A multi-method approach to assess long-term urbanization impacts on an ecologically sensitive urban wetland in Northeast India

Abstract

Deepor Beel, a natural wetland fringing the outskirts of the sub-Himalayan city of Guwahati in North-East India, has been under threat of urbanization since the past few decades. With a shrinking perimeter, the wetland – a favorite winter halt of migrating Siberian birds, manages to survive between anthropogenic aggression and ecological existence. This study maps the wetland's aerial shrinkage and environmental health from the 1990s to the 2020s using satellite imagery at five-year intervals. The water quality indicators used are Chlorophyll-a (Chl-a), turbidity, and total suspended solids (TSS) – the optically active parameters commonly used in satellite-image supported monitoring of water bodies. The comparisons indicate that while Chl-a or TSS levels in the wetland appears to have not changed significantly over the years, the expanse of the water-body shows a rapid reduction. Landuse and land cover (LULC) classification reveals maximum built-up area expansion during 2000–2010 at 52.38 %, followed by 21.6 % growth from 2010 to 2020. Additionally, two machine learning (ML) algorithms, artificial neural network (ANN) and random forest (RF), are incorporated to identify predictors from Landsat satellite bands and band ratios that reflect water quality characteristics for the different years. The correlations are validated against field-acquired data for three seasons: pre-monsoon, monsoon and post monsoon of 2021 and pre-monsoon as well as monsoon seasons of 2022. The ML models show encouraging predictions with the Green Normalized Difference Vegetation Index (GNDVI) and Normalized Difference Turbidity Index (NDTI) for evaluation of the Chl-a and TSS parameters. The moderate but increasing Chl-a values indicate the wetland's susceptibility to eutrophication, possibly due to urbanization. Thus, the use of satellite derived data along with machine learning tools and synoptic sampling for water quality assessment and predictions will be beneficial for urban planners and environmental managers for effective wetland management, especially in data poor regions.