scholarly journals Estimating snow depth on Arctic sea ice using satellite microwave radiometry and a neural network

2019 ◽  
Vol 13 (9) ◽  
pp. 2421-2438 ◽  
Author(s):  
Anne Braakmann-Folgmann ◽  
Craig Donlon
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Sea Ice ◽  
Snow Depth ◽  
Microwave Radiometer ◽  
Microwave Radiometry ◽  
The Arctic ◽  
Network Approach ◽  
Neural Network Approach ◽  
Satellite Microwave

Abstract. Snow lying on top of sea ice plays an important role in the radiation budget because of its high albedo and the Arctic freshwater budget, and it influences the Arctic climate: it is a fundamental climate variable. Importantly, accurate snow depth products are required to convert satellite altimeter measurements of ice freeboard to sea ice thickness (SIT). Due to the harsh environment and challenging accessibility, in situ measurements of snow depth are sparse. The quasi-synoptic frequent repeat coverage provided by satellite measurements offers the best approach to regularly monitor snow depth on sea ice. A number of algorithms are based on satellite microwave radiometry measurements and simple empirical relationships. Reducing their uncertainty remains a major challenge. A High Priority Candidate Mission called the Copernicus Imaging Microwave Radiometer (CIMR) is now being studied at the European Space Agency. CIMR proposes a conically scanning radiometer having a swath >1900 km and including channels at 1.4, 6.9, 10.65, 18.7 and 36.5 GHz on the same platform. It will fly in a high-inclination dawn–dusk orbit coordinated with the MetOp-SG(B). As part of the preparation for the CIMR mission, we explore a new approach to retrieve snow depth on sea ice from multi-frequency satellite microwave radiometer measurements using a neural network approach. Neural networks have proven to reach high accuracies in other domains and excel in handling complex, non-linear relationships. We propose one neural network that only relies on AMSR2 channel brightness temperature data input and another one using both AMSR2 and SMOS data as input. We evaluate our results from the neural network approach using airborne snow depth measurements from Operation IceBridge (OIB) campaigns and compare them to products from three other established snow depth algorithms. We show that both our neural networks outperform the other algorithms in terms of accuracy, when compared to the OIB data and we demonstrate that plausible results are obtained even outside the algorithm training period and area. We then convert CryoSat freeboard measurements to SIT using different snow products including the snow depth from our networks. We confirm that a more accurate snow depth product derived using our neural networks leads to more accurate estimates of SIT, when compared to the SIT measured by a laser altimeter at the OIB campaign. Our network with additional SMOS input yields even higher accuracies, but has the disadvantage of a larger “hole at the pole”. Our neural network approaches are applicable over the whole Arctic, capturing first-year ice and multi-year ice conditions throughout winter. Once the networks are designed and trained, they are fast and easy to use. The combined AMSR2 + SMOS neural network is particularly important as a precursor demonstration for the Copernicus CIMR candidate mission highlighting the benefit of CIMR.

scholarly journals Estimating Snow Depth on Arctic Sea Ice using Satellite Microwave Radiometry and a Neural Network

2019 ◽  
Author(s):  
Anne Braakmann-Folgmann ◽  
Craig Donlon
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Sea Ice ◽  
Snow Depth ◽  
Microwave Radiometer ◽  
Microwave Radiometry ◽  
The Arctic ◽  
Network Approach ◽  
Neural Network Approach ◽  
Satellite Microwave

Abstract. Snow lying on top of sea ice plays an important role in the radiation budget because of its high albedo, the Arctic freshwater budget, and influences the Arctic climate: it is fundamental climate variable. Importantly, accurate snow depth products are required to convert satellite altimeter measurements of ice freeboard to sea ice thickness (SIT). Due to the harsh environment and challenging accessibility, in situ measurements of snow depth are sparse. The quasi-synoptic frequent repeat coverage provided by satellite measurements offers the best approach to regularly monitor snow depth on sea ice. A number of algorithms are based on satellite microwave radiometry measurements and simple empirical relationships. Reducing their uncertainty remains a major challenge. A High Priority Candidate Mission called the Copernicus Imaging Microwave Radiometer (CIMR) is now being studied at the European Space Agency. CIMR proposes a conically scanning radiometer having a swath > 1900 km and including channels at 1.4, 6.9, 10.65, 18.7 and 36.5 GHz on the same platform. It will fly in a high inclination dawn-dusk orbit coordinated with the MetOp-SG(B). As part of the preparation for the CIMR mission, we explore a new approach to retrieve snow depth on sea ice from multi-frequency satellite microwave radiometer measurements using a neural network approach. Neural networks have proven to reach high accuracies in other domains and excel in handling complex, non-linear relationships. We propose one neural network that only relies on AMSR2 channel brightness temperature data input and another one using both AMSR2 and SMOS data as input. We evaluate our results from the neural network approach using airborne snow depth measurements from Operation IceBridge (OIB) campaigns and compare them to products from three other established snow depth algorithms. We show that both our neural networks outperform the other algorithms in terms of accuracy, when compared to the OIB data and we demonstrate that plausible results are obtained even outside the algorithm training period and area. We then convert CryoSat freeboard measurements to SIT using different snow products including the snow depth from our networks. We confirm that a more accurate snow depth product derived using our neural networks leads to more accurate estimates of SIT, when compared to the SIT measured by a laser altimeter at the OIB campaign. Our network with additional SMOS input yields even higher accuracies, but has the disadvantage of a larger “hole at the pole”. Our neural network approaches are applicable over the whole Arctic, capturing first-year ice and multi-year ice conditions throughout winter. Once the networks are designed and trained, they are fast and easy to use. The combined AMSR2 + SMOS neural network is particularly important as a pre-cursor demonstration for the Copernicus CIMR candidate mission highlighting the benefit of CIMR.

scholarly journals Retrieval of Snow Depth over Arctic Sea Ice Using a Deep Neural Network

2019 ◽  
Vol 11 (23) ◽  
pp. 2864 ◽  
Author(s):  
Jiping Liu ◽  
Yuanyuan Zhang ◽  
Xiao Cheng ◽  
Yongyun Hu
Keyword(s):  
Neural Network ◽  
Sea Ice ◽  
Snow Depth ◽  
Deep Neural Network ◽  
Arctic Basin ◽  
Temporal Variations ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Ice Thickness ◽  
Arctic Sea

The accurate knowledge of spatial and temporal variations of snow depth over sea ice in the Arctic basin is important for understanding the Arctic energy budget and retrieving sea ice thickness from satellite altimetry. In this study, we develop and validate a new method for retrieving snow depth over Arctic sea ice from brightness temperatures at different frequencies measured by passive microwave radiometers. We construct an ensemble-based deep neural network and use snow depth measured by sea ice mass balance buoys to train the network. First, the accuracy of the retrieved snow depth is validated with observations. The results show the derived snow depth is in good agreement with the observations, in terms of correlation, bias, root mean square error, and probability distribution. Our ensemble-based deep neural network can be used to extend the snow depth retrieval from first-year sea ice (FYI) to multi-year sea ice (MYI), as well as during the melting period. Second, the consistency and discrepancy of snow depth in the Arctic basin between our retrieval using the ensemble-based deep neural network and two other available retrievals using the empirical regression are examined. The results suggest that our snow depth retrieval outperforms these data sets.

scholarly journals Sea Ice Concentration and Sea Ice Extent Mapping with L-Band Microwave Radiometry and GNSS-R Data from the FFSCat Mission Using Neural Networks

2021 ◽  
Vol 13 (6) ◽  
pp. 1139
Author(s):  
David Llaveria ◽  
Juan Francesc Munoz-Martin ◽  
Christoph Herbert ◽  
Miriam Pablos ◽  
Hyuk Park ◽  
...  
Keyword(s):  
Sea Ice ◽  
Microwave Radiometer ◽  
Cost Effective ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
Sea Ice Extent ◽  
Neural Network Approach ◽  
Ice Concentration ◽  
L Band ◽  
Moderate Cost

CubeSat-based Earth Observation missions have emerged in recent times, achieving scientifically valuable data at a moderate cost. FSSCat is a two 6U CubeSats mission, winner of the ESA S3 challenge and overall winner of the 2017 Copernicus Masters Competition, that was launched in September 2020. The first satellite, 3Cat-5/A, carries the FMPL-2 instrument, an L-band microwave radiometer and a GNSS-Reflectometer. This work presents a neural network approach for retrieving sea ice concentration and sea ice extent maps on the Arctic and the Antarctic oceans using FMPL-2 data. The results from the first months of operations are presented and analyzed, and the quality of the retrieved maps is assessed by comparing them with other existing sea ice concentration maps. As compared to OSI SAF products, the overall accuracy for the sea ice extent maps is greater than 97% using MWR data, and up to 99% when using combined GNSS-R and MWR data. In the case of Sea ice concentration, the absolute errors are lower than 5%, with MWR and lower than 3% combining it with the GNSS-R. The total extent area computed using this methodology is close, with 2.5% difference, to those computed by other well consolidated algorithms, such as OSI SAF or NSIDC. The approach presented for estimating sea ice extent and concentration maps is a cost-effective alternative, and using a constellation of CubeSats, it can be further improved.

Estimation of Annual Average Daily Traffic on Low-Volume Roads: Factor Approach Versus Neural Networks

2000 ◽  
Vol 1719 (1) ◽  
pp. 103-111 ◽  
Author(s):  
Satish C. Sharma ◽  
Pawan Lingras ◽  
Guo X. Liu ◽  
Fei Xu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Traffic Monitoring ◽  
Network Approach ◽  
Annual Average ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Low Volume Roads ◽  
Annual Average Daily Traffic ◽  
Low Volume

Estimation of the annual average daily traffic (AADT) for low-volume roads is investigated. Artificial neural networks are compared with the traditional factor approach for estimating AADT from short-period traffic counts. Fifty-five automatic traffic recorder (ATR) sites located on low-volume rural roads in Alberta, Canada, are used as study samples. The results of this study indicate that, when a single 48-h count is used for AADT estimation, the factor approach can yield better results than the neural networks if the ATR sites are grouped appropriately and the sample sites are correctly assigned to various ATR groups. Unfortunately, the current recommended practice offers little guidance on how to achieve the assignment accuracy that may be necessary to obtain reliable AADT estimates from a single 48-h count. The neural network approach can be particularly suitable for estimating AADT from two 48-h counts taken at different times during the counting season. In fact, the 95th percentile error values of about 25 percent as obtained in this study for the neural network models compare favorably with the values reported in the literature for low-volume roads using the traditional factor approach. The advantage of the neural network approach is that classification of ATR sites and sample site assignments to ATR groups are not required. The analysis of various groups of low-volume roads presented also leads to a conclusion that, when defining low-volume roads from a traffic monitoring point of view, it is not likely to matter much whether the AADT on the facility is less than 500 vehicles, less than 750 vehicles, or less than 1,000 vehicles.

Individualizing Displays through the Use of Neural Networks

1997 ◽  
Vol 41 (1) ◽  
pp. 269-273
Author(s):  
Kai-Chun Cheng ◽  
Ray E. Eberts
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Intelligent Vehicle ◽  
Network Approach ◽  
Neural Network Approach ◽  
Traveler Information ◽  
Gas Stations ◽  
The Neural Network ◽  
Advanced Traveler Information System ◽  
Near Future

An Advanced Traveler Information System (ATIS), a key component of Intelligent Vehicle highway Systems (IVHS) in the near future, will help travelers find locations of restaurants, lodging, gas stations, and rest stops. On typical ATIS displays, which are now being incorporated in some advanced vehicles, the choices for these traveler services are presented to the vehicle occupants alphabetically. An experiment was conducted to determine whether individualizing the display through the use of neural networks enhanced performance when choosing restaurants. The neural network ATIS was compared to an ATIS that displayed the most frequently chosen restaurants at the top, one that alphabetized the list of restaurants, and one that randomly displayed the restaurant choices. The time to choose a restaurant was significantly faster for the individualized displays (neural network and frequency) when compared to the nonindividualized displays (alphabetical and random). When the two individualized displays were compared, choice time was significantly faster for the neural network approach.

scholarly journals A Comparison Study of Constitutive Equation, Neural Networks, and Support Vector Regression for Modeling Hot Deformation of 316L Stainless Steel

Materials ◽  
2020 ◽  
Vol 13 (17) ◽  
pp. 3766 ◽  
Author(s):  
Shin-Hyung Song
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stainless Steel ◽  
Flow Stress ◽  
Support Vector Regression ◽  
Hot Deformation ◽  
316L Stainless Steel ◽  
Support Vector ◽  
Network Approach ◽  
Neural Network Approach

In this research, hot deformation experiments of 316L stainless steel were carried out at a temperature range of 800–1000 °C and strain rate of 2 × 10−3–2 × 10−1. The flow stress behavior of 316L stainless steel was found to be highly dependent on the strain rate and temperature. After the experimental study, the flow stress was modeled using the Arrhenius-type constitutive equation, a neural network approach, and the support vector regression algorithm. The present research mainly focused on a comparative study of three algorithms for modeling the characteristics of hot deformation. The results indicated that the neural network approach and the support vector regression algorithm could be used to model the flow stress better than the approach of the Arrhenius-type equation. The modeling efficiency of the support vector regression algorithm was also found to be more efficient than the algorithm for neural networks.

Prediction of dissolved oxygen in the Mediterranean Sea along Gaza, Palestine – an artificial neural network approach

2009 ◽  
Vol 60 (12) ◽  
pp. 3051-3059 ◽  
Author(s):  
Hossam Adel Zaqoot ◽  
Abdul Khalique Ansari ◽  
Mukhtiar Ali Unar ◽  
Shaukat Hyat Khan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Dissolved Oxygen ◽  
Radial Basis Function ◽  
Mediterranean Sea ◽  
Basis Function ◽  
Data Sets ◽  
Network Approach ◽  
Neural Network Approach ◽  
The Mediterranean

Artificial Neural Networks (ANNs) are flexible tools which are being used increasingly to predict and forecast water resources variables. The human activities in areas surrounding enclosed and semi-enclosed seas such as the Mediterranean Sea always produce in the long term a strong environmental impact in the form of coastal and marine degradation. The presence of dissolved oxygen is essential for the survival of most organisms in the water bodies. This paper is concerned with the use of ANNs — Multilayer Perceptron (MLP) and Radial Basis Function neural networks for predicting the next fortnight’s dissolved oxygen concentrations in the Mediterranean Sea water along Gaza. MLP and Radial Basis Function (RBF) neural networks are trained and developed with reference to five important oceanographic variables including water temperature, wind velocity, turbidity, pH and conductivity. These variables are considered as inputs of the network. The data sets used in this study consist of four years and collected from nine locations along Gaza coast. The network performance has been tested with different data sets and the results show satisfactory performance. Prediction results prove that neural network approach has good adaptability and extensive applicability for modelling the dissolved oxygen in the Mediterranean Sea along Gaza. We hope that the established model will help in assisting the local authorities in developing plans and policies to reduce the pollution along Gaza coastal waters to acceptable levels.

scholarly journals ESTIMATION OF THE LYAPUNOV SPECTRUM FROM ONE-DIMENSIONAL OBSERVATIONS USING NEURAL NETWORKS

2014 ◽  
pp. 30-34
Author(s):  
Vladimir Golovko
Keyword(s):  
Neural Network ◽  
Dynamical System ◽  
Neural Networks ◽  
Time Series ◽  
Lyapunov Spectrum ◽  
Network Approach ◽  
Neural Network Approach ◽  
One Dimensional ◽  
The Neural Network ◽  
Attractor Dynamics

This paper discusses the neural network approach for computing of Lyapunov spectrum using one dimensional time series from unknown dynamical system. Such an approach is based on the reconstruction of attractor dynamics and applying of multilayer perceptron (MLP) for forecasting the next state of dynamical system from the previous one. It allows for evaluating the Lyapunov spectrum of unknown dynamical system accurately and efficiently only by using one observation. The results of experiments are discussed.

Back Propagation Method of Artificial Neural Networks for Finding the Position Control of Stanford Manipulator and Direct Kinematic Analysis of Elbow Manipulator

2018 ◽  
Vol 7 (1) ◽  
pp. 46 ◽  
Author(s):  
M. Sailaja ◽  
R. D. V. Prasad
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Inverse Kinematics ◽  
Back Propagation ◽  
Network Approach ◽  
Neural Network Approach ◽  
Artificial Neural ◽  
Direct Kinematics

Nowadays the robot technology is advancing rapidly and the use of robots in industries has been increasing. In designing a robot manipulator, kinematicsplays a vital role. The kinematic problem of manipulator control is divided into two types, direct kinematics and inverse kinematics. Robot inverse kinematics, which is important in robot path planning, is a fundamental problem in robotic control. Past solutions for this problem have been through the use of various algebraic or algorithmic procedures, which may be less accurate and time consuming. Artificial neural networks have the ability to approximate highly non-linear functions applied in robot control. The neural network approach deserves examination because of the fundamental properties of computation speed, and they can generalize untrained solutions. In the present work an attempt has been made to evaluate the problemof robot inverse kinematics of Stanford manipulator using artificial neural network approach. Finally two programs are written using C language to solve inverse kinematic problem of Stanford manipulator using Back propagation method of artificial neural network. In this network, the input layer has six nodes, the hidden layer has three nodes, and the output layer has two nodes. And also Elbow manipulator was modelled and its direct kinematics was analysed.

Sign in / Sign up

Export Citation Format

Share Document