Jun Jian

Prof. Dr. Jun Jian

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
26 November 2020 in Nature Communications
Verified
Journal Article
Open access
PDF file
MRMukund P. Rao
Mukund P. Rao
ECEdward R. Cook
Edward R. Cook
BCBenjamin I. Cook
Benjamin I. Cook
RDRosanne D. D’arrigo
Rosanne D. D’arrigo
JPJonathan G. Palmer
Jonathan G. Palmer
PWPeter J. Webster
Peter J. Webster
The lower Brahmaputra River in Bangladesh and Northeast India often floods during the monsoon season, with catastrophic consequences for people throughout the region. While most climate models predict an intensified monsoon and increase in flood risk with warming, robust baseline estimates of natural climate variability in the basin are limited by the short observational record. Here we use a new seven-century (1309–2004 C.E) tree-ring reconstruction of monsoon season Brahmaputra discharge to demonstrate that the early instrumental period (1956–1986 C.E.) ranks amongst the driest of the past seven centuries (13th percentile). Further, flood hazard inferred from the recurrence frequency of high discharge years is severely underestimated by 24–38% in the instrumental record compared to previous centuries and climate model projections. A focus on only recent observations will therefore be insufficient to accurately characterise flood hazard risk in the region, both in the context of natural variability and climate change.

1 September 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JJJun Jian
Jun Jian
LLLong Liu Liu
Long Liu Liu
YZYingxiang Zhang
Yingxiang Zhang
KXKe Xu
Ke Xu
Jiaxuan YangJiaxuan Yang
Jiaxuan Yang
Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area of ship targets is small, and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed and false detection. To solve these problems, this paper proposes an improved-YOLOv5 algorithm mainly including: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce a cross-layer connection channel and lightweight GSConv structures into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) Use the Wise-IoU loss function to calculate the localization loss in the Output, and assign reasonable gradient gains to cope with differences in image quality. In addition, during the preprocessing stage of experimental data, a median+bilateral filter method was used to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Improved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; compared to the original YOLOv5s, the mean Average Precision (mAP) improved by 3.2% and the Frames Per Second (FPN) accelerated by 8.7%.

2 May 2025 in Agricultural and Forest Meteorology
Verified
Journal Article
Open access
Tao ZhuTao Zhu
Tao Zhu
MLMengqian Lu
Mengqian Lu
JYJing Yang
Jing Yang
QBQing Bao
Qing Bao
SNStacey New
Stacey New
BPBaoxiang Pan
Baoxiang Pan

4 July 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
JJJun Jian
Jun Jian
LLLong Liu Liu
Long Liu Liu
YZYingxiang Zhang
Yingxiang Zhang
KXKe Xu
Ke Xu
Jiaxuan YangJiaxuan Yang
Jiaxuan Yang
Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area ratio of ship targets is small and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed detection and false detection. In this study, we propose an improved-YOLOv5 algorithm. The improvement strategies mainly include: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce cross-layer connection channel and lightweight GSConv structure into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) The Wise-IoU loss function is used to cal-culate the localization loss in the Output, and assign reasonable gradient gains to cope with dif-ferences in image quality. In addition, during the preprocessing stage of experimental data, a me-dian and bilateral filter method is used for noise reduction to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Im-proved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; Compared to the original YOLOv5s, the mean Average Precision (mAP) has improved by 3.2% and the Frames Per Second (FPN) has accelerated by 8.7%.

28 January 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
JJJun Jian
Jun Jian
ZSZheng Sun
Zheng Sun
KSKai Sun
Kai Sun
Sailing vessel navigators always want to receive state-of-the-art prompt and accurate marine weather-forecasting services. However, the weather-routing services by private sectors are expensive. Further, forecasting results from public institutes are usually free, and they are not in real-time or numerical modes, so they are not quite suitable for small-size or offshore vessels. In this study, an intelligent system was constructed for delivering sea forecasting at specific areas according to the navigator’s order. The system can automatically obtain web-based forecasting charts issued from multi-source meteorological agencies and convert the regional information into numerical text at requested points. During this step, several intelligent algorithms, like the OpenCV digital image processing algorithm and the YOLO wind vector deep learning recognition method, were applied. By applying this state-of-the-art system, navigators on board do not need to download different institutional graphics (usually with large stream bytes) to explore the future states of the sea surface in a specific area in the sailing route but can obtain the multi-source text forecasting information just by sending the area coordinates to a designated email address. The field tests confirmed that this auto-intelligent system could assist the navigator within a few minutes and thus greatly enhance the navigation safety with minor text-based communication costs. It is expected that by improving the efficiency of marine services and bringing in more artificial intelligence technology, maritime security would be more sustainable.

Verified
Journal Article
Open access
PDF file
JJJun Jian
Jun Jian
YZYingxiang Zhang
Yingxiang Zhang
KXKe Xu
Ke Xu
PWPeter J. Webster
Peter J. Webster
This study is aimed to improve the intelligence level, efficiency, and accuracy of ship safety and security systems by contributing to the development of marine weather forecasting. The accurate and prompt recognition of weather fax charts is very important for navigation safety. This study employed many artificial intelligent (AI) methods including a vectorization approach and target recognition algorithm to automatically detect the severe weather information from Japanese and US weather charts. This enabled the expansion of an existing auto-response marine forecasting system’s applications toward north Pacific and Atlantic Oceans, thus enhancing decision-making capabilities and response measures for sailing ships at actual sea. The OpenCV image processing method and YOLOv5s/YOLO8vn algorithm were utilized to make template matches and locate warning symbols and weather reports from surface weather charts. After these improvements, the average accuracy of the model significantly increased from 0.920 to 0.928, and the detection rate of a single image reached a maximum of 1.2 ms. Additionally, OCR technology was applied to retract texts from weather reports and highlighted the marine areas where dense fog and great wind conditions are likely to occur. Finally, the field tests confirmed that this auto and intelligent system could assist the navigator within 2–3 min and thus greatly enhance the navigation safety in specific areas in the sailing routes with minor text-based communication costs.