Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation
Accurate, automated monitoring of river gauge plates is critical for hydrological analysis and effective water resource management. Traditional monitoring methods, relying on pressure probes and expensive cabling, often incur high installation and maintenance costs and typically require calibration...
| Autores principales: | , , , , |
|---|---|
| Formato: | Póster |
| Lenguaje: | Inglés |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/179573 |
| _version_ | 1855519822950957056 |
|---|---|
| author | Kayathri, Vigneswaran Retief, Hugo Clifford-Holmes, J. Garcia Andarcia, Mariangel Tennakoon, Hansaka |
| author_browse | Clifford-Holmes, J. Garcia Andarcia, Mariangel Kayathri, Vigneswaran Retief, Hugo Tennakoon, Hansaka |
| author_facet | Kayathri, Vigneswaran Retief, Hugo Clifford-Holmes, J. Garcia Andarcia, Mariangel Tennakoon, Hansaka |
| author_sort | Kayathri, Vigneswaran |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Accurate, automated monitoring of river gauge plates is critical for hydrological analysis and effective water resource management. Traditional monitoring methods, relying on pressure probes and expensive cabling, often incur high installation and maintenance costs and typically require calibration at intervals of up to two weeks. Imagery-based solutions can significantly reduce these costs and provide continuous, verifiable field data, enabling more frequent validation. This study introduces a novel, two-stage approach that combines real-time object detection with generative AI to extract gauge readings and compute corresponding river discharges. In the first stage, a YOLOv8 model localizes gauge plates and waterline regions within field images. In the second stage, a dedicated YOLOv8 network performs key-point detection to identify scale-gap markers along the gauge face. These detections are then ingested by a Gemini-powered generative AI pipeline via task-specific prompting to translate image features into precise numeric readings. Subsequent conversion of extracted gauge readings into volumetric discharge leverages established rating curves, enabling end-to-end automation of river flow estimation. This study evaluated model performance on three image subsets: the full dataset, a good–moderate quality subset (≈91% of samples), and a challenging “worst” subset (≈9%, including blurred, corroded, or occluded scales). The coefficient of determination (R²) for these categories was 0.552, 0.816, and 0.061, respectively, indicating robust predictive capability in moderate-to-high quality imagery with diminished accuracy under severe visual degradation. This hybrid AI solution offers scalable, real-time water level and discharge monitoring with minimal human intervention. Its resilience to varying image quality and seamless integration of object detection and generative reasoning position it as a promising tool for automated hydrological monitoring. |
| format | Poster |
| id | CGSpace179573 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| record_format | dspace |
| spelling | CGSpace1795732026-01-09T05:40:41Z Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation Kayathri, Vigneswaran Retief, Hugo Clifford-Holmes, J. Garcia Andarcia, Mariangel Tennakoon, Hansaka artificial intelligence rivers discharge water management water levels models Accurate, automated monitoring of river gauge plates is critical for hydrological analysis and effective water resource management. Traditional monitoring methods, relying on pressure probes and expensive cabling, often incur high installation and maintenance costs and typically require calibration at intervals of up to two weeks. Imagery-based solutions can significantly reduce these costs and provide continuous, verifiable field data, enabling more frequent validation. This study introduces a novel, two-stage approach that combines real-time object detection with generative AI to extract gauge readings and compute corresponding river discharges. In the first stage, a YOLOv8 model localizes gauge plates and waterline regions within field images. In the second stage, a dedicated YOLOv8 network performs key-point detection to identify scale-gap markers along the gauge face. These detections are then ingested by a Gemini-powered generative AI pipeline via task-specific prompting to translate image features into precise numeric readings. Subsequent conversion of extracted gauge readings into volumetric discharge leverages established rating curves, enabling end-to-end automation of river flow estimation. This study evaluated model performance on three image subsets: the full dataset, a good–moderate quality subset (≈91% of samples), and a challenging “worst” subset (≈9%, including blurred, corroded, or occluded scales). The coefficient of determination (R²) for these categories was 0.552, 0.816, and 0.061, respectively, indicating robust predictive capability in moderate-to-high quality imagery with diminished accuracy under severe visual degradation. This hybrid AI solution offers scalable, real-time water level and discharge monitoring with minimal human intervention. Its resilience to varying image quality and seamless integration of object detection and generative reasoning position it as a promising tool for automated hydrological monitoring. 2025-12-16 2026-01-09T05:39:13Z 2026-01-09T05:39:13Z Poster https://hdl.handle.net/10568/179573 en Open Access Kayathri, V.; Retief, H.; Clifford-Holmes, J.; Garcia Andarcia, M.; Tennakoon, H. 2025. Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation. Poster presented at the American Geophysical Union Fall (AGU25) Conference 2025: Where Science Connects Us. New Orleans, USA. 15-19 December 2025. |
| spellingShingle | artificial intelligence rivers discharge water management water levels models Kayathri, Vigneswaran Retief, Hugo Clifford-Holmes, J. Garcia Andarcia, Mariangel Tennakoon, Hansaka Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title | Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title_full | Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title_fullStr | Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title_full_unstemmed | Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title_short | Hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| title_sort | hybrid object detection and generative ai framework for automated river gauge plate reading and discharge estimation |
| topic | artificial intelligence rivers discharge water management water levels models |
| url | https://hdl.handle.net/10568/179573 |
| work_keys_str_mv | AT kayathrivigneswaran hybridobjectdetectionandgenerativeaiframeworkforautomatedrivergaugeplatereadinganddischargeestimation AT retiefhugo hybridobjectdetectionandgenerativeaiframeworkforautomatedrivergaugeplatereadinganddischargeestimation AT cliffordholmesj hybridobjectdetectionandgenerativeaiframeworkforautomatedrivergaugeplatereadinganddischargeestimation AT garciaandarciamariangel hybridobjectdetectionandgenerativeaiframeworkforautomatedrivergaugeplatereadinganddischargeestimation AT tennakoonhansaka hybridobjectdetectionandgenerativeaiframeworkforautomatedrivergaugeplatereadinganddischargeestimation |