A novel system for assessing paraquat toxicity using Desmodesmus maximus as a potential bio-indicator and deep learning-based approach

Abstract

Microalgae play a crucial role as environmental indicators, offering valuable insights into ecosystem health and aiding in the assessment of water source contamination by toxins. In recent times, the presence of paraquat in water sources has become a grave concern due to its high toxicity and persistence. The detection of paraquat in natural water is of paramount importance for safeguarding water quality and public safety. Microalgae are invaluable bio-indicators for pollutant detection, but using small-sized microalgae according to OECD guidelines may not suit toxicity field combined with deep learning due to limitations. In this regard, this study proposes the use of Desmodesmus maximus as a potential bio-indicator, known for its larger cell size, surpassing Desmodesmus subspicatus, the reference strain specified by OECD guidelines. Exposure of D. maximus to 2 mg/L paraquat resulted in significant internal damage and loss of chlorophyll content, with a determined 72 h-EC50 of 0.25 mg/L. Accurate microalgae recognition typically requires time-consuming and inaccessible expert analysis. Therefore, this study explores deep learning techniques to enhance the efficiency and accuracy of microalgae toxicity testing. Deep convolutional neural networks (D-CNNs), including RetinaNet, YOLOv5, EfficientDet, and Faster R-CNN models, are compared for microalgae detection and differentiation. The analysis demonstrates the superiority of the Faster R-CNN model, achieving a remarkable mAP@0.5 value of 0.98 in multiclass conditions for identifying normal, empty, and toxified colonies. These findings underscore the considerable potential of deep learning techniques in advancing microalgae toxicity testing, thereby facilitating enhanced accessibility and cost-effectiveness in monitoring the environmental impact on water resources.