China 
Africa 
Explore chapters and articles related to this topic
Spatiotemporal Data Mining
Published in Arturo Román Messina, Data Fusion and Data Mining for Power System Monitoring, 2020
The complexity of spatiotemporal data and intrinsic relationships may limit the usefulness of conventional data science techniques for extracting spatiotemporal patterns. It is therefore necessary to develop new techniques that efficiently summarize and discover trends in spatiotemporal data in order to facilitate decision making. To be of practical use, data mining techniques should consider space and time in an integrated manner.
Geographic pattern of human mobility and COVID-19 before and after Hubei lockdown
Published in Annals of GIS, 2021
T. Edwin Chow, Yusik Choi, Mei Yang, David Mills, Ricci Yue
Research leveraging migration data are helpful to understand spatial epidemiology and public health intervention. Spatial analysis of human mobility data can support decision making by modelling disease spread, detecting patterns and statistically significant hotspot, and predicting future risk (Dong et al. 2020). Geographic Information Systems (GIS) and spatial analysis are multidisciplinary toolsets that can be used to identify and understand the spatiotemporal patterns of geographic epidemiology (Rezaeian et al. 2007). As demonstrated by John Snow in advancing our understanding about cholera, simply mapping, geographic visualization and point pattern analysis can help exploring and confirming the disease origin and its relationship with environmental factors (Yuan et al. 2020). Lai et al. (2004) used cluster analysis and kernel density surfaces to examine and explain the hotspots of Severe Acute Respiratory Syndrome (SARS) in Hong Kong during 2003. In addition to clinical analysis in epidemiology, the geographic approach offers a supplementary framework to explore and identify not only where but also why the emergence, spread and subsidence of an acute infectious disease.
Systematic analysis of satellite image-based land cover classification techniques: literature review and challenges
Published in International Journal of Computers and Applications, 2021
Anil B. Gavade, Vijay S. Rajpurohit
Saroj K. Meher and Sankar K. Pal [54] devised a rough-wavelet framework for the classification of land cover from the MS images. In this framework, a Class-Dependent (CD) wavelet granulation was formulated for improving the estimation of class label and exploring the feature dependency into distinct classes. This framework provided effective results even during the spatiotemporal pattern analysis.