Considering spatiotemporal processes in big data analysis: Insights from remote sensing of land cover and land use

Abstract

Data are increasingly spatio‐temporal—they are collected some‐where and at some‐time. The role of proximity in spatial process is well understood, but its value is much more uncertain for many temporal processes. Using the domain of land cover/land use (LCLU), this article asserts that analyses of big data should be grounded in understandings of underlying process. Processes exhibit behaviors over both space and time. Observations and measurements may or may not coincide with the process of interest. Identifying the presence or absence of a given process, for instance disentangling vegetation phenology from stress, requires data analysis to be informed by knowledge of the process characteristics and, critically, how these manifest themselves over the spatio‐temporal unit of analysis. Drawing from LCLU, we emphasize the need to identify process and consider process phase to quantify important signals associated with that process. The aim should be to link the seriality of the spatio‐temporal data to the phase of the process being considered. We elucidate on these points and opportunities for insights and leadership from the geographic community.

Monitoring land degradation at national level using satellite Earth Observation time-series data to support SDG15 – exploring the potential of data cube

“…This issue has not been yet tackled but various possibilities can be explored such as advanced processing and classification algorithms such as Artificial Neural Networks (ANN), Support Vector Machine classifier (SVM) (Mountrakis, Im, & Ogole 2011), decision tree classifiers and Random Forest used in conjunction with time-series metrics, integration of ancillary data (e.g. Digital Elevation Model), and post-classification error reduction and accuracy assessment (Comber & Wulder, 2019;Dong, Metternicht, Hostert, Fensholt, & Chowdhury, 2019;Wulder, Coops, Roy, White, & Hermosilla, 2018).…”

Exploring the Use of Computer Vision Metrics for Spatial Pattern Comparison

“…These inferences further highlight the widely debated issues of scale in geographical research. Therefore, to properly quantify and characterize spatial patterns using these metrics, an appropriate window choice should be adopted vis‐a‐vis prior knowledge pertaining to scale and extent of spatial dependence in processes generating spatial patterns (Comber and Wulder ).…”

“…Two separate sets of images were simulated on a 50 × 50 grid. Though spatial patterns as well as the outcomes of metrics computed on them are largely a function of spatial grain and extent (Gustafson ; Comber and Wulder ), the selected grid dimension considered here is useful for analyzing patterns characterized by small‐scale moving average fields and ensures relatively simple patterns. Moreover, patterns in moving average fields can be easily detected by the HVS due to smooth nature of the spatial structure (Dungan et al ).…”

“…In a pattern/process framework, detection of change in spatial process typically resolves to characterizing changes in temporally distal spatial patterns, and ideally, assessing the significance of this change relative to candidate spatial processes (Boots and Csillag ; Miller and Goodchild ). Increasingly, this is making use of time series of patterns/images obtained from growing archives of earth observation data obtained from satellite sensors (Greig, Robertson, and Lacerda ; Comber and Wulder ). In the geographic analysis context, we consider spatial pattern comparison to be a specific geographic instance of a broader class of spatial pattern comparison problems which are prevalent across a wide range of disciplines.…”

“…For example, we may want to identify similar sites to function as reference locations when evaluating disturbance from resource extraction. As global and regional archives of satellite images and routine mapping programs expand, the need for spatial pattern similarity analysis is likely to increase (Comber and Wulder ).…”