Learning to Find Hydrological Corrections

Arge, Lars; Grønlund, Allan; Svendsen, Svend C.; Tranberg, Jonas

doi:10.1145/3347146.3359095

Cited by 3 publications

(3 citation statements)

References 12 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mao et al (2016) showed that the use of skip connections helps the training process to converge much faster and attain a higher-quality local optimum. So far, U-Net and its variants have been used in a large number of DL applications in geosciences (Sun, 2018;Arge et al, 2019;Karimpouli and Tahmasebi, 2019;Mo et al, 2019;Zhong et al, 2019;Zhu et al, 2019).…”

Section: Attention-based Deep Convolutional Neural Netmentioning

confidence: 99%

Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets

Sun

Tang

2020

Front. Water

View full text Add to dashboard Cite

High-quality and high-resolution precipitation products are critically important to many hydrological applications. Advances in satellite remote sensing instruments and data retrieval algorithms continue to improve the quality of the operational precipitation products. However, most satellite products existing today are still too coarse to be ingested for local water management and planning purposes. Recent advances in deep learning algorithms enable the fusion of multi-source, high-dimensional data for statistical learning. In this study, we investigated the efficacy of an attention-based, deep convolutional neural network (AU-Net) for learning spatial and temporal mappings from coarse-resolution to fine-resolution precipitation products. The skills of AU-Net models, developed using combinations of static and dynamic predictors, were evaluated over a 3 × 3° study area in Central Texas, U.S., a region known for its complex precipitation patterns and low predictability. Three coarse-resolution satellite/reanalysis precipitation products, ERA5-Land (0.1°), TRMM (0.25°), and IMERG (0.1°), are used as part of the inputs, while the predictand is the 1-km PRISM data. Auxiliary predictors include elevation, vegetation index, and air temperature. The study period includes 18 years of data (2001–2018) at the monthly scale for training, validation, and testing. Results show that the trained AU-Net models achieve different degrees of success in downscaling the baseline coarse-resolution products, depending on the total precipitation, the accuracy of large-scale patterns captured by the baseline products, and the amount of information transferable from predictors. Higher precipitation rate tends to affect AU-Net model performance negatively. Use of the attention mechanism in the AU-Net models allows for infilling of multiscale features and generation of sharper images. Correction using gauge data, if there is any, can further improve the results significantly.

show abstract

Section: Attention-based Deep Convolutional Neural Netmentioning

confidence: 99%

Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets

Sun

Tang

2020

Front. Water

View full text Add to dashboard Cite

show abstract

“…Further details are given in Section 4. To be able to handle arbitrarily sized and shaped regions with the U-Net model, we follow the construction from [1] that handles this exact problem. In short, we cover the given input region with fixed size overlapping rectangles, called tiles, matching the expected input size for the U-Net, and use the U-Net model to compute the probability of fortification for each cell in each tile.…”

Section: Applying U-net and Handling Arbitrarily Sized Regionsmentioning

confidence: 99%

“…For this computation the weights depend on the position in the covering tile: The closer to the center of the tile the cell is (more context) the higher the weight and the closer to the boundary the less weight. For a full description of this algorithm we refer to [1]. Figure 5 shows an example where this algorithm combined with our U-Net has been applied to a large area.…”

Section: Applying U-net and Handling Arbitrarily Sized Regionsmentioning

confidence: 99%

Learning to Detect Fortified Areas

Grønlund,

Tranberg

2021

Preprint

Self Cite

View full text Add to dashboard Cite

High resolution data models like grid terrain models made from LiDAR data are a prerequisite for modern day Geographic Information Systems applications. Besides providing the foundation for the very accurate digital terrain models, LiDAR data is also extensively used to classify which parts of the considered surface comprise relevant elements like water, buildings and vegetation. In this paper we consider the problem of classifying which areas of a given surface are fortified by for instance, roads, sidewalks, parking spaces, paved driveways and terraces. We consider using LiDAR data and orthophotos, combined and alone, to show how well the modern machine learning algorithms Gradient Boosted Trees and Convolutional Neural Networks are able to detect fortified areas on large real world data. The LiDAR data features, in particular the intensity feature that measures the signal strength of the return, that we consider in this project are heavily dependent on the actual LiDAR sensor that made the measurement. This is highly problematic, in particular for the generalisation capability of pattern matching algorithms, as this means that data features for test data may be very different from the data the model is trained on. We propose an algorithmic solution to this problem by designing a neural net embedding architecture that transforms data from all the different sensor systems into a new common representation that works as well as if the training data and test data originated from the same sensor. The final algorithm result has an accuracy above 96 percent, and an AUC score above 0.99.

show abstract

Learning to Find Hydrological Corrections

Arge

Grønlund

Svendsen

et al. 2019

Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

High resolution Digital Elevation models, such as the (Big) grid terrain model of Denmark with more than 200 billion measurements, is a basic requirement for water flow modelling and flood risk analysis. However, a large number of modifications often need to be made to even very accurate terrain models, such as the Danish model, before they can be used in realistic flow modeling. These modifications include removal of bridges, which otherwise will act as dams in flow modeling, and inclusion of culverts that transport water underneath roads. In fact, the danish model is accompanied by a detailed set of hydrological corrections for the digital elevation model. However, producing these hydrological corrections is a very slow an expensive process, since it is to a large extent done manually and often with local input. This also means that corrections can be of varying quality. In this paper we propose a new algorithmic apporach based on machine learning and convolutional neural networks for automatically detecting hydrological corrections for such large terrain data. Our model is able to detect most hydrological corrections known for the danish model and quite a few more that should have been included in the original list.

show abstract

Learning to Find Hydrological Corrections

Cited by 3 publications

References 12 publications

Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets

Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets

Learning to Detect Fortified Areas

Learning to Find Hydrological Corrections

Contact Info

Product

Resources

About