Han Li

Dr. Han Li

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
CLChao Liu
Chao Liu
HLHan Li
Han Li
JXJiuzhe Xu
Jiuzhe Xu
WGWeijun Gao
Weijun Gao
XSXiang Shen
Xiang Shen
SMSheng Miao
Sheng Miao
The development of ecological restoration projects is unsatisfactory, and soil erosion is still a problem in ecologically restored areas. Traditional soil erosion studies are mostly based on satellite remote sensing data and traditional soil erosion models, which cannot accurately characterize the soil erosion conditions in ecological restoration areas (mainly plantation forests). This paper uses high-resolution unmanned aerial vehicle (UAV) images as the base data, which could improve the accuracy of the study. Considering that traditional soil erosion models cannot accurately express the complex relationships between erosion factors, this paper applies convolutional neural network (CNN) models to identify the soil erosion intensity in ecological restoration areas, which can solve the problem of nonlinear mapping of soil erosion. In this study area, compared with the traditional method, the accuracy of soil erosion identification by applying the CNN model improved by 25.57%, which is better than baseline methods. In addition, based on research results, this paper analyses the relationship between land use type, vegetation cover, and slope and soil erosion. This study makes five recommendations for the prevention and control of soil erosion in the ecological restoration area, which provides a scientific basis and decision reference for subsequent ecological restoration decisions.

23 January 2025 in Water
Verified
Journal Article
Open access
PDF file
HLHan Li
Han Li
CLChao Liu
Chao Liu
XGXiao Guo
Xiao Guo
HSHaotian Sun
Haotian Sun
XLXuefei Li
Xuefei Li
SMSheng Miao
Sheng Miao
When confronted with different influent conditions, WWTPs often lack targeted and effective operational control strategies. For the three typical scenarios of low C/N, low water temperature and high water temperature, 441 carbon source dosage and DO concentration coordination control strategies were designed under the premise of ensuring the effluent water quality meets the standard. The purpose was to provide clear operational guidance for the efficient operation of WWTPs in different scenarios. To determine the optimal strategy, the effluent quality prediction model based on LSTM and GRU was constructed for testing. The results showed that: (1) the LSTM-GRU model is better than SVR and RF in predicting effluent COD and TN; (2) In the low C/N scenario, the carbon source dosage should be controlled between 0.23 t/h and 0.26 t/h, with the DO concentration ranging from 2.0 mg/L to 2.6 mg/L; (3) In the low water temperature scenario, the carbon source dosage should be controlled between 0.25 t/h and 0.27 t/h, with the DO concentration ranging from 2.6 mg/L to 2.8 mg/L; (4) In the high water temperature scenario, the carbon source dosage should be controlled between 0.20 t/h and 0.27 t/h, with the DO concentration ranging from 2.0 mg/L to 2.5 mg/L.

4 February 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
HLHan Li
Han Li
SMSheng Miao
Sheng Miao
YQYansu Qi
Yansu Qi
HGHuiwen Gao
Huiwen Gao
HDHaoyan Duan
Haoyan Duan
WGWeijun Gao
Weijun Gao
Soil is an important nonrenewable resource. Soil erosion is increasingly severe, and the accurate identification of soil erosion is crucial for ecological sustainability. In recent years, advancements in artificial intelligence have significantly contributed to the development of precise modeling technologies. This study utilizes high-resolution multispectral images captured by unmanned aerial vehicles and applies five machine learning models, namely convolutional neural network (CNN), support vector classification, random forest, extreme gradient boosting, and fully connected neural network, to identify regional soil erosion. The performance of each model is evaluated using F1-score, precision, and recall measurements. The results show that all models exhibit strong recognition capabilities, with CNN outperforming the others in both training and testing phases. Specifically, CNN achieved a recall rate of 0.99 on the training set and an F1-score of 0.98. Given the black-box nature of machine learning models, the shapley additive explanations method is further used for interpreting model outputs. The analysis reveals that the normalized difference salinity index and soil erodibility factor are the primary factors influencing soil erosion in the study area.

31 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
CLChuanyu Luo
Chuanyu Luo
XLXiaohan Li
Xiaohan Li
NCNuo Cheng
Nuo Cheng
HLHan Li
Han Li
SLShengguang Lei
Shengguang Lei
Pu LiPu Li
Pu Li
Semantic segmentation of 3D point cloud is an essential task for autonomous driving environment perception. The pipeline of most pointwise point cloud semantic segmentation methods includes points sampling, neighbor searching, feature aggregation, and classification. Neighbor searching method like K-nearest neighbors algorithm, KNN, has been widely applied. However, the complexity of KNN is always a bottleneck of efficiency. In this paper, we propose an end-to-end neural architecture, Multiple View Pointwise Net, MVP-Net, to efficiently and directly infer large-scale outdoor point cloud without KNN or any complex pre/postprocessing. Instead, assumption-based space filling curves and multi-rotation of point cloud methods are introduced to point feature aggregation and receptive field expanding. Numerical experiments show that the proposed MVP-Net is 11 times faster than the most efficient pointwise semantic segmentation method RandLA-Net and achieves the same accuracy on the large-scale benchmark SemanticKITTI dataset.

14 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
CLChuanyu Luo
Chuanyu Luo
NCNuo Cheng
Nuo Cheng
SMSikun Ma
Sikun Ma
HLHan Li
Han Li
XLXiaohan Li
Xiaohan Li
Pu LiPu Li
Pu Li
Large-scale LiDAR-based point cloud semantic segmentation is a critical task in autonomous driving perception. Almost all of the previous state-of-the-art LiDAR semantic segmentation methods are variants of sparse 3D convolution. Although the Transformer architecture is becoming popular in the field of natural language processing and 2D computer vision, its application to large-scale point cloud semantic segmentation is still limited. In this paper, we propose a LiDAR sEmantic Segmentation architecture with pure Transformer, LEST. LEST comprises two novel components: a Space Filling Curve (SFC) Grouping strategy and a Distance-based Cosine Linear Transformer, DISCO. On the public nuScenes semantic segmentation validation set and SemanticKITTI test set, our model outperforms all the other state-of-the-art methods.