Bharat in Betastartup field guide
← Back to the atlas
No. 1371Problem statementSpace and research

Deep Learning Based Super Resolution Mapping (SRM) from Medium Resolution Satellite Imageries

Source

Source summary

Develop satellite-image super-resolution taking 10 m Sentinel-2 inputs toward products below 4 m, retaining geographic and spectral consistency. Teams may choose transformer, generative or CNN approaches, but must include preprocessing, paired-data training, accuracy assessment and high-resolution reference validation. Report uncertainty and error explicitly because reconstructed details are inferred, not observed. Crop, urban and disaster analysis are intended uses; visual sharpness alone does not satisfy scientific reliability.

No. 1046Problem statementSpace and research

Target detection by optimizing Anomaly Detection in Hyperspectral Image Processing using AI/ML

Research AI/ML anomaly detection in public hyperspectral datasets such as Hyperion or AVIRIS, identifying spectrally unusual pixels and object signatures. The source discusses preprocessing, denoising, fusion and radiometric/atmospheric correction before evaluating deep-learning models. This overview retains image-analysis research scope without target-engagement instructions; improved detection remains to be demonstrated.

No. 1112Problem statementSpace and research

Integrated Geo-Referenced Fish Catch Data Repository and Access System

Create an INCOIS repository consolidating georeferenced fish-catch records from researchers, industry, cruises and image-based collection. Accept Excel data and organise by date, location, depth and species, with filters, visualisation and downloads for species-specific habitat research. Preserve distinctions between species-level weights and aggregate catch weights with species presence. Use separate occurrence and abundance modules, geographic/time filters, mapped results, Excel/CSV exports and authenticated access with an updating administration interface.

No. 1114Problem statementSpace and research

Data download Duplication Alert System (DDAS)

Develop a dataset-download duplication alert for institutes and research organisations. Maintain download metadata and use history or unique identifiers to recognise a dataset even under another filename. Before downloading, notify users of an existing copy in institutional repositories or user accounts, including its location, timestamp, period and spatial coverage. The source envisages applicability across research, academia, government and other sectors.