Language: English ❌
You searched for subject:(Nowcasting Meteorology ).
Showing records 1 – 4 of
4 total matches.
No search limiters apply to these results.
Hong Kong University of Science and Technology
1.
Shi, Xingjian CSE.
Exploring deep learning architectures for spatiotemporal sequence forecasting.
Degree: 2018, Hong Kong University of Science and Technology
URL: http://repository.ust.hk/ir/Record/1783.1-97739 
;
https://doi.org/10.14711/thesis-991012671057603412
;
http://repository.ust.hk/ir/bitstream/1783.1-97739/1/th_redirect.html
► Spatiotemporal systems are common in the real world. Forecasting the multi-step future of these spatiotemporal systems based on past observations, or, Spatiotemporal Sequence Forecasting (STSF),…
(more)
▼ Spatiotemporal systems are common in the real world. Forecasting the multi-step future of these spatiotemporal systems based on past observations, or, Spatiotemporal Sequence Forecasting (STSF), is a significant and challenging problem. Due to the complex spatial and temporal relationships within the data and the potential long forecast horizon, it is challenging to design appropriate Deep Learning (DL) architectures for STSF. In this thesis, we explore DL architectures for STSF. We first define the STSF problem and classify it into three subcategories: Trajectory Forecasting of Moving Point Cloud (TF-MPC), STSF on Regular Grid (STSF-RG), and STSF on Irregular Grid (STSF-IG). We then propose architectures for STSF-RG and STSF-IG problems. For the STSF-RG problems, we proposed the Convolutional Long-Short Term Memory (ConvLSTM) and the Trajectory Gated Recurrent Unit (TrajGRU). ConvLSTM uses convolution in both the input-state and state-state transitions of LSTM and is better at capturing the spatiotemporal correlations than the Fully-connected LSTM (FC-LSTM). TrajGRU improves upon ConvLSTM by actively learning the recurrent connection structure, which achieves better prediction performance with less parameters. To better investigate the effectiveness of our proposed architectures and other DL models for STSF-RG, we chose to tackle the precipitation nowcasting problem, which is a representative STSF-RG problem with a huge real-world impact. By incorporating ConvLSTM into an Encoder-Forecaster (EF) structure, we proposed the first machine learning based solution for precipitation nowcasting that outperforms the operational algorithm. To facilitate future studies for this problem and gauge the state-of the-art methods, we proposed the first large-scale benchmark for precipitation nowcasting: HKO-7. HKO-7 has new evaluation metrics and has both the offline setting and the online settings in the evaluation protocol. We evaluated seven models in the offline and online settings. Experiment results show that 1) all deep learning models outperform the optical flow based models, 2) TrajGRU attains the best overall performance among deep learning models, and 3) models consistently perform better in the online setting. For the STSF-IG problems, we converted the sparsely distributed observations into data on a spatiotemporal graph and utilized graph convolution operators, or graph aggregators, to build the model. We proposed a new graph aggregator called Gated Attention Network (GaAN). GaAN not only uses multiple attention heads to aggregate information from the neighborhoods but also uses another set of gates to control each attention head's importance. With experiments on two large-scale inductive node classification datasets, we showed that GaAN outperforms the baseline graph aggregators. Also, we proposed a unified framework called Graph GRU (GGRU), which transforms any valid graph aggregators to RNNs that are designed for STSF-IG. We compared GGRU with other state-of-the-art methods in traffic speed forecasting and…
Subjects/Keywords: Machine learning
; Nowcasting (Meteorology)
; Data processing
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Shi, X. C. (2018). Exploring deep learning architectures for spatiotemporal sequence forecasting. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-97739 ; https://doi.org/10.14711/thesis-991012671057603412 ; http://repository.ust.hk/ir/bitstream/1783.1-97739/1/th_redirect.html
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Shi, Xingjian CSE. “Exploring deep learning architectures for spatiotemporal sequence forecasting.” 2018. Thesis, Hong Kong University of Science and Technology. Accessed April 22, 2021.
http://repository.ust.hk/ir/Record/1783.1-97739 ; https://doi.org/10.14711/thesis-991012671057603412 ; http://repository.ust.hk/ir/bitstream/1783.1-97739/1/th_redirect.html.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Shi, Xingjian CSE. “Exploring deep learning architectures for spatiotemporal sequence forecasting.” 2018. Web. 22 Apr 2021.
Vancouver:
Shi XC. Exploring deep learning architectures for spatiotemporal sequence forecasting. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2018. [cited 2021 Apr 22].
Available from: http://repository.ust.hk/ir/Record/1783.1-97739 ; https://doi.org/10.14711/thesis-991012671057603412 ; http://repository.ust.hk/ir/bitstream/1783.1-97739/1/th_redirect.html.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Shi XC. Exploring deep learning architectures for spatiotemporal sequence forecasting. [Thesis]. Hong Kong University of Science and Technology; 2018. Available from: http://repository.ust.hk/ir/Record/1783.1-97739 ; https://doi.org/10.14711/thesis-991012671057603412 ; http://repository.ust.hk/ir/bitstream/1783.1-97739/1/th_redirect.html
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of KwaZulu-Natal
2.
Sinclair, Scott.
Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting.
Degree: PhD, Civil engineering, 2007, University of KwaZulu-Natal
URL: http://hdl.handle.net/10413/2247
► Floods cannot be prevented, but their devastating effects can be minimized if advance warning of the event is available. The South African Disaster Management Act…
(more)
▼ Floods cannot be prevented, but their devastating effects can be minimized if advance warning of the event is available. The South African Disaster Management Act (Act 57 of 2002) advocates a paradigm shift from the current "bucket and blanket brigade" response-based mind set to one where disaster prevention or mitigation are the preferred options. It is in the context of mitigating the effects of floods that the development and implementation of a reliable flood forecasting system has major significance. In the case of flash floods, a few hours lead time can afford disaster managers the opportunity to take steps which may significantly reduce loss of life and damage to property. The engineering challenges in developing and implementing such a system are numerous. In this thesis, the design and implement at ion of a flash flood forecasting system in South Africa is critically examined. The technical aspect s relating to spatio-temporal rainfall estimation and now casting are a key area in which new contributions are made. In particular, field and optical flow advection algorithms are adapted and refined to help predict future path s of storms; fast and pragmatic algorithms for combining rain gauge and remote sensing (rada r and satellite) estimates are re fined and validated; a two-dimensional adaptation of Empirical Mode Decomposition is devised to extract the temporally persistent structure embedded in rainfall fields. A second area of significant contribution relates to real-time fore cast updates, made in response to the most recent observed information. A number of techniques embedded in the rich Kalm an and adaptive filtering literature are adopted for this purpose. The work captures the current "state of play" in the South African context and hopes to provide a blueprint for future development of an essential tool for disaster management. There are a number of natural spin-offs from this work for related field s in water resources management.
Advisors/Committee Members: Pegram, Geoffrey Guy Sinclair. (advisor).
Subjects/Keywords: Civil engineering.; Nowcasting (Meteorology); Precipitation forecasting.; Flood forecasting.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Sinclair, S. (2007). Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting. (Doctoral Dissertation). University of KwaZulu-Natal. Retrieved from http://hdl.handle.net/10413/2247
Chicago Manual of Style (16th Edition):
Sinclair, Scott. “Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting.” 2007. Doctoral Dissertation, University of KwaZulu-Natal. Accessed April 22, 2021.
http://hdl.handle.net/10413/2247.
MLA Handbook (7th Edition):
Sinclair, Scott. “Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting.” 2007. Web. 22 Apr 2021.
Vancouver:
Sinclair S. Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting. [Internet] [Doctoral dissertation]. University of KwaZulu-Natal; 2007. [cited 2021 Apr 22].
Available from: http://hdl.handle.net/10413/2247.
Council of Science Editors:
Sinclair S. Spatio-temporal rainfall estimation and nowcasting for flash flood forecasting. [Doctoral Dissertation]. University of KwaZulu-Natal; 2007. Available from: http://hdl.handle.net/10413/2247
University of Missouri – Columbia
3.
DeWees, Todd A., 1979-.
A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting.
Degree: 2009, University of Missouri – Columbia
URL: https://doi.org/10.32469/10355/9888
► [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] We study a hierarchical Bayesian framework for finite mixtures of distributions. We first consider…
(more)
▼ [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] We study a hierarchical Bayesian framework for finite mixtures of distributions. We first consider a Dirichlet mixture of normal components and utilize it to model spatial fields that arise as pixelated images of intensities. We demonstrate our models using results from simulated data as well as using "real-world" weather radar reflectivity fields. We propose model adequacy and verification tests to further illustrate the effectiveness of the model. We then consider and define spatio-temporal processes using a hierarchical Bayesian mixture model to help us predict the evolution of these processes based on several radar reflectivity fields observed over a short-term time period. We illustrate the methodology with simulated data and apply verification methods to demonstrate the ability of the methods to model such data. We implement these models in
nowcasting the evolution of storm systems observed around the area of Kansas City, Missouri, on June 7, 2007.
Advisors/Committee Members: Micheas, Athanasios Christos (advisor).
Subjects/Keywords: Bayesian statistical decision theory; Dirichlet principle; Radar meteorology; Reflectance; Nowcasting (Meteorology)
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
DeWees, Todd A., 1. (2009). A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting. (Thesis). University of Missouri – Columbia. Retrieved from https://doi.org/10.32469/10355/9888
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
DeWees, Todd A., 1979-. “A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting.” 2009. Thesis, University of Missouri – Columbia. Accessed April 22, 2021.
https://doi.org/10.32469/10355/9888.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
DeWees, Todd A., 1979-. “A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting.” 2009. Web. 22 Apr 2021.
Vancouver:
DeWees, Todd A. 1. A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting. [Internet] [Thesis]. University of Missouri – Columbia; 2009. [cited 2021 Apr 22].
Available from: https://doi.org/10.32469/10355/9888.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
DeWees, Todd A. 1. A hierarchical Bayesian mixture approach for modeling reflectivity fields with application to Nowcasting. [Thesis]. University of Missouri – Columbia; 2009. Available from: https://doi.org/10.32469/10355/9888
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Colorado State University
4.
Ruzanski, Evan.
Nowcasting for a high-resolution weather radar network.
Degree: PhD, Electrical and Computer Engineering, 2010, Colorado State University
URL: http://hdl.handle.net/10217/45965
► Short-term prediction (nowcasting) of high-impact weather events can lead to significant improvement in warnings and advisories and is of great practical importance. Nowcasting using weather…
(more)
▼ Short-term prediction (
nowcasting) of high-impact weather events can lead to significant improvement in warnings and advisories and is of great practical importance.
Nowcasting using weather radar reflectivity data has been shown to be particularly useful. The Collaborative Adaptive Sensing of the Atmosphere (CASA) radar network provides high-resolution reflectivity data amenable to producing valuable nowcasts. The high-resolution nature of CASA data requires the use of an efficient
nowcasting approach, which necessitated the development of the Dynamic Adaptive Radar Tracking of Storms (DARTS) and sinc kernel-based advection
nowcasting methodology. This methodology was implemented operationally in the CASA Distributed Collaborative Adaptive Sensing (DCAS) system in a robust and efficient manner necessitated by the high-resolution nature of CASA data and distributed nature of the environment in which the
nowcasting system operates. Nowcasts up to 10 min to support emergency manager decision-making and 1-5 min to steer the CASA radar nodes to better observe the advecting storm patterns for forecasters and researchers are currently provided by this system. Results of
nowcasting performance during the 2009 CASA IP experiment are presented. Additionally, currently state-of-the-art scale-based filtering methods were adapted and evaluated for use in the CASA DCAS to provide a scale-based analysis of
nowcasting. DARTS was also incorporated in the Weather Support to Deicing Decision Making system to provide more accurate and efficient snow water equivalent nowcasts for aircraft deicing decision support relative to the radar-based
nowcasting method currently used in the operational system. Results of an evaluation using data collected from 2007-2008 by the Weather Service Radar-1988 Doppler (WSR-88D) located near Denver, Colorado, and the National Center for Atmospheric Research Marshall Test Site near Boulder, Colorado, are presented. DARTS was also used to study the short-term predictability of precipitation patterns depicted by high-resolution reflectivity data observed at microalpha (0.2-2 km) to mesobeta (20-200 km) scales by the CASA radar network. Additionally, DARTS was used to investigate the performance of
nowcasting rainfall fields derived from specific differential phase estimates, which have been shown to provide more accurate and robust rainfall estimates compared to those made from radar reflectivity data.
Advisors/Committee Members: Chandrasekar, V. (advisor), Jayasumana, Anura P. (committee member), Mielke, Paul W. (committee member), Notaros, Branislav M. (committee member).
Subjects/Keywords: weather radar; weather forecasting; nowcasting; specific differential phase; prediction; Nowcasting (Meteorology); Meteorological satellites; Weather forecasting; Weather radar networks
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ruzanski, E. (2010). Nowcasting for a high-resolution weather radar network. (Doctoral Dissertation). Colorado State University. Retrieved from http://hdl.handle.net/10217/45965
Chicago Manual of Style (16th Edition):
Ruzanski, Evan. “Nowcasting for a high-resolution weather radar network.” 2010. Doctoral Dissertation, Colorado State University. Accessed April 22, 2021.
http://hdl.handle.net/10217/45965.
MLA Handbook (7th Edition):
Ruzanski, Evan. “Nowcasting for a high-resolution weather radar network.” 2010. Web. 22 Apr 2021.
Vancouver:
Ruzanski E. Nowcasting for a high-resolution weather radar network. [Internet] [Doctoral dissertation]. Colorado State University; 2010. [cited 2021 Apr 22].
Available from: http://hdl.handle.net/10217/45965.
Council of Science Editors:
Ruzanski E. Nowcasting for a high-resolution weather radar network. [Doctoral Dissertation]. Colorado State University; 2010. Available from: http://hdl.handle.net/10217/45965
. 
Open Access Theses and Dissertations