Cyclones are among the most devastating natural disasters impacting human society. One of the critical challenges following a cyclone is the assessment of building damage. Essential information such as the extent, severity, rate, and types of damage is required for rescue operations, humanitarian aid, and post-disaster reconstruction. Remote sensing techniques play a crucial role in acquiring such damage-related data due to their non-contact nature, cost-effectiveness, wide coverage, and rapid response capabilities. Across various disaster scenarios, including cyclones and armed conflicts, accurate and timely data on building damage and population displacement remain essential for effective relief efforts. In this research, a novel dataset has been prepared by preprocessing raw satellite images, which have been manually annotated by an expert team. A baseline result has also been produced for this dataset using widely adopted computer vision algorithms. Satellite imagery serves as a valuable source of information for assessing damage in disaster-affected regions. However, the vast amount of data that requires analysis makes manual evaluation impractical. The proposed dataset and baseline results aim to facilitate advancements in automated cyclone damage detection and geospatial analysis.
Sanskrit, one of humanity's most ancient languages, has a vast collection of books and manuscripts on diverse topics that have been accumulated over millennia. However, its digital content (audio and text), which is vital for the training of AI systems, is profoundly limited. Furthermore, its intricate linguistics make it hard to develop robust NLP tools for wider accessibility. Given these constraints, we have developed an automatic speech recognition model for Sanskrit by employing transfer learning mechanism on OpenAI's Whisper model. After carefully optimising the hyper-parameters, we obtained promising results with our transfer-learned model achieving a word error rate of 15.42% on Vaksancayah dataset. An online demo of our model is made available for the use of public and to evaluate its performance firsthand thereby paving the way for improved accessibility and technological support for Sanskrit learning in the modern era.
