Neural network retrieval of wind velocity profiles from satellite data

The collection and management of vast quantities of meteorological data, including satellite-based as well as ground-based measurements, is presenting great challenges in the optimal usage of this information. To address these issues, the Army Research Laboratory has developed neural networks for combining multisensor meteorological data for Army battlefield weather forecasting models. As a demonstration of this data fusion methodology, multi-sensor data was taken from the Meteorological Measurement Set Profiler (MMSP-POC) system and from satellites with orbits coinciding with the geographical locations of interest. The MMS Profiler-POC comprises a suite of remote sensing instrumentation and surface measuring devices. Neural network techniques were used to retrieve temperature and wind information from a combination of polar orbiter and/or geostationary satellite observations and ground-based measurements. Back-propagation neural networks were constructed which used satellite radiances, simulated microwave radiometer measurements, and other ground-based measurements as inputs and produced temperature and wind profiles as outputs. The network was trained with rawinsonde measurements used as truth-values. The final outcome will be an integrated, merged temperature/wind profile from the surface up to the upper troposphere.

show abstract

“…Figure 5. Vertical profile of RMSE for the initial wind velocity neural network using GOES radiances (Cogan, et al, 2000).…”

Section: A Typical Neural Network Design For Data Fusion Of Meteorolomentioning

confidence: 99%

“…To remedy these limitations, neural network techniques have been developed for wind profile retrievals from satellite sounder radiance measurements. (Cogan, et al, 2000).…”

Section: Introductionmentioning

confidence: 99%

<title>Neural networks for sensor fusion of meteorological measurements</title>

et al. 2001

View full text Add to dashboard Cite

show abstract

“…In the literature, numerous applications of ANNs can be found for estimating the missing climatic data or ET. Cogan et al (2000), Trajkovic et al (2003), Tapiador et al (2004), Capacci and Conway (2005), Ustaoglu et al (2008), Dahamsheh and Aksoy (2009) and Voyant et al (2014) used ANN techniques for modelling climatic data such as air temperature, wind velocity, global radiation and precipitation. Rezaeian-Zadeh et al (2012).…”

Section: Introductionmentioning

confidence: 99%

Estimating missing hourly climatic data using artificial neural network for energy balance based ET mapping applications

Köksal

Cemek

Çetin

et al. 2017

Meteorological Applications

View full text Add to dashboard Cite

Remote sensing based evapotranspiration (ET) mapping has become an important tool for water resources management at a regional scale. Accurate hourly climatic data and alfalfa‐reference ET (ETr) are crucial inputs for successfully implementing remote sensing based ET models such as Mapping Evapotranspiration at High Resolution with Internalized Calibration (METRIC) and Surface Energy Balance Algorithm for Land (SEBAL). In Turkey, hourly climatic data may not be available at all locations, either due to cost constraints or due to equipment malfunctioning. In this study, the artificial neural network (ANN) technique was used to estimate missing and unmeasured hourly climatic data and ETr for the agriculturally important semi‐humid Bafra plains located in northern Turkey. Modelled and actual climatic data were used to derive ET maps from two Landsat 5 Thematic Mapper images acquired on 2 September 2009 and 4 August 2010. The METRIC algorithm was used to generate ET maps. Accuracy assessment of the METRIC‐derived ET maps indicated that climatic data and ETr estimated through ANN could be used for accurately mapping ET, where hourly climatic data are missing or not measured.

show abstract