Monitoring the Impact of Wildfires on Tree Species with Deep Learning

One of the impacts of climate change is the difficulty of tree regrowth after wildfires over areas that traditionally were covered by certain tree species. Here a deep learning model is customized to classify land covers from four-band aerial imagery before and after wildfires to study the prolonged consequences of wildfires on tree species. The tree species labels are generated from manually delineated maps for five land cover classes: Conifer, Hardwood, Shrub, ReforestedTree and Barren land. With an accuracy of $92\%$ on the test split, the model is applied to three wildfires on data from 2009 to 2018. The model accurately delineates areas damaged by wildfires, changes in tree species and rebound of burned areas. The result shows clear evidence of wildfires impacting the local ecosystem and the outlined approach can help monitor reforested areas, observe changes in forest composition and track wildfire impact on tree species.

[1]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Monica G. Turner,et al.  Adapt to more wildfire in western North American forests as climate changes , 2017, Proceedings of the National Academy of Sciences.

[3]  M. Goulden,et al.  California forest die-off linked to multi-year deep soil drying in 2012–2015 drought , 2019, Nature Geoscience.

[4]  A. McGuire,et al.  Potential shifts in dominant forest cover in interior Alaska driven by variations in fire severity. , 2011, Ecological applications : a publication of the Ecological Society of America.

[5]  Maggi Kelly,et al.  Twentieth-century shifts in forest structure in California: Denser forests, smaller trees, and increased dominance of oaks , 2015, Proceedings of the National Academy of Sciences.

[6]  S. Dobrowski,et al.  Wildfires and climate change push low-elevation forests across a critical climate threshold for tree regeneration , 2019, Proceedings of the National Academy of Sciences.

[7]  Siyuan Lu,et al.  PAIRS AutoGeo: an Automated Machine Learning Framework for Massive Geospatial Data , 2020, 2020 IEEE International Conference on Big Data (Big Data).

[8]  Nathalie Pettorelli,et al.  The Normalized Difference Vegetation Index , 2014 .

[9]  Enrico Magli,et al.  DeepSUM: Deep Neural Network for Super-Resolution of Unregistered Multitemporal Images , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Geoffrey E. Hinton,et al.  When Does Label Smoothing Help? , 2019, NeurIPS.

[11]  Aditya Krishna Menon,et al.  Does label smoothing mitigate label noise? , 2020, ICML.

[12]  Nigel Hinds,et al.  PAIRS: A scalable geo-spatial data analytics platform , 2015, IEEE BigData.

[13]  Cristina Vega-García,et al.  Assessing Post-Fire Regeneration in a Mediterranean Mixed Forest Using Lidar Data and Artificial Neural Networks , 2013 .

[14]  M. Turner,et al.  Origins of abrupt change? Postfire subalpine conifer regeneration declines nonlinearly with warming and drying , 2019, Ecological Monographs.

[15]  Tony Chang,et al.  Chimera: A Multi-Task Recurrent Convolutional Neural Network for Forest Classification and Structural Estimation , 2019, Remote. Sens..

[16]  C. Nitschke,et al.  Frequent wildfires erode tree persistence and alter stand structure and initial composition of a fire‐tolerant sub‐alpine forest , 2017 .

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  K. Esler,et al.  Fire and life history affect the distribution of plant species in a biodiversity hotspot , 2019, Diversity and Distributions.

[19]  Hamid Hamraz,et al.  Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[20]  Zhihua Liu,et al.  Post-fire tree recruitment of a boreal larch forest in Northeast China , 2013 .

[21]  Janet Franklin,et al.  A Convolutional Neural Network Classifier Identifies Tree Species in Mixed-Conifer Forest from Hyperspectral Imagery , 2019, Remote. Sens..

[22]  Juha Hyyppä,et al.  Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging , 2017, Remote. Sens..

[23]  Wang Zhou,et al.  N-dimensional geospatial data and analytics for critical infrastructure risk assessment , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[24]  J. Overpeck,et al.  Climate-induced changes in forest disturbance and vegetation , 1990, Nature.

[25]  Verónica Vilaplana,et al.  Super-Resolution of Sentinel-2 Imagery Using Generative Adversarial Networks , 2020, Remote. Sens..