Carbon derived from Tannery Solid Waste LSTM-Based Deep Learning Framework for Real-Time Water Pollution Monitoring in Tannery Effluent–Affected Regions

Abstract

Research summary supplied by the authors

Water pollution resulting from tannery effluents in the leather industry poses a striking environmental challenge due to high organic load and toxic heavy metals. This study proposes a Long Short-Term Memory (LSTM)–based deep learning framework for real-time monitoring and prediction of water quality. Sequential water quality parameters, including pH, dissolved oxygen, biochemical oxygen demand, chemical oxygen demand, turbidity, and chromium concentration, are modeled as time-series inputs to capture temporal dependencies and pollution dynamics. The LSTM network effectively learns longterm variations and nonlinear patterns in water quality data, enabling accurate pollution level prediction and early anomaly detection. The results highlight the suitability of LSTM models for continuous water pollution surveillance and intelligent environmental management in leather industry–affected regions.