Jinchen Zhu

Mr. Jinchen Zhu


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
14 October 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JYJiaqi Yang
Jiaqi Yang
SCShengbo Chen
Shengbo Chen
ZWZibo Wang
Zibo Wang
YZYaqi Zhang
Yaqi Zhang
YSYuqiao Suo
Yuqiao Suo
QLQiqi Li
Qiqi Li
In recent years, the increasing frequency of global seismic events has imposed severe impacts on human society. Timely and accurate assessment of post-earthquake damage and recovery is essential for developing effective emergency response strategies and enhancing urban resilience. This study investigates 11 provinces in Turkey affected by the February 2023 Turkey–Syria earthquake, conducting a multidimensional evaluation of disaster loss and recovery. For loss assessment, existing studies typically focus on changes in the total value of nighttime lights at the regional level, overlooking variations at the pixel scale. In this study, we introduce a pixel-level NTL loss metric, which provides finer-grained insights and helps interpret outcomes driven by spatial heterogeneity. For recovery assessment, we propose a Composite Nighttime Light Index (CNLI) that integrates multiple recovery-phase indicators into a single quantitative measure, thus capturing more information than a one-dimensional metric. To account for complex interrelationships among indicators, a Bayesian network is employed, which moves beyond the conventional independence assumption. Moreover, an information gain (IG) approach is applied to optimize indicator weights, minimizing subjectivity and avoiding abnormal weight distributions compared with traditional methods, thereby ensuring a more objective construction of the Resilience Index (RI). Results show that Sanliurfa, Kilis, and Hatay suffered the most severe damage; Kahramanmaras and Malatya exhibited the lowest CNLI values, while Hatay, Kilis, and Gaziantep showed higher CNLI values. In contrast, Gaziantep and Adana obtained the highest RI values. Since CNLI reflects actual recovery performance while RI characterizes inherent resilience, accordingly, effectively linking CNLI and RI establishes a dual-perspective and novel framework, the 11 provinces are classified into four categories, and differentiated recovery strategies are suggested. This study contributes a refined quantitative framework for post-earthquake loss and recovery assessment and provides scientific evidence to support emergency response and targeted reconstruction.

19 January 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YZYaqi Zhang
Yaqi Zhang
SCShengbo Chen
Shengbo Chen
XXXitong Xu
Xitong Xu
JYJiaqi Yang
Jiaqi Yang
YSYuqiao Suo
Yuqiao Suo
QLQiqi Li
Qiqi Li
Accurate registration of optical and synthetic aperture radar (SAR) images is a fundamental prerequisite for multi-source remote sensing data fusion and analysis. However, due to the substantial differences in imaging mechanisms, optical–SAR image pairs often exhibit significant radiometric discrepancies and spatially varying geometric inconsistencies, which severely limit the robustness of traditional feature or region-based registration methods in cross-modal scenarios. To address these challenges, this paper proposes an end-to-end Optical–SAR Registration Network (OSR-Net) based on multi-constraint joint optimization. The proposed framework explicitly decouples cross-modal feature alignment and geometric correction, enabling robust registration under large appearance variation. Specifically, a multi-modal feature extraction module constructs a shared high-level representation, while a multi-scale channel attention mechanism adaptively enhances cross-modal feature consistency. A multi-scale affine transformation prediction module provides a coarse-to-fine geometric initialization, which stabilizes parameter estimation under complex imaging conditions. Furthermore, an improved spatial transformer network is introduced to perform structure-preserving geometric refinement, mitigating spatial distortion induced by modality discrepancies. In addition, a multi-constraint loss formulation is designed to jointly enforce geometric accuracy, structural consistency, and physical plausibility. By employing a dynamic weighting strategy, the optimization process progressively shifts from global alignment to local structural refinement, effectively preventing degenerate solutions and improving robustness. Extensive experiments on public optical–SAR datasets demonstrate that the proposed method achieves accurate and stable registration across diverse scenes, providing a reliable geometric foundation for subsequent multi-source remote sensing data fusion.

21 May 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
QLQiqi Li
Qiqi Li
SCShengbo Chen
Shengbo Chen
LCLiang Cui
Liang Cui
YZYaqi Zhang
Yaqi Zhang
HCHao Chen
Hao Chen
JYJiaqi Yang
Jiaqi Yang
Accurately estimating leaf area index (LAI) is vital for evaluating crop growth and predicting yields. Conventional approaches, however, often struggle due to the limited representativeness of available data and the complex structure of plant canopies, which reduce their reliability across diverse canopy architectures and observation conditions. To overcome these challenges, this work introduces an LAI retrieval framework that combines a three-dimensional radiative transfer model (3D RTM) with deep learning techniques. Representative 3D maize canopy scenarios were generated using the LESS model, producing synthetic LiDAR point clouds constrained by realistic structural parameters. A deep learning model based on PointNet++ was trained, and transfer learning (TL) was employed to facilitate knowledge transfer from simulated to actual measured data. The TL-enhanced model demonstrated significant improvement, with R2 rising from 0.537 to 0.842 and RMSE dropping from 0.541 to 0.288 m2·m−2. Moreover, retrieval performance was notably affected by scanning mode, angle, and stem diameter, achieving optimal results under TLS acquisition, moderate scanning angles, and intermediate stem widths. These findings suggest that integrating 3D RTM-generated synthetic point clouds with transfer learning is an effective strategy for enhancing the robustness and generalization of LiDAR-based LAI retrieval.

29 May 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MWMenghan WU
Menghan WU
SCShengbo Chen
Shengbo Chen
XXXitong Xu
Xitong Xu
YZYaqi Zhang
Yaqi Zhang
YSYuqiao Suo
Yuqiao Suo
QLQiqi Li
Qiqi Li
Ground control point (GCP) selection is a critical step in the automated high-precision geometric correction of remote sensing imagery. While the quantity, quality, and distribution of GCPs are three factors which may affect the accuracy of geometric correction, traditional automated selection methods predominantly focus on optimizing spatial distribution, often neglecting the inherent quality heterogeneity within matched point sets. This paper proposes a Reliability-weighted Spatial Coverage Sampling (SCS+R) method, which integrates matching reliability into the spatial coverage sampling framework via an adaptive weight factor (α). Experiments using Gaofen-2 (GF-2) imagery demonstrate that with 58 GCPs selected by SCS+R, the relative geometric consistency with the reference imagery is improved to a sub-pixel level (1.55–2.23 m) for multispectral images and within two pixels (0.99–1.81 m) for panchromatic images. Compared to the standard SCS, Voronoi, and weighted Voronoi methods, SCS+R improves the average accuracy by approximately 25%, 16%, and 8%, respectively. These results verify the enhanced stability and robustness of the proposed method in complex environments. Moreover, the optimal adaptive reliability weight α consistently stabilizes in a low range of 0.1–0.3, quantitatively revealing a key principle for small-sample GCP selection: spatial uniformity provides the foundation, while point reliability is the key to achieving high precision.

14 October 2026 in Sensors
Verified
Journal Article
Open access
PDF file
JZJinchen Zhu
Jinchen Zhu
SCShengbo Chen
Shengbo Chen
XXXitong Xu
Xitong Xu
LCLiang Cui
Liang Cui
YZYaqi Zhang
Yaqi Zhang
QLQiqi Li
Qiqi Li
High-resolution remote sensing building extraction often requires large amounts of manually labeled data, and models trained on one dataset may not perform equally well on another without additional annotations. To reduce this dependency on labeled target data, we propose SIGA-UNet3+, which combines a Spectral Index Gated Attention (SIGA) module with a transfer learning strategy. The SIGA module fuses DSBI, NDVI, and NDWI to emphasize building features and suppress vegetation/water interference. Pre-training on the public SpaceNet dataset followed by fine-tuning on a self-built GF-2 dataset (Changchun, China) allows the model to adapt with limited local labels. On SpaceNet, SIGA-UNet3+ achieves F1 = 83.21% and IoU = 70.19%, obtaining the best overall segmentation performance among the compared methods. On the GF-2 dataset, it attains F1 = 84.56% and IoU = 72.17%. Moreover, using only 10% of the GF-2 training samples, transfer learning improves the F1 score by 6–8 percentage points compared to training from scratch. These results indicate that SIGA-UNet3+ can provide a promising and data-efficient approach for high-resolution remote sensing building extraction.