The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
A Comparison of Machine Learning Approaches to Improve Free Topography Data for Flood Modelling
Abstract
Given the high financial and institutional cost of collecting and processing accurate topography data, many large-scale flood hazard assessments continue to rely instead on freely-available global Digital Elevation Models, despite the significant vertical biases known to affect them. To predict (and thereby reduce) these biases, we apply a fully-convolutional neural network (FCN), a form of artificial neural network originally developed for image segmentation which is capable of learning from multi-variate spatial patterns at different scales. We assess its potential by training such a model on a wide variety of remote-sensed input data (primarily multi-spectral imagery), using high-resolution, LiDAR-derived Digital Terrain Models published by the New Zealand government as the reference topography data. In parallel, two more widely used machine learning models are also trained, in order to provide benchmarks against which the novel FCN may be assessed. We find that the FCN outperforms the other models (reducing root mean square error in the testing dataset by 71%), likely due to its ability to learn from spatial patterns at multiple scales, rather than only a pixel-by-pixel basis. Significantly for flood hazard modelling applications, corrections were found to be especially effective along rivers and their floodplains. However, our results also suggest that models are likely to be biased towards the land cover and relief conditions most prevalent in their training data, with further work required to assess the importance of limiting training data inputs to those most representative of the intended application area(s).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Data on building footprints and density from OpenStreetMap were not used due to the lack of global consistency [63] and the low importance of the variable(s) in other location specific random forest based DEM correction studies [35,39].”
From A 30 m global map of elevation with forests and buildings removed (2022) · cites this paper as [39]
In the citing paper
“With the rich amount of auxiliary data related to global building and forest coverage now available, there is increasing potential to utilise machine learning techniques to remove trees [31], buildings [35,36] or both [37][38][39], although to date these studies are limited to the local or quasi global scale.”
From A 30 m global map of elevation with forests and buildings removed (2022) · cites this paper as [39]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Larian Studios Dev Team (2024) · doi:10.1145/3292500.3330701 · Cited by 8,618
High-resolution mapping of global surface water and its long-term changes
Pekel, J.-F., Cottam, A., Gorelick, N., & Belward, A. S. (2016) · Nature · doi:10.1038/nature20584 · Cited by 5,513
Use of normalized difference built-up index in automatically mapping urban areas from TM imagery
Zha, Y., Gao, J., & Ni, S. (2003) · International Journal of Remote Sensing · doi:10.1080/01431160304987 · Cited by 3,454
Deep learning in remote sensing applications: A meta-analysis and review
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.04.015 · Cited by 2,456
Pixel-wise regression using U-Net and its application on pansharpening
Yao, W., Zeng, Z., Lian, C., & Tang, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.103 · Cited by 133 · cited 3×
“We addressed this by generating contiguous “patches” of target data (the elevation corrections required) consisting of 12 × 12 grid cells, as well as sets of corresponding feature patches (for all 23 selected features) with a larger spatial extent (100 × 100 grid cells), to ensure that all grid…”
BackgroundMethod
Research works printed but not linked: 49
- Simpson, 2015, An urgent case for higher resolution digital elevation models in the world’s poorest and most vulnerable countries, Front. Earth Sci., 3, 50, 10.3389/feart.2015.00050 · doi:10.3389/feart.2015.00050
- Kulp, 2018, CoastalDEM: A global coastal digital elevation model improved from SRTM using a neural network, Remote Sens. Environ., 206, 231, 10.1016/j.rse.2017.12.026 · DOI · Paper page
- Paiva, 2016, A multi-sensor approach towards a global vegetation corrected SRTM DEM product, Remote Sens. Environ., 182, 49, 10.1016/j.rse.2016.04.018 · DOI · Paper page
- Jena, 2016, Assessment of Cartosat-1 DEM for Modeling Floods in Data Scarce Regions, Water Resour. Manag., 30, 1293, 10.1007/s11269-016-1226-9 · doi:10.1007/s11269-016-1226-9
- Hawker, 2018, Perspectives on Digital Elevation Model (DEM) Simulation for Flood Modeling in the Absence of a High-Accuracy Open Access Global DEM, Front. Earth Sci., 6, 233, 10.3389/feart.2018.00233 · DOI · Paper page
- Sanders, 2007, Evaluation of on-line DEMs for flood inundation modeling, Adv. Water Resour., 30, 1831, 10.1016/j.advwatres.2007.02.005 · DOI · Paper page
- Wilson, 2007, Modeling large-scale inundation of Amazonian seasonally flooded wetlands, Geophys. Res. Lett., 34, 4, 10.1029/2007GL030156 · DOI · Paper page
- Yan, 2013, Exploring the potential of SRTM topographic data for flood inundation modelling under uncertainty, J. Hydroinform., 15, 849, 10.2166/hydro.2013.137 · DOI
- Domeneghetti, 2016, On the use of SRTM and altimetry data for flood modeling in data-sparse regions, Water Resour. Res., 52, 2901, 10.1002/2015WR017967 · DOI
- Farr, 2007, The Shuttle Radar Topography Mission, Rev. Geophys., 45, 33, 10.1029/2005RG000183 · DOI · Paper page
- Boulton, 2018, Which DEM is best for analyzing fluvial landscape development in mountainous terrains?, Geomorphology, 310, 168, 10.1016/j.geomorph.2018.03.002 · DOI · Paper page
- Takaku, 2016, Validation of “AW3D” Global DSM Generated from ALOS PRISM, ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., 3, 25, 10.5194/isprs-annals-III-4-25-2016 · doi:10.5194/isprs-annals-iii-4-25-2016 · Paper page
- Yamazaki, 2012, Adjustment of a spaceborne DEM for use in floodplain hydrodynamic modeling, J. Hydrol., 436–437, 81, 10.1016/j.jhydrol.2012.02.045 · DOI
- Becek, 2014, Assessing global digital elevation models using the runway method: The advanced spaceborne thermal emission and reflection radiometer versus the shuttle radar topography mission case, IEEE Trans. Geosci. Remote Sens., 52, 4823, 10.1109/TGRS.2013.2285187 · DOI
- Kulp, 2016, Global DEM Errors Underpredict Coastal Vulnerability to Sea Level Rise and Flooding, Front. Earth Sci., 4, 36, 10.3389/feart.2016.00036 · DOI
- Wendi, 2016, An innovative approach to improve SRTM DEM using multispectral imagery and artificial neural network, J. Adv. Model. Earth Syst., 8, 691, 10.1002/2015MS000536 · DOI · Paper page
- Maire, C., Datcu, M., and Audenino, P. (2003, January 21–25). SAR DEM filtering by mean of Bayesian and multi-scale, nonstationary methods. Proceedings of the IGARSS 2003—2003 IEEE International Geoscience and Remote Sensing Symposium, Toulouse, France.
- Falorni, 2005, Analysis and characterization of the vertical accuracy of digital elevation models from the Shuttle Radar Topography Mission, J. Geophys. Res. Earth Surf., 110, 1, 10.1029/2003JF000113 · DOI · Paper page
- Stevenson, 2010, Despeckling SRTM and other topographic data with a denoising algorithm, Geomorphology, 114, 238, 10.1016/j.geomorph.2009.07.006 · DOI · Paper page
- Ettritch, 2018, Enhancing digital elevation models for hydraulic modelling using flood frequency detection, Remote Sens. Environ., 217, 506, 10.1016/j.rse.2018.08.029 · DOI
- Zhao, 2018, A global corrected SRTM DEM product for vegetated areas, Remote Sens. Lett., 9, 393, 10.1080/2150704X.2018.1425560 · DOI
- Yamazaki, 2017, A high-accuracy map of global terrain elevations, Geophys. Res. Lett., 44, 5844, 10.1002/2017GL072874 · DOI · Paper page
- Saunders, W. (1999, January 24–30). Preparation of DEMs for use in environmental modeling analysis. Proceedings of the ESRI User Conference, San Diego, CA, USA.
- Mathieu, P., and Aubrecht, C. (2018). Machine Learning Applications for Earth Observation. Earth Observation Open Science and Innovation, International Space Science Institute (ISSI). · DOI
- Yu, M., Yang, C., and Li, Y. (2018). Big Data in Natural Disaster Management: A Review. Geosciences, 8. · DOI · Paper page
- Pyo, 2019, A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery, Remote Sens. Environ., 233, 111350, 10.1016/j.rse.2019.111350 · DOI · Paper page
- Parente, L., Taquary, E., Silva, A.P., Souza, C., and Ferreira, L. (2019). Next generation mapping: Combining deep learning, cloud computing, and big remote sensing data. Remote Sens., 11. · DOI
- Xie, B., Zhang, H.K., and Xue, J. (2019). Deep convolutional neural network for mapping smallholder agriculture using high spatial resolution satellite image. Sensors, 19. · DOI
- Flood, 2019, Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia, Int. J. Appl. Earth Obs. Geoinf., 82, 101897
- Long, 2017, Fully Convolutional Networks for Semantic Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 39, 640, 10.1109/TPAMI.2016.2572683 · DOI · Paper page
- Jasanoff, S. (2017). Virtual, visible, and actionable: Data assemblages and the sightlines of justice. Big Data Soc., 4. · DOI · Paper page
- Wilson, 2007, Multiscale terrain analysis of multibeam bathymetry data for habitat mapping on the continental slope, Mar. Geod., 30, 3, 10.1080/01490410701295962 · DOI · Paper page
- Xu, 2006, Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery, Int. J. Remote Sens., 27, 3025, 10.1080/01431160600589179 · DOI · Paper page
- Feyisa, 2014, Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery, Remote Sens. Environ., 140, 23, 10.1016/j.rse.2013.08.029 · DOI · Paper page
- Doll, 2006, Mapping regional economic activity from night-time light satellite imagery, Ecol. Econ., 57, 75, 10.1016/j.ecolecon.2005.03.007 · DOI · Paper page
- Levin, 2012, High spatial resolution night-time light images for demographic and socio-economic studies, Remote Sens. Environ., 119, 1, 10.1016/j.rse.2011.12.005 · DOI · Paper page
- Mellander, C., Lobo, J., Stolarick, K., and Matheson, Z. (2015). Night-Time Light Data: A Good Proxy Measure for Economic Activity?. PLoS ONE, 10. · DOI · Paper page
- Boeing, 2017, OSMnx: New methods for acquiring, constructing, analyzing, and visualizing complex street networks, Comput. Environ. Urban Syst., 65, 126, 10.1016/j.compenvurbsys.2017.05.004 · DOI · Paper page
- Poppenga, 2016, Hydrologic Connectivity: Quantitative Assessments of Hydrologic-Enforced Drainage Structures in an Elevation Model, J. Coast. Res., 76, 90, 10.2112/SI76-009 · doi:10.2112/si76-009
- Lidberg, 2017, Evaluating preprocessing methods of digital elevation models for hydrological modelling, Hydrol. Process., 31, 4660, 10.1002/hyp.11385 · DOI
- Simard, 2011, Mapping forest canopy height globally with spaceborne lidar, J. Geophys. Res. Biogeosci., 116, 1, 10.1029/2011JG001708 · DOI · Paper page
- Hansen, 2013, High-Resolution Global Maps of 21st-Century Forest Cover Change, Science, 342, 850, 10.1126/science.1244693 · DOI · Paper page
- Hastie, T., Tibshirani, R., and Friedman, J. (2017). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.].
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
- Fukushima, 1988, Neocognitron: A hierarchical neural network capable of visual pattern recognition, Neural Netw., 1, 119, 10.1016/0893-6080(88)90014-7 · DOI · Paper page
- LeCun, 1989, Backpropagation applied to Handwritten Zip Code Recognition, Neural Comput., 1, 541, 10.1162/neco.1989.1.4.541 · DOI · Paper page
- Wieland, M., and Martinis, S. (2019). A modular processing chain for automated flood monitoring from multi-spectral satellite data. Remote Sens., 11. · DOI
- Srivastava, 2014, Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res., 15, 1929
- Nobre, 2011, Height Above the Nearest Drainage—A hydrologically relevant new terrain model, J. Hydrol., 404, 13, 10.1016/j.jhydrol.2011.03.051 · DOI · Paper page
Cited by
A 30 m global map of elevation with forests and buildings removed
Hawker, L., Uhe, P., Paulo, L., Sosa, J., Savage, J., Sampson, C., & Neal, J. (2022) · Environmental Research Letters · doi:10.1088/1748-9326/ac4d4f · Cited by 907
Metadata
- Authors
- Meadows, M., & Wilson, M.
- Affiliations
- School of Earth and Environment, University of Canterbury, Christchurch 8041, New Zealand
- ORCID
- Wilson, Matthew
- Venue
- Remote Sensing
- Publisher
- MDPI AG
- Published
- 2021-01-14
- Volume
- 13
- Issue
- 2
- Pages
- 275
- ISSN
- 2072-4292
- Cited by
- 36
- References
- 7
- Language
- en
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.