Alireza Taheri Dehkordi: Estimation of water quality parameters using remote sensing data and machine learning models

The global decline in water quality, exacerbated by climate change and population growth, underscores the need for continuous and accurate monitoring of water quality parameters (WQPs). Remote sensing (RS) data, especially from multispectral satellites like Sentinel-2 and Landsat-8, offers large-scale, periodic observations for tracking WQPs. 

However, deriving accurate estimates solely from RS data is complex due to the intricate relationships between spectral bands and water quality indicators. This talk presents two novel machine learning approaches that leverage advanced RS data processing to enhance water quality monitoring.

Alireza is a doctoral student in Water Resources Engineering at Lund University, focusing on the combined applications of machine/deep learning, and remote sensing in hydrology. His primary interests lie in developing innovative AI-based models for groundwater level estimation using InSAR data and for water quality estimation through optical remote sensing. He is currently working on applying advanced models to extract more accurate, large-scale hydrological insights from these diverse data sources.