Biology subjects

McCord, S. E.

Publications and source records attributed to McCord, S. E..

4 recordsLinked to original sources

bioRxiv2025

A 0.6-meter resolution canopy height and structure model for the contiguous United States

Above-ground vertical structure is a critical variable for ecosystem monitoring, carbon accounting, and land management. However, the high cost and limited coverage of airborne lidar hinder its widespread application. To address this, we developed NAIP-CHM, a 0.6-meter resolution canopy height and structure model (CHM) covering the contiguous United States, derived from National Agriculture Imagery Program (NAIP) aerial imagery. Unlike forestry-specific models that exclude human-made features, NAIP-CHM characterizes the full vertical structure of the landscape including vegetation, buildings, and infrastructure. We utilized a U-Net convolutional neural network with attention mechanisms and environmental conditioning, training and validating the model with a peer-reviewed, publicly available dataset of 22.8 million co-registered NAIP imagery and lidar-derived CHM pairs, with stratified sampling to ensure robustness in open-canopy ecosystems. The model achieved a pixel-wise root mean square error (RMSE) of 2.28 meters and an r2 of 0.87. Forested sites alone produced an r2 of 0.82 and RMSE of 3.82 meters. We provide the dataset, source code, and cloud-based tools to enable broad application without requiring specialized computational resources.

ecology↗

bioRxiv2025

Estimating rangeland fractional cover and canopy gap size class with Sentinel-2 imagery

Rangelands are extensive ecosystems, providing important ecosystem services while undergoing continuous change. As a result, improved monitoring technologies can help better characterize vegetation change. Satellite remote sensing has proven effective in this regard, tracking vegetation dynamics at broad and fine scales. We leveraged the spatial, spectral, and temporal resolution of Sentinel-2 satellites to estimate fractional cover and canopy gap across rangelands of the western United States. We produced annual, 10 m spatial resolution estimates of fractional cover and canopy gap size class for years 2018 to 2024. Fractional cover estimates include that of common plant functional types (annual forb and grass, bareground, littler, perennial forb and grass, shrub, tree) and select genera (including invasive annual grass species, pinyon-juniper species, and sagebrush species); canopy gap size classes include gap sizes 25 to 50, 51 to 100, 101 to 200, and greater than 200 cm. We make these data available as Cloud Optimized GeoTIFFs, organized as 75x75 km tiles covering the 17 western states of the United States.

ecology↗

bioRxiv2024

Canopy height model and NAIP imagery pairs across CONUS

Canopy height models (CHM) provide detailed environmental vertical structure information and are an important indicator and input for ecological and geospatial applications. These models are often spatiotemporally inconsistent, necessitating additional modeling to scale them in space and time. Yet, such scaling is hindered by a lack of spatially diverse data. To address this, we use United States Geological Survey 3D Elevation Program lidar data to produce 22,796,764 one meter resolution CHM chips, stratified across the dominant land covers of the conterminous United States. For each CHM, we pair a matching time-aligned aerial image from the United States Department of Agriculture National Agriculture Imagery Program. This dataset can be used to train models for large scale CHM production.

ecology↗

bioRxiv2020

Improving Landsat predictions of rangeland fractional cover with multitask learning and uncertainty

O_LIOperational satellite remote sensing products are transforming rangeland management and science. Advancements in computation, data storage, and processing have removed barriers that previously blocked or hindered the development and use of remote sensing products. When combined with local data and knowledge, remote sensing products can inform decision making at multiple scales. C_LIO_LIWe used temporal convolutional networks to produce a fractional cover product that spans western United States rangelands. We trained the model with 52,012 on-the-ground vegetation plots to simultaneously predict fractional cover for annual forbs and grasses, perennial forbs and grasses, shrubs, trees, litter, and bare ground. To assist interpretation and to provide a measure of prediction confidence, we also produced spatiotemporal-explicit, pixel-level estimates of uncertainty. We evaluated the model with 5,780 on-the-ground vegetation plots removed from the training data. C_LIO_LIModel evaluation averaged 6.3% mean absolute error and 9.6% root mean squared error. Evaluation with additional datasets that were not part of the training dataset, and that varied in geographic range, method of collection, scope, and size, revealed similar metrics. Model performance increased across all functional groups compared to the previously produced fractional product. C_LIO_LIThe advancements achieved with the new rangeland fractional cover product expand the management toolbox with improved predictions of fractional cover and pixel-level uncertainty. The new product is available on the Rangeland Analysis Platform (https://rangelands.app/), an interactive web application that tracks rangeland vegetation through time. This product is intended to be used alongside local on-the-ground data, expert knowledge, land use history, scientific literature, and other sources of information when making interpretations. When being used to inform decision-making, remotely sensed products should be evaluated and utilized according to the context of the decision and not be used in isolation. C_LI

ecology↗