TY - JOUR
AU1 - Iyer, Radhakrishnan Thanu
AU2 - Krishnan, Manojkumar Thananthu
AB - Spatial planning often requires a scientific understanding of the spatial variation of environmental variables. This is accomplished by spatial prediction of point observations from geographic locations, transforming point data into seamless raster interpolations for the region of interest. The most widely used geostatistical interpolation technique is kriging that minimises errors and produces unbiased predictions. Machine learning (ML) and Deep Learning based spatial estimation approaches have recently received a lot of attention. A significant amount of research has gone into creating new methods of data-driven, computationally efficient spatial prediction of variables with increased prediction accuracy. Using Citation Network Analysis of journal papers published over the past 30 years, we investigated the development, evolution and significant milestones in the spatial prediction techniques and their applications. The main path analysis of research evolution in a citation network was carried out to understand the development trajectory and direction of future of research in this field.
TI - Citation network analysis of geostatistical and machine learning based spatial prediction
JF - Spatial Information Research
DO - 10.1007/s41324-023-00526-0
DA - 2023-12-01
UR - https://www.deepdyve.com/lp/springer-journals/citation-network-analysis-of-geostatistical-and-machine-learning-based-Yo5BohVXCY
SP - 625
EP - 636
VL - 31
IS - 6
DP - DeepDyve
ER -