Triangle Water Index (TWI): An Advanced Approach for More Accurate Detection and Delineation of Water Surfaces in Sentinel-2 Data
Bibliographic record
Abstract
One of the most basic classification tasks in remote sensing is to distinguish between water bodies and other surface types. Although there are numerous techniques for extracting surface water from satellite imagery, there is still a need for research to more accurately identify water bodies with a view to efficient water maintenance in the future. Delineation accuracy is limited by varying amounts of suspended matter and different background land covers, especially those with low albedo. Therefore, the objective of this study was to develop an advanced index that improves the accuracy of extracting water bodies characterized by varying amounts of water constituents, especially in mountainous regions with highly rugged terrain, urban areas with cast shadows, and snow- and ice-covered areas. In this context, we propose a triangle water index (TWI) based on Sentinel-2 data. The principle of the TWI is that it first analyzes the reflectance values of water bodies in different wavelength bands to determine specific types. Then, triangles are constructed in a cartesian coordinate system according to the reflectance values of different water bodies in the respective wavelength bands. Finally, the TWI is achieved by using the triangle similarity theorem. We tested the accuracy and robustness of the TWI method using Sentinel-2 data of several water bodies in Mongolia, Canada, Sweden, the United States, and China and determined kappa coefficients and the overall precision. The performance of the classifier was compared with methods such as the normalized difference water index (NDWI), the modified normalized difference water index (MNDWI), the enhanced water index (EWI), the automated water extraction index (AWEI), and the land surface water index (LSWI). The classification accuracy of the TWI for all test sites is significantly higher than that of these indices that are commonly used classification methods. The overall precision of the TWI ranges between 95% and 97%. Moreover, the TWI is also effective in extracting flooded areas. Hence, the TWI can automatically extract different water bodies from Sentinel-2 data with high accuracy, which provides also a favorable analysis method for the study of droughts and flood disasters and for the general maintenance of water bodies in the future.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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 teacher head, 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".