Jihong Sun

Dr. Jihong Sun

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
13 May 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
RYRong Ye
Rong Ye
QGQuan Gao
Quan Gao
YQYe Qian
Ye Qian
JSJihong Sun
Jihong Sun
LTLi Tong
Li Tong
Pest target identification in agricultural production environments is challenging due to the dense distribution, small size, and high density of pests. Additionally, changeable environmental lighting and complex backgrounds further complicate the detection process. This study focuses on enhancing the recognition performance of tea pests by introducing a lightweight pest image recognition model based on the improved YOLOv8 architecture. First, slicing-aided fine-tuning and slicing-aided hyper inference (SAHI) are proposed to partition input images for enhanced model performance on low-resolution images and small-target detection. Then, based on an ELAN, a generalized efficient layer aggregation network (GELAN) is designed to replace the C2f module in the backbone network, enhance its feature extraction ability, and construct a lightweight model. Additionally, the MS structure is integrated into the neck network of YOLOv8 for feature fusion, enhancing the extraction of fine-grained and coarse-grained semantic information. Furthermore, the BiFormer attention mechanism, based on the Transformer architecture, is introduced to amplify target characteristics of tea pests. Finally, the inner-MPDIoU, based on auxiliary borders, is utilized as a replacement for the original loss function to enhance its learning capacity for complex pest samples. Our experimental results demonstrate that the enhanced YOLOv8 model achieves a precision of 96.32% and a recall of 97.95%, surpassing those of the original YOLOv8 model. Moreover, it attains an mAP@50 score of 98.17%. Compared to Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8, its average accuracy is 17.04, 11.23, 5.78, 3.75, and 2.71 percentage points higher, respectively. The overall performance of YOLOv8 outperforms that of current mainstream detection models, with a detection speed of 95 FPS. This model effectively balances lightweight design with high accuracy and speed in detecting small targets such as tea pests. It can serve as a valuable reference for the identification and classification of various insect pests in tea gardens within complex production environments, effectively addressing practical application needs and offering guidance for the future monitoring and scientific control of tea insect pests.

5 July 2024 in Plant Methods
Verified
Journal Article
Open access
PDF file
ZLZhaowen Li
Zhaowen Li
YQYe Qian
Ye Qian
YSYingming Shen
Yingming Shen
YYYing Yang
Ying Yang
XWXijin Wang
Xijin Wang
JSJihong Sun
Jihong Sun
Background: The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan Big leaf kind of tea within its complex ecological niche.Results: Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 98.58% and a verification accuracy rate of 98.2310%.Conclusions: These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan.

15 January 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
JSJihong Sun
Jihong Sun
PTPeng Tian
Peng Tian
ZLZhaowen Li
Zhaowen Li
XWXinrui Wang
Xinrui Wang
ZHZhang Haokai
Zhang Haokai
YQYe Qian
Ye Qian
An intelligent prediction model for rice yield in small-scale cultivation areas can provide precise forecasting results for farmers, rice planting enterprises, and researchers, holding significant importance for agricultural industries and crop science research within small regions. Although machine learning can handle complex nonlinear problems to enhance prediction accuracy, further improvements in models are still needed to accurately predict rice yields in small areas facing complex planting environments, thereby enhancing model performance. This study employs four rice phenotypic traits, namely, panicle angle, panicle length, total branch length, and grain number, along with seven machine learning methods—multiple linear regression, support vector machine, MLP, random forest, GBR, XGBoost, and LightGBM—to construct a yield prediction model group. Subsequently, the top three models with the best performance in individual model predictions are integrated using voting and stacking ensemble methods to obtain the optimal integrated model. Finally, the impact of different rice phenotypic traits on the performance of the stacked ensemble model is explored. Experimental results indicate that the random forest model performs best after individual machine learning modeling, with RMSE, R2, and MAPE values of 0.2777, 0.9062, and 17.04%, respectively. After model integration, Stacking–3m demonstrates the best performance, with RMSE, R2, and MAPE values of 0.2483, 0.9250, and 6.90%, respectively. Compared to the performance after random forest modeling, the RMSE decreased by 10.58%, R2 increased by 1.88%, and MAPE decreased by 0.76%, indicating improved model performance after stacking ensemble. The Stacking–3m model, which demonstrated the best comprehensive evaluation metrics, was selected for model validation, and the validation results were satisfactory, with MAE, R2, and MAPE values of 8.3384, 0.9285, and 0.2689, respectively. The above research findings demonstrate that this integrated model possesses high practical value and fills a gap in precise yield prediction for small-scale rice cultivation in the Yunnan Plateau region.

13 December 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
JSJihong Sun
Jihong Sun
CSChen Sun
Chen Sun
ZLZhaowen Li
Zhaowen Li
YQYe Qian
Ye Qian
TLTong Li
Tong Li
The efficacy of generalized sugarcane yield prediction models holds significant implications for global food security. Given that machine learning algorithms often surpass the precision of remote sensing technology, further exploration of machine learning algorithms in the development of sugarcane yield prediction models is imperative. In this study, we employed six key phenotypic traits of sugarcane, specifically plant height, stem diameter, third-node length (internode length), leaf length, leaf width, and field brix, along with eight machine learning methods: logistic regression, linear regression, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Backpropagation Neural Network (BPNN), Decision Tree, Random Forest, and the XGBoost algorithm. The aim was to establish an intelligent model ensemble for predicting two crucial phenotypic characteristics—stem diameter and plant height—that determine sugarcane yield, ultimately enhancing the overall yield.The experimental findings indicate that the XGBoost algorithm outperforms the other seven algorithms in predicting these significant phenotypic traits of sugarcane. Furthermore, an analysis of the sugarcane intelligent prediction model’s performance under a specialized data environment, incorporating self-prepared data, reveals that the XGBoost algorithm exhibits greater stability. Notably, the data pertaining to these crucial phenotypic traits have a profound impact on the efficacy of the intelligent models. The research demonstrates that a sugarcane yield prediction model ensemble, incorporating multiple intelligent algorithms, can accurately forecast stem diameter and plant height, thereby predicting sugarcane yield. Additionally, this approach, combined with the principles of sugarcane cross-breeding, provides a valuable reference for the artificial breeding of new sugarcane varieties that excel in stem diameter and plant height, bridging a research gap in indirect yield prediction through sugarcane phenotypic traits.

22 November 2025 in Smart Agricultural Technology
Verified
Journal Article
Open access
PTPeng Tian
Peng Tian
JSJihong Sun
Jihong Sun
JCJing Cheng
Jing Cheng
JZJiawei Zhao
Jiawei Zhao
XWXinrui Wang
Xinrui Wang
YQYe Qian
Ye Qian

23 September 2025 in Agronomy
Verified
Journal Article
Open access
PDF file
JSJihong Sun
Jihong Sun
PTPeng Tian
Peng Tian
XWXinrui Wang
Xinrui Wang
JZJiawei Human–Computer Collaborative Sugarcane Disease Detection Model in Complex Zhao
Jiawei Human–Computer Collaborative Sugarcane Disease Detection Model in Complex Zhao
XNXianwei Niu
Xianwei Niu
YQYe Qian
Ye Qian
Multispectral technology and deep learning are widely used in field crop yield prediction. Existing studies mainly focus on large-scale estimation in plain regions, while integrated applications for small-scale plateau plots are rarely reported. To solve this problem, this study proposes a WT-CNN-BiLSTM hybrid model that integrates UAV-borne multispectral imagery and deep learning for rice yield prediction in small-scale greenhouses on the Yunnan Plateau. Initially, a rice dataset covering five drip irrigation levels was constructed, including vegetation index images of rice throughout its entire growth cycle and yield data from 500 sub-plots. After data augmentation (image rotation, flipping, and yield augmentation with Gaussian noise), the dataset was expanded to 2000 sub-plots. Then, with CNN-LSTM as the baseline, four vegetation indices (NDVI, NDRE, OSAVI, and RECI) were compared, and RECI-Yield was determined as the optimal input dataset. Finally, the convolutional layers in the first residual block of ResNet50 were replaced with WTConv to enhance multi-frequency feature extraction; the extracted features were then input into BiLSTM to capture the long-term growth trends of rice, resulting in the development of the WT-CNN-BiLSTM model. Experimental results showed that in small-scale greenhouses on the Yunnan Plateau, the model achieved the best prediction performance under the 50% drip irrigation level (R2 = 0.91). Moreover, the prediction performance based on the merged dataset of all irrigation levels was even better (RMSE = 9.68 g, MAPE = 11.41%, R2 = 0.92), which was significantly superior to comparative models such as CNN-LSTM, CNN-BiLSTM, and CNN-GRU, as well as the prediction results under single irrigation levels. Cross-validation based on the RECI-Yield-VT dataset (RMSE = 8.07 g, MAPE = 9.22%, R2 = 0.94) further confirmed its generalization ability, enabling its effective application to rice yield prediction in small-scale greenhouse scenarios on the Yunnan Plateau.