Do green schoolyards promote nature-based activities?

Exploring geographical, curricular, and demographic predictors of nature use by children in urban schoolyards.

Installing nature-rich spaces in schoolyards may not guarantee their use, and research is needed to understand how the physical make-up of schoolyards may interact with teacher and student-related factors to predict use of natural elements in schoolyards. This study surveyed 3rd-6th grade students and to measure children’s awareness and use of nature-rich vs. traditional outdoor spaces as predicted by teachers’ behaviors and education-related training, student demography, and schoolyard physical environment. Results shows that children were less aware of nature-rich spaces (gardens 69%, woodlands 28%) than traditional outdoor spaces (playgrounds 73%, athletic fields 77%) and spent less time there.

However, teachers taking children outdoors and trained in environmental education positively predicted student awareness and use of nature-rich spaces, highlighting the importance of teacher training in successful green schoolyard efforts. (#greenschoolyard #children #childrenandnature)

Mapping urban flooding risk using machine learning

Combining Convolutional Neural Network (CNN) and geospatial data for mapping flooding risk areas

Climate change is increasing the intensity of storm events and hurricanes. Assessments of potential flood hazards can promote rapid emergency response and facilitate coastal adaptation. This study combined image-based machine learning CNN and geospatial data (i.e. elevation, slope, topographic wetness index, soil texture, surface runoff, land use/cover) for mapping flooding risk areas based on Hurricane Matthew imagery data. CNN demonstrated the highest overall accuracy (90.8%), precision (94.1%), recall (93.6%), and F-measures (93.8%). While further work should seek to establish the general applicability of this approach to other contexts, it has the potential to facilitate community planning for the increasingly extreme precipitation and intense storm events forecast by climate models. (#hurricane #machinelearning #flooding #climatechange)