Jianmin Wang

Jianmin Wang

Auto-generated profile, based on publicly available information

Jianmin Wang

College of Geological and Surveying Engineering, Taiyuan University of Technology, Taiyuan, China

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
21 August 2025 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
QZQi Zhang
Qi Zhang
YQYonggang Qian
Yonggang Qian
KLKun Li
Kun Li
QLQiyao Li
Qiyao Li
JWJianmin Wang
Jianmin Wang
DLDacheng Li
Dacheng Li
Land surface emissivity (LSE) is crucial for retrieving land surface temperature (LST) from Landsat 9 TIRS-2 thermal infrared data. However, the single-band LSE product (band 10) provided officially is insufficient for split-window (SW) algorithm requiring dual-band emissivity inputs. This letter proposes a land cover and channel transformed (LCCT-LSE) method to estimate band 11 LSE and enables LST retrieval using SW algorithm on Google Earth Engine. Cross-validation with MOD21 LSE products showed that the LCCT-LSE method achieved a mean absolute error (MAE) of 0.004 and a root mean square error (RMSE) of 0.005, outperforming classification-based method, NDVI threshold method, and vegetation cover (VCM) methods. In situ validation showed SW-retrieved LST attains MAE/RMSE of 1.27 K/ 2.13 K, with consistent accuracy across diverse land covers (water: 0.86 K, soil: 1.58 K, desert: 1.71 K, sand: 1.80 K, vegetation: 0.87 K). A comparison with the official Landsat 9 LST product indicated that the bias of retrieved LST is within 1K for all land cover classes (cropland, forest, grassland, shrubland, water, barren and impervious) in Beijing. These results demonstrated that the LCCT-LSE method is capable of estimating the LSE in Landsat 9 band 11 with a reliable and accurate result. This study provides a new insight for LST retrieval from Landsat 9 data.

27 May 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SDSunwen Du
Sunwen Du
XHXiaowei Hu
Xiaowei Hu
BLBaocheng Li
Baocheng Li
GFGuorui Feng
Guorui Feng
JWJianmin Wang
Jianmin Wang
YCYanwei Chen
Yanwei Chen
Ground fissures will damage the ecological environment and endanger infrastructure. However, due to slender shape, discontinuity and complex background, the precise detection of these data remains quite challenging. To address this issue, an efficient Deep Learning (DL) network named PGD-UNet++ is proposed to detect ground fissures in Unmanned Aerial Vehicle (UAV) imagery from the coal mining area automatically and accurately. Our novel network consists of four key components: Position Prior Generator (PPG)module, Enhanced UNet3+, Global-Local Feature Decoupling (GLFD) module, and Skeleton Connectivity Loss. PPG module captures the spatial orientation of fissures using a prior generation approach with multi-directional convolution kernels and spatial pooling. GLFD module decouples contextual information from multi-scale features, using global representations from spatial pooling and local details from hybrid deformable convolutions. Skeleton Connectivity Loss uses morphological operations to compare predicted and ground truth skeletons, explicitly preserving the topological structure of fissures. We also establish a standardized dataset of 8,564 mining-area images, featuring fissure masks annotated at an experimentally validated optimal width of 7 pixels. Experimental results show that PGD-UNet++ outperforms state-of-the-art methods on both the full dataset (F1=85.93%, mIoU=86.69%) and a mining subset (F1=88.93%, mIoU=89.51%), while remaining lightweight with only 10.53 M parameters. This research brings a new network for ground fissures detection and a high-quality dataset, advancing the tools for automated geological hazard monitoring and mining safety.