000			02652nam a2200133 4500
008			250624b |||||||| |||| 00| 0 eng d
100			_aS. Vasavi
245			_aCorrelation analysis of offshore wind and wave power potential at Indian exclusive economic zone during 2014–23 using deep learning model
300			_aP 269-282
520			_aClimate change is increasingly influencing energy resources across the globe, and its effects on renewable energy sources like offshore wind and wave power are becoming crucial topics of study. India, with its extensive coastline and vast exclusive economic zone (EEZ), has significant potential for harnessing these oceanbased renewable energies. By analysing the localised nature of offshore winds and their sensitivity to climate variations, we can improve predictions of future wind power output. Therefore, to sustain wind energy development within India’s EEZ, it’s essential to evaluate the region’s wave energy potential and its vulnerability to climate change. This paper investigates the potential for offshore wind energy within the Indian EEZ and assesses its vulnerability to climate change. Spatial and temporal wave data such as wave period and wave height are collected from Copernicus Marine Data Store to generate the wave power layer and validate the proposed U-Net model. For improvement of data quality, assimilation techniques such as the Kalman filter and Bilateral filter are used. For finding the wave power density hotspot region, the semantic segmentation is performed using an enhanced U-Net model. The model archives an impressive IoU score of 82.66%, conforming its accuracy to identify the wave power density hotspots. To analyse the impact of climate change on wave power potentials, the Pearson correlation technique is used to correlate between ocean surface salinity and ocean surface temperature. The r value of correlation between ocean surface temperature and ocean surface salinity ranges from –0.59 to –0.0 and indicates a weak, moderate inverse relationship, the positive range varies from 0.01 to 0.62, suggest that a weak to strong positive correlation, where both temperature and salinity tend to increase together. In the case of temperature and wave power density, there is a negative correlation from June to October, influenced by seasonal temperature variation due to rainfall and it effects to correlate with wave power density.
654			_aExclusive economic zone _aKalman filter _aU-net model _awave energy potential _awave power density hotspots
773	0		_0125299 _9112520 _tCurrent Science _x 0011-3891
942			_cJA
999			_c131815 _d131815