Integration of Satellite Remote Sensing and Machine Learning for Pond Water Quality Prediction in Eluru
Bibliographic record
Abstract
Aquaculture is essential for addressing global food security, but its sustainable expansion faces significant hurdles—particularly in monitoring water quality. In key aquaculture hubs like Eluru, India, the well-being and output of fishponds hinge on critical factors like dissolved oxygen (DO), pH levels, and ammonia concentrations. Conventional monitoring techniques, which involve labor-intensive manual sampling, are costly, inefficient, and difficult to scale across vast pond networks. To overcome these limitations, this study introduces an innovative solution: a fusion of satellite remote sensing and machine learning designed to deliver scalable, affordable, and near-instantaneous water quality assessments. At the core of this approach is Sentinel-2 multispectral imagery, offering detailed optical data spanning visible, near-infrared (NIR), and shortwave infrared (SWIR) wavelengths. While DO, ammonia, and pH cannot be directly measured by satellites, they can be estimated using spectral indicators such as reflectance values (B2, B3, B4, B8, B11, B12) and water-vegetation indices like NDVI, NDWI, MNDWI, and NDCI. The methodology follows a two-phase process: (i) reconstructing missing satellite data caused by cloud cover or gaps using interpolation and regression techniques to maintain dataset continuity; and (ii) training a Random Forest regression model on historical in-situ measurements alongside satellite-derived metrics to predict DO, ammonia, and pH concurrently. Findings reveal that this combined method effectively compensates for incomplete satellite observations while yielding precise estimates of vital water quality metrics. By facilitating large-scale, routine monitoring of thousands of ponds, the system drastically reduces reliance on manual sampling. This advancement holds promise for bolstering aquaculture welfare programs, enhancing fish health and productivity, and promoting the long-term viability of inland aquaculture operations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".