bstract

Ecosystem Informatics brings together mathemat-ical  and  computational tools  to  address  scientific and  policy  challenges  in  the  ecosystem  sciences.These  challenges  include  novel  sensors  for  col-lecting data, algorithms fo r automated data clean-ing, learning methods for building statistical mod-els from data and for fitting mechanistic models to data, and algorithms for designing optimal policies for biosphere management.  This presentation dis-cusses these challenges and then describes recent work on the first two of these—new methods for automated arthropod population counting and lin-ear Gaussian DBNs for automated cleaning of sen-sor network data