Jie Zhu

Dr. Jie 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
26 September 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SZSen Zhuang
Sen Zhuang
YHYujuan Huang
Yujuan Huang
JZJie Zhu
Jie Zhu
QYQingluo Yang
Qingluo Yang
Wei LiWei Li
Wei Li
XYXia Yao
Xia Yao
Wheat, a globally vital food crop, faces severe threats from numerous foliar diseases, which often infect agricultural fields, significantly compromising yield and quality. Rapid and accurate identification of the specific disease is crucial for ensuring food security. Although progress has been made in wheat foliar disease detection using RGB imaging and spectroscopy, most prior studies have focused on identifying the presence of a single disease, without considering the need to operationalize such methods, and it will be necessary to differentiate between multiple diseases. In this study, we systematically investigate the differentiation of three wheat foliar diseases (e.g., powdery mildew, stripe rust, and leaf rust) and evaluate feature selection strategies and machine learning models for disease identification. Based on field experiments conducted from 2017 to 2024 employing artificial inoculation, we established a standardized hyperspectral database of wheat foliar diseases classified by disease severity. Four feature selection methods were employed to extract spectral features prior to classification: continuous wavelet projection algorithm (CWPA), continuous wavelet analysis (CWA), successive projections algorithm (SPA), and Relief-F. The selected features (which are derived by CWPA, CWA, SPA, and Relief-F algorithm) were then used as predictors for three disease-identification machine learning models: random forest (RF), k-nearest neighbors (KNN), and naïve Bayes (BAYES). Results showed that CWPA outperformed other feature selection methods. The combination of CWPA and KNN for discriminating disease-infected (powdery mildew, stripe rust, leaf rust) and healthy leaves by using only two key features (i.e., 668 nm at wavelet scale 5 and 894 nm at wavelet scale 7), achieved an overall accuracy (OA) of 77% and a map-level image classification efficacy (MICE) of 0.63. This combination of feature selection and machine learning model provides an efficient and precise procedure for discriminating between multiple foliar diseases in agricultural fields, thus offering technical support for precision agriculture.

25 November 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Wei LiWei Li
Wei Li
JZJie Zhu
Jie Zhu
TLTongjie Li
Tongjie Li
ZMZhiyuan Ma
Zhiyuan Ma
TWTimothy Warner
Timothy Warner
XYXia Yao
Xia Yao
Accurately mapping crop distribution is important for environmental and food security applications. The success of machine learning algorithms (MLs) applied to mapping crops is partly dependent on the acquisition of sufficient training samples. However, since minor crops typically cover only few areas within agricultural landscapes, opportunities for collecting training data for those classes are often constrained. This problem is particularly acute in high-elevation regions, where fields tend to be small and heterogeneous in shape. This often leads to imbalanced training datasets, where the proportions of samples for each class differ greatly. To address this issue, a novel resampling algorithm, i.e., the adaptive synthetic and repeat oversampling technique (ASROT), was proposed by coupling two existed algorithms: adaptive synthetic sampling (ADASYN) and density-based spatial clustering of applications with noise (DBSCAN). Then, we explored the application of the proposed ASROT approach and compared it with six commonly used alternative algorithms, using 13 imbalanced datasets generated from GF-6 images of a high-elevation region. The imbalanced training datasets as well as balanced versions produced by ASROT and the comparison algorithms were used with two classifiers (i.e., random forest (RF) and a stacking classifier) to map crop types. The results showed a negative correlation between overall accuracy and the imbalance degree of datasets, illustrating the latter does affect the models in calibrating the crop classification. The balanced datasets produced higher accuracy for crop classification than the original imbalanced datasets for both the RF and stacking classifiers. The classification accuracy of almost all the crop classes and the overall classification accuracy (OA) increased. Most notably, the accuracy for minor crops (e.g., highland barley and broad beans) increased by approximately 30%. Overall, the proposed ASROT algorithm provides an effective method for balancing training datasets, simultaneously improving classification accuracy of both major and minor crops in high-elevation regions.

28 September 2026 in Plants
Verified
Journal Article
Open access
PDF file
KZKe Zhang
Ke Zhang
ASAoxue Shen
Aoxue Shen
RGRuocheng Gao
Ruocheng Gao
HCHong Cheng
Hong Cheng
JZJie Zhu
Jie Zhu
JSJin Sun
Jin Sun
Greenhouse tomato production requires frequent, fruit-level information on maturity, quality, and yield, yet conventional assessment is often destructive, labor-intensive, or dependent on costly sensing hardware. This study presents a lightweight RGB-based framework for non-destructive measurement of greenhouse tomato fruits under foliage occlusion, uneven illumination, and fruit overlap. By improving instance segmentation while constraining computational cost, the framework generated cleaner fruit masks for downstream color analysis, quality inference, and single-fruit weight estimation. Compared with YOLO11n, the proposed model reduced GFLOPs from 10.2 to 8.2 and improved mask precision from 78.2% to 84.6% and mask F1-score from 82.8% to 85.2%, while box recall, mask recall, and IoU showed small trade-offs. Segmentation remained comparatively stable across maturity stages. RGB features from the refined masks were most useful for vitamin C and soluble solids, supporting rapid, indirect quality screening. In parallel, disk-based geometric reconstruction from fruit contours estimated single-fruit weight with MAE values of 1.69 g·fruit−1 for large-fruited tomatoes and 1.29 g·fruit−1 for cherry tomatoes. The improved masks enhanced single-fruit weight estimation, whereas biochemical quality prediction remained an indirect, trait-dependent estimation that may partly reflect maturity-related color variation rather than direct measurement. Overall, the results demonstrate that improving segmentation fidelity can strengthen downstream trait estimation without increasing sensing complexity, providing a practical RGB-based solution for automated greenhouse tomato phenotyping, while also highlighting the need for standardized imaging and cautious interpretation of biochemical trait predictions.