Temperature Anomalies Research Articles

A Coupled Quadrupole Mode in the South Pacific

Abstract Although links between the atmospheric convergence zone and the local ocean dipole in the South Atlantic are well established, relationships between the South Pacific convergence zone (SPCZ) and the South Pacific quadrupole (SPQ) remain largely unexplored. Based on maximum covariance analysis applied to a 110-yr monthly coupled atmosphere–ocean reanalysis, we describe a coupled quadrupole mode (CQM) that connects the SPCZ and SPQ during austral summer [December–February (DJF)]. The CQM is linked to the “enhanced SPCZ” mode in the atmosphere and the SPQ in the ocean, with the atmospheric signal leading the ocean signal by about 1 month. This coupled mode essentially represents the atmospheric and oceanic responses to a stationary Rossby wave train that propagates from low- to high latitudes before reflecting back toward lower latitudes around 150°E. Coupled atmosphere–ocean feedbacks help to maintain anomalous convective activity in the SPCZ and related circulation anomalies. The stationary waves that organize the CQM are often rooted in anomalous convection over the Maritime Continent and have close connections with the atmospheric wavenumber-4 mode in the midlatitude Southern Hemisphere. Significance Statement In this study, we investigate the relationships between coherent large-scale patterns in the South Pacific Ocean and the overlying atmosphere. These patterns, which we refer to as a coupled quadrupole for their four centers of action, impact both local communities and the global climate by shaping rainfall and temperature anomalies across the “four corners” of the South Pacific: east–west and north–south. We show that this coupled quadrupole arises as the joint atmospheric and oceanic response to a large-scale wave that arcs across the entire South Pacific basin more than 10 km above the surface and that feedbacks from the ocean to the atmosphere help it to last longer.

Prediction of Summer Precipitation via Machine Learning with Key Climate Variables：A Case Study in Xinjiang, China

Study region: Xinjiang is located in the mid-latitude region of Eurasia in northwestern China. Precipitation is predominantly concentrated in northern Xinjiang, while southern Xinjiang remains comparatively arid. Summer precipitation accounts for 54.4% of the annual total. Study focus: This study aims to develop a machine learning model to predict summer precipitation (June–August) in XJ and explore the key variables contributing to summer precipitation in this region. The SHapley Additive exPlanations method was integrated with an extreme tree model to quantify the contributions of variables towards precipitation. Artificial neural networks, support vector machines, and extreme gradient boosting were considered to predict summer precipitation. To train the ML model, we used precipitation data from 1961 to 2012, whilst the forecast results from 2013 to 2017 were used for validation.New hydrological insights for the regions: The results demonstrated that the ANN model achieved robust performance during both the training and validation periods. For Northern and Southern XJ, the Mean Absolute Error and Root Mean Square Error of the ANN model were 15.34 (20.40) and 23.21 (30.01), respectively. The SHAP analysis showed that in the context of Northern Xinjiang, the Niño B Sea Surface Temperature Anomaly, Western Pacific Subtropical High Intensity, Pacific Subtropical High Intensity, and Multivariate ENSO Index play crucial roles in the prediction of summer precipitation. In Southern Xinjiang, the South China Sea Subtropical High Intensity, South China Sea Subtropical High Area, Western Pacific Warm Pool Strength, and Atlantic multidecadal oscillation have emerged as key variables affecting summer precipitation forecasting.

Investigating the Relative Contribution from Tropical Indo-Pacific SST to Asian Monsoon Precipitation Variability Using LIM

Abstract A critical issue is determining the factors that control the year-to-year variability in precipitation over southern Asia. In this study, we employ a cyclostationary linear inverse model (CS-LIM) to quantify the relative contribution of tropical Pacific and Indian Ocean sea surface temperature anomalies (SSTAs) to the interannual variability of the Asian monsoon, especially Indian summer monsoon rainfall (ISMR). Through a series of CS-LIM experiments, we isolate the impacts of the direct forcing from Pacific SSTAs, Indian Ocean SSTAs, and their interaction on Asian monsoon rainfall variability. Our results reveal distinct patterns of influence with the direct forcing from the Pacific (Indian) Ocean tending to enhance (reduce) the magnitude of precipitation variability, while the Indo-Pacific interaction acts to strongly damp the variability of Asian monsoon precipitation, especially over India. We further investigate these specific impacts on ISMR by analyzing the relationship between tropical Indo-Pacific SSTAs and the leading three empirical orthogonal functions (EOFs) of ISMR. The results from our CS-LIM experiments indicate that the direct forcing from El Niño–Southern Oscillation (ENSO) enhances the variability of the first and third EOFs, while the Indian Ocean SSTA opposes ENSO’s effects, which is consistent with previous studies. Our new results show that the tropical Indo-Pacific interaction strongly damps ISMR variability, which is due to the ENSO-induced Indian Ocean dipole (IOD) opposing the direct impacts from ENSO on ISMR. Additionally, reduced ENSO amplitude and duration associated with the Indo-Pacific interaction may also contribute to the damping effect on ISMR, but this requires further study to understand the relevant mechanisms.

Equatorial Pacific Cold Tongue Bias Degrades Simulation of ENSO Asymmetry due to Underestimation of Strong Eastern Pacific El Niños

Abstract El Niño–Southern Oscillation (ENSO) exhibits a considerable asymmetry in sea surface temperature anomalies (SSTa), as El Niño events tend to be stronger and centered further east than La Niña events. Here, we analyze ENSO asymmetry in observations and preindustrial control integrations of 32 models participating in phase 6 of the Coupled Model Intercomparison Project (CMIP6). Observations indicate a significant link between strong eastern Pacific (EP) El Niño events and the ENSO amplitude and asymmetry. The large CMIP6 database confirms this strong link. Most CMIP6 models suffer from an equatorial Pacific cold SST bias. This cold tongue bias hinders the southward migration of the ITCZ toward the equator over the eastern equatorial Pacific, which is characteristic of strong EP El Niño events in observations. Therefore, many models underestimate the eastern equatorial Pacific rainfall anomalies and simulate a wind stress feedback over the western Pacific that is too weak and too far west. As a result, the cold tongue bias exerts a strong control on the climate models’ ability to generate strong EP El Niño events and therefore on the ENSO overall amplitude and asymmetry. We discuss the relevance of these results in view of a potential increase of strong EP El Niño events under global warming. Significance Statement El Niño and La Niña are asymmetric, as El Niño events tend to be stronger and further east than La Niña events. Due to an equatorial Pacific cold tongue bias with too cold SSTs, the simulation of ENSO asymmetry is degraded in many climate models participating in CMIP6. Here, we show how the cold tongue bias influences ENSO asymmetry. The cold bias hampers the simulation of strong eastern Pacific El Niños by making it more difficult for SST to exceed the threshold for deep atmospheric convection over the eastern equatorial Pacific. Recent research indicates that climate models with a realistic ENSO asymmetry agree on the projected ENSO under global warming. The results of this study suggest that reducing the cold tongue bias has the potential to enhancing the reliability of future ENSO projections.

Long-span multi-layer spillovers between moments of advanced equity markets: The role of climate risks

In this paper, we examine the potential spillovers between returns, volatility, skewness and kurtosis of developed stock markets under the lenses of rare disaster events, proxied by climate risks. The aforementioned moments based on model-implied distributions of stock returns are derived from the quantile autoregressive distributed lag mixed-frequency data sampling (QADL-MIDAS) method, using a long span of data. The empirical findings are as follows: firstly, spillovers are significant within- and across stock markets for each of the four moments. Secondly, based on a nonparametric causality-in-quantiles approach, changes in temperature anomalies, have the predictive power to shape the entire conditional distribution of various metrics of spillover involving single- and multiple-layers of returns and risks layers. In sum, we show that the multi-layer approach offers a comprehensive and nuanced view of how stock market-related information is transmitted across the stock markets of advanced economies, carrying implications for investors and policymakers.

Localization and Delocalization During Seismic Slip

AbstractThe thickness of a seismic slip layer controls style and rate of rupture propagation, frictional heating, weakening, and energy budget of earthquakes. Slip layer thickness changes dynamically with feedbacks between temperature rise, roughness, damage, and fluid pressurization. Natural faults have complex slip histories, ambiguating which layer thicknesses represent a record of seismic slip. The thickness of proven paleoseismic slip layers in nature are 1 mm–1 cm. Thicker slip layers do not get hot enough to retain coseismic frictional temperature anomalies and thereby prevent the detection of big earthquakes using current methods. We suggest that delocalization—the spontaneous increase in slipping layer thickness during slip—plays a role in coseismic healing and cause biases in the rock record of earthquakes. Recognizing the importance of feedbacks affecting slipping layer thickness is critical to understanding strength and stress variations during earthquakes and to correctly interpreting earthquake source parameters from exhumed faults.

Remote Sensing Technologies Using UAVs for Pest and Disease Monitoring: A Review Centered on Date Palm Trees

Remote Sensing Technologies Using UAVs for Pest and Disease Monitoring: A Review Centered on Date Palm Trees

Contrasting impact of single-year and multi-year El Niño on the Pacific-North American teleconnection pattern

Abstract Distinct Pacific-North American (PNA) teleconnection patterns and their associated climate impacts in North America have been observed during single-year El Niño events, as well as during both the first and second years of multi-year El Niño events. The research highlights the critical role of PNA-related North Pacific circulation anomalies, which shift northwestward during multi-year events and reach their peak intensity in the second year. Multiple dynamical diagnostic methods are employed to elucidate the reasons behind the diverse subtropical circulation responses. Differences in the anomalous tropical heat sources influence the formation of Rossby wave sources through adjustments in divergent wind anomalies, subsequently modulating the position and intensity of the PNA patterns. Additionally, variations in the meridional range of sea surface temperature anomalies affect the edge of tropospheric temperature through moist-adiabatic adjustment, leading to distinct subtropical jet stream responses. This, in turn, modifies the position of North Pacific circulation anomalies through the advection of anomalous kinetic energy. Furthermore, synoptic-scale transient eddies act as a feedback mechanism, helping to maintain and intensify these diverse atmospheric anomalies.

Effect of the uncertainty of autocorrelation estimation on trend analysis

Autocorrelation is ubiquitous in real-life time series. For trend analysis, positive autocorrelation mainly increases the statistical uncertainty of the detected trend. The theoretical framework has been established to quantify how the autocorrelation can impact trend analysis if its characteristic is known precisely. However, if the autocorrelation is also uncertain like that estimated in real-life data, then the consequences are yet unclear. The situation is further complicated by the concurrence of both short- and long-range correlation (SLRC), e.g., in air temperature. In this study, we use an appropriate minimal model with one short-range autoregressive parameter and one long-range fractional parameter to account for such SLRC, and then accordingly propose a framework to integrate the effect of the uncertainty of autocorrelation estimation into trend analysis, on the basis of the detrended fluctuation analysis and Akaike weights. This framework can also obtain a joint probability density function of the estimated autoregressive and fractional parameters for measuring their uncertainty, identifying their combined optimal estimates, uncovering their strong interdependence, and determining their two-dimensional confidence region. The effectiveness and applicability of the proposed framework are verified by a numerical experiment and a case study of daily air temperature anomalies at the Potsdam station. This study can provide a solid theoretical basis to underpin our understanding of the autocorrelation effect on trend analysis in theory and applications. Published by the American Physical Society 2024

Variance‐driven security optimisation in industrial IoT sensors

AbstractThe Industrial Internet of Things (IIoT) has transformed industrial operations with real‐time monitoring and control, enhancing efficiency and productivity. However, this connectivity brings significant security challenges. This study addresses these challenges by identifying abnormal sensor data patterns using machine learning‐based anomaly detection models. The proposed framework employs advanced algorithms to strengthen industrial defences against cyber threats and disruptions. Focusing on temperature anomalies, a critical yet often overlooked aspect of industrial security, this research fills a gap in the literature by evaluating machine learning models for this purpose. A novel variance‐based model for temperature anomaly detection is introduced, demonstrating high efficacy with accuracy scores of 0.92 and 0.82 on the NAB and AnoML‐IOT datasets, respectively. Additionally, the model achieved F1 scores of 0.96 and 0.89 on these datasets, underscoring its effectiveness in enhancing IIoT security and optimising cybersecurity for industrial processes. This research not only identifies security vulnerabilities but also presents concrete solutions to improve the security posture of IIoT systems.

Possible Causes for the Unprecedented Low/High Tropical Cyclone Activities in the Northern Pacific/Atlantic in 2023 El Niño

AbstractThis study reported the unprecedented tropical cyclone (TC) activity in the western North Pacific (WNP) and North Atlantic (NA) during the developing year of the 2023/2024 El Niño. The possible causes behind these unusual features were addressed. In contrast to previous El Niño events, an unusual low/high TC genesis number in the WNP/NA was identified during the typhoon season (June–November) in 2023. Meanwhile, the mean TC genesis location in the WNP exhibited a La Niña‐like northwestward shift, rarely observed in an El Niño developing year. An observational diagnosis on TC‐genesis‐related large‐scale dynamics and thermodynamics revealed that the lower/higher TC numbers in the WNP/NA were primarily attributed to an anticyclonic/cyclonic anomaly linked to trans‐basin sea surface temperature anomalies in the tropics and extratropics. Additionally, weaker intraseasonal oscillation activity compared to previous El Niños also partially contributed to fewer TCs in the WNP.

Unveiling the devastating effect of the spring 2022 mega-heatwave on the South Asian snowpack

Global warming has led to a notable increase in heatwaves globally and regionally. In spring 2022, South Asia witnessed an unprecedented heatwave with temperatures breaking historical records and exceeding 5° C from climatological mean at several locations in the northern Indian subcontinent. Here, using 3D tracking, this heatwave ranked the most severe in the past 64 years, characterized by its protracted duration and wide spatial extent. The excess atmospheric heat, represented by temperature anomalies, during the mega-heatwave triggered rapid snowmelt across the snow-covered areas in the region, leading to an average loss of 42% in snow cover and 57% in snow depth of the regional snowpack. This rapid melting resulted in the complete disappearance of low-level snowpack in the western Himalayas, Pir Panjal, and Afghanistan highlands, leading to the lowest snowpack observed in the last six decades. Moreover, during the heatwave, the amount of snowfall received was only 29% of the long-term average. This combination of excessive melting and reduced snowfall culminated in a severe regional snow drought in spring 2022. The heatwave genesis lay a persistent high-pressure system over Northwest South Asia, reinforced by a quasi-stationary Rossby wave packet over Europe during the initial spell. Continuous heat from high-pressure ridges associated with circumglobal Rossby waves combined with the physical barrier of the Himalayas, lent staying power to this system during the second phase.

Counteracting Impacts of ENSO and the Aleutian Low on Winter Surface Air Temperature over Japan Sea Rim Region

Abstract Exploring the mechanisms modulating Japan Sea Rim (JSR) winter surface air temperature (JSRWT) holds significant scientific and societal importance. The present study unravels the counteracting impacts of El Niño–Southern Oscillation (ENSO) and the Aleutian low (AL) on JSRWT. Although ENSO and the AL have a significant positive correlation on interannual timescale, they exert totally opposite impacts on JSRWT. The positive Niño-3.4 sea surface temperature anomalies (SSTAs) usually lead to positive JSRWT anomalies, while an enhanced AL often results in negative JSRWT anomalies. The tropical convection anomalies associated with the positive Niño-3.4 SSTA induce two tropical to extratropical Rossby wave trains, leading to a barotropic anomalous anticyclone over northeast Asia, and thereby positive JSRWT anomalies. Conversely, the strengthened AL perturbs the westerly jet and induces an eastward-propagating Rossby wave train, leading to a barotropic anomalous cyclone over northeast Asia and negative JSRWT anomalies. The northeastward-propagating Rossby wave induced by the ENSO-related tropical convection anomalies over the Indian Ocean offsets the downstream Rossby wave induced by the strengthened AL, leading to counteracting impacts of ENSO and the AL on JSRWT. Finally, a novel index for monitoring JSRWT is proposed based on the indices of ENSO and AL. Significance Statement Despite the advantage of ENSO as a well-known predictability source, the seasonal predictability of Japan Sea Rim winter surface air temperature (JSRWT) is far from satisfactory. Here, we discovered that the Aleutian low (AL) has an independent influence on JSRWT contrasting with that of ENSO. When the AL and ENSO are in-phase, JSRWT shows no significant anomalies, but the JSRWT anomalies are largely amplified when AL and ENSO are out-of-phase. Therefore, a novel index for monitoring JSRWT is proposed based on the indices of ENSO and AL. These findings shed light on the low capacity of the seasonal prediction of JSRWT when only considering ENSO as the precursor.

Seasonal evolution modes of tropical sea surface temperature anomalies and their links to antarctic sea ice anomalies

Abstract Previous studies have explored the teleconnections between variability of Antarctic sea ice cover and tropical sea surface temperature (SST) across the Pacific, Atlantic, and Indian Ocean basins, typically focusing on each basin individually. However, there has been limited investigation into the impact of tropical SSTs—particularly from a seasonal evolution perspective—on Antarctic sea ice cover. In this study, we employ the self-organizing map method to identify and analyze the primary modes of seasonal SST evolution in the tropical oceans from 1854 to 2022. We also project changes in the frequency of these modes through the 21st century. Moreover, we examine the seasonal variability of Antarctic sea ice concentration in relation to these tropical SST modes over the past four decades. Our results reveal that tropical SST anomalies display both uniform and shifted seasonal evolution patterns. Notably, the frequency of switched modes—namely, transitions from La Niña to El Niño (node 8) and from El Niño to La Niña (node 3)—is expected to increase in future climate. Interestingly, nearly mirrored SST seasonal evolution patterns do not lead to entirely opposite atmospheric circulation anomalies in the southern mid-high latitudes, nor do they result in completely inverse Antarctic sea ice cover anomalies.

Impacts of Climate Change: Examining Precipitation, Temperature Anomalies, and Effects on Water Resources in Turkey

Climate change is a significant global issue that affects our everyday lives and water resources. One of the most critical impacts of climate change is on our water resources, which are vital for sustaining life and supporting various ecosystems. Understanding the complex relationship between climate change and water resources is crucial for developing effective mitigation and adaptation strategies. This study aims to investigate the impact of climate change on water resources and to shed light on the importance of addressing this issue. Water is a limited resource, and its availability and quality directly affect human well-being, agriculture, energy production, and ecosystem health. However, climate change alters the patterns and dynamics of precipitation, temperature, and evaporation, leading to significant changes in water availability and distribution. Increasing global temperatures cause glaciers and ice caps to melt, progressively depleting freshwater resources. Moreover, changing precipitation patterns are leading to more frequent and severe droughts in some regions, while others experience increased rainfall and flooding events. The effects of these changes are profound. As water scarcity becomes more widespread, competition for limited resources intensifies, potentially leading to conflicts and social unrest. Given the importance of water resources and the undeniable impact of climate change on their availability and quality, it is imperative that we deepen our understanding of this complex relationship. This study aims to assess the socio-economic and environmental impacts of climate change on water resources. By doing so, it seeks to provide policymakers, scientists, and communities with information that will guide decision-making processes and direct effective climate change adaptation and mitigation strategies. In conclusion, the impact of climate change on water resources cannot be overstated. This study aims to contribute to our understanding of this critical issue by highlighting the urgency of addressing climate change and its consequences on water resources and sustainability. This study examines the effects of changing precipitation patterns and increasing temperatures due to climate change on underground and surface water resources in Turkey. By conducting this research, we hope to pave the way for informed decision-making and encourage collective responsibility to protect our water resources for future generations.

Improvement in the Low Temperature Prediction Skill During Cold Winters Over the Mid–High Latitudes of Eurasia in CFSv2

ABSTRACTRegional cold winters have occurred frequently in Eurasia since the beginning of the 21st century, increasing the interannual variability in winter temperatures and increasing the difficulty of prediction. In this study, we evaluate the performance of Climate Forecast version 2 (CFSv2) of the National Centers for Environmental Prediction (NCEP) in predicting winter temperature anomalies over the Northern Hemisphere and find that CFSv2 has significantly lower temperature prediction ability for cold winters in the mid–high latitudes of Eurasia since the 21st century. This is mainly due to the stronger response to global warming and the weaker response to sea ice anomalies in the preceding autumn in CFSv2 than the in reanalysis. Accordingly, two targeted correction methods have been developed to improve the prediction ability, with the first method removing the linear temperature trend of CFSv2 predictions and the second method considering the effects of autumn Arctic Sea ice anomalies via a dynamical–statistical correction approach (DSCA). Both methods can effectively improve the prediction ability of winter temperature anomalies in the mid–high latitudes of Eurasia, especially in cold winters. The anomaly correlation coefficient (ACC) increased from −0.03 to 0.13 before and after the modification by the DSCA, and from −0.12 to 0.25 for cold winters. The DSCA significantly reduced the root mean square error (RMSE) of the CFSv2 predictions by approximately 10%.

Few shot learning for Korean winter temperature forecasts

To address the challenge of limited training samples, this study employs the model-agnostic meta-learning (MAML) algorithm along with domain-knowledge-based data augmentation to predict winter temperatures on the Korean Peninsula. While data augmentation has been achieved by using global climate model simulations, the proposed augmentation is purely based on the observed data by defining the labels using large-scale climate variabilities associated with the Korean winter temperatures. The MAML-applied convolutional neural network (CNN) (referred to as the MAML model) demonstrates superior correlation skills for Korean temperature anomalies compared to a reference model (i.e., the CNN without MAML) and state-of-the-art dynamical forecast models across all target lead months during the boreal winter seasons. Sensitivity experiments show that the domain-knowledge-based data augmentation enhances the forecast skill of the MAML model. Moreover, occlusion sensitivity results reveal that the MAML model better captures the physical precursors that influence Korean winter temperatures, resulting in more accurate predictions.

Trends of Climate Extremes and Their Relationships with Tropical Ocean Temperatures in South America

South America has experienced significant changes in climate patterns over recent decades, particularly in terms of precipitation and temperature extremes. This study analyzes trends in climate extremes from 1979 to 2020 across South America, focusing on their relationships with sea surface temperature (SST) anomalies in the Pacific and Atlantic Oceans. The analysis uses precipitation and temperature indices, such as the number of heavy rainfall days (R10mm, R20mm, R30mm), total annual precipitation (PRCPTOT), hottest day (TXx), and heatwave duration (WSDI), to assess changes over time. The results show a widespread decline in total annual precipitation across the continent, although some regions, particularly in the northeast and southeast, experienced an increase in the intensity and frequency of extreme precipitation events. Extreme temperatures have also risen consistently across South America, with an increase in both the frequency and duration of heat extremes, indicating an ongoing warming trend. The study also highlights the significant role of SST anomalies in both the Pacific and Atlantic Oceans in driving these climate extremes. Strong correlations were found between Pacific SST anomalies (Niño 3.4 region) and extreme precipitation events in the northern and southern regions of South America. Similarly, Atlantic SST anomalies, especially in the Northern Atlantic (TNA), exhibited notable impacts on temperature extremes, particularly heatwaves. These findings underscore the complex interactions between SST anomalies and climate variability in South America, providing crucial insights into the dynamics of climate extremes in the region. Understanding these relationships is essential for developing effective adaptation and mitigation strategies in response to the increasing frequency and intensity of climate extremes.

Climate Extremes in the New Zealand Region: Mechanisms, Impacts and Attribution

ABSTRACTAs global surface temperatures have increased with human‐induced climate change, notable compound climate extremes in the New Zealand (NZ) region associated with atmospheric heatwaves (AHWs) and marine heatwaves (MHWs) have occurred in the past 6 years. Natural modes of variability that also played a key role regionally include the Interdecadal Pacific Oscillation (IPO), El Niño/Southern Oscillation (ENSO) and changes in the location and strength of the westerlies as seen in the Southern Annular Mode (SAM). Along with mean warming of 0.8°C since 1900, a negative phase of the IPO, La Niña phase of ENSO and a strongly positive SAM contributed to five compound warm extremes in the extended austral summer seasons (NDJFM) of 1934/35, 2017/18, 2018/19, 2021/22 and 2022/23. These are the most intense coupled ocean/atmosphere (MHWs/AHWs) heatwaves on record with average temperature anomalies over land and sea +0.8°C to 1.1°C above 1991–2020 averages. The number of days above 25°C and above the 90th percentile of maximum temperature has increased, while the number of nights below 0°C and below the 10th percentile has decreased. Coastal waters around NZ recently experienced their longest MHW in the satellite era (1982‐present) of 289 days through 2023. The estimated recurrence interval reduces from 1 in 300‐years for the AHW event during the 1930s climate to a 1 in 25‐year event for the most recent decade. Consequences include major loss of ice of almost one‐third volume from Southern Alps glaciers from 2017 to 2021 with rapid melt of seasonal snow in all four cases. Above‐average temperatures in the December/January grape flowering period resulted in advances in veraison (the onset of ripening); and higher‐than‐average grape yields in 2022 and 2023 vintages. Marine impacts include widespread sea‐sponge bleaching around northern and southern NZ.

Seasonal prediction of North Atlantic sea surface temperature anomalies using the LSTM machine learning method

Seasonal prediction of North Atlantic sea surface temperature anomalies using the LSTM machine learning method