AUTHOR=Sousa Daniel , Davis Frank W. , Easterday Kelly , Reynolds Mark , Riege Laura , Butterfield H. Scott , Katkowski Moses 

TITLE=Predictive Ecological Land Classification From Multi-Decadal Satellite Imagery

JOURNAL=Frontiers in Forests and Global Change

VOLUME=Volume 5 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/forests-and-global-change/articles/10.3389/ffgc.2022.867369

DOI=10.3389/ffgc.2022.867369

ISSN=2624-893X

ABSTRACT=Ecological land classifications serve multiple purposes such as sample stratification, inventory, impact assessment and environmental planning. Data-driven classifications are challenged by the need for large training samples and ongoing rapid environmental that can weaken their predictive power. We evaluate the potential to derive useful, durable ecological land classifications from multi-decadal satellite imagery and geospatial environmental data. Using random forests and multivariate regression trees, we analyze 1982-2000 Landsat Thematic Mapper (L45) and 2013-2020 Harmonized Landsat Sentinel (HLS) imagery to develop and then test the predictive skill of an ecological land classification for monitoring Mediterranean-climate oak woodlands at the recently established Jack and Laura Dangermond Preserve (JLDP) near Point Conception, California. Image pixels were scored using linear spectral mixture models, temporal mixture models, and temporal mixture model residuals. The residual scores were highly correlated with oak canopy trends between 2012 and 2020 (r2 = 0.74, p << 0.001). The topoclimatic-edaphic land classification fitted to L45 temporal mixture model scores distinguished areas of the preserve where oak woodlands showed systematically higher or lower dieback during severe drought that occurred between 2012 and 2020, with a 5-fold difference in dieback rates between land classes. Our results highlight the largely untapped potential for developing predictive ecological land classifications from multi-decadal satellite imagery to guide scalable ground-supported monitoring of rapid environmental change.