scholarly journals Soft Periodic Convolutional Recurrent Network for Spatiotemporal Climate Forecast

2021 ◽  
Vol 11 (20) ◽  
pp. 9728
Author(s):  
Ekasit Phermphoonphiphat ◽  
Tomohiko Tomita ◽  
Takashi Morita ◽  
Masayuki Numao ◽  
Ken-Ichi Fukui
Keyword(s):  
Southern Oscillation ◽  
Recurrent Network ◽  
Prediction Algorithm ◽  
Enso Cycle ◽  
Periodic Patterns ◽  
Forecasting Accuracy ◽  
Climate Forecasting ◽  
Machine Learning Applications ◽  
Sequential Information ◽  
Periodicity Component

Many machine-learning applications and methods are emerging to solve problems associated with spatiotemporal climate forecasting; however, a prediction algorithm that considers only short-range sequential information may not be adequate to deal with periodic patterns such as seasonality. In this paper, we adopt a Periodic Convolutional Recurrent Network (Periodic-CRN) model to employ the periodicity component in our proposals of the periodic representation dictionary (PRD). Phase shifts and non-stationarity of periodicity are the key components in the model to support. Specifically, we propose a Soft Periodic-CRN (SP-CRN) with three proposals of utilizing periodicity components: nearby-time (PRD-1), periodic-depth (PRD-2), and periodic-depth differencing (PRD-3) representation to improve climate forecasting accuracy. We experimented on geopotential height at 300 hPa (ZH300) and sea surface temperature (SST) datasets of ERA-Interim. The results showed the superiority of PRD-1 plus or minus one month of a prior cycle to capture the phase shift. In addition, PRD-3 considered only the depth of one differencing periodic cycle (i.e., the previous year) can significantly improve the prediction accuracy of ZH300 and SST. The mixed method of PRD-1, and PRD-3 (SP-CRN-1+3) showed a competitive or slight improvement over their base models. By adding the metadata component to indicate the month with one-hot encoding to SP-CRN-1+3, the prediction result was a drastic improvement. The results showed that the proposed method could learn four years of periodicity from the data, which may relate to the El Niño–Southern Oscillation (ENSO) cycle.

scholarly journals Influence of the 2015–2016 El Niño on the record-breaking mangrove dieback along northern Australia coast

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
S. Abhik ◽  
Pandora Hope ◽  
Harry H. Hendon ◽  
Lindsay B. Hutley ◽  
Stephanie Johnson ◽  
...  
Keyword(s):  
El Niño ◽  
El Nino ◽  
Southern Oscillation ◽  
Low Frequency ◽  
Multiple Linear Regression Model ◽  
Frequency Component ◽  
Enso Cycle ◽  
Northern Australia ◽  
Climate Conditions

AbstractThis study investigates the underlying climate processes behind the largest recorded mangrove dieback event along the Gulf of Carpentaria coast in northern Australia in late 2015. Using satellite-derived fractional canopy cover (FCC), variation of the mangrove canopies during recent decades are studied, including a severe dieback during 2015–2016. The relationship between mangrove FCC and climate conditions is examined with a focus on the possible role of the 2015–2016 El Niño in altering favorable conditions sustaining the mangroves. The mangrove FCC is shown to be coherent with the low-frequency component of sea level height (SLH) variation related to the El Niño Southern Oscillation (ENSO) cycle in the equatorial Pacific. The SLH drop associated with the 2015–2016 El Niño is identified to be the crucial factor leading to the dieback event. A stronger SLH drop occurred during austral autumn and winter, when the SLH anomalies were about 12% stronger than the previous very strong El Niño events. The persistent SLH drop occurred in the dry season of the year when SLH was seasonally at its lowest, so potentially exposed the mangroves to unprecedented hostile conditions. The influence of other key climate factors is also discussed, and a multiple linear regression model is developed to understand the combined role of the important climate variables on the mangrove FCC variation.

Changes in Observed Daily Precipitation over the United States between 1950–79 and 1980–2009

2013 ◽  
Vol 14 (1) ◽  
pp. 105-121 ◽  
Author(s):  
R. W. Higgins ◽  
V. E. Kousky
Keyword(s):  
United States ◽  
Great Plains ◽  
El Niño ◽  
Daily Precipitation ◽  
El Nino ◽  
Southern Oscillation ◽  
Heavy Precipitation ◽  
The United States ◽  
Enso Cycle ◽  
Precipitation Events

Abstract Changes in observed daily precipitation over the conterminous United States between two 30-yr periods (1950–79 and 1980–2009) are examined using a 60-yr daily precipitation analysis obtained from the Climate Prediction Center (CPC) Unified Raingauge Database. Several simple measures are used to characterize the changes, including mean, frequency, intensity, and return period. Seasonality is accounted for by examining each measure for four nonoverlapping seasons. The possible role of the El Niño–Southern Oscillation (ENSO) cycle as an explanation for differences between the two periods is also examined. There have been more light (1 mm ≤ P < 10 mm), moderate (10 mm ≤ P < 25 mm), and heavy (P ≥ 25 mm) daily precipitation events (P) in many regions of the country during the more recent 30-yr period with some of the largest and most spatially coherent increases over the Great Plains and lower Mississippi Valley during autumn and winter. Some regions, such as portions of the Southeast and the Pacific Northwest, have seen decreases, especially during the winter. Increases in multiday heavy precipitation events have been observed in the more recent period, especially over portions of the Great Plains, Great Lakes, and Northeast. These changes are associated with changes in the mean and frequency of daily precipitation during the more recent 30-yr period. Difference patterns are strongly related to the ENSO cycle and are consistent with the stronger El Niño events during the more recent 30-yr period. Return periods for both heavy and light daily precipitation events during 1950–79 are shorter during 1980–2009 at most locations, with some notable regional exceptions.

scholarly journals AMO- and ENSO-Driven Summertime Circulation and Precipitation Variations in North America

2012 ◽  
Vol 25 (19) ◽  
pp. 6477-6495 ◽  
Author(s):  
Qi Hu ◽  
Song Feng
Keyword(s):  
North America ◽  
Atmospheric Circulation ◽  
Time Scale ◽  
Southern Oscillation ◽  
Precipitation Anomaly ◽  
Enso Cycle ◽  
Interannual Variations ◽  
Recent Climate ◽  
Precipitation Anomalies ◽  
Forced Waves

Abstract Interannual and multidecadal time-scale anomalies in sea surface temperatures (SST) of the North Atlantic and North Pacific Oceans could result in persistent atmospheric circulation and regional precipitation anomalies for years to decades. Understanding the processes that connect such SST forcings with circulation and precipitation anomalies is thus important for understanding climate variations and for improving predictions at interannual–decadal time scales. This study focuses on the interrelationship between the Atlantic multidecadal oscillation (AMO) and El Niño–Southern Oscillation (ENSO) and their resulting interannual to multidecadal time-scale variations in summertime precipitation in North America. Major results show that the ENSO forcing can strongly modify the atmospheric circulation variations driven by the AMO. Moreover, these modifications differ considerably between the subtropics and the mid- and high-latitude regions. In the subtropics, ENSO-driven variations in precipitation are fairly uniform across longitudes so ENSO effects only add interannual variations to the amplitude of the precipitation anomaly pattern driven by the AMO. In the mid- and high latitudes, ENSO-forced waves in the atmosphere strongly modify the circulation anomalies driven by the AMO, resulting in distinctive interannual variations following the ENSO cycle. The role of the AMO is shown by an asymmetry in precipitation during ENSO between the warm and cold phases of the AMO. These results extend the outcomes of the studies of the recent Climate Variability and Predictability (CLIVAR) Drought Working Group from the AMO and ENSO effects on droughts to understanding of the mechanisms and causal processes connecting the individual and combined SST forcing of the AMO and ENSO with the interannual and multidecadal variations in summertime precipitation and droughts in North America.

Analysis of the ENSO Cycle in the NCEP Coupled Forecast Model

2007 ◽  
Vol 20 (7) ◽  
pp. 1265-1284 ◽  
Author(s):  
Qin Zhang ◽  
Arun Kumar ◽  
Yan Xue ◽  
Wanqiu Wang ◽  
Fei-Fei Jin
Keyword(s):  
Model Simulation ◽  
Southern Oscillation ◽  
Coupled Model ◽  
Coupled System ◽  
Forecast Model ◽  
Enso Cycle ◽  
Positive Contribution ◽  
Test Bed ◽  
Model Simulations ◽  
Thermocline Feedback

Abstract Simulations from the National Centers for Environmental Prediction (NCEP) coupled model are analyzed to document and understand the behavior of the evolution of the El Niño–Southern Oscillation (ENSO) cycle. The analysis is of importance for two reasons: 1) the coupled model used in this study is also used operationally to provide model-based forecast guidance on a seasonal time scale, and therefore, an understanding of the ENSO mechanism in this particular coupled system could also lead to an understanding of possible biases in SST predictions; and 2) multiple theories for ENSO evolution have been proposed, and coupled model simulations are a useful test bed for understanding the relative importance of different ENSO mechanisms. The analyses of coupled model simulations show that during the ENSO evolution the net surface heat flux acts as a damping mechanism for the mixed-layer temperature anomalies, and positive contribution from the advection terms to the ENSO evolution is dominated by the linear advective processes. The subsurface temperature–SST feedback, referred to as thermocline feedback in some theoretical literature, is found to be the primary positive feedback, whereas the advective feedback by anomalous zonal currents and the thermocline feedback are the primary sources responsible for the ENSO phase transition in the model simulation. The basic mechanisms for the model-simulated ENSO cycle are thus, to a large extent, consistent with those highlighted in the recharge oscillator. The atmospheric anticyclone (cyclone) over the western equatorial northern Pacific accompanied by a warm (cold) phase of the ENSO, as well as the oceanic Rossby waves outside of 15°S–15°N and the equatorial higher-order baroclinic modes, all appear to play minor roles in the model ENSO cycles.

The Influence of the El Niño–Southern Oscillation on Cloud-to-Ground Lightning Activity along the Gulf Coast. Part I: Lightning Climatology

2008 ◽  
Vol 136 (7) ◽  
pp. 2523-2542 ◽  
Author(s):  
Mark LaJoie ◽  
Arlene Laing
Keyword(s):  
El Niño ◽  
Gulf Coast ◽  
El Nino ◽  
Southern Oscillation ◽  
Winter Season ◽  
Lightning Activity ◽  
El Niño Southern Oscillation ◽  
El Nino Southern Oscillation ◽  
Enso Cycle ◽  
Lightning Flash

Abstract Cloud-to-ground (CG) lightning flashes from the National Lightning Detection Network are analyzed to determine if the El Niño–Southern Oscillation (ENSO) cycle influences lighting activity along the Gulf Coast region. First, an updated climatology of lightning was developed for the region. Flash density maps are constructed from an 8-yr dataset (1995–2002) and compared with past lightning climatologies. Second, lightning variability is compared with the phases of ENSO. Winter lightning distributions are compared with one published study of ENSO and lightning days in the Southeast. Flash density patterns are, overall, consistent with past U.S. lightning climatology. However, the peak flash density for the annual mean was less than observed in previous climatologies, which could be due to the disproportionately large percentage of cool ENSO periods compared to previous lightning climatologies. The highest annual lightning counts were observed in 1997, which consisted of mostly warm ENSO seasons; the 1997–98 El Niño was one of the strongest on record. The lowest lightning counts were observed in 2000, which had mostly cool or neutral phases of ENSO including the lowest Niño-3.4 anomaly of the study period. Analysis of winter season lightning flash densities substantiated the role of the ENSO cycle in winter season lightning fluctuations. Winter lightning activity increased dramatically during the 1997–98 El Niño. The lowest winter flash densities are associated with cool ENSO phases. Although 8 yr is inadequate to establish a long-term pattern, results indicate that ENSO influences lightning and that further study is warranted. As more years of lightning data are acquired, a more complete climatology can be developed.

scholarly journals Reexamining El Niño and Cholera in Peru: A Climate Affairs Approach

2013 ◽  
Vol 5 (2) ◽  
pp. 148-161 ◽  
Author(s):  
Iván J. Ramírez ◽  
Sue C. Grady ◽  
Michael H. Glantz
Keyword(s):  
El Niño ◽  
Elevated Temperatures ◽  
El Nino ◽  
Southern Oscillation ◽  
La Niña ◽  
Enso Cycle ◽  
Holistic View ◽  
La Nina ◽  
Cholera Epidemic ◽  
The Impact

Abstract In the 1990s Peru experienced the first cholera epidemic after almost a century. The source of emergence was initially attributed to a cargo ship, but later there was evidence of an El Niño association. It was hypothesized that marine ecosystem changes associated with El Niño led to the propagation of V. cholerae along the coast of Peru, which in turn initiated the onset of the epidemic in 1991. Earlier studies supported this explanation by demonstrating a relationship between elevated temperatures and increased cholera incidence in Peru; however, other aspects of El Niño–Southern Oscillation (ENSO) and their potential impacts on cholera were not investigated. Therefore, this study examines the relationship between El Niño and cholera in Peru from a holistic view of the ENSO cycle. A “climate affairs” approach is employed as a conceptual framework to incorporate ENSO’s multidimensional nature and to generate new hypotheses about the ENSO and cholera association in Peru. The findings reveal that ENSO may have been linked to the cholera epidemic through multiple pathways, including rainfall extremes, La Niña, and social vulnerability, with impacts depending on the geography of teleconnections within Peru. When the definition of an ENSO event is examined, cholera appears to have emerged either during ENSO neutral or La Niña conditions. Furthermore, the analysis herein suggests that the impact of El Niño arrived much later, possibly resulting in heightened transmission in the austral summer of 1992. In conclusion, a modified hypothesis with these new insights on cholera emergence and transmission in Peru is presented.

scholarly journals The ENSO–Asian Monsoon Interaction in a Coupled Ocean–Atmosphere GCM

2007 ◽  
Vol 20 (20) ◽  
pp. 5164-5177 ◽  
Author(s):  
Ying Li ◽  
Riyu Lu ◽  
Buwen Dong
Keyword(s):  
El Niño ◽  
Asian Monsoon ◽  
El Nino ◽  
Southern Oscillation ◽  
La Niña ◽  
Enso Cycle ◽  
Central Pacific ◽  
La Nina ◽  
Ocean Atmosphere ◽  
The Relationship

Abstract In this study, the authors evaluate the (El Niño–Southern Oscillation) ENSO–Asian monsoon interaction in a version of the Hadley Centre coupled ocean–atmosphere general circulation model (CGCM) known as HadCM3. The main focus is on two evolving anomalous anticyclones: one located over the south Indian Ocean (SIO) and the other over the western North Pacific (WNP). These two anomalous anticyclones are closely related to the developing and decaying phases of the ENSO and play a crucial role in linking the Asian monsoon to ENSO. It is found that the HadCM3 can well simulate the main features of the evolution of both anomalous anticyclones and the related SST dipoles, in association with the different phases of the ENSO cycle. By using the simulated results, the authors examine the relationship between the WNP/SIO anomalous anticyclones and the ENSO cycle, in particular the biennial component of the relationship. It is found that a strong El Niño event tends to be followed by a more rapid decay and is much more likely to become a La Niña event in the subsequent winter. The twin anomalous anticyclones in the western Pacific in the summer of a decaying El Niño are crucial for the transition from an El Niño into a La Niña. The El Niño (La Niña) events, especially the strong ones, strengthen significantly the correspondence between the SIO anticyclonic (cyclonic) anomaly in the preceding autumn and WNP anticyclonic (cyclonic) anomaly in the subsequent spring, and favor the persistence of the WNP anomaly from spring to summer. The present results suggest that both El Niño (La Niña) and the SIO/WNP anticyclonic (cyclonic) anomalies are closely tied with the tropospheric biennial oscillation (TBO). In addition, variability in the East Asian summer monsoon, which is dominated by the internal atmospheric variability, seems to be responsible for the appearance of the WNP anticyclonic anomaly through an upper-tropospheric meridional teleconnection pattern over the western and central Pacific.

scholarly journals Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns

2018 ◽  
Author(s):  
Ali Zonoozi ◽  
Jung-jae Kim ◽  
Xiao-Li Li ◽  
Gao Cong
Keyword(s):  
Traffic Management ◽  
State Of The Art ◽  
Recurrent Network ◽  
Temporal Data ◽  
Periodic Patterns ◽  
Temporal Correlations ◽  
Density Prediction ◽  
Crowd Density ◽  
Spatial Domains ◽  
Spatio Temporal

Time-series forecasting in geo-spatial domains has important applications, including urban planning, traffic management and behavioral analysis. We observed recurring periodic patterns in some spatio-temporal data, which were not considered explicitly by previous non-linear works. To address this lack, we propose novel `Periodic-CRN' (PCRN) method, which adapts convolutional recurrent network (CRN) to accurately capture spatial and temporal correlations, learns and incorporates explicit periodic representations, and can be optimized with multi-step ahead prediction. We show that PCRN consistently outperforms the state-of-the-art methods for crowd density prediction across two taxi datasets from Beijing and Singapore.

Sign in / Sign up

Export Citation Format

Share Document