In the heart of Odisha, the Baitarani River flows, a lifeline for communities and industries alike. Yet, this vital water source is under threat, its quality deteriorating due to a mix of domestic, industrial, and environmental pressures. Abhijeet Das, a research scholar at the Department of Civil Engineering, C.V. Raman Global University (CGU), Bhubaneswar, Odisha, has been at the forefront of understanding and addressing this critical issue.
Das and his team have published a comprehensive study in the journal ‘Desalination and Water Treatment’ that not only assesses the current state of the Baitarani River’s water quality but also predicts future trends using a combination of advanced techniques. “The river is facing serious problems with water quality,” Das explains, “and it’s crucial to estimate water output and locate potential surface water zones to ensure sustainable water management.”
The research team collected water samples from thirteen strategic locations along the Baitarani River, analyzing nineteen physicochemical parameters related to water quality. They employed a multifaceted approach, integrating scientific data with local insights, to map water quality at every point along the river using ArcGIS tools. The study revealed significant fluctuations in key parameters such as pH, calcium, and chloride levels, with some sites showing alarmingly low dissolved oxygen (DO) levels. “The reduced DO at site X-(8) reflects the pressing need for actions to safeguard the river and the towns that depend on it,” Das notes.
The team used a combination of Drinking Water Quality Index (Dr-WQI) and multivariate statistical techniques, including discriminant analysis (DA), to assess the variations in surface water quality. They also applied machine learning (ML) algorithms such as Artificial Neural Network (ANN), Gaussian Process Regression (GPR), Support Vector Machine (SVM), and Linear Regression Model (LRM) to forecast and confirm the quality of the water. The ANN model, in particular, showed exceptional accuracy in water quality prediction, highlighting the reliability and precision of the current work.
The findings are stark: eight out of the thirteen sites represent polluted sources, with agricultural practices identified as a significant contributor to the contamination. “By employing Discriminant Analysis, five water quality parameters such as TH, TDS, Na+, DO, and BOD, were successfully identified, with 100% assignment rate,” Das says. The spatial distribution map, created with the assistance of the inverse distance weighted (IDW) method, provides a clear visual representation of the contamination zones.
The implications of this research are profound, not just for environmental conservation but also for the energy sector. Water quality directly impacts the efficiency and sustainability of energy production, particularly in regions reliant on hydropower or cooling water for thermal power plants. Understanding and predicting water quality trends can help energy companies mitigate risks and optimize their operations.
Das’s work paves the way for future developments in water quality management. By combining scientific data with local perspectives, the study offers a holistic approach to understanding water quality issues. This highlights the critical need for focused interventions to protect the river ecosystem and the welfare of the communities that depend on it. The integration of machine learning models adds a predictive dimension, enabling proactive rather than reactive management strategies.
As the world grapples with climate change and water scarcity, studies like Das’s are more crucial than ever. They provide insightful information for sustainable environmental management and underscore the importance of interdisciplinary approaches in tackling complex environmental challenges. The energy sector, in particular, stands to gain from these advancements, ensuring a more sustainable and resilient future.