Regrowth after fire is critical to long-term persistence of chaparral shrub communities in southern California. This region is subject to frequent fire, habitat fragmentation, and protracted droughts linked to climatic change. Short-interval fire (SIF) is considered an inhibitor of recovery and cause of “type conversion” in chaparral, based on field studies of small extents and limited time periods. Sub-regional scale investigations based on remotely sensed data, however, suggest that SIF may explain little variance in postfire chaparral recovery. Drought may contribute to poor recovery or worsen the impact of repeated, short-interval fires. Previous studies have not shown whether drought reduces chaparral recovery significantly across the region, while variations in response among community types and climate zones are not well resolved. This research evaluates a regional pattern of chaparral recovery, based on series of Normalized Difference Vegetation Index (NDVI) from annual, June-solstice Landsat images (1984–2018). High resolution aerial images were used in validation and calibration. The main objectives were (1) to assess effects of fire-return interval and number of burns on chaparral recovery using 0.25 km2 sample plots (n = 528) which were paired and stratified for experimental control, and (2) to explain recovery variations across the region based on geospatial climate, vegetation, soil, terrain, and temporal drought metric data (seasonal precipitation, climatic water deficit (CWD), and Palmer Drought Severity Index (PDSI)) from 982 locations. Results suggest that SIF is most impactful in sites that burned three times within 25 years. More substantial effects were observed due to drought. In particular, ecotonal chaparral bounding the Colorado Desert is most subject to drought impact. We also highlight utility in landscape-scale predictors of drought impact on recovering chaparral, including Very Atmospherically Resistant Index (VARI).

Our study uses field training data, airborne LiDAR (Light Detection and Ranging), imaging spectroscopy, and a Convolutional Neural Network (CNN) classifier to identify individual tree species in a mixed conifer forest in the Southern Sierra Nevada Mountains. The remote sensing data was collected on the National Ecological Observatory Network (NEON) Airborne Observation Platform in 2017. We trained the classifier using existing field plot data, and an independently collected validation dataset which identifies trees location of the 7 dominant species (Pine, Fir, Cedar and Oak), including condition and ‘live’ or ‘dead’ status. The LiDAR canopy height model was used to identify tree crowns and imaging spectroscopy data around these crowns were created as image ‘labels’. These species level ‘labels’ were used to train, test and validate a CNN tree species classifier. Our method achieved greater than 63-90% accuracy for all field validated stems and worked best for large diameter trees. On an independent tree stem dataset, we performed a species-level logistic regression to study which cases the classifier works most and least effectively. Spatially, in the southern areas scattered Black Oak were present and tree species often were confused with shrub species or covered by adjacent conifer species. In the north where the upper elevation forest is dominated by red and white fir the classifier achieved greater than 96% accuracy for larger canopy trees, with accuracy degrading to about 59-70% when smaller trees are included in the model. There is also genus level mis-classification, particularly between Red and White Fir species. There was high tree mortality in this forest and the classifier was effective in detecting large tree mortality, which also varies as a function of species and size of trees. This work leverages newly developed ‘deep learning’ tools which have yet to be extensively applied to the remote detection of large trees or in plant biogeography generally. This research is a proof-of-concept for forest community ecologists who want accurate ‘tree species maps’ to study how plants are distributed across space. Generally, this method will be of interest to biogeographers or remote sensing scientists looking to apply novel classification methods to problems beyond remote tree species identification.