Jianfen Wei

China Meteorological Administration

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Zhaomin Wang

Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)

Xiangdong Zhang

University of Alaska Fairbanks

Renlong Hang

Nanjing University of Information Science and Technology

Mingyi Gu

Nanjing University of Information Science and Technology

Jie Su

Ocean University of China

Jing‐Jia Luo

Nanjing University of Information Science and Technology

Lingling Ge

China Meteorological Administration

Xue Mei

Shandong First Medical University

Yunhe Wang

Chinese Academy of Sciences

Changming Dong

Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)

Cooperative Institutions

Nanjing University of Information Science and Technology

Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)

Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)

Ministry of Natural Resources

China Meteorological Administration

Second Institute of Oceanography

Shandong First Medical University

Chinese Academy of Sciences

Institute of Oceanology

University of Chinese Academy of Sciences

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Mechanism of an Abrupt Decrease in Sea-Ice Cover in the Pacific Sector of the Arctic during the Late 1980s

ATMOSPHERE-OCEAN (2014)

Jianfen Wei Jie Su

The recent decline in Arctic sea-ice cover (SIC) shows seasonal and regional characteristics. The retreat of summer sea ice has occurred mainly in the Pacific sector of the Arctic. In this study, using the moving t-test, we found an abrupt change event in the long-term sea-ice area in the Pacific sector in summer 1989. This event was linked to the phase shift of the Arctic Oscillation (AO) or the Northern Annular Mode (NAM). Corresponding with the AO/NAM phase shift from negative to positive, the area of the northern hemisphere stratospheric polar vortex decreased abruptly in winter 1988/89. Comparisons of two periods before (1979–1988) and after (1989–1993) the abrupt decrease in sea ice show that an anomalous winter sea level pressure (SLP) was induced by changes in the polar vortex leading to an anomalous cyclonic ice drift in the Pacific sector. The changes in SLP and wind field persisted into the following spring, resulting in a decrease in SIC and warming of the surface air temperature (SAT). The influence of the spring SLP and SAT on ice persisted into the following summer. Meanwhile, the increased summer net surface heat flux over the ocean and sea ice as a result of the decreased spring ice cover further contributed to the summer sea-ice melt.

Arctic oscillation

Arctic geoengineering

Arctic dipole anomaly

10.1080/07055900.2014.970505

Cite

Citations (2)

Impacts of extratropical storm tracks on Arctic sea ice export through Fram Strait

Climate Dynamics (2018)

Jianfen Wei Xiangdong Zhang Zhaomin Wang

Studies have indicated regime shifts in atmospheric circulation, and associated changes in extratropical storm tracks and Arctic storm activity, in particular on the North Atlantic side of the Arctic Ocean. To improve understanding of changes in Arctic sea ice mass balance, we examined the impacts of the changed storm tracks and cyclone activity on Arctic sea ice export through Fram Strait by using a high resolution global ocean–sea ice model, MITgcm–ECCO2. The model was forced by the Japanese 25-year Reanalysis (JRA-25) dataset. The results show that storm-induced strong northerly wind stress can cause simultaneous response of daily sea ice export and, in turn, exert cumulative effects on interannual variability and long-term changes of sea ice export. Further analysis indicates that storm impact on sea ice export is spatially dependent. The storms occurring southeast of Fram Strait exhibit the largest impacts. The weakened intensity of winter (in this study winter is defined as October–March and summer as April–September) storms in this region after 1994/95 could be responsible for the decrease of total winter sea ice export during the same time period.

Extratropical cyclone

Arctic dipole anomaly

Arctic geoengineering

Storm track

Winter storm

10.1007/s00382-018-4254-8

Cite

Citations (16)

Prediction of Pan-Arctic Sea Ice Using Attention-Based LSTM Neural Networks

Frontiers in Marine Science (2022)

Jianfen Wei Renlong Hang Jing‐Jia Luo

Within the rapidly changing Arctic region, accurate sea ice forecasts are of crucial importance for navigation activities, such as the planning of shipping routes. Numerical climate models have been widely used to generate Arctic sea ice forecasts at different time scales, but they are highly dependent on the initial conditions and are computationally expensive. Recently, with the increasing availability of geoscience data and the advances in deep learning algorithms, the use of artificial intelligence (AI)-based sea ice prediction methods has gained significant attention. In this study, we propose a supervised deep learning approach, namely attention-based long short-term memory networks (LSTMs), to forecast pan-Arctic sea ice at monthly time scales. Our method makes use of historical sea ice concentration (SIC) observations during 1979–2020, from passive microwave brightness temperatures. Based on the persistence of SIC anomalies, which is known as one of the dominant sources of sea ice predictability, our approach exploits the temporal relationships of sea ice conditions across different time windows of the training period. We demonstrate that the attention-based LSTM is able to learn the variations of the Arctic sea ice and can skillfully forecast pan-Arctic SIC on monthly time scale. By designing the loss function and utilizing the attention mechanism, our approach generally improves the accuracy of sea ice forecasts compared to traditional LSTM networks. Moreover, it outperforms forecasts with the climatology and persistence based empirical models, as well as two dynamical models from the Copernicus Climate Change Service (C3S) datastore. This approach shows great promise in enhancing forecasts of Arctic sea ice using AI methods.

Predictability

Sea ice concentration

10.3389/fmars.2022.860403

Cite

Citations (20)

An assessment of Arctic cloud water paths in atmospheric reanalyses

Acta Oceanologica Sinica (2021)

Mingyi Gu Zhaomin Wang Jianfen Wei Xiaoyong Yu

Interim

10.1007/s13131-021-1706-5

Cite

Citations (16)

An evaluation of the Arctic clouds and surface radiative fluxes in CMIP6 models

Acta Oceanologica Sinica (2021)

Jianfen Wei Zhaomin Wang Mingyi Gu Jing‐Jia Luo Yunhe Wang

Shortwave radiation

Shortwave

Cloud fraction

Longwave

Liquid water path

10.1007/s13131-021-1705-6

Cite

Citations (13)

Impacts of Changed Extratropical Storm Tracks on Arctic Sea Ice Export through Fram Strait

AGU Fall Meeting Abstracts (2017)

Jianfen Wei X. Zhang Z. Wang

Extratropical cyclone

Winter storm

Source

Cite

Citations (0)

Reexamination of Fram Strait sea ice export and its role in recently accelerated Arctic sea ice retreat

Climate Dynamics (2019)

Jianfen Wei Xiangdong Zhang Zhaomin Wang

Using the high-resolution global ocean-sea ice model MITgcm-ECCO2, variability and changes of Arctic sea ice export through Fram Strait during 1979–2012 are examined. The simulated annual mean ice export is about 3216 km3/year, which is 12.7% of the 34-year averaged Arctic sea ice volume, with the maximum and minimum occurring in 1994/95 and 1984/1985, respectively. Winter (October–March) ice export is much more than summer (April–September) and exhibits a greater interannual variation. This study suggests that a significant regime shift of Fram Strait ice export from high to low value occurs around the mid-1990s. Further analysis shows that the regime shift of the atmospheric circulation from conventional Arctic Oscillation/North Atlantic Oscillation (AO/NAO) to the dipole-structure Arctic Rapid change Pattern (ARP) plays an important role on the regime shift of ice export. This shift of atmospheric circulation pattern dominates the variability of ice motion and changes the main source region of ice outflow. Combined with the decreased ice thickness and the less ice outflow related to the weakened northerly/northeasterly winds near the strait, sea ice export decreased, eventually generating a regime shift around the mid-1990s. The distinct impact of changes in Fram Strait ice export on the Arctic sea ice inside the basin before and after mid-1990s indicates that the recent continuing loss of Arctic sea ice was mainly induced by the accelerated ice melting in the Arctic Ocean, rather than the ice outflow through Fram Strait.

Lead (geology)

Outflow

Fast ice

Arctic dipole anomaly

Ice core

Arctic geoengineering

10.1007/s00382-019-04741-0

Cite

Citations (22)

Correction to: Impacts of extratropical storm tracks on Arctic sea ice export through Fram Strait

Climate Dynamics (2019)

Jianfen Wei Xiangdong Zhang Zhaomin Wang

The article Impacts of extratropical storm tracks on Arctic sea ice export through Fram Strait.

Extratropical cyclone

Winter storm

10.1007/s00382-019-04770-9

Cite

Citations (0)

Correction to: Reexamination of Fram Strait sea ice export and its role in recently accelerated Arctic sea ice retreat

Climate Dynamics (2019)

Jianfen Wei Xiangdong Zhang Zhaomin Wang

The article Reexamination of Fram Strait sea ice export and its role in recently accelerated Arctic sea ice retreat, written by, was originally published electronically on the publisher's internet portal (currently SpringerLink) on 29 March 2019 without open access.

Internet portal

10.1007/s00382-019-04828-8

Cite

Citations (1)

Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2022)

Renlong Hang Gang Li Xue Mei Changming Dong Jianfen Wei

Identifying oceanic eddy from remotely sensed sea surface height (SSH) data is challenging, mainly because of its large-size variations. This article proposes an automatic identification model upon convolutional neural networks for dealing with this issue. The proposed network is comprised of two branches: an eddy identification branch and an edge extraction branch. Both of them adopt encoder–decoder frameworks, and the encoder is shared with each other. The eddy identification branch simultaneously uses multiscale convolution modules in the encoder and skip-layer connections between the encoder and the decoder to learn multiscale features, thus effectively identifying eddies with different sizes. Differently, the edge extraction branch is designed to learn the edge information of eddies, which is not fully captured by the eddy identification branch. To sufficiently evaluate the identification performance of our proposed model, several experiments are conducted on a public eddy identification dataset named SCSE-Eddy, and the results indicate that the proposed model is capable of achieving higher performance than those of the existing identification models.

Identification

Eddy

10.1109/jstars.2022.3215696

Cite

Citations (22)