Detecting Arsenic Contamination Using Satellite Imagery and Machine Learning
Problem
Arsenic contamination affects over 200 million people, but current detection methods are laborious, expensive, and unscalable.
Why it matters
Arsenic is a carcinogen and neurotoxin exposing over 200 million people globally.
What the AI did
Tested four regression machine learning models on NASA Hyperion hyperspectral satellite soil data, using data augmentation, genetic algorithm, second derivative transformation, and noise reduction.
Results
R²=0.840 and normalized RMSE (rescaled to [0,1])=0.122 for the best combination.
Impact
Demonstrates feasibility of satellite-based arsenic detection with strong correlation on bare-land soil.
Record
| Venue | Toxics |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Ayush Agrawal, Mark Roger Petersen |
| Citations | 22 (OpenAlex, at import time) |
| References | 65 |
| Model or method | Random Forest regression (with Genetic Algorithm) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/toxics9120333 |
| Open access | gold |
| Keywords | arsenic contamination, satellite imagery, hyperspectral, random forest, soil detection |
Importance rating
major — millions of lives, an industry or a field
Abstract states arsenic, a carcinogen and neurotoxin, affects over 200 million people globally, and current detection is laborious, expensive, unscalable; satellite method shows feasibility.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|