
This folder contains the datasets and python codes implemented for “Approximating 1D and 2D Saint-Venant Equations using Physics-Informed Neural Networks for Flood Inundation Modelling”. It has three folders, “data” folder contains the data used for this study “codes” folder contains all python codes, and “results” folder contains the predicted flood maps along with the figures. The “codes” folder contains eight python files each corresponding to each case study conducted in this article. The “data” folder contains sub-folders with folder name corresponding the case study. These folders contain the reference solutions obtained from HEC-RAS for 1D case studies and from LISFLOOD-FP model for 2D case studies. The “results” folder contains eight sub-folders, each corresponding to each case study conducted in this article. Each sub-folder corresponding to each case study contains, the PINNs model parameters with file names ending with “.pth”, excel file containing PINNs loss at every epoch, the results plots from the article for 1D case studies and for 2D case studies along with these results, the flood maps at every time interval are also provided along the error metrics.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
