Enhancement of land subsidence prediction capabilities using machine learning and SHAP value analysis with Sentinel-1 InSAR Data

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 22, 2024

Abstract Land subsidence has been a significant focus of geoscience studies, and researching the factors contributing to it predicting future incidents is essential. However, current research requires systematic coherent strategy identify symptoms land sinking with scientific rigor. This study employs neural networks SHAP values forecast subsidence. We utilized as substitute for usual random forest (RF) technique evaluate attributes In addition, we employed predict prospective areas where may occur in Chongqing Chengdu future, considering diverse set conceivable situations. The results indicate that using prediction improves model's accuracy by 16% compared traditional approach. performance enhanced approximately 22% after optimizing input characteristics. feature optimization proposed this study, which relies on values, particularly advantageous Moreover, determinants sinking, ascertained data analysis intricate topography, correspond conclusions previous research. Utilizing method can improve selection variables model, increasing providing solid theoretical foundation preventing urban

Language: Английский

Particle Swarm Optimization-Based Artificial Neural Network for prediction of thyroid disease

2022 11th Mediterranean Conference on Embedded Computing (MECO), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 4

Published: June 11, 2024

Language: Английский

Statistical analysis and comprehensive optimisation of zero-gap electrolyser: Transitioning catalysts from laboratory to industrial scale

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 498, P. 155486 - 155486

Published: Sept. 6, 2024

Language: Английский