Convolutional neural networks for time series classification

Time series classification is an important task in time series data mining, and has attracted great interests and tremendous efforts during last decades. However, it remains a challenging problem due to the nature of time series data: high dimensionality, large in data size and updating continuously. The deep learning techniques are explored to improve the performance of traditional feature-based approaches. Specifically, a novel convolutional neural network (CNN) framework is proposed for time series classification. Different from other feature-based classification approaches, CNN can discover and extract the suitable internal structure to generate deep features of the input time series automatically by using convolution and pooling operations. Two groups of experiments are conducted on simulated data sets and eight groups of experiments are conducted on real-world data sets from different application domains. The final experimental results show that the proposed method outperforms state-of-the-art methods for time series classification in terms of the classification accuracy and noise tolerance. ? 1990-2011 Beijing Institute of Aerospace Information.

Recent Strengthening of the Regional Hadley Circulation over the Western Pacific during Boreal Spring

Previous studies suggested that there are large discrepancies in the intensity trend of the zonally averaged Hadley circulation (ZAHC) among different reanalyses. As the land, ocean, and topography are not evenly distributed, the ZAHC may mask the regional variability. Changes in the regional HC have important implications for regional climate change. Here, we detect the long-term trend of the boreal spring regional Hadley circulation intensity over the western Pacific (WPHC) since 1979 in both hemispheres using six reanalysis datasets. Unlike the ZAHC, we find that the trend of the spring WPHC intensity is consistent among various reanalysis datasets. All reanalyses show pronounced strengthening trends for the WPHC in both the Northern and Southern Hemisphere, which may be partly attributable to the robust warming trends of sea surface temperature in the tropical western Pacific. The result could improve our understanding of Hadley circulation variability at the regional scale and has implications for regional climate changes.

Intensified Impact of Northern Tropical Atlantic SST on Tropical Cyclogenesis Frequency over the Western North Pacific after the Late 1980s

Previous studies suggest that spring SST anomalies over the northern tropical Atlantic（NTA） affect the tropical cyclone（TC） activity over the western North Pacific（WNP） in the following summer and fall. The present study reveals that the connection between spring NTA SST and following summer–fall WNP TC genesis frequency is not stationary. The influence of spring NTA SST on following summer–fall WNP TC genesis frequency is weak and insignificant before, but strong and significant after, the late 1980 s. Before the late 1980 s, the NTA SST anomaly-induced SST anomalies in the tropical central Pacific are weak, and the response of atmospheric circulation over the WNP is not strong. As a result, the connection between spring NTA SST and following summer–fall WNP TC genesis frequency is insignificant in the former period. In contrast,after the late 1980 s, NTA SST anomalies induce pronounced tropical central Pacific SST anomalies through an Atlantic–Pacific teleconnection. Tropical central Pacific SST anomalies further induce favorable conditions for WNP TC genesis,including vertical motion, mid-level relative humidity, and vertical zonal wind shear. Hence, the connection between NTA SST and WNP TC genesis frequency is significant in the recent period. Further analysis shows that the interdecadal change in the connection between spring NTA SST and following summer–fall WNP TC genesis frequency may be related to the climatological SST change over the NTA region.

Improvement of a Snow Albedo Parameterization in the Snow–Atmosphere–Soil Transfer Model:Evaluation of Impacts of Aerosol on Seasonal Snow Cover

The presence of light-absorbing aerosols （LAA） in snow profoundly influence the surface energy balance and water budget. However, most snow-process schemes in land-surface and climate models currently do not take this into consider- ation. To better represent the snow process and to evaluate the impacts of LAA on snow, this study presents an improved snow albedo parameterization in the Snow-Atmosphere-Soil on snow. Specifically, the Snow, Ice and Aerosol Radiation Transfer （SAST） model, which includes the impacts of LAA （SNICAR） model is incorporated into the SAST model with an LAA mass stratigraphy scheme. The new coupled model is validated against in-situ measurements at the Swamp Angel Study Plot （SASP）, Colorado, USA. Results show that the snow albedo and snow depth are better reproduced than those in the original SAST, particularly during the period of snow ablation. Furthermore, the impacts of LAA on snow are esti- mated in the coupled model through case comparisons of the snowpack, with or without LAA. The LAA particles directly absorb extra solar radiation, which accelerates the growth rate of the snow grain size. Meanwhile, these larger snow particles favor more radiative absorption. The average total radiative forcing of the LAA at the SASP is 47.5 W m-2. This extra radiative absorption enhances the snowmelt rate. As a result, the peak runoff time and ＂snow all gone＂ day have shifted 18 and 19.5 days earlier, respectively, which could further impose substantial impacts on the hydrologic cycle and atmospheric processes.

The Weakening Relationship between ENSO and the South China Sea Summer Monsoon Onset in Recent Decades

The El Ni?o-Southern Oscillation(ENSO) is traditionally regarded as the most important factor modulating the interannual variation of the South China Sea summer monsoon(SCSSM) onset. A preceding El Ni?o(La Ni?a) usually tends to be followed by a delayed(an advanced) monsoon onset. However, the close relationship between ENSO and SCSSM onset breaks down after the early-2000 s, making seasonal prediction very difficult in recent years. Three possible perspectives have been proposed to explain the weakening linkage between ENSO and SCSSM onset, including interdecadal change of the ENSO teleconnection(i.e., the Walker circulation), interferences of other interannual variability(i.e., the Victoria mode), and disturbances on intraseasonal time scales(i.e., the quasi-biweekly oscillation). By comparing the epochs of 1979–2001 and 2002–19, it is found that the anomalous tropical Walker circulation generated by ENSO is much weaker in the latter epoch and thus cannot deliver the ENSO signal to the SCSSM onset. Besides, in recent years, the SCSSM onset is more closely linked to extratropical factors like the Victoria mode, and thus its linkage with ENSO becomes weaker. In addition to these interannual variabilities, the intraseasonal oscillations like the quasi-biweekly oscillation can disrupt the slow-varying seasonal march modulated by ENSO. Thus, the amplified quasi-biweekly oscillation may also contribute to the weakening relationship after the early-2000 s. Given the broken relationship between ENSO and SCSSM onset, the extratropical factors should be considered in order to make skillful seasonal predictions of SCSSM onset, and more attention should be paid to the extended-range forecast based on intraseasonal oscillations.

Micro-motion dynamics analysis of ballistic targets based on infrared detection

The dynamic characteristics related to micro-motions, such as mechanical vibration or rotation, play an essential role in classifying and recognizing ballistic targets in the midcourse, and recent researches explore ways of extracting the micro-motion features from radar signals of ballistic targets. In this paper, we focus on how to investigate the micro-motion dynamic characteristics of the ballistic targets from the signals based on infrared (IR) detection, which is mainly achieved by analyzing the periodic fluctuation characteristics of the target IR irradiance intensity signatures. Simulation experiments demonstrate that the periodic characteristics of IR signatures can be used to distinguish different micro motion types and estimate related parameters. Consequently, this is possible to determine the micro-motion dynamics of ballistic targets based on IR detection.

Impact of the Winter North Pacific Oscillation on the Surface Air Temperature over Eurasia and North America: Sensitivity to the Index Definition

This study analyzes the impact of the winter North Pacific Oscillation（NPO） on the surface air temperature（SAT）variations over Eurasia and North America based on six different NPO indices. Results show that the influences of the winter NPO on the SAT over Eurasia and North America are sensitive to the definition of the NPO index. The impact of the winter NPO on the SAT variations over Eurasia（North America） is significant（insignificant） when the anticyclonic anomaly associated with the NPO index over the North Pacific midlatitudes shifts westward and pronounced northerly wind anomalies appear around Lake Baikal. By contrast, the impact of the winter NPO on the SAT variations over Eurasia（North America）is insignificant（significant） when the anticyclonic anomaly over the North Pacific related to the NPO index shifts eastward and the associated northerly wind anomalies to its eastern flank extend to North America. The present study suggests that the NPO definition should be taken into account when analyzing the impact of the winter NPO on Eurasian and North American SAT variations.

Interdecadal Modulation of AMO on the Winter North Pacific Oscillation-Following Winter ENSO Relationship

It is known that the wintertime North Pacific Oscillation (NPO) is an important extratropical forcing for the occurrence of an El Ni-o-Southern Oscillation (ENSO) event in the subsequent winter via the “seasonal footprinting mechanism ”(SFM). This study reveals that the Atlantic Multidecadal Oscillation (AMO) can notably modulate the relationship between the winter NPO and the following winter ENSO. During the negative AMO phase, the winter NPO has significant impacts on the following winter ENSO via the SFM. In contrast, the influence of the winter NPO on ENSO is not robust at all during the positive AMO phase. Winter NPO-generated westerly wind anomalies over the equatorial western Pacific during the following spring are much stronger during negative than positive AMO phases. It is suggested that the AMO impacts the winter NPO-induced equatorial westerly winds over the western Pacific via modulating the precipitation climatology over the tropical central Pacific and via modulating the connection of the winter NPO with spring sea surface temperature in the tropical North Atlantic.