Browsing by Author "Ritz, Alison L."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Assessing the utility of NAIP digital aerial photogrammetric point clouds for estimating canopy height of managed loblolly pine plantations in the southeastern United States
    Ritz, Alison L.; Thomas, Valerie A.; Wynne, Randolph H.; Green, P. Corey; Schroeder, Todd A.; Albaugh, Timothy J.; Burkhart, Harold E.; Carter, David R.; Cook, Rachel L.; Campoe, Otavio C.; Rubilar, Rafael A.; Rakestraw, Jim (Elsevier, 2022-09)
    Remote sensing offers many advantages to supplement traditional, ground-based forest measurements, such as limiting time in the field and fast spatial coverage. Data from airborne laser scanning (lidar) have provided accurate estimates of forest height, where, and when available. However, lidar is expensive to collect, and wall-to-wall coverage in the United States is lacking. Recent studies have investigated whether point clouds derived from digital aerial photogrammetry (DAP) can supplement lidar data for estimating forest height due to DAP's lower costs and more frequent acquisitions. We estimated forest heights using point clouds derived from the National Agricultural Imagery Program (NAIP) DAP program in the United States to create a predicted height map for managed loblolly pine stands. For 534 plots in Virginia and North Carolina, with stand age ranging from 1 year to 42 years old, field-collected canopy heights were regressed against the 90th percentile of heights derived from NAIP point clouds. Model performance was good, with an R2 of 0.93 and an RMSE of 1.44 m. However, heights in recent heavily thinned stands were consistently underestimated, likely due to between-row shadowing leading to a poor photogrammetric solution. The model was applied to non-thinned evergreen areas in Virginia, North Carolina, and Tennessee to produce a multi-state 5 m x 5 m canopy height map. NAIP-derived point clouds are a viable means of predicting canopy height in southern pine stands that have not been thinned recently.
  • Thumbnail Image
    Mapping Tropical Forest Cover and Deforestation with Planet NICFI Satellite Images and Deep Learning in Mato Grosso State (Brazil) from 2015 to 2021
    Wagner, Fabien H.; Dalagnol, Ricardo; Silva-Junior, Celso H. L.; Carter, Griffin; Ritz, Alison L.; Hirye, Mayumi C. M.; Ometto, Jean P. H. B.; Saatchi, Sassan (MDPI, 2023-01-16)
    Monitoring changes in tree cover for assessment of deforestation is a premise for policies to reduce carbon emission in the tropics. Here, a U-net deep learning model was used to map monthly tropical tree cover in the Brazilian state of Mato Grosso between 2015 and 2021 using 5 m spatial resolution Planet NICFI satellite images. The accuracy of the tree cover model was extremely high, with an F1-score >0.98, further confirmed by an independent LiDAR validation showing that 95% of tree cover pixels had a height >5 m while 98% of non-tree cover pixels had a height <5 m. The biannual map of deforestation was then built from the monthly tree cover map. The deforestation map showed relatively consistent agreement with the official deforestation map from Brazil (67.2%) but deviated significantly from Global Forest Change (GFC)’s year of forest loss, showing that our product is closest to the product made by visual interpretation. Finally, we estimated that 14.8% of Mato Grosso’s total area had undergone clear-cut logging between 2015 and 2021, and that deforestation was increasing, with December 2021, the last date, being the highest. High-resolution imagery from Planet NICFI in conjunction with deep learning techniques can significantly improve the mapping of deforestation extent in tropical regions.