scholarly journals Feasibility of Different Weather Data Sources Applied to Building Indoor Temperature Estimation Using LSTM Neural Networks

2021 ◽  
Vol 13 (24) ◽  
pp. 13735
Author(s):  
Martín Pensado-Mariño ◽  
Lara Febrero-Garrido ◽  
Pablo Eguía-Oller ◽  
Enrique Granada-Álvarez
Keyword(s):  
Meteorological Data ◽  
Energy Performance ◽  
Meteorological Station ◽  
Data Sources ◽  
Weather Data ◽  
Learning Models ◽  
Indoor Temperature ◽  
Temperature Estimation ◽  
The Third ◽  
Machine Learning Models

The use of Machine Learning models is becoming increasingly widespread to assess energy performance of a building. In these models, the accuracy of the results depends largely on outdoor conditions. However, getting these data on-site is not always feasible. This article compares the temperature results obtained for an LSTM neural network model, using four types of meteorological data sources. The first is the monitoring carried out in the building; the second is a meteorological station near the site of the building; the third is a table of meteorological data obtained through a kriging process and the fourth is a dataset obtained using GFS. The results are analyzed using the CV(RSME) and NMBE indices. Based on these indices, in the four series, a CV(RSME) slightly higher than 3% is obtained, while the NMBE is below 1%, so it can be deduced that the sources used are interchangeable.

Prediction of aircraft estimated time of arrival using machine learning methods

2021 ◽  
pp. 1-15
Author(s):  
O. Basturk ◽  
C. Cetek
Keyword(s):  
Machine Learning ◽  
Web Application ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Weather Data ◽  
Time Of Arrival ◽  
Learning Models ◽  
Trajectory Data ◽  
Different Sources ◽  
Machine Learning Models

ABSTRACT In this study, prediction of aircraft Estimated Time of Arrival (ETA) is proposed using machine learning algorithms. Accurate prediction of ETA is important for management of delay and air traffic flow, runway assignment, gate assignment, collaborative decision making (CDM), coordination of ground personnel and equipment, and optimisation of arrival sequence etc. Machine learning is able to learn from experience and make predictions with weak assumptions or no assumptions at all. In the proposed approach, general flight information, trajectory data and weather data were obtained from different sources in various formats. Raw data were converted to tidy data and inserted into a relational database. To obtain the features for training the machine learning models, the data were explored, cleaned and transformed into convenient features. New features were also derived from the available data. Random forests and deep neural networks were used to train the machine learning models. Both models can predict the ETA with a mean absolute error (MAE) less than 6min after departure, and less than 3min after terminal manoeuvring area (TMA) entrance. Additionally, a web application was developed to dynamically predict the ETA using proposed models.

scholarly journals Utilising Open Geospatial Data to Refine Weather Variables for Building Energy Performance Evaluation—Incident Solar Radiation and Wind-Driven Infiltration Modelling

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 802
Author(s):  
Kristian Skeie ◽  
Arild Gustavsen
Keyword(s):  
Solar Radiation ◽  
Web Service ◽  
Meteorological Data ◽  
Surface Wind ◽  
Building Energy ◽  
Energy Performance ◽  
Geospatial Data ◽  
Weather Data ◽  
Building Site ◽  
Incident Solar Radiation

In building thermal energy characterisation, the relevance of proper modelling of the effects caused by solar radiation, temperature and wind is seen as a critical factor. Open geospatial datasets are growing in diversity, easing access to meteorological data and other relevant information that can be used for building energy modelling. However, the application of geospatial techniques combining multiple open datasets is not yet common in the often scripted workflows of data-driven building thermal performance characterisation. We present a method for processing time-series from climate reanalysis and satellite-derived solar irradiance services, by implementing land-use, and elevation raster maps served in an elevation profile web-service. The article describes a methodology to: (1) adapt gridded weather data to four case-building sites in Europe; (2) calculate the incident solar radiation on the building facades; (3) estimate wind and temperature-dependent infiltration using a single-zone infiltration model and (4) including separating and evaluating the sheltering effect of buildings and trees in the vicinity, based on building footprints. Calculations of solar radiation, surface wind and air infiltration potential are done using validated models published in the scientific literature. We found that using scripting tools to automate geoprocessing tasks is widespread, and implementing such techniques in conjunction with an elevation profile web service made it possible to utilise information from open geospatial data surrounding a building site effectively. We expect that the modelling approach could be further improved, including diffuse-shading methods and evaluating other wind shelter methods for urban settings.

scholarly journals Three machine learning models for the 2019 Solubility Challenge

ADMET & DMPK ◽  
2020 ◽  
Author(s):  
John Mitchell
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Gold Standard ◽  
Challenge Test ◽  
Wisdom Of Crowds ◽  
Learning Models ◽  
The Third ◽  
Aqueous Solubilities ◽  
Machine Learning Models ◽  
Better Than

<p class="ADMETabstracttext">We describe three machine learning models submitted to the 2019 Solubility Challenge. All are founded on tree-like classifiers, with one model being based on Random Forest and another on the related Extra Trees algorithm. The third model is a consensus predictor combining the former two with a Bagging classifier. We call this consensus classifier Vox Machinarum, and here discuss how it benefits from the Wisdom of Crowds. On the first 2019 Solubility Challenge test set of 100 low-variance intrinsic aqueous solubilities, Extra Trees is our best classifier. One the other, a high-variance set of 32 molecules, we find that Vox Machinarum and Random Forest both perform a little better than Extra Trees, and almost equally to one another. We also compare the gold standard solubilities from the 2019 Solubility Challenge with a set of literature-based solubilities for most of the same compounds.</p>

scholarly journals Forecasting residential gas consumption with machine learning algorithms on weather data

2019 ◽  
Vol 111 ◽  
pp. 05019
Author(s):  
Brian de Keijzer ◽  
Pol de Visser ◽  
Víctor García Romillo ◽  
Víctor Gómez Muñoz ◽  
Daan Boesten ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Consumption ◽  
Energy Use ◽  
Machine Learning Algorithms ◽  
Weather Data ◽  
Computational Time ◽  
Percentage Error ◽  
Learning Models ◽  
Gas Consumption ◽  
Machine Learning Models

Machine learning models have proven to be reliable methods in the forecasting of energy use in commercial and office buildings. However, little research has been done on energy forecasting in dwellings, mainly due to the difficulty of obtaining household level data while keeping the privacy of inhabitants in mind. Gaining insight into the energy consumption in the near future can be helpful in balancing the grid and insights in how to reduce the energy consumption can be received. In collaboration with OPSCHALER, a measurement campaign on the influence of housing characteristics on energy costs and comfort, several machine learning models were compared on forecasting performance and the computational time needed. Nine months of data containing the mean gas consumption of 52 dwellings on a one hour resolution was used for this research. The first 6 months were used for training, whereas the last 3 months were used to evaluate the models. The results showed that the Deep Neural Network (DNN) performed best with a 50.1 % Mean Absolute Percentage Error (MAPE) on a one hour resolution. When comparing daily and weekly resolutions, the Multivariate Linear Regression (MVLR) outperformed other models, with a 20.1 % and 17.0 % MAPE, respectively. The models were programmed in Python.

scholarly journals INFLUENCE OF THE METEOROLOGICAL CONDITIONS ON FOREST FIRES OCCURRENCES IN LICHINGA DISTRICT, NORTHERN MOZAMBIQUE

FLORESTA ◽  
2015 ◽  
Vol 45 (3) ◽  
pp. 577 ◽  
Author(s):  
Aires Afonso Mbanze ◽  
Antonio Carlos Batista ◽  
Alexandre França Tetto ◽  
Henrique Soares Koehler ◽  
Jose Bernardo Manteiga
Keyword(s):  
Forest Fires ◽  
Meteorological Data ◽  
Great Influence ◽  
Meteorological Conditions ◽  
Meteorological Station ◽  
Weather Data ◽  
Monitoring And Control ◽  
Tukey Test ◽  
Daily Weather Data ◽  
And Control

AbstractThe aim of this study was to assess the influence of meteorological conditions on the fire occurrences in forest stands of Lichinga district, in the period from 2010 to 2012. Data about fire occurrences records of the district of Lichinga and two others close districts (Lago and Sanga) were provided by the Center for Monitoring and Control of Forest Fires (CCMIF) of the company Chikweti. Daily weather data: temperature, rainfall and relative humidity of the same period, recorded at 13:00 PM, by the meteorological station of the Institute of Agronomic Research of Mozambique (IIAM) in Lichinga district were also provided to this work. Meteorological data were submitted to regression analysis and Tukey test. The results showed a significant variation in temperature and humidity on both tests. The overlapping of fire occurrences and meteorological variables, suggested a great influence of the meteorological conditions in the occurrence of fires, mainly due to the very long dry periods. In 2010 there was a delay in the occurrence of fires; this was related to the rainy season which was slightly longer. September and October was the months that recorded the highest number of fire occurrences throughout the studied period.ResumoInfluência das condições meteorológicas na ocorrência dos incêndios florestais no distrito de Lichinga, norte de Moçambique. O objetivo deste estudo foi avaliar a influência das variáveis meteorológicas na ocorrência de incêndios em povoamentos florestais no distrito de Lichinga, no período de 2010 a 2012. Para tal, foram analisados os registros de ocorrências de incêndios do distrito de Lichinga e de outros dois distritos vizinhos (Lago e Sanga), disponibilizados pelo Centro de Controle e Monitoramento de Incêndios Florestais (CCMIF) da empresa Chikweti Forest of Niassa, e dados meteorológicos diários de temperatura (máxima e mínima), precipitação e umidade relativa, do mesmo período, registrados às 13 horas, pela estação meteorológica do Instituto de Investigação Agronômica de Moçambique em Lichinga (IIAM-Lichinga). Os dados meteorológicos foram submetidos ao teste de análise de regressão e ao teste de Tukey, tendo sido observado uma variação significativa da temperatura e umidade em ambos os testes. A sobreposição das ocorrências dos incêndios com as variáveis meteorológicas demostrou uma grande influênca dessas variáveis na ocorrência dos incêndios, principalmente devido aos períodos secos prolongados. No ano 2010 observou-se um atraso na ocorrência dos incêndios, devido ao período chuvoso que foi ligeiramente mais longo. Os meses que registraram maior número de ocorrências em todo o período foram setembro e outubro.Palavras-chave: Povoamentos florestais; variáveis meteorológicas; prevenção de incêndios florestais.

Near-extreme summer meteorological data set for sub-tropical climates

2016 ◽  
Vol 38 (2) ◽  
pp. 197-208 ◽  
Author(s):  
Kevin Ka-Lun Lau ◽  
Edward Yan-Yung Ng ◽  
Pak-Wai Chan ◽  
Justin Ching-Kwan Ho
Keyword(s):  
Meteorological Data ◽  
Energy Performance ◽  
Weather Data ◽  
Building Performance ◽  
Extreme Conditions ◽  
Night Time ◽  
Data Set ◽  
Performance Simulation ◽  
Building Performance Simulation ◽  
Tropical Climates

Building performance simulation requires representative weather data of specific locations. Test Reference Year (TRY) and Typical Meteorological Year (TMY) are common hourly dataset for typical year conditions. In sub-tropical climates, overheating is very common in buildings due to high temperature and intense solar radiation. However, there are no universal approaches to develop a dataset for estimating summer discomfort in naturally ventilated and free-running buildings. This article employs the concept of Summer Reference Years (SRY) in order to represent the near-extreme summer conditions in Hong Kong. The derived SRY is able to capture the near-extreme conditions in the multi-year series. The SRY was found to represent the high Tdry values reasonably well during daytime when such near-extreme conditions occur. On the contrary, according to the number of HN-DHs, the SRY does not satisfactorily represent high night-time Tdry. It is possible to incorporate the sorting of Tdry-min in the SRY adjustment in order to better reflect night-time situations in sub-tropical climate. Further studies are therefore required to confirm whether such modifications give more accurate results in the assessment of building energy performance. Nonetheless, the SRY dataset can be applied in building performance simulation and the assessment of indoor thermal comfort. Practical application: The present study found that there are deficiencies for the SRY to represent the high night-time Tdry, which affects the building performance assessment in sub-tropical climates. It suggests potential improvement to the existing adjustment of SRY for representing the near-extreme summer conditions in order to obtain more accurate results of building assessment.

scholarly journals Machine Learning to Predict 10-year Cardiovascular Mortality from the Electrocardiogram: Analysis of the Third National Health and Nutrition Examination Survey (NHANES III)

2021 ◽  
Author(s):  
Chang H Kim ◽  
Sadeer Al-Kindi ◽  
Yasir Tarabichi ◽  
Suril Gohel ◽  
Riddhi Vyas ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiovascular Mortality ◽  
Predictive Performance ◽  
Nhanes Iii ◽  
Nutrition Examination Survey ◽  
Learning Models ◽  
The Third ◽  
Health And Nutrition ◽  
Machine Learning Models ◽  
Ecg Data

Background: The value of the electrocardiogram (ECG) for predicting long-term cardiovascular outcomes is not well defined. Machine learning methods are well suited for analysis of highly correlated data such as that from the ECG. Methods: Using demographic, clinical, and 12-lead ECG data from the Third National Health and Nutrition Examination Survey (NHANES III), machine learning models were trained to predict 10-year cardiovascular mortality in ambulatory U.S. adults. Predictive performance of each model was assessed using area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), sensitivity, and specificity. These were compared to the 2013 American College of Cardiology/American Heart Association Pooled Cohort Equations (PCE). Results: 7,067 study participants (mean age: 59.2 +/- 13.4 years, female: 52.5%, white: 73.9%, black: 23.3%) were included. At 10 years of follow up, 338 (4.8%) had died from cardiac causes. Compared to the PCE (AUROC: 0.668, AUPRC: 0.125, sensitivity: 0.492, specificity: 0.859), machine learning models only required demographic and ECG data to achieve comparable performance: logistic regression (AUROC: 0.754, AUPRC: 0.141, sensitivity: 0.747, specificity: 0.759), neural network (AUROC: 0.764, AUPRC: 0.149, sensitivity: 0.722, specificity: 0.787), and ensemble model (AUROC: 0.695, AUPRC: 0.166, sensitivity: 0.468, specificity: 0.912). Additional clinical data did not improve the predictive performance of machine learning models. In variable importance analysis, important ECG features clustered in inferior and lateral leads. Conclusions: Machine learning can be applied to demographic and ECG data to predict 10-year cardiovascular mortality in ambulatory adults, with potentially important implications for primary prevention.

scholarly journals Global solar radiation modeling using different machine learning and empirical models in Northeast China

2021 ◽  
Author(s):  
Yue Jia ◽  
Yongjun Su ◽  
Fengchun Wang ◽  
Pengcheng Li ◽  
Shuyi Huo
Keyword(s):  
Machine Learning ◽  
Solar Radiation ◽  
Solar Energy ◽  
Northeast China ◽  
Sunshine Duration ◽  
Meteorological Data ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Learning Models ◽  
Machine Learning Models

Abstract Reliable global solar radiation (Rs) information is crucial for the design and management of solar energy systems for agricultural and industrial production. However, Rs measurements are unavailable in many regions of the world, which impedes the development and application of solar energy. To accurately estimate Rs, this study developed a novel machine learning model, called a Gaussian exponential model (GEM), for daily global Rs estimation. The GEM was compared with four other machine learning models and two empirical models to assess its applicability using daily meteorological data from 1997–2016 from four stations in Northeast China. The results showed that the GEM with complete inputs had the best performance. Machine learning models provided better estimates than empirical models when trained by the same input data. Sunshine duration was the most effective factor determining the accuracy of the machine learning models. Overall, the GEM with complete inputs had the highest accuracy and is recommended for modeling daily Rs in Northeast China.

scholarly journals A general method for estimating the prevalence of influenza-like-symptoms with Wikipedia data

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256858
Author(s):  
Giovanni De Toni ◽  
Cristian Consonni ◽  
Alberto Montresor
Keyword(s):  
Machine Learning ◽  
The Netherlands ◽  
State Of The Art ◽  
Data Sources ◽  
Learning Models ◽  
Personalized Pagerank ◽  
Web Searches ◽  
The Impact ◽  
Machine Learning Models ◽  
General Method

Influenza is an acute respiratory seasonal disease that affects millions of people worldwide and causes thousands of deaths in Europe alone. Estimating in a fast and reliable way the impact of an illness on a given country is essential to plan and organize effective countermeasures, which is now possible by leveraging unconventional data sources like web searches and visits. In this study, we show the feasibility of exploiting machine learning models and information about Wikipedia’s page views of a selected group of articles to obtain accurate estimates of influenza-like illnesses incidence in four European countries: Italy, Germany, Belgium, and the Netherlands. We propose a novel language-agnostic method, based on two algorithms, Personalized PageRank and CycleRank, to automatically select the most relevant Wikipedia pages to be monitored without the need for expert supervision. We then show how our model can reach state-of-the-art results by comparing it with previous solutions.

Sign in / Sign up

Export Citation Format

Share Document