Research Interests

GeoAI: Developing innovative machine learning and deep learning models, such as CNNs, ConvLSTM, and transformer-based architectures, for hyperspectral image classification, anomaly detection, and crop yield prediction.

Remote Sensing Applications: Utilizing multispectral and hyperspectral satellite imagery (e.g., Sentinel-1, Sentinel-2, DESIS) for crop monitoring, land cover classification, and environmental analysis.

Environmental Monitoring: Mapping environmental phenomena, including floods, droughts, heavy metal concentrations, and nitrogen dioxide pollution, using remote sensing and spatio-temporal analysis.

Precision Agriculture and Vegetation Analysis: Applying remote sensing and machine learning to estimate forest biomass, crop yields, detect plant diseases, and monitor vegetation health for sustainable agricultural practices.

Geospatial Analysis and GIS Application: Integrating spatial and non-spatial data in GIS for modeling urban livability, public health (e.g., tuberculosis, infertility), and ridesharing optimization.