Abstract
From multiple raster datasets to spatial association patterns, the data-mining technique is divided into three subtasks, i.e., raster dataset pretreatment, mining algorithm design, and spatial pattern exploration from the mining results. Comparison with the former two subtasks reveals that the latter remains unresolved. Confronted with the interrelated marine environmental parameters, we propose a Tree-based Approach for eXploring Marine Spatial Patterns with multiple raster datasets called TAXMarSP, which includes two models. One is the Tree-based Cascading Organization Model (TCOM), and the other is the Spatial Neighborhood-based CAlculation Model (SNCAM). TCOM designs the “Spatial node→Pattern node” from top to bottom layers to store the table-formatted frequent patterns. Together with TCOM, SNCAM considers the spatial neighborhood contributions to calculate the pattern-matching degree between the specified marine parameters and the table-formatted frequent patterns and then explores the marine spatial patterns. Using the prevalent quantification Apriori algorithm and a real remote sensing dataset from January 1998 to December 2014, a successful application of TAXMarSP to marine spatial patterns in the Pacific Ocean is described, and the obtained marine spatial patterns present not only the well-known but also new patterns to Earth scientists.
Highlights
Marine spatial pattern represents abnormal variations in one to several marine environmental parameters, e.g., sea-surface temperature (SST), sea-surface chlorophyll-a (Chl-a), sea-surface precipitation (SSP), and sea level anomaly (SLA), that occur or co-occur in a specified spatial region
One subset of m−p belongs to NFPs One subset of m−p belongs to NFPs One subset of m−p belongs to NFPs, and one anti-subset belongs to NFPs Anti-pattern of m−p belongs to NFPs One anti-subset belongs to NFPs The matched degree of the first pattern is zero, and the second is 0.5
To address the great challenges of dealing with table-formatted frequent patterns resulting from rule mining using multiple long-term raster datasets, we have proposed an original approach to explore marine spatial patterns named TAXMarSP
Summary
Marine spatial pattern represents abnormal variations in one to several marine environmental parameters, e.g., sea-surface temperature (SST), sea-surface chlorophyll-a (Chl-a), sea-surface precipitation (SSP), and sea level anomaly (SLA), that occur or co-occur in a specified spatial region. The third task obtains marine spatial patterns from the table-formatted frequent patterns of all grid pixels. The frequent patterns that arise from remote sensing datasets are complicated, i.e., each grid pixel may have several patterns, and each pattern may involve several geographical parameters These complicated patterns require sophisticated organization model. To resolve the grid pixel with both several frequent patterns and multiple marine parameters, we propose a novel Tree-based Approach for eXploring Marine Spatial Patterns with multiple raster datasets called TAXMarSP. The other challenge is to explore the spatial patterns from the table-formatted frequent ones
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
