scholarly journals APPLICABILITY OF VARIOUS INTERPOLATION APPROACHES FOR HIGH RESOLUTION SPATIAL MAPPING OF CLIMATE DATA IN KOREA

2018 ◽  
Vol XLII-3 ◽  
pp. 703-710 ◽  
Author(s):  
A. Jo ◽  
J. Ryu ◽  
H. Chung ◽  
Y. Choi ◽  
S. Jeon
Keyword(s):  
Interpolation Method ◽  
Training Data ◽  
Spatial Mapping ◽  
Observation Data ◽  
Climate Data ◽  
Weather System ◽  
Validation Data ◽  
Instantaneous Temperature ◽  
Elevation Model ◽  
Total Point

The purpose of this study is to create a new dataset of spatially interpolated monthly climate data for South Korea at high spatial resolution (approximately 30m) by performing various spatio-statistical interpolation and comparing with forecast LDAPS gridded climate data provided from Korea Meterological Administration (KMA). Automatic Weather System (AWS) and Automated Synoptic Observing System (ASOS) data in 2017 obtained from KMA were included for the spatial mapping of temperature and rainfall; instantaneous temperature and 1-hour accumulated precipitation at 09:00 am on 31th March, 21th June, 23th September, and 24th December. Among observation data, 80 percent of the total point (478) and remaining 120 points were used for interpolations and for quantification, respectively. With the training data and digital elevation model (DEM) with 30 m resolution, inverse distance weighting (IDW), co-kriging, and kriging were performed by using ArcGIS10.3.1 software and Python 3.6.4. Bias and root mean square were computed to compare prediction performance quantitatively. When statistical analysis was performed for each cluster using 20 % validation data, co kriging was more suitable for spatialization of instantaneous temperature than other interpolation method. On the other hand, IDW technique was appropriate for spatialization of precipitation.

scholarly journals Applicability of the Deep Learning Flood Forecast Model Against the Inexperienced Magnitude of Flood

10.29007/fdp5 ◽  
2018 ◽  
Author(s):  
Masayuki Hitokoto ◽  
Masaaki Sakuraba
Keyword(s):  
Deep Learning ◽  
First Grade ◽  
Training Data ◽  
Observation Data ◽  
Validation Data ◽  
River Catchment ◽  
River Stage ◽  
Hourly Rainfall ◽  
Feed Forward Network ◽  
Ann Models

Although artificial neural networks (ANN) is widely used for real-time flood prediction model, it is pointed out that the weak point of the model is poor applicability for the inexperienced magnitude of flood. In this study, the ANN models were applied to first-grade rivers in Japan, Tokoro River catchment and Abashiri River catchment. The training data of the ANN models were all the rainfall-runoff event which exceeded the Flood Watch Water Level during the period of 1998-2015. Types of observation data were river-stage and rainfall at 1-hour pitch. The validation data was the largest flood since the river-stage observation had started. The main component of the model was the four-layer feed-forward network. As a network training method, the deep learning based on the denoising autoencoder was applied. The output of the neural network was change in river-stage in T hours at the prediction point. The input data was the upstream river-stage, hourly change in river-stage and hourly rainfall. The river- stage prediction up to 6 hours showed very good accuracy, and It was proved that it can be nicely predicted even for the past largest flood.

New methodical approaches to mapping of geosystems (by the example of Baikalian Siberia’s geosystems)

2018 ◽  
Vol 937 (7) ◽  
pp. 23-34 ◽  
Author(s):  
I.N. Vladimirov
Keyword(s):  
Global Climate ◽  
Remote Sensing Data ◽  
Field Research ◽  
Scientific Basis ◽  
Nature Management ◽  
Climate Data ◽  
Structural Dynamic ◽  
Digital Elevation ◽  
North Asia ◽  
Elevation Model

The article considers a new approach to landscape mapping based on the synthesis of remote sensing data of high and medium spatial resolution, a digital elevation model, maps of various thematic contents, a set of global climate data, and materials of field research. The map of the Baikalian’s Siberia geosystems is based on the principles of the multistage regional-typological and structural-dynamic classification of geosystems proposed by Academician V.B. Sochava. The structure of the geosystems of the Baikalian Siberia is characterized by great complexity, both in the set of natural complexes and in the degree of their contrast. The regional classification range covers the geosystems inherent in different subcontinents of Asia and reflects their interpenetration, being a unique landscape-situational example of Siberian nature within North Asia. The map of the geosystems of the Baikalian Siberia reflects the main structural and dynamic diversity of geosystems in the region in the systems of their geographic and genetic spatial structures. These landscape cartographic studies fit into a single system of geographic forecasting and create a new fundamental scientific basis for developing recommendations for optimizing nature management in the Baikal region within the framework of implementing state environmental policy.

Fully automated contrast and non-contrast cardiac view detection in echocardiography a multi-centre, multi-vendor study

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Gao ◽  
D Stojanovski ◽  
A Parker ◽  
P Marques ◽  
S Heitner ◽  
...  
Keyword(s):  
Neural Network ◽  
Training Data ◽  
Classification Model ◽  
Validation Dataset ◽  
Funding Source ◽  
Private Company ◽  
Validation Data ◽  
Independent Test ◽  
Model Training ◽  
Confusion Matrices

Abstract Background Correctly identifying views acquired in a 2D echocardiographic examination is paramount to post-processing and quantification steps often performed as part of most clinical workflows. In many exams, particularly in stress echocardiography, microbubble contrast is used which greatly affects the appearance of the cardiac views. Here we present a bespoke, fully automated convolutional neural network (CNN) which identifies apical 2, 3, and 4 chamber, and short axis (SAX) views acquired with and without contrast. The CNN was tested in a completely independent, external dataset with the data acquired in a different country than that used to train the neural network. Methods Training data comprised of 2D echocardiograms was taken from 1014 subjects from a prospective multisite, multi-vendor, UK trial with the number of frames in each view greater than 17,500. Prior to view classification model training, images were processed using standard techniques to ensure homogenous and normalised image inputs to the training pipeline. A bespoke CNN was built using the minimum number of convolutional layers required with batch normalisation, and including dropout for reducing overfitting. Before processing, the data was split into 90% for model training (211,958 frames), and 10% used as a validation dataset (23,946 frames). Image frames from different subjects were separated out entirely amongst the training and validation datasets. Further, a separate trial dataset of 240 studies acquired in the USA was used as an independent test dataset (39,401 frames). Results Figure 1 shows the confusion matrices for both validation data (left) and independent test data (right), with an overall accuracy of 96% and 95% for the validation and test datasets respectively. The accuracy for the non-contrast cardiac views of >99% exceeds that seen in other works. The combined datasets included images acquired across ultrasound manufacturers and models from 12 clinical sites. Conclusion We have developed a CNN capable of automatically accurately identifying all relevant cardiac views used in “real world” echo exams, including views acquired with contrast. Use of the CNN in a routine clinical workflow could improve efficiency of quantification steps performed after image acquisition. This was tested on an independent dataset acquired in a different country to that used to train the model and was found to perform similarly thus indicating the generalisability of the model. Figure 1. Confusion matrices Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Ultromics Ltd.

scholarly journals A novel ferroptosis related gene signature is associated with prognosis in patients with ovarian serous cystadenocarcinoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zhixiang Yu ◽  
Haiyan He ◽  
Yanan Chen ◽  
Qiuhe Ji ◽  
Min Sun
Keyword(s):  
Cox Regression ◽  
Expression Profiles ◽  
Critical Role ◽  
Gene Signature ◽  
Cancer Genome ◽  
Training Data ◽  
Hub Genes ◽  
Validation Data ◽  
Data Set ◽  
Cox Regression Analysis

AbstractOvarian cancer (OV) is a common type of carcinoma in females. Many studies have reported that ferroptosis is associated with the prognosis of OV patients. However, the mechanism by which this occurs is not well understood. We utilized Genotype-Tissue Expression (GTEx) and The Cancer Genome Atlas (TCGA) to identify ferroptosis-related genes in OV. In the present study, we applied Cox regression analysis to select hub genes and used the least absolute shrinkage and selection operator to construct a prognosis prediction model with mRNA expression profiles and clinical data from TCGA. A series of analyses for this signature was performed in TCGA. We then verified the identified signature using International Cancer Genome Consortium (ICGC) data. After a series of analyses, we identified six hub genes (DNAJB6, RB1, VIMP/ SELENOS, STEAP3, BACH1, and ALOX12) that were then used to construct a model using a training data set. The model was then tested using a validation data set and was found to have high sensitivity and specificity. The identified ferroptosis-related hub genes might play a critical role in the mechanism of OV development. The gene signature we identified may be useful for future clinical applications.

scholarly journals The Open Global Glacier Model (OGGM) v1.0

2018 ◽  
Author(s):  
Fabien Maussion ◽  
Anton Butenko ◽  
Julia Eis ◽  
Kévin Fourteau ◽  
Alexander H. Jarosch ◽  
...  
Keyword(s):  
Mass Balance ◽  
Open Source ◽  
Sea Level ◽  
Computational Cost ◽  
Balance Model ◽  
Climate Data ◽  
Estimation Model ◽  
Model Framework ◽  
Validation Data ◽  
Wide Range

Abstract. Despite of their importance for sea-level rise, seasonal water availability, and as source of geohazards, mountain glaciers are one of the few remaining sub-systems of the global climate system for which no globally applicable, open source, community-driven model exists. Here we present the Open Global Glacier Model (OGGM, http://www.oggm.org), developed to provide a modular and open source numerical model framework for simulating past and future change of any glacier in the world. The modelling chain comprises data downloading tools (glacier outlines, topography, climate, validation data), a preprocessing module, a mass-balance model, a distributed ice thickness estimation model, and an ice flow model. The monthly mass-balance is obtained from gridded climate data and a temperature index melt model. To our knowledge, OGGM is the first global model explicitly simulating glacier dynamics: the model relies on the shallow ice approximation to compute the depth-integrated flux of ice along multiple connected flowlines. In this paper, we describe and illustrate each processing step by applying the model to a selection of glaciers before running global simulations under idealized climate forcings. Even without an in-depth calibration, the model shows a very realistic behaviour. We are able to reproduce earlier estimates of global glacier volume by varying the ice dynamical parameters within a range of plausible values. At the same time, the increased complexity of OGGM compared to other prevalent global glacier models comes at a reasonable computational cost: several dozens of glaciers can be simulated on a personal computer, while global simulations realized in a supercomputing environment take up to a few hours per century. Thanks to the modular framework, modules of various complexity can be added to the codebase, allowing to run new kinds of model intercomparisons in a controlled environment. Future developments will add new physical processes to the model as well as tools to calibrate the model in a more comprehensive way. OGGM spans a wide range of applications, from ice-climate interaction studies at millenial time scales to estimates of the contribution of glaciers to past and future sea-level change. It has the potential to become a self-sustained, community driven model for global and regional glacier evolution.

scholarly journals Deteksi Gulma Berdasarkan Warna HSV dan Fitur Bentuk Menggunakan Jaringan Syaraf Tiruan

2021 ◽  
Vol 8 (5) ◽  
pp. 929
Author(s):  
Hurriyatul Fitriyah ◽  
Rizal Maulana
Keyword(s):  
Learning Algorithm ◽  
Color Space ◽  
Outdoor Environment ◽  
Training Data ◽  
Distance Transform ◽  
Validation Data ◽  
Hsv Color Space ◽  
Testing Data ◽  
Artificial Neural Network Ann ◽  
Center Distance

<p class="Abstrak">Gulma merupakan tanaman pengganggu dalam lahan pertanian. Herbisida merupakan obat yang efektif membunuh gulma tersebut. Penyemprotan herbisida harus tepat sasaran kepada gulma saja dan tidak mengenai tanaman. Penelitian ini membuat sistem yang dapat mendeteksi gulma secara otomatis di antara tanaman pada lahan pertanian riil. Sistem ini menggunakan gambar lahan pertanian riil dimana tanaman tampak utuh (daun dapat lebih dari satu) yang diambil menggunakan kamera dengan posisi vertikal menghadap ke bawah. Algoritma yang dibuat menggunakan segmentasi berdasarkan warna hijau dalam ruang warna HSV untuk mendeteksi daun, baik gulma maupun tanaman pada beragam pencahayaan. Sebanyak tiga fitur bentuk domain spasial digunakan untuk membedakan gulma dengan tanaman yang memiliki karakteristik bentuk daun yang berbeda. Fitur bentuk yang digunakan adalah <em>Rectangularity, Edge-to-Center distances function</em>, dan <em>Distance Transform function</em>. Klasifikasi gulma dan tanaman menggunakan metode Jaringan syaraf tiruan (JST) yang dapat dilatih secara <em>offline. </em>Dari 149 tanaman yang terdeteksi dimana 70% sebagai data training, 15% data validasi dan 15% data uji, didapati akurasi pengujian sebesar 95.46%.</p><p class="Abstrak"><em><strong><br /></strong></em></p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>Weed is a major challenge in a crop plantation. A herbicide is the most effective substance to kill this unwanted vegetation. Spraying the herbicide must be done carefully to target the weeds only. Here in this research, we develop an algorithm that detects weeds among the plants based on the shape of their leaves. The detection is based on images that were acquired using a camera. The leaves of weeds and plants were detected based on their green color using segmentation in HSV color-space as it is more effective to detect objects in various illumination. Three shape features were extracted, which are Rectangularity that is based on Rectangularity, Edge-to-Center distance function, and Distance Transform function. Those features were fed into a learning algorithm, Artificial Neural Network (ANN), to classify whether it is the plant or the weed. The testing on the weed classification in a real outdoor environment showed 95.46% accuracy using a total of 149 detected plants (70% as training data, 15%  as validation data, and 15% as testing data).<strong></strong></em></p><p class="Abstrak"><em><strong><br /></strong></em></p>

scholarly journals Inclusive Design of Earth Observation Decision Support Systems for Environmental Governance: A Case Study of Lake Nokoué

2021 ◽  
Vol 3 ◽  
Author(s):  
Ufuoma Ovienmhada ◽  
Fohla Mouftaou ◽  
Danielle Wood
Keyword(s):  
Decision Support ◽  
Decision Support Systems ◽  
Support Systems ◽  
Earth Observation ◽  
Inclusive Design ◽  
Observation Data ◽  
Climate Data ◽  
Technology Design ◽  
Data Services

Earth Observation (EO) data can enhance understanding of human-environmental systems for the creation of climate data services, or Decision Support Systems (DSS), to improve monitoring, prediction and mitigation of climate harm. However, EO data is not always incorporated into the workflow for decision-makers for a multitude of reasons including awareness, accessibility and collaboration models. The purpose of this study is to demonstrate a collaborative model that addresses historical power imbalances between communities. This paper highlights a case study of a climate harm mitigation DSS collaboration between the Space Enabled Research Group at the MIT Media Lab and Green Keeper Africa (GKA), an enterprise located in Benin. GKA addresses the management of an invasive plant species that threatens ecosystem health and economic activities on Lake Nokoué. They do this through a social entrepreneurship business model that aims to advance both economic empowerment and environmental health. In demonstrating a Space Enabled-GKA collaboration model that advances GKA's business aims, this study first considers several popular service and technology design methods and offer critiques of each method in terms of their ability to address inclusivity in complex systems. These critiques lead to the selection of the Systems Architecture Framework (SAF) as the technology design method for the case study. In the remainder of the paper, the SAF is applied to the case study to demonstrate how the framework coproduces knowledge that would inform a DSS with Earth Observation data. The paper offers several practical considerations and values related to epistemology, data collection, prioritization and methodology for performing inclusive design of climate data services.

scholarly journals Status of Major Glaciers of Hunza River Basin, Under Changing Climatic Conditions of Pakistan Over the Period of (1990-2018)

2021 ◽  
Author(s):  
Sajid Ali ◽  
Garee Khan ◽  
Wajid Hassan ◽  
Javed Akhter Qureshi ◽  
Iram Bano
Keyword(s):  
River Basin ◽  
Primary Source ◽  
Climatic Conditions ◽  
Climate Data ◽  
Outburst Floods ◽  
Glacial Lake Outburst Floods ◽  
Digital Elevation ◽  
Remote Sensing Techniques ◽  
Elevation Model ◽  
Hunza River

Abstract Ice masses and snow of Hunza River Basin (HRB) are an important primary source of fresh water and lifeline for downstream inhabitants. Changing climatic conditions seriously put an impact on these available ice and snow masses. These glaciers may affect downstream population by glacial lake outburst floods (GLOF) and surge events due to climatic variation. So, monitoring of these glaciers and available ice masses are important. This research delivers an approach for selected glaciers of the Hunza river basin. An attempt is made in this study using Landsat (OLI, ETM, ETM+, TM), digital elevation model (DEM), Geographic Information System and Remote Sensing techniques (RS&GIS) techniques. We delineated 27 glaciers within HRB from the period of 1990-2018. These glaciers' total area is about 2589.75 ±86km 2 in 1990 and about 2565.12 ±68km 2 in 2018. Our results revealed that from 2009 to 2015, glacier coverage of HRB advanced with a mean annual advance rate of 2.22±0.1 km 2 a -1 . Conversely, from 1994 to 1999, the strongest reduction in glacier area with a mean rate of - 3.126±0.3km 2 a -1 is recorded. The glaciers of HRB are relatively stable compared to Hindukush, Himalayan and Tibetan Plateau (TP) region of the world. The steep slope glacier's retreat rate is more than that of gentle slope glaciers, and the glaciers below elevation of 5000 m above sea level change significantly. Based on climate data from 1995-2018, HRB shows a decreasing trend in temperature and increasing precipitation. The glacier area's overall retreat is due to an increase in summer temperature while the glacier advancement is induced possibly by winter and autumn precipitation.

scholarly journals A Novel Convolutional Neural Network for Classifying Indian Coins by Denomination

2021 ◽  
Author(s):  
Yash Chauhan ◽  
Prateek Singh
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Academic Research ◽  
High Volume ◽  
Classification Problem ◽  
General Purpose ◽  
Training Data ◽  
Slot Machines ◽  
Validation Data ◽  
Starting Point

Coins recognition systems have humungous applications from vending and slot machines to banking and management firms which directly translate to a high volume of research regarding the development of methods for such classification. In recent years, academic research has shifted towards a computer vision approach for sorting coins due to the advancement in the field of deep learning. However, most of the documented work utilizes what is known as ‘Transfer Learning’ in which we reuse a pre-trained model of a fixed architecture as a starting point for our training. While such an approach saves us a lot of time and effort, the generic nature of the pre-trained model can often become a bottleneck for performance on a specialized problem such as coin classification. This study develops a convolutional neural network (CNN) model from scratch and tests it against a widely-used general-purpose architecture known as Googlenet. We have shown in this study by comparing the performance of our model with that of Googlenet (documented in various previous studies) that a more straightforward and specialized architecture is more optimal than a more complex general architecture for the coin classification problem. The model developed in this study is trained and tested on 720 and 180 images of Indian coins of different denominations, respectively. The final accuracy gained by the model is 91.62% on the training data, while the accuracy is 90.55% on the validation data.

scholarly journals Facial Expression Recognition using Residual Convnet with Image Augmentations

2021 ◽  
Vol 14 (2) ◽  
pp. 127-135
Author(s):  
Fadhil Yusuf Rahadika ◽  
Novanto Yudistira ◽  
Yuita Arum Sari
Keyword(s):  
Neural Networks ◽  
Facial Expression ◽  
Test Data ◽  
Facial Expression Recognition ◽  
Optimization Method ◽  
Training Data ◽  
Batch Size ◽  
Online Video ◽  
Expression Recognition ◽  
Validation Data

During the COVID-19 pandemic, many offline activities are turned into online activities via video meetings to prevent the spread of the COVID 19 virus. In the online video meeting, some micro-interactions are missing when compared to direct social interactions. The use of machines to assist facial expression recognition in online video meetings is expected to increase understanding of the interactions among users. Many studies have shown that CNN-based neural networks are quite effective and accurate in image classification. In this study, some open facial expression datasets were used to train CNN-based neural networks with a total number of training data of 342,497 images. This study gets the best results using ResNet-50 architecture with Mish activation function and Accuracy Booster Plus block. This architecture is trained using the Ranger and Gradient Centralization optimization method for 60000 steps with a batch size of 256. The best results from the training result in accuracy of AffectNet validation data of 0.5972, FERPlus validation data of 0.8636, FERPlus test data of 0.8488, and RAF-DB test data of 0.8879. From this study, the proposed method outperformed plain ResNet in all test scenarios without transfer learning, and there is a potential for better performance with the pre-training model. The code is available at https://github.com/yusufrahadika-facial-expressions-essay.

Sign in / Sign up

Export Citation Format

Share Document