scholarly journals Unlocking the Predictive Power of Heterogeneous Data to Build an Operational Dengue Forecasting System

2020 ◽  
Author(s):  
Carrie Manore ◽  
Geoffrey Fairchild ◽  
Amanda Ziemann ◽  
Nidhi Parikh ◽  
Katherine Kempfert ◽  
...  

ABSTRACTPredicting an infectious disease can help reduce its impact by advising public health interventions and personal preventive measures. While availability of heterogeneous data streams and sensors such as satellite imagery and the Internet have increased the opportunity to indirectly measure, understand, and predict global dynamics, the data may be prohibitively large and/or require intensive data management while also requiring subject matter experts to properly exploit the data sources (e.g., deriving features from fundamentally different data sets). Few efforts have quantitatively assessed the predictive benefit of novel data streams in comparison to more traditional data sources, especially at fine spatio-temporal resolutions. We have combined multiple traditional and non-traditional data streams (satellite imagery, Internet, weather, census, and clinical surveillance data) and assessed their combined ability to predict dengue in Brazil’s 27 states on a weekly and yearly basis over seven years. For each state, we nowcast dengue based on several time series models, which vary in complexity and inclusion of exogenous data. We also predict yearly cumulative risk by municipality and state. The top-performing model and utility of predictive data varies by state, implying that forecasting and nowcasting efforts in the future may be made more robust by and benefit from the use of multiple data streams and models. One size does not fit all, particularly when considering state-level predictions as opposed to the whole country. Our first-of-its-kind high resolution flexible system for predicting dengue incidence with heterogeneous (and still sometimes sparse) data can be extended to multiple applications and regions.

Author(s):  
B. Margan ◽  
F. Hakimpour

Abstract. Linked Data is available data on the web in a standard format that is useful for content inspection and insights deriving from data through semantic queries. Querying and Exploring spatial and temporal features of various data sources will be facilitated by using Linked Data. In this paper, an application is presented for linking transport data on the web. Data from Google Maps API and OpenStreetMap linked and published on the web. Spatio-Temporal queries were executed over linked transport data and resulted in network and traffic information in accordance with the user’s position. The client-side of this application contains a web and a mobile application which presents a user interface to access network and traffic information according to the user’s position. The results of the experiment show that by using the intrinsic potential of Linked Data we have tackled the challenges of using heterogeneous data sources and have provided desirable information that could be used for discovering new patterns. The mobile GIS application enables assessing the profits of mentioned technologies through an easy and user-friendly way.


2018 ◽  
Vol 930 (12) ◽  
pp. 39-43 ◽  
Author(s):  
V.P. Savinikh ◽  
A.A. Maiorov ◽  
A.V. Materuhin

The article is a brief summary of current research results of the authors in the field of spatial modeling of air pollution based on spatio-temporal data streams from geosensor networks. The urban environment is characterized by the presence of a large number of different sources of emissions and rapidly proceeding processes of contamination spread. So for the development of an adequate spatial model is required to make measurements with a large spatial and temporal resolution. It is shown that geosensor network provide researchers with the opportunity to obtain data with the necessary spatio-temporal detail. The article describes a prototype of a geosensor network to build a detailed spatial model of air pollution in a large city. To create a geosensor in the prototype of the system, calibrated gas sensors for a nitrogen dioxide and carbon monoxide concentrations measurement were interfaced to the module, which consist of processing unit and communication unit. At present, the authors of the article conduct field tests of the prototype developed.


Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1432
Author(s):  
Xwégnon Ghislain Agoua ◽  
Robin Girard ◽  
Georges Kariniotakis

The efficient integration of photovoltaic (PV) production in energy systems is conditioned by the capacity to anticipate its variability, that is, the capacity to provide accurate forecasts. From the classical forecasting methods in the state of the art dealing with a single power plant, the focus has moved in recent years to spatio-temporal approaches, where geographically dispersed data are used as input to improve forecasts of a site for the horizons up to 6 h ahead. These spatio-temporal approaches provide different performances according to the data sources available but the question of the impact of each source on the actual forecasting performance is still not evaluated. In this paper, we propose a flexible spatio-temporal model to generate PV production forecasts for horizons up to 6 h ahead and we use this model to evaluate the effect of different spatial and temporal data sources on the accuracy of the forecasts. The sources considered are measurements from neighboring PV plants, local meteorological stations, Numerical Weather Predictions, and satellite images. The evaluation of the performance is carried out using a real-world test case featuring a high number of 136 PV plants. The forecasting error has been evaluated for each data source using the Mean Absolute Error and Root Mean Square Error. The results show that neighboring PV plants help to achieve around 10% reduction in forecasting error for the first three hours, followed by satellite images which help to gain an additional 3% all over the horizons up to 6 h ahead. The NWP data show no improvement for horizons up to 6 h but is essential for greater horizons.


2016 ◽  
Vol 53 ◽  
pp. 172-191 ◽  
Author(s):  
Eduardo M. Eisman ◽  
María Navarro ◽  
Juan Luis Castro

Sign in / Sign up

Export Citation Format

Share Document