3D Settling Map Method

Intelligent sludge characterization

Encodes the sludge settling process into a spatiotemporal optical fingerprint, enabling deep-learning-based quantification of MLSS, SVI30, and other key parameters with robustness to interferences and cross-site applicability.

Lei, Jie · Liu, Zhe · Wang, Jiaxuan · Yang, Rushuo · Tianyu, Han · Zhuangzhuang, Yang · Li, Ang · Liu, Yongjun · Luo, Zhenmin · Chen, Rong

Water Research 2026

Specifications

MLSS determination R²

{'zh': '0.957', 'en': '0.957'}

SV30 determination R²

{'zh': '0.953', 'en': '0.953'}

SVI30 determination R²

{'zh': '0.962', 'en': '0.962'}

Filamentous level classification accuracy

{'zh': '99.3', 'en': '99.3'} %

Advantages

Interference-resistant

The 3D-SM showed low sensitivity to tested environmental factors (e.g., pH, conductivity, and color) within the evaluated range.

Complete dynamics fingerprint

By capturing the entire settling process as one unified fingerprint, it encodes richer state information than single-point measurements.

Applications

• Wastewater treatment process monitoring：Real-time MLSS/SVI30 for aeration and sludge wasting control.
• Sludge bulking early warning：Detects filamentous enrichment and settling dysfunction before bulking.
• Online water quality analyzers：Replaces manual settling tests, enabling automated analyzers.
• Smart water sensing：Provides AI-parsable digital signature for smart water decisions.