Multi-Source Data Fusion for Harmful Algal Bloom Detection and Prediction: A Survey of Satellite, IoT, and Citizen-Science Approaches Using Machine Learning

Authors

Hemanth Chandra N

Assistant Professor Department of Information Science and Engineering Global Academy of Technology (India)

Kaveendra Sri Chakradari

Dept. of Information Science and Engineering Global Academy of Technology (India)

Rajath L

Dept. of Information Science and Engineering Global Academy of Technology (India)

Vamshi Krishna D

Dept. of Information Science and Engineering Global Academy of Technology (India)

Yashpal Singh

Dept. of Information Science and Engineering Global Academy of Technology (India)

Article Information

DOI: 10.51584/IJRIAS.2026.11110010

Subject Category: Information Technology

Volume/Issue: 11/11 | Page No: 113-121

Publication Timeline

Submitted: 2026-11-02

Accepted: 2026-11-07

Published: 2026-11-21

Abstract

Harmful Algal Blooms (HABs) are an escalating threat to freshwater ecosystems, urban water infrastructure, and public health, particularly in densely populated urban water bodies such as Bellandur Lake. Existing monitoring approaches largely rely on a single observation source satellite remote sensing, in-situ sensor networks, laboratory sampling, or citizen-submitted photographs and each of these, taken alone, suffers from well-known gaps: satellite imagery is disrupted by cloud cover, sensor networks are spatially limited, and manual sampling cannot support continuous, real-time monitoring. This paper presents a structured survey of vision- and sensor-driven HAB detection and prediction systems, spanning single-image computer vision techniques, satellite spectral-index-based remote sensing, IoT-based water quality monitoring, and machine learning ensembles such as XGBoost, Support Vector Regression (SVR), and Artificial Neural Networks (ANN). We review recent literature on chlorophyll-a estimation, algal bloom severity classification, and multi-source data fusion, and we examine widely used spectral indices including the Normalized Difference Chlorophyll Index (NDCI) and the Floating Algae Index (FAI). Building on the identified gaps namely the near-universal reliance on a single data modality, the trade-off between detection and prediction capability, and the limited integration of citizen-science data we outline a proposed Multi-Tier Hybrid Monitoring Framework, Eco-Watch, that fuses satellite analysis, IoT sensing, and citizen-submitted imagery within a unified ensemble learning and early-warning pipeline. This survey is intended as a structured reference for researchers and practitioners working toward integrated, real-time decision-support systems for algal bloom monitoring and water quality management.

Keywords

Harmful Algal Blooms, Remote Sensing, NDCI, Google Earth Engine, IoT Water Quality Monitoring, Citizen Science

Downloads

References

1. C. W. Park, J. J. Jeon, Y. H. Moon, and I. K. Eom, “Single Image Based Algal Bloom Detection Using Water Body Extraction and Probabilistic Algae Indices,” 2019. [Google Scholar] [Crossref]

2. D. Kaiser and J. J. Qu, “Detecting Harmful Algae Blooms (HABs) on the Ohio River Using Landsat and Google Earth Engine,” 2025. [Google Scholar] [Crossref]

3. P. Joshi, R. Storey, S. Sharma, and B. Mishra, “Monitoring chlorophyll-a in Phewa Lake, Nepal using satellite images and ensemble-based learning,” Frontiers in Environmental Science, vol. 14, p. 1717629, 2026. [Google Scholar] [Crossref]

4. Z. Wu and K. L. E. Law, “Remote Sensing and Deep Learning for Algal Blooms: A Review,” IEEE Access, vol. 13, pp. 180891–180908, 2025. [Google Scholar] [Crossref]

5. I. Nasios, “AI-driven multi-source data fusion for algal bloom severity classification in small inland water bodies: Leveraging Sentinel-2, DEM, and NOAA climate data,” Remote Sensing Applications: Society and Environment, vol. 40, p. 101800, 2025. [Google Scholar] [Crossref]

6. O. Mermer, E. Zhang, and I. Demir, “Predicting Harmful Algal Blooms Using Ensemble Machine Learning Models and Explainable AI Technique: A Comparative Study,” 2024/2025. [Google Scholar] [Crossref]

7. S. Mohan, B. Kumar, and A. P. Nejadhashemi, “Integration of Machine Learning and Remote Sensing for Water Quality Monitoring and Prediction: A Review,” Sustainability, vol. 17, no. 3, p. 998, 2025. [Google Scholar] [Crossref]

8. W. Jang, J. Kim, J. H. Kim, J.-K. Shin, K. Chon, E. T. Kang, Y. Park, and [Google Scholar] [Crossref]

9. S. Kim, “Evaluation of Sentinel-2 Based Chlorophyll-a Estimation in a Small-Scale Reservoir: Assessing Accuracy and Availability,” Remote Sensing, vol. 16, no. 2, p. 315, 2024. [Google Scholar] [Crossref]

10. V. Oliveira Santos, B. M. D. M. Guimarães, I. E. L. Neto, F. de A. de Souza Filho, P. A. Costa Rocha, J. Van Griensven Thé, and B. Gharabaghi, “Chlorophyll-a Estimation in 149 Tropical Semi-Arid Reservoirs Using Remote Sensing Data and Six Machine Learning Methods,” Remote Sensing, vol. 16, no. 11, p. 1870, 2024. [Google Scholar] [Crossref]

11. X. Bu, K. Liu, J. Liu, and Y. Ding, “A Harmful Algal Bloom Detection Model Combining Moderate Resolution Imaging Spectroradiometer Multi-Factor and Meteorological Heterogeneous Data,” Sustainability, vol. 15, no. 21, p. 15386, 2023. [Google Scholar] [Crossref]

Metrics

Views & Downloads

Similar Articles