scholarly journals Estimation of Hourly Rainfall during Typhoons Using Radar Mosaic-Based Convolutional Neural Networks

2020 ◽  
Vol 12 (5) ◽  
pp. 896 ◽  
Author(s):  
Chih-Chiang Wei ◽  
Po-Yu Hsieh
Keyword(s):  
Neural Network ◽  
Relative Error ◽  
Mean Squared Error ◽  
Subtropical Climate ◽  
Arrival Times ◽  
Radar Images ◽  
Hourly Rainfall ◽  
Typhoon Rainfall ◽  
Central Weather Bureau ◽  
Moon Lake

Taiwan is located at the junction of the tropical and subtropical climate zones adjacent to the Eurasian continent and Pacific Ocean. The island frequently experiences typhoons that engender severe natural disasters and damage. Therefore, efficiently estimating typhoon rainfall in Taiwan is essential. This study examined the efficacy of typhoon rainfall estimation. Radar images released by the Central Weather Bureau were used to estimate instantaneous rainfall. Additionally, two proposed neural network-based architectures, namely a radar mosaic-based convolutional neural network (RMCNN) and a radar mosaic-based multilayer perceptron (RMMLP), were used to estimate typhoon rainfall, and the commonly applied Marshall–Palmer Z-R relationship (Z-R_MP) and a reformulated Z-R relationship at each site (Z-R_station) were adopted to construct benchmark models. Monitoring stations in Hualien, Sun Moon Lake, and Taichung were selected as the experimental stations in Eastern, Central, and Western Taiwan, respectively. This study compared the performance of the models in predicting rainfall at the three stations, and the results are outlined as follows: at the Hualien station, the estimations of the RMCNN, RMMLP, Z-R_MP, and Z-R_station models were mostly identical to the observed rainfall, and all models estimated an increase during peak rainfall on the hyetographs, but the peak values were underestimated. At the Sun Moon Lake and Taichung stations, however, the estimations of the four models were considerably inconsistent in terms of overall rainfall rates, peak rainfall, and peak rainfall arrival times on the hyetographs. The relative root mean squared error for overall rainfall rates of all stations was smallest when computed using RMCNN (0.713), followed by those computed using RMMLP (0.848), Z-R_MP (1.030), and Z-R_station (1.392). Moreover, RMCNN yielded the smallest relative error for peak rainfall (0.316), followed by RMMLP (0.379), Z-R_MP (0.402), and Z-R_station (0.688). RMCNN computed the smallest relative error for the peak rainfall arrival time (1.507 h), followed by RMMLP (2.673 h), Z-R_MP (2.917 h), and Z-R_station (3.250 h). The results revealed that the RMCNN model in combination with radar images could efficiently estimate typhoon rainfall.

Replicating Advanced Detection using Low Ping Frequency Probe Vehicle Trajectory Data to Optimize Signal Progression

2020 ◽  
Vol 2674 (7) ◽  
pp. 528-539
Author(s):  
Jonathan M. Waddell ◽  
Stephen M. Remias ◽  
Jenna N. Kirsch ◽  
Mohsen Kamyab
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Mean Squared Error ◽  
Linear Interpolation ◽  
Traffic Signal ◽  
Trajectory Data ◽  
Arrival Times ◽  
Probe Vehicle ◽  
The Neural Network ◽  
Vehicle Trajectory

Probe vehicle trajectory data has the potential to transform the current practice of traffic signal optimization. Current scalable trajectory data is limited in both the penetration rate and the ping frequency, or the length of time between vehicle waypoints. This paper introduces a methodology to create binary vehicle trajectories which can be used in a neural network to predict when vehicles will arrive at a virtual detector. The methodology allows for vehicles with ping frequencies of up to 60 s to be utilized for the optimization of offsets at signalized intersections. A nine-signal corridor in west Michigan was used to test the proposed methodology. The neural network was compared to traditional linear interpolation strategies and found to improve the root mean squared error of the arrival times by up to 6.18 s. Using the virtual detector data stacked over time to optimize the offsets of the corridor resulted in 77% of the benefit of an offset optimization performed with continuously collected high resolution signal controller data. In the era of big data, this alternative approach can assist with the large-scale implementation of traffic signal performance measures for improved operations.

Estimating normal moveout velocity using the recurrent neural network

2019 ◽  
Vol 7 (4) ◽  
pp. T819-T827
Author(s):  
Reetam Biswas ◽  
Anthony Vassiliou ◽  
Rodney Stromberg ◽  
Mrinal K. Sen
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Mean Squared Error ◽  
Correction Term ◽  
Computation Time ◽  
Velocity Estimation ◽  
Data Set ◽  
Arrival Times ◽  
Nmo Correction ◽  
Novel Method

Machine learning (ML) has recently gained immense popularity because of its successful application in complex problems. It develops an abstract relation between the input and output. We have evaluated the application of ML to the most basic seismic processing of normal moveout (NMO) correction. The arrival times of reflection events in a common midpoint (CMP) gather follow a hyperbolic trajectory; thus, they require a correction term to flatten the CMP gather before stacking. This correction term depends on an rms velocity, also referred to as the NMO velocity. In general, NMO velocity is estimated using the semblance measures and picking the peaks in the velocity panel. This process requires a lot of human intervention and computation time. We have developed a novel method using one of the tools based on an ML- approach and applied to the NMO velocity estimation problem. We use the recurrent neural network (RNN) to estimate the NMO velocity directly from the seismic data. The input to the network is a seismic gather and corresponding precalculated NMO velocity (as prelabeled data set) to flatten the gather. We first train the network to develop a relationship between the input gathers (before NMO correction) and the corresponding NMO velocities for a few CMPs as a supervised learning process. Adam optimization algorithm is used to train the RNN. The output from the network is then compared against the correct NMO velocity. The error between the two velocities is then used to update the weight of the neurons and to minimize the mean-squared error between the two velocities. After the network is trained, it can be used to calculate the NMO velocity for the rest of the seismic gathers. We evaluate our method on a noisy data set from Poland. We used only 10% of the CMPs to train the network, and then we used the trained network to predict NMO velocity for the remaining CMP locations. The stack section obtained by using RNN-generated NMO velocities is nearly identical to that obtained by the conventional semblance method.

scholarly journals Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

Atmosphere ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 244 ◽  
Author(s):  
Quang-Khai Tran ◽  
Sa-kwang Song
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Mean Squared Error ◽  
Neural Network Models ◽  
Common Mean ◽  
Radar Images ◽  
Squared Error

This paper presents a viewpoint from computer vision to the radar echo extrapolation task in the precipitation nowcasting domain. Inspired by the success of some convolutional recurrent neural network models in this domain, including convolutional LSTM, convolutional GRU and trajectory GRU, we designed a new sequence-to-sequence neural network structure to leverage these models in a realistic data context. In this design, we decreased the numbers of channels in high abstract recurrent layers rather than increasing them. We formulated the task as a problem of encoding five radar images and predicting 10 steps ahead at the pixel level, and found that using only the common mean squared error can misguide the training and mislead the testing. Especially, the image quality of last predictions usually degraded rapidly. As a solution, we employed some visual image quality assessment techniques including Structural Similarity (SSIM) and multi-scale SSIM to train our models. Experimental results show that our structure was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue. Moreover, we found that using SSIM was very effective and a combination of SSIM with mean squared error and mean absolute error yielded the best prediction quality.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Development of a Deep Neural Network Model for Estimating Joint Location of Occupant Indoor Activities for Providing Thermal Comfort

Energies ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 696
Author(s):  
Eun Ji Choi ◽  
Jin Woo Moon ◽  
Ji-hoon Han ◽  
Yongseok Yoo
Keyword(s):  
Neural Network ◽  
Thermal Comfort ◽  
Deep Neural Network ◽  
Mean Squared Error ◽  
Thermal Environment ◽  
The Body ◽  
Estimation Accuracy ◽  
Accurate Estimation ◽  
Body Parts ◽  
Joint Location

The type of occupant activities is a significantly important factor to determine indoor thermal comfort; thus, an accurate method to estimate occupant activity needs to be developed. The purpose of this study was to develop a deep neural network (DNN) model for estimating the joint location of diverse human activities, which will be used to provide a comfortable thermal environment. The DNN model was trained with images to estimate 14 joints of a person performing 10 common indoor activities. The DNN contained numerous shortcut connections for efficient training and had two stages of sequential and parallel layers for accurate joint localization. Estimation accuracy was quantified using the mean squared error (MSE) for the estimated joints and the percentage of correct parts (PCP) for the body parts. The results show that the joint MSEs for the head and neck were lowest, and the PCP was highest for the torso. The PCP for individual activities ranged from 0.71 to 0.92, while typing and standing in a relaxed manner were the activities with the highest PCP. Estimation accuracy was higher for relatively still activities and lower for activities involving wide-ranging arm or leg motion. This study thus highlights the potential for the accurate estimation of occupant indoor activities by proposing a novel DNN model. This approach holds significant promise for finding the actual type of occupant activities and for use in target indoor applications related to thermal comfort in buildings.

Prognosis of water levels in a moor groundwater system influenced by hydrology and water extraction using an artificial neural network 

2021 ◽  
Author(s):  
Sascha Flaig ◽  
Timothy Praditia ◽  
Alexander Kissinger ◽  
Ulrich Lang ◽  
Sergey Oladyshkin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Squared Error ◽  
Meteorological Data ◽  
Water Levels ◽  
Typical Structure ◽  
Water Abstraction ◽  
Physical Knowledge ◽  
Artificial Neural ◽  
The Impact

<p>In order to prevent possible negative impacts of water abstraction in an ecologically sensitive moor south of Munich (Germany), a “predictive control” scheme is in place. We design an artificial neural network (ANN) to provide predictions of moor water levels and to separate hydrological from anthropogenic effects. As the moor is a dynamic system, we adopt the „Long short-term memory“ architecture.</p><p>To find the best LSTM setup, we train, test and compare LSTMs with two different structures: (1) the non-recurrent one-to-one structure, where the series of inputs are accumulated and fed into the LSTM; and (2) the recurrent many-to-many structure, where inputs gradually enter the LSTM (including LSTM forecasts from previous forecast time steps). The outputs of our LSTMs then feed into a readout layer that converts the hidden states into water level predictions. We hypothesize that the recurrent structure is the better structure because it better resembles the typical structure of differential equations for dynamic systems, as they would usually be used for hydro(geo)logical systems. We evaluate the comparison with the mean squared error as test metric, and conclude that the recurrent many-to-many LSTM performs better for the analyzed complex situations. It also produces plausible predictions with reasonable accuracy for seven days prediction horizon.</p><p>Furthermore, we analyze the impact of preprocessing meteorological data to evapotranspiration data using typical ETA models. Inserting knowledge into the LSTM in the form of ETA models (rather than implicitly having the LSTM learn the ETA relations) leads to superior prediction results. This finding aligns well with current ideas on physically-inspired machine learning.</p><p>As an additional validation step, we investigate whether our ANN is able to correctly identify both anthropogenic and natural influences and their interaction. To this end, we investigate two comparable pumping events under different meteorological conditions. Results indicate that all individual and combined influences of input parameters on water levels can be represented well. The neural networks recognize correctly that the predominant precipitation and lower evapotranspiration during one pumping event leads to a lower decrease of the hydrograph.</p><p>To further demonstrate the capability of the trained neural network, scenarios of pumping events are created and simulated.</p><p>In conclusion, we show that more robust and accurate predictions of moor water levels can be obtained if available physical knowledge of the modeled system is used to design and train the neural network. The artificial neural network can be a useful instrument to assess the impact of water abstraction by quantifying the anthropogenic influence.</p>

scholarly journals Using Monte Carlo method to estimate the behavior of neural training between balanced and unbalanced data in classification of patterns

2018 ◽  
Vol 7 (2) ◽  
pp. 1
Author(s):  
Paulo Marcelo Tasinaffo ◽  
Gildárcio Sousa Gonçalves ◽  
Adilson Marques da Cunha ◽  
Luiz Alberto Vieira Dias
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Monte Carlo ◽  
Monte Carlo Method ◽  
Mean Squared Error ◽  
Classification Problem ◽  
Computational Environment ◽  
The Monte Carlo Method ◽  
Proposed Model ◽  
Artificial Neural

This paper proposes to develop a model-based Monte Carlo method for computationally determining the best mean squared error of training for an artificial neural network with feedforward architecture. It is applied for a particular non-linear classification problem of input/output patterns in a computational environment with abundant data. The Monte Carlo method allows computationally checking that balanced data are much better than non-balanced ones for an artificial neural network to learn by means of supervised learning. The major contribution of this investigation is that, the proposed model can be tested by analogy, considering also the fraud detection problem in credit cards, where the amount of training patterns used are high.

scholarly journals Research on GDP Forecast Analysis Combining BP Neural Network and ARIMA Model

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shaobo Lu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Model ◽  
Error Correction ◽  
Relative Error ◽  
Bp Neural Network ◽  
Arima Model ◽  
Forecast Model ◽  
Price Prediction ◽  
The Neural Network

Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model. First, the focus is on the ARMA model in the univariate time series. However, in real life, forecasts are often affected by many factors, so the following introduces the ARIMAX model in the multivariate time series. In the prediction process, the network structure and various parameters of the neural network are not given in a systematic way, so the operation of the neural network is affected by many factors. Each forecasting method has its scope of application and also has its own weaknesses caused by the characteristics of its own model. Secondly, this paper proposes an effective combination method according to the GDP characteristics and builds an improved algorithm BP neural network price prediction model, the research on the combination of GDP prediction model is currently mostly focused on the weighted form, and this article proposes another combination, namely, error correction. According to the price characteristics, we determine the appropriate number of hidden layer nodes and build a BP neural network price prediction model based on the improved algorithm. Validation of examples shows that the error-corrected GDP forecast model is also better than the weighted GDP forecast model, which shows that error correction is also a better combination of forecasting methods. The forecast results of BP neural network have lower errors and monthly prices. The relative error of prediction is about 2.5%. Through comparison with the prediction results of the ARIMA model, in the daily price prediction, the relative error of the BP neural network prediction is 1.5%, which is lower than the relative error of the ARIMA model of 2%.

scholarly journals Prediksi Indeks Harga Saham Gabungan (IHSG) Menggunakan Algoritma Neural Network

2018 ◽  
Vol 4 (1) ◽  
pp. 24
Author(s):  
Imam Halimi ◽  
Wahyu Andhyka Kusuma
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Linear Regression ◽  
Mean Squared Error ◽  
Composite Index ◽  
T Test ◽  
Sliding Windows ◽  
Root Mean Squared Error ◽  
Squared Error

Investasi saham merupakan hal yang tidak asing didengar maupun dilakukan. Ada berbagai macam saham di Indonesia, salah satunya adalah Indeks Harga Saham Gabungan (IHSG) atau dalam bahasa inggris disebut Indonesia Composite Index, ICI, atau IDX Composite. IHSG merupakan parameter penting yang dipertimbangkan pada saat akan melakukan investasi mengingat IHSG adalah saham gabungan. Penelitian ini bertujuan memprediksi pergerakan IHSG dengan teknik data mining menggunakan algoritma neural network dan dibandingkan dengan algoritma linear regression, yang dapat dijadikan acuan investor saat akan melakukan investasi. Hasil dari penelitian ini berupa nilai Root Mean Squared Error (RMSE) serta label tambahan angka hasil prediksi yang didapatkan setelah dilakukan validasi menggunakan sliding windows validation dengan hasil paling baik yaitu pada pengujian yang menggunakan algoritma neural network yang menggunakan windowing yaitu sebesar 37,786 dan pada pengujian yang tidak menggunakan windowing sebesar 13,597 dan untuk pengujian algoritma linear regression yang menggunakan windowing yaitu sebesar 35,026 dan pengujian yang tidak menggunakan windowing sebesar 12,657. Setelah dilakukan pengujian T-Test menunjukan bahwa pengujian menggunakan neural network yang dibandingkan dengan linear regression memiliki hasil yang tidak signifikan dengan nilai T-Test untuk pengujian dengan windowing dan tanpa windowing hasilnya sama, yaitu sebesar 1,000.

Sign in / Sign up

Export Citation Format

Share Document