CNN‐Based ENSO Forecasts With a Focus on SSTA Zonal Pattern and Physical Interpretation

Sun, Ming; Chen, Lin; Li, Tim; Luo, Jing‐Jia

doi:10.1029/2023gl105175

Cited by 8 publications

(18 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that the recharge process in the tropical Pacific and the modulation of the PMM are also detected in Sun et al. (2023) using a different DL model and heatmap method. This implies the DL‐based techniques are robust in detecting core ENSO physical mechanisms.…”

Section: Resultsmentioning

confidence: 58%

“…Sun et al. (2023) proposed that the South Pacific quadrupole (SPQ) mode can also play a part in ENSO evolution at a 10‐month lead in their CNN model while it was not detected in our SERCNN model. The essential differences between Sun et al.…”

Section: Discussionmentioning

confidence: 65%

“…The essential differences between Sun et al. (2023) and our study are large, including DL algorithms, inputs, and model architectures. Sun et al.…”

Section: Discussionmentioning

confidence: 85%

“…Sun et al. (2023) adopted the original CAM based on gradients but we used here the Score‐CAM based on confidence. Sun et al.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, high HCA heatmap values emerge in the northeastern Pacific, presumably related to the trade wind charging associated with the peak phase of PMM in the boreal spring (Anderson & Perez, 2015;Hu et al, 2023). It is worth noting that the recharge process in the tropical Pacific and the modulation of the PMM are also detected in Sun et al (2023) using a different DL model and heatmap method. This implies the DL-based techniques are robust in detecting core ENSO physical mechanisms.…”

Section: Prominent Precursors Revealed By Sercnn For Enso Eventsmentioning

confidence: 95%

See 4 more Smart Citations

Quantifying the Relative Contributions of the Global Oceans to ENSO Predictability With Deep Learning

Li,

Tang,

Lian

et al. 2024

Geophysical Research Letters

View full text Add to dashboard Cite

We propose a unified statistical method based on deep learning and analysis to quantify the relative contributions of the global oceans to El Niño–Southern Oscillation (ENSO) predictability. By incorporating subsurface signals in the Indian Ocean and Atlantic, the forecast lead can be skillfully extended by about one season. This skill enhancement mainly originates from the tropical Indian Ocean, presumably related to signals of the Indian Ocean Dipole passing to the tropical Pacific through the Indonesian Throughflow. The sea surface temperature anomaly (SSTA) in the Indian Ocean accounts for nearly 50% of surface contributions to both El Niño and La Niña predictions at a 15‐month lead. The north tropical Atlantic SSTA has a moderate impact on La Niña at a 9‐month lead. The Pacific Meridional Mode plays a significant role in both ENSO phases at a 12‐month lead. Thus, our study suggests that trans‐basin effects for ENSO are more vigorous than previously thought.

show abstract

Section: Resultsmentioning

confidence: 58%

Section: Discussionmentioning

confidence: 65%

“…The essential differences between Sun et al. (2023) and our study are large, including DL algorithms, inputs, and model architectures. Sun et al.…”

Section: Discussionmentioning

confidence: 85%

“…Sun et al. (2023) adopted the original CAM based on gradients but we used here the Score‐CAM based on confidence. Sun et al.…”

Section: Discussionmentioning

confidence: 99%

Section: Prominent Precursors Revealed By Sercnn For Enso Eventsmentioning

confidence: 95%

See 3 more Smart Citations

Quantifying the Relative Contributions of the Global Oceans to ENSO Predictability With Deep Learning

Li,

Tang,

Lian

et al. 2024

Geophysical Research Letters

View full text Add to dashboard Cite

show abstract

Investigating the seasonal SST Predictability in the Northern Tropical Atlantic Ocean in an ensemble prediction system

Liu,

Wang,

Yang

et al. 2024

Clim Dyn

View full text Add to dashboard Cite

The present study comprehensively investigates the practical and intrinsic predictability of the sea surface temperature (SST) in the Northern Tropical Atlantic (NTA) based on the 138-year-long coupled hindcasts with a recently developed seasonal ensemble prediction system. This system can yield skillful deterministic predictions for the prominent warm and cold events at least 6 months ahead. Notably, it excels in providing probabilistic predictions for below- and above-normal events rather than for neutral events. The predictability of SST in the NTA undergoes remarkable seasonal variation with two peaks of predictability targeted at April and October regardless of the lead time. Various sources of predictability for these target months are revealed. For the target month of April, the preceding remote forcing from the El Niño–Southern Oscillation (ENSO) in the tropical Pacific Ocean combined with local signal results in the phase locking of the SST variation and seasonality of signal component over the NTA. This ultimately contributes to the high predictability targeted at April. However, From the perspective of potential predictability of the predictability targeted at October, which has been rarely mentioned in previous studies. It is also encouraging that, similar to the Indian Ocean Dipole, ENSO and the signal-to-noise ratio of the system mainly contribute to predictability beyond persistence at long lead times for the spring SST in the NTA. This indicates that potential future ENSO improvements may leave much room for improvement in the current SST prediction in the NTA.

show abstract

ENSO‐Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer‐Based Deep Learning Model in the Tropical Pacific

Zhou,

Zhang

2024

Geophysical Research Letters

View full text Add to dashboard Cite

Recent studies have demonstrated great values of deep‐learning (DL) methods for improving El Niño‐Southern Oscillation (ENSO) predictions. However, the black‐box nature of DL makes it challenging to physically interpret mechanisms responsible for successful ENSO predictions. Here, we demonstrate an interpretable method by performing perturbation experiments to predictors and quantifying input‐output relationships in predictions by using a transformer‐based model; ENSO‐related thermal precursors serving as initial conditions during multi‐month time intervals (TIs) are identified in the equatorial‐northern Pacific, acting to precondition input predictors to provide for long‐lead ENSO predictability. Results reveal the existence of upper‐ocean temperature anomaly pathways and consistent phase propagations of thermal precursors around the tropical Pacific. It is illustrated that three‐dimensional thermal fields and their basinwide evolution during long TIs act to enhance long‐lead prediction skills of ENSO. These physically explainable results indicate that neural networks can adequately represent predictable precursors in the input predictors for successful ENSO predictions.

show abstract

CNN‐Based ENSO Forecasts With a Focus on SSTA Zonal Pattern and Physical Interpretation

Cited by 8 publications

References 73 publications

Quantifying the Relative Contributions of the Global Oceans to ENSO Predictability With Deep Learning

Quantifying the Relative Contributions of the Global Oceans to ENSO Predictability With Deep Learning

Investigating the seasonal SST Predictability in the Northern Tropical Atlantic Ocean in an ensemble prediction system

ENSO‐Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer‐Based Deep Learning Model in the Tropical Pacific

Contact Info

Product

Resources

About