Enhanced land subsidence interpolation through a hybrid deep convolutional neural network and InSAR time series
Bibliographic record
Abstract
Land subsidence, whether gradual or sudden, poses a significant global threat to infrastructure and the environment. This study introduces a hybrid approach that combines deep convolutional neural networks (CNNs) with persistent scatterer interferometric synthetic aperture radar (PSInSAR) to estimate land subsidence in areas where PSInSAR data are unreliable or sparse. The proposed method trains a deep CNN using subsidence driving forces and PSInSAR data to learn spatial patterns and predict subsidence values. Our evaluation demonstrates that the CNN effectively mitigates discontinuities in PSInSAR results, producing a continuous and reliable subsidence surface. The model's performance was assessed using training, validation, and testing datasets, achieving root mean square errors (RMSEs) of 3.99, 8.47, and 9 mm, respectively. In contrast, traditional interpolation methods such as kriging, inverse distance weighting (IDW), and radial basis function (RBF) interpolation yielded RMSE values of 61.60, 66.21, and 61.76 mm, respectively, on the test dataset. Additionally, the coefficients of determination ( R 2 ) for CNN, kriging, IDW, and RBF were 0.98, −0.06, −0.22, and −0.06, respectively. The deep CNN model demonstrated an 85 % improvement in subsidence prediction accuracy compared to conventional interpolation methods, highlighting its potential for accurate and continuous land subsidence estimation.
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 | 0.000 |
| 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) | 0.001 | 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".