id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-035277-napw1pxe	Paul, Swarna Kamal	A Multivariate Spatiotemporal Model of COVID-19 Epidemic Using Ensemble of ConvLSTM Networks	2020-11-11		.txt	text/plain	2793	181	62	A proposed ensemble of convolutional LSTM-based spatiotemporal model can forecast the spread of the epidemic with high resolution and accuracy in a large geographic region. It achieved 5.57% and 0.3% mean absolute percent error for total number of predicted infection cases in a 5-day prediction period for USA and Italy, respectively. To address the problem of spatiotemporal prediction of Covid-19 spread in a large geographical region with high resolution, an ensemble of Convolutional LSTM [4]based model is proposed which needs to be trained with multilayer temporal geospatial data, transformed as sequence of frames. Experimentation is carried out with data of USA and Italy and achieved country-level mean absolute percent error (MAPE) of 5.57% and 0.3%, respectively, on forecasting of total infection cases in 5 days period. Thus, a large geographic region is divided into relatively smaller grids and model is trained with samples drawn from local distribution of infection cases.	./cache/cord-035277-napw1pxe.txt	./txt/cord-035277-napw1pxe.txt