BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:Asia/Kolkata X-WR-TIMEZONE:Asia/Kolkata BEGIN:VEVENT UID:137@cds.iisc.ac.in DTSTART;TZID=Asia/Kolkata:20250807T143000 DTEND;TZID=Asia/Kolkata:20250807T153000 DTSTAMP:20250725T075732Z URL:https://cds.iisc.ac.in/events/ph-d-thesis-defense-102-cds-seminar-hall -07-august-2025-quantifying-the-past-and-future-variability-in-the-bay-of- bengal-using-statistical-and-deep-learning-methods/ SUMMARY:Ph.D. Thesis Defense: #102: CDS Seminar Hall: 07\, August 2025 "Qua ntifying the past and future variability in the Bay of Bengal using statis tical and deep learning methods" DESCRIPTION:DEPARTMENT OF COMPUTATIONAL AND DATA SCIENCES\nPh.D. Thesis Def ense\n\n\n\nSpeaker : Mr. Abhishek. P\nS.R. Number : 05-03-00-10-12-19-1-1 7560\nTitle : "Quantifying the past and future variability in the Bay of B engal using statistical and deep learning methods"\nResearch Supervisor : Dr. Deepak Subramani\nThesis examiner : Prof. Sridhar Balasubramanian\, II TB\nDate &\; Time : August 07\, 2025 (Thursday)\, 02:30 PM\nVenue : # 1 02 CDS Seminar Hall\n\n\n\nABSTRACT\nThe Bay of Bengal\, the world’s lar gest bay\, along with the Andaman Sea\, a peripheral sea situated in the s outheastern part of the bay\, is crucial to the economic and maritime secu rity of India. Understanding the dynamics and uncertainties of the Bay of Bengal is particularly important\, given India’s increased investment in the Deep Ocean Mission and Blue Economy. This thesis examines the variabi lity in the features of the Bay of Bengal in the past and future using rea nalysis and climate projections. In two parts\, this thesis makes the foll owing specific contributions. In the first part\, a new statistical analys is is completed on the reanalysis data to uncover the relationship of sali nity dynamics in the Andaman Sea with the Southwest Monsoon Current and a data-assimilative forecast system is developed for synoptic forecasts of t he Andaman Sea. In the second part\, a novel deep learning model is develo ped to correct the future projections of the climate models in the Bay of Bengal and uncover new dynamical insights.\n\nTo transition from analysis to forecasting\, we developed a data assim[1]ilation system that integrate s satellite observations with numerical models\, producing data-driven syn optic forecasts for the Andaman Sea. This research marks the first applica tion of a time-evolving\, high-resolution data assimila[1]tion ocean model in the Andaman Sea\, offering an accurate assessment of the ocean’s sta te in this area. First\, we performed a high-resolution data-driven numeri cal Regional Ocean Modeling System (ROMS) control run. Second\, a data ass imilative ROMS simulation is performed with MODIS SST observa[1]tions and compared to the control run. The initial and boundary conditions are taken from the Nucleus for European Modeling of the Ocean (NEMO) reanalysis mod el for the control and data assimilation runs. The incremental strong-cons traint 4-dimensional variational data assimilation scheme (IS4D[1]Var) was used. The data assimilation run significantly reduces the difference betw een the Andaman Sea simulations and the in situ observations from a moored OMNI buoy (BD12) over the control run. Significantly\, the data assimilat ion run reduces the surface temperature error by 0.5◦C compared to the c ontrol run. This data assimilation setup is crucial for improving our unde rstanding of the synoptic dynamics of the Andaman Sea.\n\nIn the second pa rt of the thesis\, we study the variability of the features of the Bay of Bengal in the future. Climate change impacts the ocean state\, including t emperature\, salinity\, and sea level\, affecting monsoons and ocean produ ctivity. Future projections based on shared socioeconomic pathways (SSP) f rom the Coupled Model Intercomparison Project (CMIP) are widely used to un derstand the effects of climate change. However\, CMIP models exhibit cons iderable errors compared to observations in the Bay of Bengal for the time period when both projections and observations are available. In this regi on\, there is a 1.5◦C root mean square error (RMSE) in the sea surface t emperature of CMIP6 compared to the Ocean Reanalysis System (ORAS5). We in troduce data-driven deep learning models to correct for this error in thre e important variables: sea surface temperature\, sea surface salinity\, an d dynamic sea level. The deep neural model for each variable is trained us ing pairs of monthly CNRM-CM6 projections and the corresponding month’s ORAS5 as input and output. This model is trained and validated with his[1] torical data (1950-2014) and future projection data (2015-2020) and tested with future projections from 2021 to 2024. Ablation studies are conducted to identify the best neural architecture. The final developed model has a UNet architecture and uses a climatology-removed CMIP6 projection as inpu t and predicts the climatology-removed corrected fields. The trained model is then used to correct the future projections from 2025 to 2100. Our new deep learning-based CMIP6 correction approach has 15% lower RMSE compared to the traditional statistical correction method called the Equidistant C u[1]mulative Distribution Function (EDCDF). Further goodness of correction metrics\, such as pattern correlation coefficient and image-based similar ity metrics\, all indicate the superiority of our correction model.\n\nTo uncover the dynamical implication of the corrected projections\, a de[1]ta iled analysis of the monthly\, seasonal mean\, and variability of the proj ec[1]tions is performed. Compared to the raw projections\, our corrected p rojec[1]tions indicate increased warming in the bay\, altered patterns of salinity\, and dynamic sea level that affect monsoons and vital oceanograp hic features of the BoB. The new findings from the corrected projections a re as follows. In winter\, the north-south temperature gradient weakens mo re than the raw projections\, potentially influencing the northeast monsoo n dynamics. The intensified warming in the corrected projections during th e pre-monsoon sea[1]son in the central bay has implications for cyclogenes is and may potentially delay or weaken the monsoon onset. The corrected SS T shows a stronger coastal warm front and a changed thermal structure in c entral and south[1]ern bays during the monsoon\, potentially impacting mon soon rainfall and SMC propagation. The corrected salinity shows a stronger variability in the propagation of SMC in the BoB\, potentially impacting the influx of high salinity to the region and subsequently affecting produ ctivity in the region. The increased post-monsoon bay warming in the corre cted projections may aid cyclogenesis and affect the EICC and its eddies. In general\, the impact of climate change on the mean and variability of t he characteristics in the BoB\, revealed by our new corrected model\, woul d be substantially different from the projections of the uncorrected clima te models.\n\n\n\nALL ARE WELCOME CATEGORIES:Events,Thesis Defense END:VEVENT BEGIN:VTIMEZONE TZID:Asia/Kolkata X-LIC-LOCATION:Asia/Kolkata BEGIN:STANDARD DTSTART:20240807T143000 TZOFFSETFROM:+0530 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE END:VCALENDAR