S. V. Amrutha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
S. V. Amrutha has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Oliver Steinbock
Florida State University
4 shared publications - T. K. Shajahan
National Institute of Technology Karnataka Surathkal
4 shared publications - Anupama Sebastian
National Institute of Technology Karnataka
3 shared publications - Beni B. Dangi
Florida Agricultural and Mechanical University
3 shared publications - Shreyas Punacha
University of Washington
3 shared publications - Puthiyapurayil Sibeesh
National Institute of Technology Karnataka Surathkal
2 shared publications
Latest Publications
- 3 July 2026
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 98 (27) , 20563-20571
Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System
Dried droplet deposits encode compositional information through evaporation-driven self-organization, offering a potential low-cost sensing modality for chemical analyses. Here, we evaluate the feasibility of inferring solute concentrations and pH from photographic images of dried synthetic urine stains by using automated experimentation and machine learning. A robotic droplet imager (RODI) combined with Latin hypercube sampling was employed to efficiently explore compositional space and generate standardized data sets comprising 70,000 images across two experimental systems: a two-component urea-NaCl model and seven-component synthetic urine mixtures spanning physiologically relevant ranges for urea, NaCl, KCl, creatinine, glucose, a combined salt group, and pH. Each image was reduced to 47 descriptors, capturing spatial morphology and texture. Random Forest regression yielded useful predictive performance for NaCl in the two-component system and identified pH as the most robustly inferred parameter in the complex mixture. However, continuous prediction of individual solute concentrations in the seven-component system remained limited, possibly due to the sparsity of training points across the high-dimensional compositional space. These findings delineate both the current capabilities and information-theoretic constraints of image-based compositional inference for complex chemical mixtures.
- 3 July 2026
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 98 (27) , 20563-20571
Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System
Dried droplet deposits encode compositional information through evaporation-driven self-organization, offering a potential low-cost sensing modality for chemical analyses. Here, we evaluate the feasibility of inferring solute concentrations and pH from photographic images of dried synthetic urine stains by using automated experimentation and machine learning. A robotic droplet imager (RODI) combined with Latin hypercube sampling was employed to efficiently explore compositional space and generate standardized data sets comprising 70,000 images across two experimental systems: a two-component urea-NaCl model and seven-component synthetic urine mixtures spanning physiologically relevant ranges for urea, NaCl, KCl, creatinine, glucose, a combined salt group, and pH. Each image was reduced to 47 descriptors, capturing spatial morphology and texture. Random Forest regression yielded useful predictive performance for NaCl in the two-component system and identified pH as the most robustly inferred parameter in the complex mixture. However, continuous prediction of individual solute concentrations in the seven-component system remained limited, possibly due to the sparsity of training points across the high-dimensional compositional space. These findings delineate both the current capabilities and information-theoretic constraints of image-based compositional inference for complex chemical mixtures.
- Open Access
- 1 December 2025
- Published by AIP Publishing in APL Machine Learning
- Vol. 3 (4)
Synthetic images from generative AI for compositional analysis of dried solution patterns
Image-based identification of solutes from dried drop stains offers a low-cost, scalable alternative to traditional chemical analysis, enabled by artificial intelligence and annotated image libraries. While recent advances in robotic droplet imaging have facilitated the collection of such datasets, experimental acquisition remains a key bottleneck. Here, we explore whether synthetic image generation can supplement or replace real data in the context of salt classification. Using Stable Diffusion with low-rank adaptation, we generate 133 000 synthetic images from as few as N = 1–128 experimental images per salt across seven common inorganic solutes. Synthetic images become visually indistinguishable from real ones for N ≥ 6; however, quantitative analysis based on 47 image metrics reveals subtle differences that vanish around N = 128. When used to train random forest, XGBoost, and multilayer perceptron (MLP) models, synthetic data alone achieve classification accuracies of up to 90% in some low-data regimes. Synthetic augmentation offers a powerful strategy for expanding training sets and enabling image-based chemical classification in data-scarce scenarios, even if it seldom outperforms models trained on real data. The realism of synthetic images also highlights the growing need for tools that detect AI-generated scientific images to ensure data integrity.
- 1 December 2025
- Published by AIP Publishing in APL Machine Learning
- Vol. 3 (4)
Open AccessSynthetic images from generative AI for compositional analysis of dried solution patterns
Image-based identification of solutes from dried drop stains offers a low-cost, scalable alternative to traditional chemical analysis, enabled by artificial intelligence and annotated image libraries. While recent advances in robotic droplet imaging have facilitated the collection of such datasets, experimental acquisition remains a key bottleneck. Here, we explore whether synthetic image generation can supplement or replace real data in the context of salt classification. Using Stable Diffusion with low-rank adaptation, we generate 133 000 synthetic images from as few as N = 1–128 experimental images per salt across seven common inorganic solutes. Synthetic images become visually indistinguishable from real ones for N ≥ 6; however, quantitative analysis based on 47 image metrics reveals subtle differences that vanish around N = 128. When used to train random forest, XGBoost, and multilayer perceptron (MLP) models, synthetic data alone achieve classification accuracies of up to 90% in some low-data regimes. Synthetic augmentation offers a powerful strategy for expanding training sets and enabling image-based chemical classification in data-scarce scenarios, even if it seldom outperforms models trained on real data. The realism of synthetic images also highlights the growing need for tools that detect AI-generated scientific images to ensure data integrity.
- 23 June 2025
- Published by American Chemical Society (ACS) in Environmental Science & Technology
Water Hardness from Photos of Dried Drop Stains: Reporter Salts Enable Low-Concentration Detection
Water hardness is critical in domestic and industrial systems, typically measured by titration, atomic absorption spectroscopy, or inductively coupled plasma mass spectrometry. Here, we present a novel, photo-based method for quantifying water hardness using deposit patterns formed during the evaporation of hard water mixed with highly concentrated solutions of the reporter salts NaHCO3 and NaCl. This indirect approach enables the detection of hardness levels as low as 25 ppm, an improvement by a factor of 1,400 over earlier stain-based studies. Our method leverages high-resolution imaging, automated sample preparation, and advanced image analysis, including machine learning, to detect subtle morphological changes in the deposit patterns. A robotic drop imager (RODI) generated over 16,000 images, from which 47 geometric and textural metrics were extracted to train high-dimensional linear regression models and multilayer perceptron (MLP) networks. Using synthetic water samples with hardness levels of up to 250 ppm, we achieved prediction accuracies exceeding 91% for sodium bicarbonate-based patterns. Extending this methodology, we validated the methodology on real-world tap water, demonstrating its potential as a cost-effective alternative to traditional techniques and a versatile tool for water quality monitoring.
- 23 June 2025
- Published by American Chemical Society (ACS) in Environmental Science & Technology
Water Hardness from Photos of Dried Drop Stains: Reporter Salts Enable Low-Concentration Detection
Water hardness is critical in domestic and industrial systems, typically measured by titration, atomic absorption spectroscopy, or inductively coupled plasma mass spectrometry. Here, we present a novel, photo-based method for quantifying water hardness using deposit patterns formed during the evaporation of hard water mixed with highly concentrated solutions of the reporter salts NaHCO3 and NaCl. This indirect approach enables the detection of hardness levels as low as 25 ppm, an improvement by a factor of 1,400 over earlier stain-based studies. Our method leverages high-resolution imaging, automated sample preparation, and advanced image analysis, including machine learning, to detect subtle morphological changes in the deposit patterns. A robotic drop imager (RODI) generated over 16,000 images, from which 47 geometric and textural metrics were extracted to train high-dimensional linear regression models and multilayer perceptron (MLP) networks. Using synthetic water samples with hardness levels of up to 250 ppm, we achieved prediction accuracies exceeding 91% for sodium bicarbonate-based patterns. Extending this methodology, we validated the methodology on real-world tap water, demonstrating its potential as a cost-effective alternative to traditional techniques and a versatile tool for water quality monitoring.
- Open Access
- 1 January 2025
- Published by Royal Society of Chemistry (RSC) in Soft Matter
Co-motion of catalytic tubes and host droplets on superhydrophobic surfaces
Catalytic chemical garden tubes self-propel in H2O2 droplets where spatial confinement induces spinning or rotation. Internal bubble growth enlarges the drop and triggers translational jumps upon bursting.
- 1 January 2025
- Published by Royal Society of Chemistry (RSC) in Soft Matter
Open AccessCo-motion of catalytic tubes and host droplets on superhydrophobic surfaces
Catalytic chemical garden tubes self-propel in H2O2 droplets where spatial confinement induces spinning or rotation. Internal bubble growth enlarges the drop and triggers translational jumps upon bursting.
- Open Access
- 1 June 2023
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 33 (6)
Theory and experiments of spiral unpinning in the Belousov–Zhabotinsky reaction using a circularly polarized electric field
We present the first experimental study of unpinning an excitation wave using a circularly polarized electric field. The experiments are conducted using the excitable chemical medium, the Belousov–Zhabotinsky (BZ) reaction, which is modeled with the Oregenator model. The excitation wave in the chemical medium is charged so that it can directly interact with the electric field. This is a unique feature of the chemical excitation wave. The mechanism of wave unpinning in the BZ reaction with a circularly polarized electric field is investigated by varying the pacing ratio, the initial phase of the wave, and field strength. The chemical wave in the BZ reaction unpins when the electric force opposite the direction of the spiral is equal to or above a threshold. We developed an analytical relation of the unpinning phase with the initial phase, the pacing ratio, and the field strength. This is then verified in experiments and simulations.
- 1 June 2023
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 33 (6)
Open AccessTheory and experiments of spiral unpinning in the Belousov–Zhabotinsky reaction using a circularly polarized electric field
We present the first experimental study of unpinning an excitation wave using a circularly polarized electric field. The experiments are conducted using the excitable chemical medium, the Belousov–Zhabotinsky (BZ) reaction, which is modeled with the Oregenator model. The excitation wave in the chemical medium is charged so that it can directly interact with the electric field. This is a unique feature of the chemical excitation wave. The mechanism of wave unpinning in the BZ reaction with a circularly polarized electric field is investigated by varying the pacing ratio, the initial phase of the wave, and field strength. The chemical wave in the BZ reaction unpins when the electric force opposite the direction of the spiral is equal to or above a threshold. We developed an analytical relation of the unpinning phase with the initial phase, the pacing ratio, and the field strength. This is then verified in experiments and simulations.
- 14 November 2022
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry C
- Vol. 126 (46) , 19618-19626
Mechanism of Spiral Wave Unpinning in the Belousov–Zhabotinsky Reaction with a DC Electric Field
- 14 November 2022
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry C
- Vol. 126 (46) , 19618-19626
Mechanism of Spiral Wave Unpinning in the Belousov–Zhabotinsky Reaction with a DC Electric Field
- 6 October 2022
- Published by Springer Nature
- p. 1241-1249
Dynamics of Chemical Excitation Waves Subjected to Subthreshold Electric Field in a Mathematical Model of the Belousov-Zhabotinsky Reaction
- 6 October 2022
- Published by Springer Nature
- p. 1241-1249
Dynamics of Chemical Excitation Waves Subjected to Subthreshold Electric Field in a Mathematical Model of the Belousov-Zhabotinsky Reaction
- 6 October 2022
- Published by Springer Nature
- p. 1311-1317
Variations in the Scroll Ring Characteristics with the Excitability and the Size of the Pinning Obstacle in the BZ Reaction
- 6 October 2022
- Published by Springer Nature
- p. 1311-1317
Variations in the Scroll Ring Characteristics with the Excitability and the Size of the Pinning Obstacle in the BZ Reaction