Zhenjiang Zhou

Dr. Zhenjiang Zhou

Department of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058 China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
2 June 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XPxuelian peng
xuelian peng
DCDianyu Chen
Dianyu Chen
Zhenjiang ZhouZhenjiang Zhou
Zhenjiang Zhou
Zhitao ZhangZhitao Zhang
Zhitao Zhang
CXCan Xu
Can Xu
XHXiaotao Hu
Xiaotao Hu
The rapid and accurate acquisition of nitrogen, phosphorus and potassium nutrient contents in grape leaves is critical for improving grape yields and quality and for industrial development. In this study, crop growth was non-destructively monitored based on unmanned aerial vehicle (UAV) remote sensing technology. Three irrigation levels (W1, W2 and W3) and four fertilization levels (F3, F2, F1 and F0) were set in this study, and drip irrigation fertilization treatments adopted a complete block design. A correlation analysis was conducted using UAV multispectral image data obtained from 2019 to 2021 and the field-measured leaf nitrogen content (LNC), leaf potassium content (LKC) and leaf phosphorus content (LPC) values; from the results, the vegetation indices (VIs) that were sensitive to LNC, LKC and LPC were determined. By combining spectral indices with partial least squares (PLS), random forest (RF), support vector machine (SVM) and extreme learning machine (ELM) machine-learning algorithms, prediction models were established. Finally, the optimal combinations of spectral variables and machine learning models for predicting LNC, LPC and LKC in each grape growth period were determined. The results showed that: (1) there were high demands for nitrogen during the new shoot growth and flowering periods, potassium was the main nutrient absorbed in the fruit expansion period, and phosphorus was the main nutrient absorbed in the veraison and maturity periods; (2) combining multiple spectral variables with the RF, SVM and ELM models could result in improved LNC, LPC and LKC predictions. The optimal prediction model determination coefficient (R2) derived during the new shoot growth period was above 0.65, and that obtained during the other growth periods was above 0.75. The relative root mean square error (RRMSE) of the above models was below 0.20, and the Willmott consistency index (WIA) was above 0.88. In conclusion, UAV multispectral images have good application effects when predicting nutrient contents in grape leaves. This study can provide technical support for accurate vineyard nutrient management using UAV platforms.

9 July 2021 in Plant Methods
Verified
Journal Article
Open access
PDF file
ZZZeqing Zhang
Zeqing Zhang
Fei LiuFei Liu
Fei Liu
Zhenjiang ZhouZhenjiang Zhou
Zhenjiang Zhou
Yong HeYong He
Yong He
HFHui Fang
Hui Fang
Background: Surface roughness has a significant effect on leaf wettability. Consequently, it influences the efficiency and effectiveness of pesticide application. Therefore, roughness measurement of leaf surface offers support to the relevant research efforts. To characterize surface roughness, the prevailing methods have drawn support from large equipment that often come with high costs and poor portability, which is not suitable for field measurement. Additionally, such equipment may even suffer from inherent drawbacks like the absence of relationship between pixel intensity and corresponding height for scanning electron microscope (SEM). Results: An imaging system with variable object distance was created to capture images of plant leaves, and a method based on shape from focus (SFF) was proposed. The given space-variantly blurred images were processed with the proposed algorithm to obtain the surface roughness of plant leaves. The algorithm improves the current SFF method through image alignment, focus distortion correction, and the introduction of NaN values that allows it to be applied for precise 3d-reconstruction and small-scale surface roughness measurement. Conclusion: Compared with methods that rely on optical three-dimensional interference microscope, the method proposed in this paper preserves the overall topography of leaf surface, and achieves superior cost performance at the same time. It is clear from experiments on standard gauge blocks that the RMSE of step was approximately 4.44 µm. Furthermore, according to the Friedman/Nemenyi test, the focus measure operator SML was expected to demonstrate the best performance.

2 November 2021 in Water
Verified
Journal Article
Open access
PDF file
XPxuelian peng
xuelian peng
XHXiaotao Hu
Xiaotao Hu
DCDianyu Chen
Dianyu Chen
Zhenjiang ZhouZhenjiang Zhou
Zhenjiang Zhou
YGYinyin Guo
Yinyin Guo
TYTinggao Yu
Tinggao Yu
Understanding variations in sap flow rates and the environmental factors that influence sap flow is important for exploring grape water consumption patterns and developing reasonable greenhouse irrigation schedules. Three irrigation levels were established in this study: adequate irrigation (W1), moderate deficit irrigation (W2) and deficit irrigation (W3). Grape sap flow estimation models were constructed using partial least squares (PLS) and random forest (RF) algorithms, and the simulation accuracy and stability of these models were evaluated. The results showed that the daily mean sap flow rates in the W2 and W3 treatments were 14.65 and 46.94% lower, respectively, than those in the W1 treatment, indicating that the average daily sap flow rate increased gradually with an increase in the irrigation amount within a certain range. Based on model error and uncertainty analyses, the RF model had better simulation results in the different grape growth stages than the PLS model did. The coefficient of determination and Willmott’s index of agreement for RF model exceeded 0.78 and 0.90, respectively, and this model had smaller root mean square error and d-factor (evaluation index of model uncertainty) values than the PLS model did, indicating that the RF model had higher prediction accuracy and was more stable. The relative importance of the model predictors was determined. Moreover, the RF model more comprehensively reflected the influence of meteorological factors and the moisture content in different soil layers on the sap flow rate than the PLS model did. In summary, the RF model accurately simulated sap flow rates, which is important for greenhouse grape irrigation.

10 July 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZNZiang Niu
Ziang Niu
NLNing Liang
Ning Liang
YHYiyin He
Yiyin He
CXChengjia Xu Xu
Chengjia Xu Xu
SSSashuang Sun
Sashuang Sun
Zhengjun QiuZhengjun Qiu
Zhengjun Qiu
The phenotypic analysis of wheat spikes plays an important role in wheat growth management, plant breeding, and yield estimation. However, the dense and tight arrangement of spikelets and grains on the spikes makes the phenotyping more challenging. This study proposed a rapid and accurate image-based method for in-field wheat spike phenotyping consisting of three steps: wheat spikelet segmentation, grain number classification, and total grain number counting. Wheat samples ranging from the early filling period to the mature period were involved in the study, including three varieties: Zhengmai 618, Yannong 19, and Sumai 8. In the first step, the in-field collected images of wheat spikes were optimized by perspective transformation, augmentation, and size reduction. The YOLOv8-seg instance segmentation model was used to segment spikelets from wheat spike images. In the second step, the number of grains in each spikelet was classified by a machine learning model like the Support Vector Machine (SVM) model, utilizing 52 image features extracted for each spikelet, involving shape, color, and texture features as the input. Finally, the total number of grains on each wheat spike was counted by adding the number of grains in the corresponding spikelets. The results showed that the YOLOv8-seg model achieved excellent segmentation performance, with an average precision (AP) @[0.50:0.95] and accuracy (A) of 0.858 and 100%. Meanwhile, the SVM model had good classification performance for the number of grains in spikelets, and the accuracy, precision, recall, and F1 score reached 0.855, 0.860, 0.865, and 0.863, respectively. Mean absolute error (MAE) and mean absolute percentage error (MAPE) were as low as 1.04 and 5% when counting the total number of grains in the frontal view wheat spike images. The proposed method meets the practical application requirements of obtaining trait parameters of wheat spikes and contributes to intelligent and non-destructive spike phenotyping.

21 August 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
JHJin Hu
Jin Hu
YXYuwen Xie
Yuwen Xie
XBXingyu Ban
Xingyu Ban
LZLiyuan Zhang
Liyuan Zhang
Zhenjiang ZhouZhenjiang Zhou
Zhenjiang Zhou
TWToby William Waine
Toby William Waine
Weeds are among the primary factors that adversely affect crop yields. Chlorophyll fluorescence, as a sensitive indicator of photosynthetic activity in green plants, provides direct insight into photosynthetic efficiency and the functional status of the photosynthetic apparatus. This makes it a valuable tool for assessing plant health and stress responses. Active chlorophyll fluorescence technology uses an external light source to excite plant leaves, enabling the rapid acquisition of fluorescence signals for real-time monitoring of vegetation in the field. This technology shows great potential for weed detection, as it allows for accurate discrimination between crops and weeds. Furthermore, since weed-induced stress affects the photosynthetic process of plants, resulting in changes in fluorescence characteristics, chlorophyll fluorescence can also be used to detect herbicide resistance in weeds. This paper reviews the progress in using active chlorophyll fluorescence sensor technology for weed detection. It specifically outlines the principles and structure of active fluorescence sensors and their applications at different stages of field operations, including rapid classification of soil and weeds during the seedling stage, identification of in-row weeds during cultivation, and assessment of herbicide efficacy after application. By monitoring changes in fluorescence parameters, herbicide-resistant weeds can be detected early, providing a scientific basis for precision herbicide application.

11 February 2021 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
SSSashuang Sun
Sashuang Sun
NLNing Liang
Ning Liang
ZZZhiyu Zuo
Zhiyu Zuo
DPDavid Parsons
David Parsons
JMJulien Morel
Julien Morel
Zhenjiang ZhouZhenjiang Zhou
Zhenjiang Zhou
This study aims to provide an effective image analysis method for clover detection and botanical composition (BC) estimation in clover–grass mixture fields. Three transfer learning methods, namely, fine-tuned DeepLab V3+, SegNet, and fully convolutional network-8s (FCN-8s), were utilized to detect clover fractions (on an area basis). The detected clover fraction (CFdetected), together with auxiliary variables, viz., measured clover height (Hclover) and grass height (Hgrass), were used to build multiple linear regression (MLR) and back propagation neural network (BPNN) models for BC estimation. A total of 347 clover–grass images were used to build the estimation model on clover fraction and BC. Of the 347 samples, 226 images were augmented to 904 images for training, 25 were selected for validation, and the remaining 96 samples were used as an independent dataset for testing. Testing results showed that the intersection-over-union (IoU) values based on the DeepLab V3+, SegNet, and FCN-8s were 0.73, 0.57, and 0.60, respectively. The root mean square error (RMSE) values for the three transfer learning methods were 8.5, 10.6, and 10.0%. Subsequently, models based on BPNN and MLR were built to estimate BC, by using either CFdetected only or CFdetected, grass height, and clover height all together. Results showed that BPNN was generally superior to MLR in terms of estimating BC. The BPNN model only using CFdetected had a RMSE of 8.7%. In contrast, the BPNN model using all three variables (CFdetected, Hclover, and Hgrass) as inputs had an RMSE of 6.6%, implying that DeepLab V3+ together with BPNN can provide good estimation of BC and can offer a promising method for improving forage management.