Smartphone-based colorimetric sensing with reference calibration and ensemble machine learning for enhanced detection...

Rapid, low-cost detection of nutrient pollutants such as nitrite (NO₂^-) and ammonium (NH₄⁺) is crucial for environmental monitoring. Conventional colorimetric instruments offer high accuracy but are expensive, bulky, and unsuitable for on-site analysis. Smartphone-based colorimetry provides a portable and affordable alternative, yet its accuracy is often compromised by variations in illumination and camera hardware. Although color reference standards and linear calibration improve consistency, achieving device-independent quantification remains challenging. This study introduces an integrated smartphone colorimetric platform combining a controlled lightbox, embedded color reference, and ensemble machine learning to enhance analytical robustness and reproducibility.

A total of 2,700 Rhodamine B images (five smartphones, 30 concentrations each) and 5,400 analyte images (six smartphones, 30 concentrations each for NO₂^- and NH₄⁺) were analyzed using eight machine learning algorithms under two pipelines: ROI-only and reference "Square" calibration. Ensemble models (Random Forest, XGBoost) consistently outperformed other approaches, achieving >95 % accuracy in concentration classification and superior regression performance. Reference calibration markedly enhanced cross-device reproducibility and precision, increasing R² from 0.76-0.89 (ROI) to 0.89-0.95 and reducing MSE by 25-75 %, depending on model and device (e.g., Mi8 Lite-XGBoost: 2.16 → 0.57 ppm²; Nokia-Random Forest: 1.49 → 0.85 ppm²). Even budget smartphones (e.g., Oppo A83, Redmi A1) reached R² ≥ 0.91, comparable to high-end models. Variance across replicate trials decreased, confirming improved stability. Combined RGB/HSV/CIELAB feature sets with reference-normalized deltas and ratios were most predictive, yielding a final R² of 0.95 with minimal error and high consistency.

By integrating standardized imaging, color reference calibration, and ensemble machine learning, this study establishes a robust and device-independent framework for quantitative smartphone colorimetry. The significant improvements in predictive accuracy (higher R²), error reduction (lower MSE), and measurement stability enable reliable analysis of NO₂^- and NH₄⁺ using common smartphones. Moreover, the modular design can be readily adapted for other analytes and incorporated into mobile or cloud-based analytical platforms for scalable environmental monitoring.