactual inference, and other methods to analyze the correlation and importance of the indicators. The results show that there are differences among the bases in various indicators, but they all reach a high level overall; base construction elements as well as production and ecological construction elements are the main factors affecting the level of urban agricultural green bases; improving the base management system (BMS), innovativeness (IN), and economic benefits (EBs) are key ways to improve the production capacity of agriculture green bases. Green base construction should pay attention to top-level design, coordinate the planning of industrial layout, technical mode, scientific and technological support, and supporting policies. Based on the conclusion, this paper provides some useful recommendations for creating urban agriculture green bases, which help promote urban agriculture transformation, upgrading, and coordinating development between urban and rural areas.

9 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
Yuchong LongYuchong Long
Yuchong Long
WSWen Sun
Wen Sun
NSNingxiao Sun
Ningxiao Sun
WWWenxiao Wang
Wenxiao Wang
CLChao Li
Chao Li
SYShan Yin
Shan Yin
Automated pollen recognition is vital to paleoclimatology, biodiversity monitoring, and public health, yet conventional methods are hampered by inefficiency and subjectivity. Existing deep learning models often struggle to achieve the requisite localization accuracy for microscopic targets like pollen, which are characterized by their minute size, indistinct edges, and complex backgrounds. To overcome this limitation, we introduce HieraEdgeNet, a multi-scale edge-enhancement framework. The framework's core innovation is the introduction of three synergistic modules: the Hierarchical Edge Module (HEM), which explicitly extracts a multi-scale pyramid of edge features that corresponds to the semantic hierarchy at early network stages; the Synergistic Edge Fusion (SEF) module, for deeply fusing these edge priors with semantic information at each respective scale; and the Cross Stage Partial Omni-Kernel Module (CSPOKM), which maximally refines the most detail-rich feature layers using an Omni-Kernel operator - comprising anisotropic large-kernel convolutions and mixed-domain attention - all within a computationally efficient Cross-Stage Partial (CSP) framework. On a large-scale dataset comprising 120 pollen classes, HieraEdgeNet achieves a mean Average Precision (mAP@.5) of 0.9501, significantly outperforming state-of-the-art baseline models such as YOLOv12n and RT-DETR. Furthermore, qualitative analysis confirms that our approach generates feature representations that are more precisely focused on object boundaries. By systematically integrating edge information, HieraEdgeNet provides a robust and powerful solution for high-precision, high-efficiency automated detection of microscopic objects.

9 April 2022 in Zhonghua Kou Qiang Yi Xue Za Zhi = Zhonghua Kouqiang Yixue Zazhi = Chinese Journal of Stomatology
Verified
Journal Article
Closed access
ZJZhang Wen Jun
Zhang Wen Jun
YLY Li
Y Li
BLB Liu
B Liu
HTHong Tao
Hong Tao
Yuchong LongYuchong Long
Yuchong Long
CMC F Ma
C F Ma
Objective: To explore and analyze the correlation between labial gingival morphology and alveolar bone morphology of maxillary anterior teeth in patients with posterior dental implant, so as to provide reference basis for restoration design and esthetic reconstruction of anterior teeth. Methods: Sixty-four patients [24 males, 40 females (25.6±3.3) years old] who planned to receive posterior dental implant restoration were recruited randomly with the inclusion and exclusion criteria in Department of Prosthodontics, School of Stomatology, The Fourth Military Medical University from May 2020 to May 2021. According to the visibility of periodontal probe through gingival margin, the subjects were divided into thin and thick gingival biotypes, including 29 cases of thin biotype and 35 cases of thick biotype. The 3Shape software was used to perform oral scanning, and cone beam CT (CBCT) was taken for each patient. Geomagic and Mimics software were used to measure and record the labial crown width and length, gingival papilla height, gingival angle, bone papilla height and bone margin angle of maxillary anterior teeth. Results: The crown width length ratios of maxillary central incisors, lateral incisors and canines were 0.85±0.08, 0.80±0.08 and 0.86±0.09 (F=10.71, P<0.01). The height of gingival papilla between maxillary central incisors, between central incisors and lateral incisors, between lateral incisors and canines were (3.93±0.86), (3.47±0.84) and (3.38±0.91) mm respectively (F=7.44, P<0.01), and the height of corresponding bone papilla were (3.44±0.88), (3.12±0.75) and (2.72±0.63) mm respectively (F=14.26, P<0.01). The gingival margin angles of maxillary central incisors, lateral incisors and canines were 88.3°±7.7°, 84.7°±8.9° and 81.2°±6.6° (F=13.15, P<0.01), and the bone margin angles were 103.2°±13.1°, 99.5°±11.2° and 110.6°±13.0° (F=13.25, P<0.01). The crown width length ratio (0.81±0.08), gingival margin angle (82.2°±7.4°) and bone margin angle (99.4°±12.9°) of thin gingival subjects were significantly lower than those of thick gingival subjects (0.85±0.09, 86.5°±8.6°, 108.5°±11.4°) (t=-2.79, 3.63, 5.20, P<0.01). The height of gingival papilla [(3.93±0.81) mm] and bone papilla [(3.43±0.80) mm] in thin gingival subjects were significantly lower than those in thick gingival subjects [(3.34±0.84) and (2.85±0.71) mm, respectively] (t=-4.89, -5.36, P<0.01). The height of labial gingival papilla of upper anterior teeth was positively correlated with that of bone papilla in all patients (r=0.66, P<0.01); the ratio of crown width to length of upper anterior teeth was positively correlated with the angle of bone margin (r=0.42, P<0.01); the height of anterior gingival papilla was negatively correlated with the angle of bone margin (r=-0.58, P<0.01), and the height of bone papilla was negatively correlated with the angle of bone margin (r=-0.82, P<0.01). Conclusions: The crown shape, gingival shape and alveolar bone shape of maxillary anterior teeth were different in different tooth positions. Patients with different periodontal phenotypes had different crown width length ratio, gingival papilla height, bone papilla height, gingival margin angle, and bone margin angle.