A dataset of cold-water coral distribution records

Range map data of marine ecosystem structuring species under global climate change

“…Occurrence records of marine ecosystem structuring species were collated from published datasets for seagrasses, kelps and fucoids [ [5] , [7] ] and cold-water corals [ 6 ] (Supplement 1; Tables S1, S3, S5 and S7). Taxonomy was verified for each species using the World Register of Marine Species (WoRMS) (Supplement 1, Tables S2, S4, S6 and S8) [ 8 ].…”

“…The models utilized 2,751,458 occurrence records derived from datasets that provide expert-revised biodiversity data [ [5] , [6] , [7] ] (Supplement 1) [ 8 ]. It specifically concerns 1,048,576 occurrence records of 59 seagrass species, 629,491 records of 103 kelp forest species, 377,986 records of 239 fucoid species, and 695,405 records of 579 cold-water corals species.…”

Range Map Data of Marine Ecosystem Structuring Species Under Global Climate Change

“…The models utilized 2,751,458 occurrence records derived from datasets that provide expertrevised biodiversity data [5][6][7] (Supplement 1) [ 8 ]. It specifically concerns 1,048,576 occurrence records of 59 seagrass species, 629,491 records of 103 kelp forest species, 377,986 records of 239 fucoid species, and 695,405 records of 579 cold-water corals species.…”

“…Occurrence records of marine ecosystem structuring species were collated from published datasets for seagrasses, kelps and fucoids [ 5,7 ] and cold-water corals [ 6 ] (Supplement 1; Tables S1, S3, S5 and S7). Taxonomy was verified for each species using the World Register of Marine Species (WoRMS) (Supplement 1, Tables S2, S4, S6 and S8) [ 8 ].…”

“…This process involved training competitive models on nine randomly selected data folds, while one-fold was reserved for testing the performance in each run. The procedure was performed using the grid search method by testing a span of learning rate (0.1, 0.01 and 0.001), tree complexity (1-4), and number of trees (50-10 0 0, step 50) for BRT, number of interactions (50-250, step 50), degrees of freedom (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12) and shrinkage (0.25-1, step 0.25) for AdaBoost, and gamma (0-5, step 1), interaction depth (1-4), shrinkage (0.1-0.5, step 0.1) and number of rounds (10-100, step 10) for XGBoost. Monotonic responses [ 4 ] were positively or negatively forced to reduce overfitting according to expected outcomes on species distribution.…”