arXiv subjects

Michael Dorman

Publications and source records attributed to Michael Dorman.

3 recordsLinked to original sources

arXiv2026

Evaluating Semantic and Spatial Guidance for Foundation Model Segmentation of Small-Scale PV in Remote Sensing Imagery

Spatio-temporal PV data are essential for understanding adoption processes in off-grid regions, yet such data remain largely unavailable. Automated segmentation of remote sensing (RS) imagery offers a promising solution; yet, residential PV systems remain challenging targets because of their small size and sparse distribution, resulting in severe target-background imbalance. Vision-language foundation models (FMs) provide a data-efficient paradigm through prompt-based semantic and spatial guidance, but the relative contribution of different prompt types remains unclear. We systematically evaluate SAM3 for small-scale PV segmentation in RS imagery by comparing textual, geometric, and hybrid prompting, under varying supervision levels, training strategies, spatial resolutions, and imaging conditions. Multi-temporal aerial imagery from a large off-grid rural region serves as a study site, with findings validated across three additional datasets. Prompting strategy emerged as the dominant factor governing model behavior. Textual prompting consistently produced the lowest performance and showed the greatest sensitivity to supervision and imaging conditions. In contrast, spatial guidance substantially improved both segmentation accuracy and robustness. Hybrid prompting achieved the highest accuracy and stability, indicating that semantic and spatial guidance provide complementary information. Most performance gains were achieved with only a few hundred annotated samples, demonstrating strong data efficiency. Transfer learning had limited overall impact, with only modest improvements observed for textual prompting under limited supervision. Overall, our findings establish prompting strategy as a key determinant of SAM3 adaptation, robustness, and generalization, highlighting the potential of promptable FMs for scalable PV mapping in data-constrained off-grid regions.

cs.CV↗

arXiv2025

Beyond Leaders and Laggards: A Typology of Renewable Energy Adoption Trajectories with Evidence from Off-Grid Communities

Understanding the dynamics of renewable energy adoption is essential for designing strategies that accelerate its spread - an urgent priority for advancing climate goals and improving well-being, especially in off-grid regions facing energy poverty. This study introduces a time-series-based analytical framework that quantifies and classifies adoption behaviors of geographic entities within a region. A novel metric, the Adoption over Time Index (ATI), captures cumulative adoption intensity and identifies shifts in adoption trends, improving the ability to distinguish between fundamental adoption paths. By combining ATI with three key features found to be indicative of adoption dynamics, we define a typology of eight distinct paths, including two newly identified trajectories - the decelerating path and the declining moderate path. Applying this framework to a case study of an off-grid Bedouin population in southern Israel reveals that these retreating paths exist in substantial proportions. Identifying such trends is critical for addressing stagnation and preventing backsliding in the diffusion process. The leaping path, by contrast, was nearly absent. We also identify behavioral diversity within both front-runner and trailing groups. Differentiating among these groups can help tailor acceleration strategies. The analysis further reveals significant disparities in adoption levels across the region, with lagging clusters being widespread and overall adoption falling short of the region's potential.

econ.GN↗

arXiv2024

Performance of Human Annotators in Object Detection and Segmentation of Remotely Sensed Data

This study introduces a laboratory experiment designed to assess the influence of annotation strategies, levels of imbalanced data, and prior experience, on the performance of human annotators. The experiment focuses on labeling aerial imagery, using ArcGIS Pro tools, to detect and segment small-scale photovoltaic solar panels, selected as a case study for rectangular objects. The experiment is conducted using images with a pixel size of 0.15\textbf{$m$}, involving both expert and non-expert participants, across different setup strategies and target-background ratio datasets. Our findings indicate that human annotators generally perform more effectively in object detection than in segmentation tasks. A marked tendency to commit more Type II errors (False Negatives, i.e., undetected objects) than Type I errors (False Positives, i.e. falsely detecting objects that do not exist) was observed across all experimental setups and conditions, suggesting a consistent bias in detection and segmentation processes. Performance was better in tasks with higher target-background ratios (i.e., more objects per unit area). Prior experience did not significantly impact performance and may, in some cases, even lead to overestimation in segmentation. These results provide evidence that human annotators are relatively cautious and tend to identify objects only when they are confident about them, prioritizing underestimation over overestimation. Annotators' performance is also influenced by object scarcity, showing a decline in areas with extremely imbalanced datasets and a low ratio of target-to-background. These findings may enhance annotation strategies for remote sensing research while efficient human annotators are crucial in an era characterized by growing demands for high-quality training data to improve segmentation and detection models.

cs.CV↗