Arya Paul
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Arya Paul has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Balaji Baduru
Indian National Centre for Ocean Information Services (INCOIS), Ministry of Earth Science (MoES), Hyderabad, India
8 shared publications Fabien Durand
LEGOS, Université de Toulouse, IRD, CNRS, CNES, UPS, Toulouse, France
6 shared publicationsRomain Bourdallé-Badie
Mercator Ocean International, Toulouse, France
5 shared publications- Vinod Daiya
Indian National Centre for Ocean Information Services (INCOIS), Ministry of Earth Sciences (MoES)
5 shared publications - Biswamoy Paul
Indian National Centre for Ocean Information Services (INCOIS), Ministry of Earth Sciences (MoES)
4 shared publications - Jagdish Prajapati
Indian National Centre for Ocean Information Services (INCOIS), Ministry of Earth Sciences (MoES)
4 shared publications
Latest Publications
- Open Access
- 1 May 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (5) , 055044
A machine learning framework for sea surface salinity prediction at short time scales
Sea surface salinity (SSS) is an integral ocean state variable that influences the global weather patterns. The conventional approach to forecast SSS maps over a basin at a lead time of a few days has been through dynamical models. However, the dearth of daily freshwater fluxes induces errors in short-term SSS predictions from these dynamical models. In this study, using only past collocated SSS data, we develop an univariate machine learning framework based on long short term memory for short-term prediction of SSS and test its veracity over Bay of Bengal—one of the most stratified ocean basins in the world. We show that the 5-day daily SSS predictions are superior to daily SSS reanalysis when compared against blended daily SSS observations. The root-mean-squared errors are typically less than 0.5 psu over the entire basin with excellent phase alignment. The SSS forecasts at 5-day lead time are on par with daily SSS reanalysis when compared against Argo SSS observations. Using hourly buoy SSS data, we show that this framework is equally adept at forecasting high-frequency SSS variability with errors in the range of 0.02 psu at a lead time of 5 h. Using the test case of supercyclone Amphan, we also show that this framework is resilient during extreme events too. This study shows that it is indeed feasible to issue a 5-day forecast of daily SSS map over an entire basin with skills on par with reanalysis.
- 1 May 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (5) , 055044
Open AccessA machine learning framework for sea surface salinity prediction at short time scales
Sea surface salinity (SSS) is an integral ocean state variable that influences the global weather patterns. The conventional approach to forecast SSS maps over a basin at a lead time of a few days has been through dynamical models. However, the dearth of daily freshwater fluxes induces errors in short-term SSS predictions from these dynamical models. In this study, using only past collocated SSS data, we develop an univariate machine learning framework based on long short term memory for short-term prediction of SSS and test its veracity over Bay of Bengal—one of the most stratified ocean basins in the world. We show that the 5-day daily SSS predictions are superior to daily SSS reanalysis when compared against blended daily SSS observations. The root-mean-squared errors are typically less than 0.5 psu over the entire basin with excellent phase alignment. The SSS forecasts at 5-day lead time are on par with daily SSS reanalysis when compared against Argo SSS observations. Using hourly buoy SSS data, we show that this framework is equally adept at forecasting high-frequency SSS variability with errors in the range of 0.02 psu at a lead time of 5 h. Using the test case of supercyclone Amphan, we also show that this framework is resilient during extreme events too. This study shows that it is indeed feasible to issue a 5-day forecast of daily SSS map over an entire basin with skills on par with reanalysis.
- Open Access
- 20 December 2025
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 12 (12)
Improving Coastal Circulation Using HF‐Radar Surface Currents
In an attempt to improve the model‐derived coastal circulation around India, we explore three different frameworks to assimilate surface currents from HF‐Radars into an ocean model for the Indian Ocean. The first approach involves correcting the winds through Ekman Theory using the discrepancy between the model surface currents and the HF‐Radar observations. The second approach entails direct assimilation of the HF‐Radar surface currents into the ocean model. The third approach combines the first two frameworks. We show that all three approaches improve coastal circulation but in varying degrees. The improvements in analysis are least in the wind‐correction approach and most prominent in the combined approach. We show that the combined approach of wind correction and assimilation of HF‐Radar currents significantly improves the coastal circulation around India with root‐mean‐squared error at par with the precision of the HF‐Radar measurements. This approach yields a correlation of ∼0.8–0.9 between the surface current analysis and the observation. We also show that this approach improves the subsurface currents. The surface current forecasts from the combined approach with a lead time of a day outperforms the free model run by a large margin thereby proving its mettle for operational adoption.
- 20 December 2025
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 12 (12)
Open AccessImproving Coastal Circulation Using HF‐Radar Surface Currents
In an attempt to improve the model‐derived coastal circulation around India, we explore three different frameworks to assimilate surface currents from HF‐Radars into an ocean model for the Indian Ocean. The first approach involves correcting the winds through Ekman Theory using the discrepancy between the model surface currents and the HF‐Radar observations. The second approach entails direct assimilation of the HF‐Radar surface currents into the ocean model. The third approach combines the first two frameworks. We show that all three approaches improve coastal circulation but in varying degrees. The improvements in analysis are least in the wind‐correction approach and most prominent in the combined approach. We show that the combined approach of wind correction and assimilation of HF‐Radar currents significantly improves the coastal circulation around India with root‐mean‐squared error at par with the precision of the HF‐Radar measurements. This approach yields a correlation of ∼0.8–0.9 between the surface current analysis and the observation. We also show that this approach improves the subsurface currents. The surface current forecasts from the combined approach with a lead time of a day outperforms the free model run by a large margin thereby proving its mettle for operational adoption.
- 18 November 2025
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 152 (775)
Optimising the design of an observational testbed using observing system simulation experiments: A case study in the southeastern Arabian Sea
Observing system simulation experiments (OSSEs) provide a cost‐effective approach to estimate the impending potential impact of new observing systems. OSSE, based on the fraternal twin framework, is used in the present study to find the optimal location of four proposed buoys off the southeastern Arabian Sea (70–77° E, 6–13° N) for process studies and improvement of ocean analysis and hence forecasts. A fraternal twin framework has three essential components – a Nature Run representing truth, Synthetic Observations (SynOPs) mimicking real observations and a Reference System playing the role of a forecast system. A high‐resolution ocean model coupled to a data assimilation system serves as the Nature Run for this study. Daily SynOPs of temperature and salinity are simulated from Nature Run at 16 regularly spaced locations within the proposed region. The Reference System comprising a coarser resolution model coupled to an inferior data assimilation system is designed following the fraternal twin prescription. Sixteen experiments are conducted corresponding to each SynOP by augmenting the Reference System with the corresponding SynOP. The impact of each SynOP is assessed through a newly introduced metric named composite impact assessment parameter that evaluates the holistic impact of a SynOP on the analysis. This metric delineates the hierarchy of impact of SynOP on ocean analysis. We find that the SynOPs lying in the north and close to the coast are not beneficial thereby narrowing down the search area for optimal locations. Six new SynOPs are generated in the narrowed down subregion and the impacts of every combination of four SynOPs out of six are evaluated to find the optimal locations of the four proposed buoys. The study finds that the SynOPs located at the southern edge of the proposed region are most optimal for improving ocean analysis.
- 18 November 2025
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 152 (775)
Optimising the design of an observational testbed using observing system simulation experiments: A case study in the southeastern Arabian Sea
Observing system simulation experiments (OSSEs) provide a cost‐effective approach to estimate the impending potential impact of new observing systems. OSSE, based on the fraternal twin framework, is used in the present study to find the optimal location of four proposed buoys off the southeastern Arabian Sea (70–77° E, 6–13° N) for process studies and improvement of ocean analysis and hence forecasts. A fraternal twin framework has three essential components – a Nature Run representing truth, Synthetic Observations (SynOPs) mimicking real observations and a Reference System playing the role of a forecast system. A high‐resolution ocean model coupled to a data assimilation system serves as the Nature Run for this study. Daily SynOPs of temperature and salinity are simulated from Nature Run at 16 regularly spaced locations within the proposed region. The Reference System comprising a coarser resolution model coupled to an inferior data assimilation system is designed following the fraternal twin prescription. Sixteen experiments are conducted corresponding to each SynOP by augmenting the Reference System with the corresponding SynOP. The impact of each SynOP is assessed through a newly introduced metric named composite impact assessment parameter that evaluates the holistic impact of a SynOP on the analysis. This metric delineates the hierarchy of impact of SynOP on ocean analysis. We find that the SynOPs lying in the north and close to the coast are not beneficial thereby narrowing down the search area for optimal locations. Six new SynOPs are generated in the narrowed down subregion and the impacts of every combination of four SynOPs out of six are evaluated to find the optimal locations of the four proposed buoys. The study finds that the SynOPs located at the southern edge of the proposed region are most optimal for improving ocean analysis.
- Open Access
- 11 September 2025
- Published by IOP Publishing in Environmental Research Letters
- Vol. 20 (10) , 104031
Using long short term memory networks to predict daily-averaged sea level anomaly and surface currents
Short-term prediction of sea level anomaly (SLA) and ocean surface currents over a domain are usually carried out using ocean general circulation models. In this study, we present a univariate machine learning framework using long short term memory networks that forecasts daily-averaged SLA with a 3 d lead time over the north Indian Ocean using historical satellite altimetry data at a spatial resolution of ∼13 km. Assuming that SLA reanalysis from state-of-the-art systems represent the pinnacle of performance skill of forecasts from dynamical models, we show that the SLA forecasts from our model exhibits superior skills through comprehensive analyses. The errors are typically less than 0.04 m over most of the domain and the correlations are close to unity. The skills of the daily-averaged forecasted currents with a 3 d lead, estimated using geostrophic and Ekman theory, are comparable with the best available reanalysis when compared to in-situ observations both in the open ocean or shelf. Treating these forecasted surface currents as synthetic observations, we show that assimilating them can significantly improve the instantaneous subsurface currents during forecasts. The subsurface correlations turn significant with 99% confidence level across depth which were otherwise mostly insignificant and the errors reduce by 0.1 m·s−1. We demonstrate that the short-term forecast of daily-averaged SLA and surface currents can be approached as a collection of localized low-dimensional independent univariate systems thereby reducing computational costs by large margins. This machine learning framework heralds a paradigm shift in the realm of ocean forecasting.
- 11 September 2025
- Published by IOP Publishing in Environmental Research Letters
- Vol. 20 (10) , 104031
Open AccessUsing long short term memory networks to predict daily-averaged sea level anomaly and surface currents
Short-term prediction of sea level anomaly (SLA) and ocean surface currents over a domain are usually carried out using ocean general circulation models. In this study, we present a univariate machine learning framework using long short term memory networks that forecasts daily-averaged SLA with a 3 d lead time over the north Indian Ocean using historical satellite altimetry data at a spatial resolution of ∼13 km. Assuming that SLA reanalysis from state-of-the-art systems represent the pinnacle of performance skill of forecasts from dynamical models, we show that the SLA forecasts from our model exhibits superior skills through comprehensive analyses. The errors are typically less than 0.04 m over most of the domain and the correlations are close to unity. The skills of the daily-averaged forecasted currents with a 3 d lead, estimated using geostrophic and Ekman theory, are comparable with the best available reanalysis when compared to in-situ observations both in the open ocean or shelf. Treating these forecasted surface currents as synthetic observations, we show that assimilating them can significantly improve the instantaneous subsurface currents during forecasts. The subsurface correlations turn significant with 99% confidence level across depth which were otherwise mostly insignificant and the errors reduce by 0.1 m·s−1. We demonstrate that the short-term forecast of daily-averaged SLA and surface currents can be approached as a collection of localized low-dimensional independent univariate systems thereby reducing computational costs by large margins. This machine learning framework heralds a paradigm shift in the realm of ocean forecasting.
- Open Access
- 1 July 2025
- Published by IOP Publishing in Environmental Research Communications
- Vol. 7 (7) , 075002
Univariate deep learning framework for short-term SST forecasting at high spatio-temporal scales
We present a univariate hybrid machine learning framework to predict daily high resolution Sea Surface Temperature (SST) near the Gulf of Kutch region at a resolution of ∼5.5 km. The hybrid model integrates Intrinsic Mode Functions (IMF) derived from variational mode decomposition with a Long Short-Term Memory (LSTM) network to augment predictive skill. The predicted SST demonstrates impressive performance up to lead times of 7 days. Using statistical metrics like Kullback-Leibler divergence and mutual information, we show that the SST predicted from the hybrid model with a lead time of 3 days decisively outperforms the high-resolution GLORYS SST reanalysis let alone forecast skills of a data-assimilated dynamical model. Using conditional probability, we show that the SST forecasts from the hybrid model are quite reliable over the entire range of SST observations in the study domain. In contrast, the reliability of GLORYS falters in the lower range of SST observations. Also, the hybrid model excels in capturing fine-scale SST features, such as SST fronts, and detecting Marine Heatwaves (MHWs) up to 3 days in advance. These capabilities hold significant applications for Potential Fishing Zone identification and coral bleaching alerts. The hybrid model framework is also adept at forecasting location specific high frequency (3 hourly) SST with a lead time of a day.
- 1 July 2025
- Published by IOP Publishing in Environmental Research Communications
- Vol. 7 (7) , 075002
Open AccessUnivariate deep learning framework for short-term SST forecasting at high spatio-temporal scales
We present a univariate hybrid machine learning framework to predict daily high resolution Sea Surface Temperature (SST) near the Gulf of Kutch region at a resolution of ∼5.5 km. The hybrid model integrates Intrinsic Mode Functions (IMF) derived from variational mode decomposition with a Long Short-Term Memory (LSTM) network to augment predictive skill. The predicted SST demonstrates impressive performance up to lead times of 7 days. Using statistical metrics like Kullback-Leibler divergence and mutual information, we show that the SST predicted from the hybrid model with a lead time of 3 days decisively outperforms the high-resolution GLORYS SST reanalysis let alone forecast skills of a data-assimilated dynamical model. Using conditional probability, we show that the SST forecasts from the hybrid model are quite reliable over the entire range of SST observations in the study domain. In contrast, the reliability of GLORYS falters in the lower range of SST observations. Also, the hybrid model excels in capturing fine-scale SST features, such as SST fronts, and detecting Marine Heatwaves (MHWs) up to 3 days in advance. These capabilities hold significant applications for Potential Fishing Zone identification and coral bleaching alerts. The hybrid model framework is also adept at forecasting location specific high frequency (3 hourly) SST with a lead time of a day.
- Open Access
- 5 November 2024
- Published by IOP Publishing in Environmental Research Letters
- Vol. 19 (12) , 124023
A probabilistic forecast for multi-year ENSO using Bayesian convolutional neural network
A robust El Niño Southern Oscillation (ENSO) prediction is essential for monitoring the global climate, regional monsoons, and weather extremes. Despite dedicated efforts spanning decades, the precise prediction of ENSO events through numerical modeling beyond a couple of seasonal lead times remains a daunting challenge. The advent of deep learning-based approaches marks a transformative era in climate and weather prediction. However, many machine learning-based studies attempting ENSO prediction are confined to singular estimates, lacking adequate quantification of uncertainty in learned parameters and overlooking the crucial need for a nuanced understanding of ENSO prediction confidence. Here, we introduce a deep learning-based Bayesian convolutional neural network model that provides robust probabilistic predictions for ENSO with a lead time of up to 9–10 months across all seasons. The Bayesian layers within the convolutional neural network maintain the capability to predict a distribution of learned parameters. Augmented with bias correction, our model reproduces the amplitude of the Niño 3.4 index with fidelity for lead up to 9–10 months. The inherent capacity for uncertainty modeling enhances the reliability of bayesian neural networks (BNNs), making them particularly valuable in operational services. This research holds substantial socio-economic implications as it enhances our forecasting capabilities and rigorously quantifies forecast uncertainties, providing valuable insights for planning and policymaking.
- 5 November 2024
- Published by IOP Publishing in Environmental Research Letters
- Vol. 19 (12) , 124023
Open AccessA probabilistic forecast for multi-year ENSO using Bayesian convolutional neural network
A robust El Niño Southern Oscillation (ENSO) prediction is essential for monitoring the global climate, regional monsoons, and weather extremes. Despite dedicated efforts spanning decades, the precise prediction of ENSO events through numerical modeling beyond a couple of seasonal lead times remains a daunting challenge. The advent of deep learning-based approaches marks a transformative era in climate and weather prediction. However, many machine learning-based studies attempting ENSO prediction are confined to singular estimates, lacking adequate quantification of uncertainty in learned parameters and overlooking the crucial need for a nuanced understanding of ENSO prediction confidence. Here, we introduce a deep learning-based Bayesian convolutional neural network model that provides robust probabilistic predictions for ENSO with a lead time of up to 9–10 months across all seasons. The Bayesian layers within the convolutional neural network maintain the capability to predict a distribution of learned parameters. Augmented with bias correction, our model reproduces the amplitude of the Niño 3.4 index with fidelity for lead up to 9–10 months. The inherent capacity for uncertainty modeling enhances the reliability of bayesian neural networks (BNNs), making them particularly valuable in operational services. This research holds substantial socio-economic implications as it enhances our forecasting capabilities and rigorously quantifies forecast uncertainties, providing valuable insights for planning and policymaking.
- 6 February 2024
- Published by Springer Nature in Pure and Applied Geophysics
- Vol. 181 (2) , 433-449
The Anomalous 2012–13 Boreal Winter Oceanic Excitation of Earth’s Polar Motion
- 6 February 2024
- Published by Springer Nature in Pure and Applied Geophysics
- Vol. 181 (2) , 433-449
The Anomalous 2012–13 Boreal Winter Oceanic Excitation of Earth’s Polar Motion
- 5 July 2023
- Published by Elsevier in Deep Sea Research Part I: Oceanographic Research Papers
- Vol. 199
The MJO-driven Indo-Pacific barotropic see-saw
- 5 July 2023
- Published by Elsevier in Deep Sea Research Part I: Oceanographic Research Papers
- Vol. 199
The MJO-driven Indo-Pacific barotropic see-saw
- 16 November 2022
- Published by Elsevier in Ocean Modelling
- Vol. 181
Showcasing model performance across space and time using single diagrams
- 16 November 2022
- Published by Elsevier in Ocean Modelling
- Vol. 181
Showcasing model performance across space and time using single diagrams
- 2 July 2022
- Published by Springer Nature in Ocean Dynamics
- Vol. 72 (7) , 523-538
Investigating the robustness of the intraseasonal see-saw in the Indo-Pacific barotropic sea level across models
- 2 July 2022
- Published by Springer Nature in Ocean Dynamics
- Vol. 72 (7) , 523-538
Investigating the robustness of the intraseasonal see-saw in the Indo-Pacific barotropic sea level across models