Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323046212> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4323046212 abstract "<p>Optical flow based nowcasting is a powerful technique to compute forecasts for small lead times up to a couple of hours. Forecasts of radar data are very useful as standalone products and serve as input data for multiple operational products, e.g., for the seamless combination of radar and NWP data and for cell-based analysis and prediction products. However, the optical flow technique has several drawbacks. It assumes stationarity in both the data values as well as the advection information. Further, it is a deterministic technique and the nowcasts have no dynamic properties. Recently, machine learning techniques have shown promising results for producing nowcasts with dynamic properties. However, for radar reflectivity and precipitation data, the predictions often lack high-intensity values and tend to become blurry for larger lead times.</p> <p>In the current work we explore the potential of deterministic convolutional neural networks (CNN) to improve the operational optical flow nowcasting at DWD. A two-year dataset consisting of radar, NWP and orography data is used for training modified UNet based neural networks. Each network predicts radar reflectivity composites for a specific lead time, in 5-minute steps. Several optimization techniques are combined, both for the input data and the network architecture. The input data contains optical flow based nowcasts of previous radar timesteps that are mapped to the target lead time. The NWP input parameters are chosen for their known importance in convective processes. To understand their impact in this application, an ablation study is performed. The network architecture is optimized. The classic UNet architecture is augmented with additional horizontal computation blocks. This adds more nonlinearity to the finer scales of the network and reduces the validation error. Individual encoders are used for the radar and NWP data and combined with affine linear transformations. Experiments with classical pointwise loss functions as well as losses with spatial context (e.g., FSS) are conducted. The new forecasts are compared with the operational nowcasting at DWD as well as a closed-loop NN approach (RainNet).</p>" @default.
- W4323046212 created "2023-03-04" @default.
- W4323046212 creator A5000948594 @default.
- W4323046212 date "2023-03-03" @default.
- W4323046212 modified "2023-10-17" @default.
- W4323046212 title "Analysis and application of CNN to improve deterministic optical flow nowcasting at DWD" @default.
- W4323046212 doi "https://doi.org/10.5194/ecss2023-166" @default.
- W4323046212 hasPublicationYear "2023" @default.
- W4323046212 type Work @default.
- W4323046212 citedByCount "0" @default.
- W4323046212 crossrefType "posted-content" @default.
- W4323046212 hasAuthorship W4323046212A5000948594 @default.
- W4323046212 hasConcept C11413529 @default.
- W4323046212 hasConcept C115961682 @default.
- W4323046212 hasConcept C121332964 @default.
- W4323046212 hasConcept C124101348 @default.
- W4323046212 hasConcept C153294291 @default.
- W4323046212 hasConcept C154945302 @default.
- W4323046212 hasConcept C155542232 @default.
- W4323046212 hasConcept C205649164 @default.
- W4323046212 hasConcept C2781013037 @default.
- W4323046212 hasConcept C41008148 @default.
- W4323046212 hasConcept C50644808 @default.
- W4323046212 hasConcept C5072599 @default.
- W4323046212 hasConcept C554190296 @default.
- W4323046212 hasConcept C62649853 @default.
- W4323046212 hasConcept C76155785 @default.
- W4323046212 hasConcept C81363708 @default.
- W4323046212 hasConcept C97355855 @default.
- W4323046212 hasConceptScore W4323046212C11413529 @default.
- W4323046212 hasConceptScore W4323046212C115961682 @default.
- W4323046212 hasConceptScore W4323046212C121332964 @default.
- W4323046212 hasConceptScore W4323046212C124101348 @default.
- W4323046212 hasConceptScore W4323046212C153294291 @default.
- W4323046212 hasConceptScore W4323046212C154945302 @default.
- W4323046212 hasConceptScore W4323046212C155542232 @default.
- W4323046212 hasConceptScore W4323046212C205649164 @default.
- W4323046212 hasConceptScore W4323046212C2781013037 @default.
- W4323046212 hasConceptScore W4323046212C41008148 @default.
- W4323046212 hasConceptScore W4323046212C50644808 @default.
- W4323046212 hasConceptScore W4323046212C5072599 @default.
- W4323046212 hasConceptScore W4323046212C554190296 @default.
- W4323046212 hasConceptScore W4323046212C62649853 @default.
- W4323046212 hasConceptScore W4323046212C76155785 @default.
- W4323046212 hasConceptScore W4323046212C81363708 @default.
- W4323046212 hasConceptScore W4323046212C97355855 @default.
- W4323046212 hasLocation W43230462121 @default.
- W4323046212 hasOpenAccess W4323046212 @default.
- W4323046212 hasPrimaryLocation W43230462121 @default.
- W4323046212 hasRelatedWork W2003507436 @default.
- W4323046212 hasRelatedWork W2011796543 @default.
- W4323046212 hasRelatedWork W2043951554 @default.
- W4323046212 hasRelatedWork W2067036725 @default.
- W4323046212 hasRelatedWork W2096519104 @default.
- W4323046212 hasRelatedWork W2159691874 @default.
- W4323046212 hasRelatedWork W2164297952 @default.
- W4323046212 hasRelatedWork W2359096974 @default.
- W4323046212 hasRelatedWork W2766051620 @default.
- W4323046212 hasRelatedWork W2187296962 @default.
- W4323046212 isParatext "false" @default.
- W4323046212 isRetracted "false" @default.
- W4323046212 workType "article" @default.