Francis Daniel Fosmire O'Neill

Mr. Francis Daniel Fosmire O'Neill

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 February 2024 in Sensors
Verified
Journal Article
Open access
PDF file
KLKristofer Lasko
Kristofer Lasko
Francis Daniel Fosmire O'NeillFrancis Daniel Fosmire O'Neill
Francis Daniel Fosmire O'Neill
ESElena Sava
Elena Sava
A near-global framework for automated training data generation and land cover classification using shallow machine learning with low-density time series imagery does not exist. This study presents a methodology to map nine-class, six-class, and five-class land cover using two dates (winter and non-winter) of a Sentinel-2 granule across seven international sites. The approach uses a series of spectral, textural, and distance decision functions combined with modified ancillary layers (such as global impervious surface and global tree cover) to create binary masks from which to generate a balanced set of training data applied to a random forest classifier. For the land cover masks, stepwise threshold adjustments were applied to reflectance, spectral index values, and Euclidean distance layers, with 62 combinations evaluated. Global (all seven scenes) and regional (arid, tropics, and temperate) adaptive thresholds were computed. An annual 95th and 5th percentile NDVI composite was used to provide temporal corrections to the decision functions, and these corrections were compared against the original model. The accuracy assessment found that the regional adaptive thresholds for both the two-date land cover and the temporally corrected land cover could accurately map land cover type within nine-class (68.4% vs. 73.1%), six-class (79.8% vs. 82.8%), and five-class (80.1% vs. 85.1%) schemes. Lastly, the five-class and six-class models were compared with a manually labeled deep learning model (Esri), where they performed with similar accuracies (five classes: Esri 80.0 ± 3.4%, region corrected 85.1 ± 2.9%). The results highlight not only performance in line with an intensive deep learning approach, but also that reasonably accurate models can be created without a full annual time series of imagery.

30 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
KLKristofer Lasko
Kristofer Lasko
Francis Daniel Fosmire O'NeillFrancis Daniel Fosmire O'Neill
Francis Daniel Fosmire O'Neill
This study presents an automated methodology to generate training data to map up-to-date artificial impervious surface (AIS) extent maps using two dates (winter and nonwinter) of a Sentinel-2 granule across six international sites (Egypt, India, Qatar, U.K., Eastern USA, and Western USA). It uses a series of spectral, textural, and distance decision functions combined with an outdated AIS layer to create nontarget and target binary masks from which to generate a balanced set of training data applied to a random forest classifier. Two outdated global AIS layers (GMIS-2010 and GISA-2016) were evaluated within the framework to create AIS maps from more recent years (e.g., 2020). For the decision functions, stepwise threshold adjustments applied to normalized difference vegetation index (NDVI) and Euclidean distance layers were evaluated on the binary masks (low-density AIS, high-density AIS, and nontarget land covers) with 729 permutations and 115 permutations for global impervious surface area (GISA) and global manmade impervious surface (GMIS), respectively. The optimal thresholds were determined globally (all six scenes), individually (scene) and grouped by climate for adaptive thresholds. The accuracy assessment found both GMIS-output and GISA-output with global thresholds can accurately map current AIS with 86.9% (±1.7%) (GISA) and 82.7% (±2.3%) (GMIS) accuracy. Adaptive climate thresholds yielded slightly higher accuracies for temperate, tropics, and arid scenes. A novel beach bare ground sampling mask and annual NDVI standard deviation were also evaluated for performance and improved the accuracy in 5/6 sites. Lastly, the global GISA output was compared with a manually labeled deep learning model (Esri) with slightly lower overall accuracy (86.9% vs 88.6%).

13 August 2025 in Land
Verified
Journal Article
Open access
PDF file
Francis Daniel Fosmire O'NeillFrancis Daniel Fosmire O'Neill
Francis Daniel Fosmire O'Neill
NWNicole Marie Wayant
Nicole Marie Wayant
SBSarah J. Becker
Sarah J. Becker
We compare several methods for predicting future built-up land cover using only a short yearly time series of satellite-derived binary urban maps. Existing methods of built-up expansion forecasting often rely on ancillary datasets such as utility networks, distance to transportation nodes, and population density maps, along with remotely sensed aerial or satellite imagery. Such ancillary datasets are not always available and lack the temporal density of satellite imagery. Moreover, existing work often focuses on quantifying the expected volume of built-up expansion, rather than predicting where exactly that expansion will occur. To address these gaps, we evaluate six methods for the creation of prediction maps showing expected areas of future built-up expansion, using yearly built/not-built maps derived from Sentinel-2 imagery as inputs: Cellular Automata, logistic regression, Support Vector Machines, Random Forests, Convolutional Neural Networks (CNNs), and CNNs with the addition of long short-term memory (ConvLSTM). Of these six, we find CNNs to be the best-performing method, with an average Cohen’s kappa score of 0.73 across nine study sites in the continental United States.