Explainable quantum inspired LSTM model for water quality classification in fishponds

Abstract Water quality monitoring is a crucial aspect of aquaculture, contributing significantly to the health, productivity, and sustainable management of aquatic environments. It is important to monitor key parameters like pH, dissolved oxygen, turbidity and temperature levels continuously to ensure optimal water conditions. The traditional monitoring methods, however, tend to be costly, time-consuming, and sometimes ineffective when trying to monitor a dynamic aquatic system in real-time. Recently, several deep learning and quantum inspired algorithms such as ANN, CNN, LSTM, GRU, QSVM and QDEDL-WQI frameworks have been developed for water quality prediction and classification. These approaches, although showing good performance, have still not overcome issues of nonlinearity in the environment, learning long-term temporal dependencies, and computational efficiency. For this reason, this paper presents an intelligent water quality classification system based on the Quantum-inspired LSTM (QLSTM) for aquaculture systems. It is suggested that the proposed QLSTM model include quantum superposition-based feature encoding and quantum entanglement mechanisms to augment feature representation and learning ability. The proposed model attained an accuracy of 99.63%, recall of 98.66%, precision of 99.32%, an F1-score of 98.99%, and a loss of 0.0291. Proposed QLSTM is better than the existing deep learning and quantum-enhanced models. The framework provides for efficient and reliable real-time water quality monitoring and sustainable aquaculture management.