cs.OHFeb 20, 2026

A Novel Approach for Testing Water Safety Using Deep Learning Inference of Microscopic Images of Unincubated Water Samples

Authors: Sanjay Srinivasan

Organizations: Eastlake High School

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Fecal-contaminated water causes diseases and even death. Current microbial water safety tests require pathogen incubation, taking 24-72 hours and costing $20-$50 per test. This paper presents a solution (DeepScope) exceeding UNICEF's ideal Target Product Profile requirements for presence/absence testing, with an estimated per-test cost of $0.44. By eliminating the need for pathogen incubation, DeepScope reduces testing time by over 98%. In DeepScope, a dataset of microscope images of bacteria and water samples was assembled. An innovative augmentation technique, generating up to 21 trillion images from a single microscope image, was developed. Four convolutional neural network models were developed using transfer learning and regularization techniques, then evaluated on a field-test dataset comprising 100,000 microscope images of unseen, real-world water samples collected from fourteen different water sources across Sammamish, WA. Precision-recall analysis showed the DeepScope model achieves 93% accuracy, with precision of 90% and recall exceeding 94%. The DeepScope model was deployed on a web server, and mobile applications for Android and iOS were developed, enabling Internet-based or smartphone-based water safety testing, with results obtained in seconds.

Figures & tables

Figure 1: Image of Rainwater Puddle Underneath Compound Microscope at 1000x Magnification
Figure 2: Image of Shower Drain Water Underneath Compound Microscope Stained with Methylene Blue Dye at 1000x Magnification.
Figure 3: Illustration of image augmentation. The image is divided into 16 tiles, and random pairs of tiles are selected and their contents swapped.
Figure 4: Locations of water bodies in Sammamish where water samples were collected for field testing.
Figure 5: Microscope images at 1000x magnification of water sample from Sources 5 (left) and 6 (right). Both sources were found to be unsafe in color change coliform testing.
Figure 6: Model Architecture of CNN-50 With Dropout, CNN-50 Without Dropout, CNN-18 With Dropout, CNN-18 Without Dropout.
Figure 7: Precision Recall Curve for the CNN50 model with dropout (left) and CNN50 model without dropout (right).
Figure 8: Precision Recall Curve for the CNN18 model with dropout (left) and for the CNN18 model without dropout (right).
Figure 9: Example workflow to test water safety over the Internet using a web server hosting the DeepScope model.
Figure 10: Screenshots of DeepScope app executing on an Android device. The app communicates with a Flask server at http://A.B.C.D:5000.
Figure 11: Screenshots and workflow of DeepScope app on iOS device. DeepScope model stored and accessed directly on the smartphone device.
More in this topic

Microscopy Image Analysis

Microscopy image analysis uses computational methods to detect, segment, track, reconstruct, and quantify structures in scientific images.

See all 198 papers

Explore similar work

CardsList

  1. Peoples Water Data: Enabling Reliable Field Data Generation and Microbial Contamination Screening in Household Drinking Water

    Apr 5, 2026Suzan Kagan, Shira Spigelman, Sankar Sudhir +2

    DST Unit of Nanoscience and Thematic Unit of Excellence, Department of Chemistry, IIT Madras, Chennai 600 036, India. · School of Mechanical Engineering, Faculty of Engineering, Tel Aviv University, Tel-Aviv, Israel. · Faculty of Statistics, Tel Aviv University, Tel-Aviv, Israel. +1

  2. Effects of model architecture and learning strategies on deep learning-based recognition of activated sludge microscopic images and comparison with quantitative image analysis

    Sep 8, 2026Suguru Hakoshima, Tomohiro Tobino, Fumiyuki NakajimaSelf-Supervised LearningVision Transformer

    Department of Urban Engineering, Graduate School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Tokyo, Japan · Environmental Science Center, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-0033, Tokyo, Japan · Collaborative Research Institute for Innovative Microbiology, The University of Tokyo, 1-1-1, Yayoi, Bunkyo-ku, 113-8657, Tokyo, Japan

  3. Video to All-in-focus Image Reconstruction Algorithm for Automated Microscopic Urinalysis

    Jul 15, 2026Chinmay Nema, Hari Om Aggrawal, Dipam Goswami +2Multi-Source Image FusionImage Reconstruction

    Birla Institute of Technology and Science Pilani, India · independent researcher, India · Institute of Mathematics and Image Computing, University of Lübeck, Germany +1