TLTeng Liu

Teng Liu

*This is an algorithmically generated author record based on publicly available information.

Teng Liu has a total of 39 co-authors. Here are the top co-authors by number of shared publications:

  • Jialin Yu

    Peking University Institute of Advanced Agricultural Sciences Weifang China

    8 shared publications
  • Danlan Zhai

    4 shared publications
  • Jinxu Wang

    Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang Weifang China

    3 shared publications
  • Xiaojun Jin

    Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang Weifang China

    3 shared publications
  • Feiyu He

    Department of Computer Science Duke University Durham NC USA

    2 shared publications
  • Wenpeng Zhu

    Peking University Institute of Advanced Agricultural Sciences Weifang China

    2 shared publications

Latest Publications

  • Rapid detection of common scab, powdery scab, and enlarged lenticels in potato tubers using deep learning

    by Jiale Lv, Teng Liu, Jian Wu, Wenpeng Zhu, Jialin Yu, Ruofang Zhang, Utpal Handique

    BACKGROUND: Differentiating between potato common scab, powdery scab, and the physiological disorder of enlarged corky lenticels is challenging due to their similar visual symptoms. To address this, we propose YOLOv8‐ST, an enhanced deep learning model that incorporates the Swin Transformer and Triplet Attention modules to effectively distinguish between these visually similar tuber blemishes. RESULTS: YOLOv8‐ST is an enhanced YOLOv8 model with the integration of Triplet Attention and the Swin Transformer, which achieved significant accuracy improvements. Compared to the baseline of YOLOv3, YOLOv5, YOLOv6, and YOLOv8, YOLOv8‐ST achieved the highest precision (0.903), recall (0.831), F1‐score (0.866), mAP@0.5 (0.931), and mAP@0.5:0.95 (0.616), with strong performance in detecting common scab and powdery scab (both >0.9 at mAP@0.5 or precision). Detection outputs showed higher confidence (e.g., 0.94 for scab), fewer false positives, and no missed lesions, outperforming models prone to misclassification or overlap. CONCLUSION: The YOLOv8‐ST model enables fast, accurate, and reliable detection of common scab, powdery scab, and enlarged lenticels on potato tubers. This field‐deployable solution supports early disease diagnosis and timely intervention, thus reducing crop losses. The model is available through the mobile app Plant Guardian, enabling growers to identify potato skin blemishes directly in the field, thereby advancing both practical disease management and agricultural AI applications. © 2025 Society of Chemical Industry.

  • Semantic segmentation for weed detection in corn

    by Teng Liu, Xiaojun Jin, Kang Han, Feiyu He, Jinxu Wang, Xin Chen, Xiaotong Kong, Jialin Yu

    BACKGROUND: Reliable, fast, and accurate weed detection in farmland is crucial for precision weed management but remains challenging due to the diverse weed species present across different fields. While deep learning models for direct weed detection have been developed in previous studies, creating a training dataset that encompasses all possible weed species, ecotypes, and growth stages is practically unfeasible. This study proposes a novel approach to detect weeds by integrating semantic segmentation with image processing. The primary aim is to simplify the weed detection process by segmenting crop pixels and identifying all vegetation outside the crop mask as weeds.RESULTS: The proposed method employs a semantic segmentation model to generate a mask of corn (Zea mays L.) crops, identifying all green plant pixels outside the mask as weeds. This indirect segmentation approach reduces model complexity by avoiding the need for direct detection of diverse weed species. To enhance real‐time performance, the semantic segmentation model was optimized through knowledge distillation, resulting in a faster, lighter‐weight inference. Experimental results demonstrated that the DeepLabV3+ model, after applying knowledge distillation, achieved an average accuracy (aAcc) exceeding 99.5% and a mean intersection over union (mIoU) across all categories above 95.5%. Furthermore, the model's operating speed surpassed 34 frames per second (FPS).CONCLUSION: This study introduces a novel method that accurately segments crop pixels to form a mask, identifying vegetation outside this mask as weeds. By focusing on crop segmentation, the method avoids the complexity associated with diverse weed species, varying densities, and different growth stages. This approach offers a practical and efficient solution to facilitate the training of effective computer vision models for precision weed detection and control. © 2024 Society of Chemical Industry.


  • Exploring the semi-supervised learning for weed detection in wheat

    by Xiaotong Kong, Teng Liu, Xin Chen, Peng Lian, Danlan Zhai, Aimin Li, Jialin Yu


  • Evaluation of two deep learning‐based approaches for detecting weeds growing in cabbage

    by Hu Sun, Teng Liu, Jinxu Wang, Danlan Zhai, Jialin Yu

    BACKGROUND: Machine vision‐based precision weed management is a promising solution to substantially reduce herbicide input and weed control cost. The objective of this research was to compare two different deep learning‐based approaches for detecting weeds in cabbage: (1) detecting weeds directly, and (2) detecting crops by generating the bounding boxes covering the crops and any green pixels outside the bounding boxes were deemed as weeds.RESULTS: The precision, recall, F1‐score, mAP0.5, mAP0.5:0.95 of You Only Look Once (YOLO) v5 for detecting cabbage were 0.986, 0.979, 0.982, 0.995, and 0.851, respectively, while these metrics were 0.973, 0.985, 0.979, 0.993, and 0.906 for YOLOv8, respectively. However, none of these metrics exceeded 0.891 when detecting weeds. The reduced performances for directly detecting weeds could be attributed to the diverse weed species at varying densities and growth stages with different plant morphologies. A segmentation procedure demonstrated its effectiveness for extracting weeds outside the bounding boxes covering the crops, and thereby realizing effective indirect weed detection.CONCLUSION: The indirect weed detection approach demands less manpower as the need for constructing a large training dataset containing a variety of weed species is unnecessary. However, in a certain case, weeds are likely to remain undetected due to their growth in close proximity with crops and being situated within the predicted bounding boxes that encompass the crops. The models generated in this research can be used in conjunction with the machine vision subsystem of a smart sprayer or mechanical weeder. © 2024 Society of Chemical Industry.


  • Semi‐supervised learning methods for weed detection in turf

    by Teng Liu, Danlan Zhai, Feiyu He, Jialin Yu

    BACKGROUND: Accurate weed detection is a prerequisite for precise automatic precision herbicide application. Previous research has adopted the laborious and time‐consuming approach of manually labeling and processing large image data sets to develop deep neural networks for weed detection. This research introduces a novel semi‐supervised learning (SSL) approach for detecting weeds in turf. The performance of SSL was compared with that of ResNet50, a fully supervised learning (FSL) method, in detecting and differentiating sub‐images containing weeds from those containing only turfgrass.RESULTS: Compared with ResNet50, the evaluated SSL methods, Π‐model, Mean Teacher, and FixMatch, increased the classification accuracy by 2.8%, 0.7%, and 3.9%, respectively, when only 100 labeled images per class were utilized. FixMatch was the most efficient and reliable model, as it exhibited higher accuracy (≥0.9530) and F1 scores (≥0.951) with fewer labeled data (50 per class) in the validation and testing data sets than the other neural networks evaluated.CONCLUSION: These results reveal that the SSL deep neural networks are capable of being highly accurate while requiring fewer labeled training images, thus being more time‐ and labor‐efficient than the FSL method. © 2024 Society of Chemical Industry.


  • Evaluation of the YOLO models for discrimination of the alfalfa pollinating bee species

    by Chuan-Jie Zhang, Teng Liu, Jinxu Wang, Danlan Zhai, Youxin Zhang, Yang Gao, Hui-Zhen Wu, Jialin Yu, Min Chen


  • Semi-supervised learning and attention mechanism for weed detection in wheat

    by Teng Liu, Xiaojun Jin, Luyao Zhang, Jie Wang, Yong Chen, Chengsong Hu, Jialin Yu


  • A smart sprayer for weed control in bermudagrass turf based on the herbicide weed control spectrum

    by Xiaojun Jin, Patrick E. McCullough, Teng Liu, Deyu Yang, Wenpeng Zhu, Yong Chen, Jialin Yu


  • Open Access

    Teleconnections among Tipping Elements in the Earth System

    by Teng Liu, Dean Chen, Lan Yang, Jun Meng, Zanchenling Wang, Josef Ludescher, Jingfang Fan, Saini Yang, Deliang Chen, Jürgen Kurths, et al.

    Tipping elements of the Earth system may shift abruptly and irreversibly from one state to another at tipping points, resulting in a growing threat to our society. Yet, it is not fully clear how to assess and quantify the influence of a tipping element and how to explore the teleconnections between different tipping elements. To fill this knowledge gap, we propose a climate network approach to quantitatively analyze the global impacts of a prominent tipping element, the Amazon Rainforest Area (ARA). We find that regions, such as, the Tibetan Plateau (TP) and West Antarctic ice sheet, are characterized by higher network weighted links and exhibit strong correlations with the ARA. We then identify a teleconnection propagation path between the ARA and the TP. This path is robust under climate change as simulated by various climate models of CMIP5 and CMIP6. In addition, we detect early warning signals for critical transition in the snow cover extent on the Tibetan Plateau by applying critical slowing down indicators, lag-1 autocorrelation and detrended fluctuation analysis. We find that the snow cover of the TP has been losing stability since 2008, revealing that the TP is operating like a tipping element and approaching a potential tipping point. We further uncover that various climate extremes between the ARA and the TP are significantly synchronized under climate change. Our framework provides new insights into how tipping elements are linked to each other and into the potential predictability of cascading tipping dynamics.