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

A 10-m national-scale map of ground-mounted photovoltaic power stations in China of 2020

We provide a remote sensing derived dataset for large-scale ground-mounted photovoltaic (PV) power stations in China of 2020, which has high spatial resolution of 10 meters. The dataset is based on the Google Earth Engine (GEE) cloud computing platform via random forest classifier and active learning strategy. Specifically, ground samples are carefully collected across China via both field survey and visual interpretation. Afterwards, spectral and texture features are calculated from publicly available Sentinel-2 imagery. Meanwhile, topographic features consisting of slope and aspect that are sensitive to PV locations are also included, aiming to construct a multi-dimensional and discriminative feature space. Finally, the trained random forest model is adopted to predict PV power stations of China parallelly on GEE. Technical validation has been carefully performed across China which achieved a satisfactory accuracy over 89%. Above all, as the first publicly released 10-m national-scale distribution dataset of China's ground-mounted PV power stations, it can provide data references for relevant researchers in fields such as energy, land, remote sensing and environmental sciences.

Weakly Supervised Solar Panel Mapping via Uncertainty Adjusted Label Transition in Aerial Images

This paper proposes a novel uncertainty-adjusted label transition (UALT) method for weakly supervised solar panel mapping (WS-SPM) in aerial Images. In weakly supervised learning (WSL), the noisy nature of pseudo labels (PLs) often leads to poor model performance. To address this problem, we formulate the task as a label-noise learning problem and build a statistically consistent mapping model by estimating the instance-dependent transition matrix (IDTM). We propose to estimate the IDTM with a parameterized label transition network describing the relationship between the latent clean labels and noisy PLs. A trace regularizer is employed to impose constraints on the form of IDTM for its stability. To further reduce the estimation difficulty of IDTM, we incorporate uncertainty estimation to first improve the accuracy of noisy dataset distillation and then mitigate the negative impacts of falsely distilled examples with an uncertainty-adjusted re-weighting strategy. Extensive experiments and ablation studies on two challenging aerial data sets support the validity of the proposed UALT.

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

Effectively supporting the United Nations' Sustainable Development Goals requires reliable, substantial, and timely data. For solar panel installation monitoring, where accurate reporting is crucial in tracking green energy production and sustainable energy access, official and regulated documentation remains inconsistent. Reports of solar panel installations have been supplemented with object detection models developed and used on openly available aerial imagery, a type of imagery collected by aircraft or drones and limited by cost, extent, and geographic location. We address these limitations by providing a solar panel dataset derived from 31 cm resolution satellite imagery to support rapid and accurate detection at regional and international scales. We also include complementary satellite imagery at 15.5 cm resolution with the aim of further improving solar panel detection accuracy. The dataset of 2,542 annotated solar panels may be used independently to develop detection models uniquely applicable to satellite imagery or in conjunction with existing solar panel aerial imagery datasets to support generalized detection models.

A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata

Photovoltaic (PV) energy generation plays a crucial role in the energy transition. Small-scale, rooftop PV installations are deployed at an unprecedented pace, and their safe integration into the grid requires up-to-date, high-quality information. Overhead imagery is increasingly being used to improve the knowledge of rooftop PV installations with machine learning models capable of automatically mapping these installations. However, these models cannot be reliably transferred from one region or imagery source to another without incurring a decrease in accuracy. To address this issue, known as distribution shift, and foster the development of PV array mapping pipelines, we propose a dataset containing aerial images, segmentation masks, and installation metadata (i.e., technical characteristics). We provide installation metadata for more than 28000 installations. We supply ground truth segmentation masks for 13000 installations, including 7000 with annotations for two different image providers. Finally, we provide installation metadata that matches the annotation for more than 8000 installations. Dataset applications include end-to-end PV registry construction, robust PV installations mapping, and analysis of crowdsourced datasets.

A Review on Machine Learning Applications for Solar Plants

A solar plant system has complex nonlinear dynamics with uncertainties due to variations in system parameters and insolation. Thereby, it is difficult to approximate these complex dynamics with conventional algorithms whereas Machine Learning (ML) methods yield the essential performance required. ML models are key units in recent sensor systems for solar plant design, forecasting, maintenance, and control to provide the best safety, reliability, robustness, and performance as compared to classical methods which are usually employed in the hardware and software of solar plants. Considering this, the goal of our paper is to explore and analyze ML technologies and their advantages and shortcomings as compared to classical methods for the design, forecasting, maintenance, and control of solar plants. In contrast with other review articles, our research briefly summarizes our intelligent, self-adaptive models for sizing, forecasting, maintenance, and control of a solar plant; sets benchmarks for performance comparison of the reviewed ML models for a solar plant's system; proposes a simple but effective integration scheme of an ML sensor solar plant system's implementation and outlines its future digital transformation into a smart solar plant based on the integrated cutting-edge technologies; and estimates the impact of ML technologies based on the proposed scheme on a solar plant value chain.

Solar array placement, electricity generation, and cropland displacement across California's Central Valley

Understanding agriculturally co-located solar photovoltaic (PV) installation capacity, practices, and preferences is imperative to foster a future where solar power and agriculture co-exist with limited impacts on food production. Crops and PV panels are often co-located as they have similar ideal conditions for maximum yield. The recent boom in solar photovoltaics is displacing a significant amount of cropland. The literature on agriculturally co-located PV array installations lacks important spatiotemporal details that could help inform future array installations and improve associated policies and incentive programs. This study used imagery from the National Agriculture Imagery Program for object-based analysis (within eCognition Developer), and from Landsat 5 TM, 7 ETM+ and 8 OLI for temporal analysis (using LandTrendr) to identify and characterize non-residential ground-mounted PV arrays in California's Central Valley installed between 2008 and 2018. This dataset includes over 210,000 individually identified panels grouped by mount and installation year into 1006 PV arrays (69% are agriculturally co-located). The most common type of mounting system is fixed-axis, and individual co-located systems tend to be small (0.34 MW). There were fewer single-axis tracking arrays, although the average capacity per system is nearly four times higher (1.20 MW). In total, the mapped arrays accounted for 3.6 GW of capacity and generated a cumulative of 32,700 GWh within the Central Valley during the study period. For the 694 identified agriculturally co-located arrays (2.1 GW), significantly sub-optimal installation practices were observed in the spacing and spatial field placement of the arrays. In terms of crop conversion preferences, commodity crops (pastureland) dominated the total cumulative area converted although specialty crops (orchards) also contributed to a large number of solar installations on cropland. These results provide important details of current PV placement practices; understanding these can help to inform future practices and guide future regulations that might promote solar installations while preserving agricultural production.

Dataset for Detecting the Electrical Behavior of Photovoltaic Panels from RGB Images

The dynamic reconfiguration and maximum power point tracking in large-scale photovoltaic (PV) systems require a large number of voltage and current sensors. In particular, the reconfiguration process requires a pair of voltage/current sensors for each panel, which introduces costs, increases size and reduces the reliability of the installation. A suitable solution for reducing the number of sensors is to adopt image-based solutions to estimate the electrical characteristics of the PV panels, but the lack of reliable data with large diversity of irradiance and shading conditions is a major problem in this topic. Therefore, this paper presents a dataset correlating RGB images and electrical data of PV panels with different irradiance and shading conditions; moreover, the dataset also provides complementary weather data and additional image characteristics to support the training of estimation models. In particular, the dataset was designed to support the design of image-based estimators of electrical data, which could be used to replace large arrays of sensors. The dataset was captured during 70 days distributed between 2020 and 2021, generating 5211 images and registers. The paper also describes the measurement platform used to collect the data, which will help to replicate the experiments in different geographical locations.

RID—Roof Information Dataset for Computer Vision-Based Photovoltaic Potential Assessment

Computer vision has great potential to accelerate the global scale of photovoltaic potential analysis by extracting detailed roof information from high-resolution aerial images, but the lack of existing deep learning datasets is a major barrier. Therefore, we present the Roof Information Dataset for semantic segmentation of roof segments and roof superstructures. We assessed the label quality of initial roof superstructure annotations by conducting an annotation experiment and identified annotator agreements of 0.15–0.70 mean intersection over union, depending on the class. We discuss associated the implications on the training and evaluation of two convolutional neural networks and found that the quality of the prediction behaved similarly to the annotator agreement for most classes. The class photovoltaic module was predicted to be best with a class-specific mean intersection over union of 0.69. By providing the datasets in initial and reviewed versions, we promote a data-centric approach for the semantic segmentation of roof information. Finally, we conducted a photovoltaic potential analysis case study and demonstrated the high impact of roof superstructures as well as the viability of the computer vision approach to increase accuracy. While this paper’s primary use case was roof information extraction for photovoltaic potential analysis, its implications can be transferred to other computer vision applications in remote sensing and beyond.

Utilizing Geospatial Data for Assessing Energy Security: Mapping Small Solar Home Systems Using Unmanned Aerial Vehicles and Deep Learning

Solar home systems (SHS), a cost-effective solution for rural communities far from the grid in developing countries, are small solar panels and associated equipment that provides power to a single household. A crucial resource for targeting further investment of public and private resources, as well as tracking the progress of universal electrification goals, is shared access to high-quality data on individual SHS installations including information such as location and power capacity. Though recent studies utilizing satellite imagery and machine learning to detect solar panels have emerged, they struggle to accurately locate many SHS due to limited image resolution (some small solar panels only occupy several pixels in satellite imagery). In this work, we explore the viability and cost-performance tradeoff of using automatic SHS detection on unmanned aerial vehicle (UAV) imagery as an alternative to satellite imagery. More specifically, we explore three questions: (i) what is the detection performance of SHS using drone imagery; (ii) how expensive is the drone data collection, compared to satellite imagery; and (iii) how well does drone-based SHS detection perform in real-world scenarios? To examine these questions, we collect and publicly-release a dataset of high-resolution drone imagery encompassing SHS imaged under a variety of real-world conditions and use this dataset and a dataset of imagery from Rwanda to evaluate the capabilities of deep learning models to recognize SHS, including those that are too small to be reliably recognized in satellite imagery. The results suggest that UAV imagery may be a viable alternative to identify very small SHS from perspectives of both detection accuracy and financial costs of data collection. UAV-based data collection may be a practical option for supporting electricity access planning strategies for achieving sustainable development goals and for monitoring the progress towards those goals.

Texture Is Important in Improving the Accuracy of Mapping Photovoltaic Power Plants: A Case Study of Ningxia Autonomous Region, China

Photovoltaic (PV) technology is becoming more popular due to climate change because it allows for replacing fossil-fuel power generation to reduce greenhouse gas emissions. Consequently, many countries have been attempting to generate electricity through PV power plants over the last decade. Monitoring PV power plants through satellite imagery, machine learning models, and cloud-based computing systems that may ensure rapid and precise locating with current status on a regional basis are crucial for environmental impact assessment and policy formulation. The effect of fusion of the spectral, textural with different neighbor sizes, and topographic features that may improve machine learning accuracy has not been evaluated yet in PV power plants’ mapping. This study mapped PV power plants using a random forest (RF) model on the Google Earth Engine (GEE) platform. We combined textural features calculated from the Grey Level Co-occurrence Matrix (GLCM), reflectance, thermal spectral features, and Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and Modified Normalized Difference Water Index (MNDWI) from Landsat-8 imagery and elevation, slope, and aspect from Shuttle Radar Topography Mission (SRTM) as input variables. We found that the textural features from GLCM prominent enhance the accuracy of the random forest model in identifying PV power plants where a neighbor size of 30 pixels showed the best model performance. The addition of texture features can improve model accuracy from a Kappa statistic of 0.904 ± 0.05 to 0.938 ± 0.04 and overall accuracy of 97.45 ± 0.14% to 98.32 ± 0.11%. The topographic and thermal features contribute a slight improvement in modeling. This study extends the knowledge of the effect of various variables in identifying PV power plants from remote sensing data. The texture characteristics of PV power plants at different spatial resolutions deserve attention. The findings of our study have great significance for collecting the geographic information of PV power plants and evaluating their environmental impact.

Current site planning of medium to large solar power systems accelerates the loss of the remaining semi-natural and agricultural habitats

The global transition to renewable energy sources has accelerated to mitigate the effects of global climate change. Sudden increases in solar power facilities have caused the physical destruction of wildlife habitats, thereby resulting in the decline of biodiversity and ecosystem functions. However, previous assessments have been based on the environmental impact of large solar photovoltaics (PVs). The impact of medium-sized PV facilities (0.5-10 MW), which can alter small habitat patches through the accumulation of installations has not been assessed. Here, we quantified the amount of habitat loss directly related to the construction of PV facilities with different size classes and estimated their siting attributes using construction patterns in Japan and South Korea. We identified that a comparable amount of natural and semi-natural habitats were lost due to the recent installation of medium solar facilities (approximately 66.36 and 85.73% of the overall loss in Japan and South Korea, respectively). Compared to large solar PVs, medium PV installations resulted in a higher area loss of semi-natural habitats, including secondary/planted forests, secondary/artificial grasslands, and agricultural lands. The siting attributes of medium and large solar PV facilities indicated a preference for cost-based site selection rather than prioritizing habitat protection for biodiversity conservation. Moreover, even conservation areas were developed when economic and topological conditions were suitable for energy production. Our simulations indicate that increasing the construction of PVs in urban areas could help reduce the loss of natural and semi-natural habitats. To improve the renewable energy share while mitigating the impacts on biodiversity, our results stress the need for a proactive assessment to enforce sustainable site-selection criteria for solar PVs in renewable energy initiatives. The revised criteria should consider the cumulative impacts of varied size classes of solar power facilities, including medium PVs, and the diverse aspects of the ecological value of natural habitats.

Towards Scalable Economic Photovoltaic Potential Analysis Using Aerial Images and Deep Learning

Roof-mounted photovoltaic systems play a critical role in the global transition to renewable energy generation. An analysis of roof photovoltaic potential is an important tool for supporting decision-making and for accelerating new installations. State of the art uses 3D data to conduct potential analyses with high spatial resolution, limiting the study area to places with available 3D data. Recent advances in deep learning allow the required roof information from aerial images to be extracted. Furthermore, most publications consider the technical photovoltaic potential, and only a few publications determine the photovoltaic economic potential. Therefore, this paper extends state of the art by proposing and applying a methodology for scalable economic photovoltaic potential analysis using aerial images and deep learning. Two convolutional neural networks are trained for semantic segmentation of roof segments and superstructures and achieve an Intersection over Union values of 0.84 and 0.64, respectively. We calculated the internal rate of return of each roof segment for 71 buildings in a small study area. A comparison of this paper’s methodology with a 3D-based analysis discusses its benefits and disadvantages. The proposed methodology uses only publicly available data and is potentially scalable to the global level. However, this poses a variety of research challenges and opportunities, which are summarized with a focus on the application of deep learning, economic photovoltaic potential analysis, and energy system analysis.

Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation

Brazil is a tropical country with continental dimensions and abundant solar resources that are still underutilized. However, solar energy is one of the most promising renewable sources in the country. The proper inspection of Photovoltaic (PV) solar plants is an issue of great interest for the Brazilian territory’s energy management agency, and advances in computer vision and deep learning allow automatic, periodic, and low-cost monitoring. The present research aims to identify PV solar plants in Brazil using semantic segmentation and a mosaicking approach for large image classification. We compared four architectures (U-net, DeepLabv3+, Pyramid Scene Parsing Network, and Feature Pyramid Network) with four backbones (Efficient-net-b0, Efficient-net-b7, ResNet-50, and ResNet-101). For mosaicking, we evaluated a sliding window with overlapping pixels using different stride values (8, 16, 32, 64, 128, and 256). We found that: (1) the models presented similar results, showing that the most relevant approach is to acquire high-quality labels rather than models in many scenarios; (2) U-net presented slightly better metrics, and the best configuration was U-net with the Efficient-net-b7 encoder (98% overall accuracy, 91% IoU, and 95% F-score); (3) mosaicking progressively increases results (precision-recall and receiver operating characteristic area under the curve) when decreasing the stride value, at the cost of a higher computational cost. The high trends of solar energy growth in Brazil require rapid mapping, and the proposed study provides a promising approach.

Decay radius of climate decision for solar panels in the city of Fresno, USA

To design incentives towards achieving climate mitigation targets, it is important to understand the mechanisms that affect individual climate decisions such as solar panel installation. It has been shown that peer effects are important in determining the uptake and spread of household photovoltaic installations. Due to coarse geographical data, it remains unclear whether this effect is generated through geographical proximity or within groups exhibiting similar characteristics. Here we show that geographical proximity is the most important predictor of solar panel implementation, and that peer effects diminish with distance. Using satellite imagery, we build a unique geo-located dataset for the city of Fresno to specify the importance of small distances. Employing machine learning techniques, we find the density of solar panels within the shortest measured radius of an address is the most important factor in determining the likelihood of that address having a solar panel. The importance of geographical proximity decreases with distance following an exponential curve with a decay radius of 210 meters. The dependence is slightly more pronounced in low-income groups. These findings support the model of distance-related social diffusion, and suggest priority should be given to seeding panels in areas where few exist.

Combined Multi-Layer Feature Fusion and Edge Detection Method for Distributed Photovoltaic Power Station Identification

Distributed photovoltaic power stations are an effective way to develop and utilize solar energy resources. Using high-resolution remote sensing images to obtain the locations, distribution, and areas of distributed photovoltaic power stations over a large region is important to energy companies, government departments, and investors. In this paper, a deep convolutional neural network was used to extract distributed photovoltaic power stations from high-resolution remote sensing images automatically, accurately, and efficiently. Based on a semantic segmentation model with an encoder-decoder structure, a gated fusion module was introduced to address the problem that small photovoltaic panels are difficult to identify. Further, to solve the problems of blurred edges in the segmentation results and that adjacent photovoltaic panels can easily be adhered, this work combines an edge detection network and a semantic segmentation network for multi-task learning to extract the boundaries of photovoltaic panels in a refined manner. Comparative experiments conducted on the Duke California Solar Array data set and a self-constructed Shanghai Distributed Photovoltaic Power Station data set show that, compared with SegNet, LinkNet, UNet, and FPN, the proposed method obtained the highest identification accuracy on both data sets, and its F1-scores reached 84.79% and 94.03%, respectively. These results indicate that effectively combining multi-layer features with a gated fusion module and introducing an edge detection network to refine the segmentation improves the accuracy of distributed photovoltaic power station identification.

Alpha 1 Antitrypsin is an Inhibitor of the SARS-CoV-2-Priming Protease TMPRSS2

Host proteases have been suggested to be crucial for dissemination of MERS, SARS-CoV, and SARS-CoV-2 coronaviruses, but the relative contribution of membrane versus intracellular proteases remains controversial. Transmembrane serine protease 2 (TMPRSS2) is regarded as one of the main proteases implicated in the coronavirus S protein priming, an important step for binding of the S protein to the angiotensin-converting enzyme 2 (ACE2) receptor before cell entry. The main cellular location where the SARS-CoV-2 S protein priming occurs remains debatable, therefore hampering the development of targeted treatments. Herein, we identified the human extracellular serine protease inhibitor (serpin) alpha 1 antitrypsin (A1AT) as a novel TMPRSS2 inhibitor. Structural modeling revealed that A1AT docked to an extracellular domain of TMPRSS2 in a conformation that is suitable for catalysis, resembling similar serine protease-inhibitor complexes. Inhibitory activity of A1AT was established in a SARS-CoV-2 viral load system. Notably, plasma A1AT levels were associated with COVID-19 disease severity. Our data support the key role of extracellular serine proteases in SARS-CoV-2 infections and indicate that treatment with serpins, particularly the FDA-approved drug A1AT, may be effective in limiting SARS-CoV-2 dissemination by affecting the surface of the host cells.

SUMMARY

Delivery of extracellular serine protease inhibitors (serpins) such as A1AT has the capacity to reduce SARS-CoV-2 dissemination by binding and inhibiting extracellular proteases on the host cells, thus, inhibiting the first step in SARS-CoV-2 cell cycle (i.e. cell entry).