scholarly journals Improved cloud detection for the Aura Microwave Limb Sounder (MLS): training an artificial neural network on colocated MLS and Aqua MODIS data

2021 ◽  
Vol 14 (12) ◽  
pp. 7749-7773
Author(s):  
Frank Werner ◽  
Nathaniel J. Livesey ◽  
Michael J. Schwartz ◽  
William G. Read ◽  
Michelle L. Santee ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Cloud Cover ◽  
Classification Performance ◽  
Classification Model ◽  
Cloud Detection ◽  
Modis Data ◽  
Artificial Neural ◽  
Cloud Top Pressure ◽  
Level 2

Abstract. An improved cloud detection algorithm for the Aura Microwave Limb Sounder (MLS) is presented. This new algorithm is based on a feedforward artificial neural network and uses as input, for each MLS limb scan, a vector consisting of 1710 brightness temperatures provided by MLS observations from 15 different tangent altitudes and up to 13 spectral channels in each of 10 different MLS bands. The model has been trained on global cloud properties reported by Aqua's Moderate Resolution Imaging Spectroradiometer (MODIS). In total, the colocated MLS–MODIS data set consists of 162 117 combined scenes sampled on 208 d over 2005–2020. A comparison to the current MLS cloudiness flag used in “Level 2” processing reveals a huge improvement in classification performance. For previously unseen data, the algorithm successfully detects > 93 % of profiles affected by clouds, up from ∼ 16 % for the Level 2 flagging. At the same time, false positives reported for actually clear profiles are comparable to the Level 2 results. The classification performance is not dependent on geolocation but slightly decreases over low-cloud-cover regions. The new cloudiness flag is applied to determine average global cloud cover maps over 2015–2019, successfully reproducing the spatial patterns of mid-level to high clouds seen in MODIS data. It is also applied to four example cloud fields to illustrate its reliable performance for different cloud structures with varying degrees of complexity. Training a similar model on MODIS-retrieved cloud top pressure (pCT) yields reliable predictions with correlation coefficients > 0.82. It is shown that the model can correctly identify > 85 % of profiles with pCT < 400 hPa. Similar to the cloud classification model, global maps and example cloud fields are provided, which reveal good agreement with MODIS results. The combination of the cloudiness flag and predicted cloud top pressure provides the means to identify MLS profiles in the presence of high-reaching convection.

scholarly journals Improved cloud detection for the Aura Microwave Limb Sounder: Training an artificial neural network on colocated MLS and Aqua-MODIS data

2021 ◽  
Author(s):  
Frank Werner ◽  
Nathaniel Livesey ◽  
Michael Schwartz ◽  
William Read ◽  
Michelle Santee ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Detection Algorithm ◽  
Classification Performance ◽  
Cloud Detection ◽  
Data Set ◽  
Modis Data ◽  
Artificial Neural ◽  
Cloud Top Pressure ◽  
Level 2

Abstract. An improved cloud detection algorithm for the Aura Microwave Limb Sounder (MLS) is presented. This new algorithm is based on a feedforward artificial neural network and uses as input, for each MLS limb scan, a vector consisting of 1,710 brightness temperatures provided by MLS observations from 15 different tangent altitudes and up to 13 spectral channels in each of 10 different MLS bands. The model has been trained on global cloud properties reported by Aqua’s Moderate Resolution Imaging Spectroradiometer (MODIS). In total, the colocated MLS-MODIS data set consists of 162,117 combined scenes sampled on 208 days over 2005–2020. We show that the algorithm can correctly classify > 96 % of cloudy and clear instances for previously unseen MLS scans. A comparison to the current MLS cloudiness flag used in “Level 2” processing reveals a huge improvement in classification performance. For all profiles in the colocated MLS-MODIS data set, the algorithm successfully detects 97.8 % of profiles affected by clouds, up from 15.8 % for the Level 2 flagging. Meanwhile, false positives reported for actually clear profiles are reduced to 1.7 %, down from 6.2 % in Level 2. The classification performance is not dependent on geolocation. The new cloudiness flag is applied to determine average global cloud cover between 2015 and 2019, successfully reproducing the spatial patterns of mid-level to high clouds reported in previous studies. It is also applied to four example cloud fields to illustrate the reliable performance for different cloud structures with varying degrees of complexity. Training a similar model on MODIS-retrieved cloud top pressure yields reliable predictions with correlation coefficients greater than 0.99. The combination of cloudiness flag and predicted cloud top pressure provides the means to identify MLS profiles in the presence of high-reaching convection.

Artificial neural network ensemble-based land-cover classifiers using MODIS data

2009 ◽  
Vol 13 (2) ◽  
pp. 570-574 ◽  
Author(s):  
Takashi Yamaguchi ◽  
Kenneth J. Mackin ◽  
Eiji Nunohiro ◽  
Jong Geol Park ◽  
Keitaro Hara ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Land Cover ◽  
Neural Network Ensemble ◽  
Modis Data ◽  
Artificial Neural ◽  
Artificial Neural Network Ensemble

scholarly journals A Randomized Bag-of-Birds Approach to Study Robustness of Automated Audio Based Bird Species Classification

2021 ◽  
Vol 11 (19) ◽  
pp. 9226
Author(s):  
Burooj Ghani ◽  
Sarah Hallerberg
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Bird Species ◽  
Classification Performance ◽  
Species Classification ◽  
Ongoing Research ◽  
Number Of Species ◽  
Artificial Neural ◽  
Sound Features

The automatic classification of bird sounds is an ongoing research topic, and several results have been reported for the classification of selected bird species. In this contribution, we use an artificial neural network fed with pre-computed sound features to study the robustness of bird sound classification. We investigate, in detail, if and how the classification results are dependent on the number of species and the selection of species in the subsets presented to the classifier. In more detail, a bag-of-birds approach is employed to randomly create balanced subsets of sounds from different species for repeated classification runs. The number of species present in each subset is varied between 10 and 300 by randomly drawing sounds of species from a dataset of 659 bird species taken from the Xeno-Canto database. We observed that the shallow artificial neural network trained on pre-computed sound features was able to classify the bird sounds. The quality of classifications were at least comparable to some previously reported results when the number of species allowed for a direct comparison. The classification performance is evaluated using several common measures, such as the precision, recall, accuracy, mean average precision, and area under the receiver operator characteristics curve. All of these measures indicate a decrease in classification success as the number of species present in the subsets is increased. We analyze this dependence in detail and compare the computed results to an analytic explanation assuming dependencies for an idealized perfect classifier. Moreover, we observe that the classification performance depended on the individual composition of the subset and varied across 20 randomly drawn subsets.

scholarly journals Predicting Vodka Adulteration: A Combination of Electronic Tongue and Artificial Neural Networks

2021 ◽  
Author(s):  
Leonardo Fabio León Marenco ◽  
Luiza Pereira Oliveira ◽  
Daniella Lopez Vale ◽  
Maiara Oliveira Salles
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Mean Squared Error ◽  
Tap Water ◽  
Electronic Tongue ◽  
Classification Model ◽  
Squared Error ◽  
Artificial Neural ◽  
Voltammetric Electronic Tongue

Abstract An artificial neural network was used to build models caple of predicting and quantifying vodka adulteration with methanol and/or tap water. A voltammetric electronic tongue based on gold and copper microelectrodes was used, and 310 analyses were performed. Vodkas were adulterated with tap water (5 to 50% (v/v)), methanol (1 to 13% (v/v)), and with a fixed addition of 5% methanol and tap water varying from 5 to 50% (v/v). The classification model showed 99.5% precision, and it correctly predicted the type of adulterant in all samples. Regarding the regression model, the root mean squared error was 3.464% and 0.535% for the water and methanol addition, respectively, and the prediction of the adulterant content presented an R2 0.9511 for methanol and 0.9831 for water adulteration.

Diagnosis of Brain Tumor Using Artificial Neural Network

2021 ◽  
Vol 8 (1) ◽  
pp. 06-10
Author(s):  
R. Ganesh ◽  
Dr.R. Sivakumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Brain Tumor ◽  
Medical Image Analysis ◽  
Region Of Interest ◽  
Classification Performance ◽  
Feed Forward Neural Network ◽  
Classification Rate ◽  
Artificial Neural ◽  
The Brain

Accurate detection and diagnosis of brain tumor is one the crucial task of medical image analysis. Brain tumor classification system aids the physician to make accurate diagnosis and to provide effective treatment. Magnetic Resonance Imaging (MRI) is the gold standard imaging technique for brain tumor diagnosis. This paper proposes a method for brain tumor detection and classification using artificial neural network. The proposed method consists of four major processes such as preprocessing, region of interest segmentation, feature extraction and classification. Feed forward neural network is employed to classify the brain tumors. Classification performance of the proposed method is evaluated using 10-cross fold validation and compared with the previous methods. Empirical findings proved that the proposed method can efficiently classify the brain tumor with higher classification rate.

scholarly journals Fault Diagnosis for UAV Blades Using Artificial Neural Network

Robotics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 59 ◽  
Author(s):  
Gino Iannace ◽  
Giuseppe Ciaburro ◽  
Amelia Trematerra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Paper Tape ◽  
Operating Conditions ◽  
Classification Model ◽  
Network Algorithms ◽  
Substantial Modification ◽  
Cargo Transport ◽  
Artificial Neural ◽  
Recreational Use

In recent years, unmanned aerial vehicles (UAVs) have been used in several fields including, for example, archaeology, cargo transport, conservation, healthcare, filmmaking, hobbies and recreational use. UAVs are aircraft characterized by the absence of a human pilot on board. The extensive use of these devices has highlighted maintenance problems with regard to the propellers, which represent the source of propulsion of the aircraft. A defect in the propellers of a drone can cause the aircraft to fall to the ground and its consequent destruction, and it also constitutes a safety problem for objects and people that are in the range of action of the aircraft. In this study, the measurements of the noise emitted by a UAV were used to build a classification model to detect unbalanced blades in a UAV propeller. To simulate the fault condition, two strips of paper tape were applied to the upper surface of a blade. The paper tape created a substantial modification of the aerodynamics of the blade, and this modification characterized the noise produced by the blade in its rotation. Then, a model based on artificial neural network algorithms was built to detect unbalanced blades in a UAV propeller. This model showed high accuracy (0.9763), indicating a high number of correct detections and suggests the adoption of this tool to verify the operating conditions of a UAV. The test must be performed indoors; from the measurements of the noise produced by the UAV it is possible to identify an imbalance in the propeller blade.

scholarly journals Transformer Winding Condition Assessment Using Feedforward Artificial Neural Network and Frequency Response Measurements

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3227
Author(s):  
Mehran Tahir ◽  
Stefan Tenbohlen
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Frequency Response ◽  
Power Transformer ◽  
Classification Model ◽  
Response Analysis ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Electrical Faults ◽  
Artificial Neural Network Ann

Frequency response analysis (FRA) is a well-known method to assess the mechanical integrity of the active parts of the power transformer. The measurement procedures of FRA are standardized as described in the IEEE and IEC standards. However, the interpretation of FRA results is far from reaching an accepted and definitive methodology as there is no reliable code available in the standard. As a contribution to this necessity, this paper presents an intelligent fault detection and classification algorithm using FRA results. The algorithm is based on a multilayer, feedforward, backpropagation artificial neural network (ANN). First, the adaptive frequency division algorithm is developed and various numerical indicators are used to quantify the differences between FRA traces and obtain feature sets for ANN. Finally, the classification model of ANN is developed to detect and classify different transformer conditions, i.e., healthy windings, healthy windings with saturated core, mechanical deformations, electrical faults, and reproducibility issues due to different test conditions. The database used in this study consists of FRA measurements from 80 power transformers of different designs, ratings, and different manufacturers. The results obtained give evidence of the effectiveness of the proposed classification model for power transformer fault diagnosis using FRA.

Sign in / Sign up

Export Citation Format

Share Document