Kyle Bradbury

Automatic solar photovoltaic panel detection in satellite imagery

The quantity of rooftop solar photovoltaic (PV) installations has grown rapidly in the US in recent years. There is a strong interest among decision makers in obtaining high quality information about rooftop PV, such as the locations, power capacity, and energy production of existing rooftop PV installations. Solar PV installations are typically connected directly to local power distribution grids, and therefore it is important for the reliable integration of solar energy to have information at high geospatial resolutions: by county, zip code, or even by neighborhood. Unfortunately, traditional means of obtaining this information, such as surveys and utility interconnection filings, are limited in availability and geospatial resolution. In this work a new approach is investigated where a computer vision algorithm is used to detect rooftop PV installations in high resolution color satellite imagery and aerial photography. It may then be possible to use the identified PV images to estimate power capacity and energy production for each array of panels, yielding a fast, scalable, and inexpensive method to obtain rooftop PV estimates for regions of any size. The aim of this work is to investigate the feasibility of the first step of the proposed approach: detecting rooftop PV in satellite imagery. Towards this goal, a collection of satellite rooftop images is used to develop and evaluate a detection algorithm. The results show excellent detection performance on the testing dataset and that, with further development, the proposed approach may be an effective solution for fast and scalable rooftop PV information collection.

Distributed solar photovoltaic array location and extent dataset for remote sensing object identification

Earth-observing remote sensing data, including aerial photography and satellite imagery, offer a snapshot of the world from which we can learn about the state of natural resources and the built environment. The components of energy systems that are visible from above can be automatically assessed with these remote sensing data when processed with machine learning methods. Here, we focus on the information gap in distributed solar photovoltaic (PV) arrays, of which there is limited public data on solar PV deployments at small geographic scales. We created a dataset of solar PV arrays to initiate and develop the process of automatically identifying solar PV locations using remote sensing imagery. This dataset contains the geospatial coordinates and border vertices for over 19,000 solar panels across 601 high-resolution images from four cities in California. Dataset applications include training object detection and other machine learning algorithms that use remote sensing imagery, developing specific algorithms for predictive detection of distributed PV systems, estimating installed PV capacity, and analysis of the socioeconomic correlates of PV deployment.

A deep convolutional neural network and a random forest classifier for solar photovoltaic array detection in aerial imagery

Power generation from distributed solar photovoltaic PV arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small geo-spatial regions (e.g., counties, cities, or even smaller regions). Unfortunately, existing sources of such information are dispersed, limited in geospatial resolution, and otherwise incomplete or publically unavailable. As result, we recently proposed a new approach for collecting such distributed PV information that relies on computer algorithms to automatically detect PV arrays in high resolution aerial imagery [1], Here we build on this work by investigating two machine learning algorithms for PV array detection: a Random Forest classifier (RF) [2] and a deep convolutional neural network (CNN) [3]. We use the RF algorithm as a benchmark, or baseline, for comparison with a CNN model. The two models are developed and tested using a large collection of publicly available [4] aerial imagery, covering 135 km2, and including over 2,700 manually annotated distributed PV array locations. The results indicate that the CNN substantially improves over the RF. The CNN is capable of excellent performance, detecting nearly 80% of true panels with a precision measure of 72%.

A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery

In this work we consider the problem of developing algorithms that automatically identify small-scale solar photovoltaic arrays in high resolution aerial imagery. Such algorithms potentially offer a faster and cheaper solution to collecting small-scale photovoltaic (PV) information, such as their location, capacity, and the energy they produce. Here we build on previous algorithmic work by employing convolutional neural networks (CNNs), which have recently yielded major improvements in other image object recognition problems. We propose a CNN architecture for our recognition problem and then measure its detection performance on the same (publicly available) dataset that was used in previous publications. The results indicate that the CNN yields substantial performance improvements over previous results. We also investigate the recently popular approach of pre-training for CNNs.

Performance comparison framework for energy disaggregation systems

Energy disaggregation algorithms decompose building-level energy data into device-level information. We conduct a head-to-head comparison of energy disaggregation techniques across multiple metrics and data sets. Our framework for analyzing the performance of a complete energy disaggregation system includes event detection, classification, and power assignment. We use receiver operating characteristics (ROCs) to evaluate event detection performance, and we introduce a technique to evaluate device-level event detection. We use confusion matrices to compare classification performance across several classifiers, and evaluate the resulting power assignments using several assignment metrics that are commonly used in the literature to demonstrate the varying strengths of the techniques that were considered. We apply this framework to several publicly available datasets and demonstrate how system performance varies with sampling frequency and the inclusion of reactive power. Our results suggest that (1) disaggregation performance varies considerably across data sets (2) increased data sampling rate improves disaggregation performance, and (3) additional features such as reactive power yields disaggregation performance improvements.

Estimating the electricity generation capacity of solar photovoltaic arrays using only color aerial imagery

In this work, the problem of developing algorithms that automatically infer information about small-scale solar photovoltaic (PV) arrays in high resolution aerial imagery is considered. Such algorithms potentially offer a faster and cheaper solution to collecting small-scale PV information, such as their location and capacity. Existing work on this topic has focused on the automatic identification and annotation of panels in the aerial imagery. We extend this work by showing that we can reliably infer the capacity of PV arrays given only (i) color aerial imagery and (ii) a precise annotation of the array location. First we demonstrate that accurate capacity estimates can be obtained simply by estimating the visible surface area of a solar array, regardless of tilt. We then build a more sophisticated model where we use additional image information related to the properties of the solar array to further improve the capacity predictions. We use a dataset of 362 manually annotated Google Earth images of solar arrays with known electricity generation capacity in North Carolina to measure the predictive performance of our models.

Image features for pixel-wise detection of solar photovoltaic arrays in aerial imagery using a random forest classifier

Power generation from distributed solar photovoltaic (PV) arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small geo-spatial regions (e.g., counties, cities, or even smaller regions). Unfortunately, existing sources of such information are dispersed, limited in geospatial resolution, and otherwise incomplete or publically unavailable. As result, we recently proposed a new approach for collecting such distributed PV information that relies on computer algorithms to automatically detect PV arrays in high resolution aerial imagery [1], Here, we build on this work by investigating a detection algorithm based on a Random Forest (RF) classifier, and we consider its detection performance using several different sets of image features. The proposed method is developed and tested using a very large collection of publicly available [2] aerial imagery, covering 112.5 km2 of surface area, with 2,328 manually annotated PV array locations. The results indicate that a combination of local color and texture (using the popular texton feature) features yield the best detection performance.

Real-time Gaussian Markov random-field-based ground tracking for ground penetrating radar data

Current ground penetrating radar algorithms for landmine detection require accurate estimates of the location of the air/ground interface to maintain high levels of performance. However, the presence of surface clutter, natural soil roughness, and antenna motion lead to uncertainty in these estimates. Previous work on improving estimates of the location of the air/ground interface have focused on one-dimensional filtering techniques to localize the air/ground interface. In this work, we propose an algorithm for interface localization using a 2- D Gaussian Markov random field (GMRF). The GMRF provides a statistical model of the surface structure, which enables the application of statistical optimization techniques. In this work, the ground location is inferred using iterated conditional modes (ICM) optimization which maximizes the conditional pseudo-likelihood of the GMRF at a point, conditioned on its neighbors. To illustrate the efficacy of the proposed interface localization approach, pre-screener performance with and without the proposed ground localization algorithm is compared. We show that accurate localization of the air/ground interface provides the potential for future performance improvements.