GM-SEUS: A harmonized dataset of ground-mounted solar energy in the US with enhanced metadata

Ground-Mounted Solar Energy in the United States (GM-SEUS)Abstract:
Solar energy generating systems are critical components of our expanding energy infrastructure, yet available datasets remain incomplete or not publicly available–particularly at the sub-array level. Combining the best open-access datasets in the US with image analysis on freely available remotely-sensed imagery, we present the Ground-Mounted Solar Energy in the United States (GM-SEUS) dataset, a harmonized, open access geospatial and temporal repository of solar energy arrays and panel-rows. GM-SEUS v1.0 includes over 15,000 commercial- and utility-scale ground-mounted solar photovoltaic and concentrating solar energy arrays (186 GW) covering 2,950 km² and includes 2.92 million unique solar panel-rows (466 km²). We use these newly compiled and delineated solar arrays and panel-rows to harmonize and independently estimate value-added attributes to existing datasets including installation year, azimuth, mount technology, panel-row area and dimensions, inter-row spacing, ground cover ratio, tilt, and installed capacity. By estimating and harmonizing these attributes of the distributed US solar energy landscape, GM-SEUS supports diverse applications in renewable energy modeling, ecosystem service assessment, and infrastructure planning. 
Technical info:
This is the data repository for creating and maintaining the Ground-Mounted Solar Energy in the United States (GM-SEUS) spatiotemporal dataset of solar arrays and panel-rows using existing datasets, machine learning, and object-based image analysis to enhance existing sources. Contents of this repository are described here briefly, with the attatched data README providing more detailed descriptions. The source Github Repository for generating this dataset can be found here. The related paper was published in Scientific Data.

This is the initial release of GM-SEUS (version 1.0). All input datasets and solar panel-row delineation results are up-to-date through December 11th, 2024. 

Primary Repository Contents Include: 

GMSEUS_Arrays_Final: Final array dataset containing over 15,000 array boundaries from existing datasets and enhanced by buffer-dissolve-erode technique with GM-SEUS panel-rows containing all array-level attributes (ESRI:102003), geopackage, shapefile, and comma separated values

GMSEUS_Panels_Final: Final panel-row dataset containing 2.92 million boundaries from existing datasets and newly delineated GM-SEUS panel-rows containing all panel-row-level attributes (ESRI:102003), geopackage, shapefile, and comma separated values

GMSEUS_NAIP_Arrays: All array boundaries created by buffer-dissolve-erode method of newly delineated (NAIP) GM-SEUS panel-rows (ESRI:102003), geopackage, shapefile, and comma separated values

GMSEUS_NAIP_Panels: All newly delineated panel-row boundaries (ESRI:102003), geopackage, shapefile, and comma separated values

GMSEUS_NAIP_PanelsNoQAQC: All newly delineated panel-rows from NAIP imagery without any quality control (ESRI:102003), geopackage, shapefile, and comma separated values

NAIPtrainRF: Training dataset of 12,000 NAIP training points (2,000 per class) containing class values, spectral index values, the year of NAIP imagery accessed, and point coordinates (WGS84), comma separated values

NAIPclassifyRF: Random forest classifier trees and weights as output from Google Earth Engine classifier, comma separated values

LabeledImages: Directory containing image and mask subdirectories with ~17,500 input and target images for deep learning pattern recognition applications, GeoTIFF

Disclaimer: 

This dataset provides a broad characterization of solar array design practices. Any characterization of solar array design and management derived from remote sensing imagery should be considered with extreme scrutiny given the limitations of such approaches. While our work fills a critical data gap and compiles and enhances existing high-fidelity datasets, the design practices reported here are thus subject to uncertainty and should not be used to represent actual conditions at individual sites. No warranty is expressed or implied regarding accuracy, completeness or fitness for a specific purpose. We publish this dataset in open access, for the broader science community, policy makers, and stakeholders in addressing questions about the existing renewable energy landscape and do not consent to this data being used to target, identify, or make claims about individual arrays, properties, or entities. Any such use case is strictly prohibited. 

GM-SEUS is released under CC-BY 4.0. However, components derived from third-party datasets retain the original license of those inputs. Some upstream datasets used in boundary generation contain non-commerical (NC) licensing terms. As a result, users intending to reuse GM-SEUS for commercial purposes must ensure compliance with the licensing conditions of those upstream sources. GM-SEUS does not incorporate metadata or attribute information from non-commercial datasets. However, certain geometry or inferred boundaries may constitute derivative works of those sources. To support transparency, GM-SEUS retains the original spatial data source in the Source attribute column, and full upstream licensing information is provided in the accompanying sourceDataLicenses.csv file.

# 美国地面安装太阳能电站数据集（GM-SEUS）
## 摘要
太阳能发电系统是不断扩张的全球能源基础设施的关键组成部分，但现有数据集仍存在不完整或未公开的问题，尤其是在子阵列层面。我们结合美国境内最优的开放获取数据集与免费遥感影像的图像分析技术，构建了美国地面安装太阳能电站数据集（Ground-Mounted Solar Energy in the United States, GM-SEUS）——这是一个经过统一整合的开放获取时空地理空间数据集，涵盖太阳能阵列与光伏板组列。GM-SEUS v1.0版本包含超过15000个商业级与公用事业级地面安装太阳能光伏及聚光太阳能阵列（总装机容量186吉瓦），覆盖面积达2950平方公里，同时包含292万个独立的光伏板组列（覆盖面积466平方公里）。我们依托新编译并勾勒出的太阳能阵列与光伏板组列数据，对现有数据集进行统一整合，并独立估算其增值属性，包括安装年份、方位角、安装技术、板组列面积与尺寸、列间距、地面覆盖率、倾斜角度以及装机容量。通过估算并统一美国分布式太阳能发电景观的各类属性，GM-SEUS可支持可再生能源建模、生态系统服务评估以及基础设施规划等多领域应用。

## 技术说明
本数据集仓库用于依托现有数据集、机器学习与面向对象的图像分析技术，构建并维护美国地面安装太阳能电站（GM-SEUS）的太阳能阵列与光伏板组列时空数据集，以优化现有数据源。本仓库的内容已在此简要说明，附属的数据README文件将提供更详细的描述。用于生成本数据集的源代码GitHub仓库可在此处获取。相关研究论文已发表于《Scientific Data》（科学数据）期刊。

本版本为GM-SEUS的首个正式发布版（v1.0）。所有输入数据集与光伏板组列勾勒结果的更新截止至2024年12月11日。

### 仓库核心内容包括：
1. **GMSEUS_Arrays_Final**：最终阵列数据集，包含来自现有数据集的15000余个阵列边界，通过缓冲区-融合-侵蚀技术进行优化，附带GM-SEUS光伏板组列的所有阵列级属性，数据格式包括ESRI:102003坐标系地理包（geopackage）、形状文件（shapefile）与逗号分隔值（CSV）文件。
2. **GMSEUS_Panels_Final**：最终板组列数据集，包含292万个来自现有数据集与新勾勒的GM-SEUS光伏板组列边界，附带所有板组列级属性，数据格式包括ESRI:102003坐标系地理包、形状文件与逗号分隔值文件。
3. **GMSEUS_NAIP_Arrays**：通过缓冲区-融合-侵蚀技术，基于新勾勒的NAIP（美国农业航空影像计划，National Agricultural Imagery Program）GM-SEUS光伏板组列生成的所有阵列边界，数据格式包括ESRI:102003坐标系地理包、形状文件与逗号分隔值文件。
4. **GMSEUS_NAIP_Panels**：所有新勾勒的光伏板组列边界，数据格式包括ESRI:102003坐标系地理包、形状文件与逗号分隔值文件。
5. **GMSEUS_NAIP_PanelsNoQAQC**：所有从NAIP影像中提取的未经过任何质量控制的新勾勒光伏板组列，数据格式包括ESRI:102003坐标系地理包、形状文件与逗号分隔值文件。
6. **NAIPtrainRF**：包含12000个NAIP训练样本点（每类2000个）的训练数据集，涵盖类别值、光谱指数值、所用NAIP影像年份与点坐标（WGS84坐标系），数据格式为逗号分隔值文件。
7. **NAIPclassifyRF**：由谷歌地球引擎（Google Earth Engine）分类器输出的随机森林分类树与权重文件，数据格式为逗号分隔值文件。
8. **LabeledImages**：包含图像与掩码子目录的文件夹，内含约17500个用于深度学习模式识别任务的输入图像与目标图像，数据格式为地理标记图像文件格式（GeoTIFF）。

## 免责声明
本数据集仅对太阳能阵列的设计实践进行宽泛表征。鉴于遥感影像分析方法的固有局限性，任何基于遥感影像推导的太阳能阵列设计与管理表征结果均需经过严格审慎的核验。尽管本研究填补了关键的数据空白，并整合优化了现有高精度数据集，但本文报告的设计实践仍存在不确定性，不得用于表征单个电站的实际运行状况。本数据集未对其准确性、完整性或特定用途的适用性做出任何明示或暗示的担保。我们以开放获取的形式发布本数据集，旨在为广大科研群体、政策制定者与利益相关方提供现有可再生能源景观相关问题的研究支撑，严禁将本数据集用于定向定位、识别或宣称单个太阳能阵列、资产或实体的相关用途。任何此类使用行为均被严格禁止。

GM-SEUS采用知识共享署名4.0协议（CC-BY 4.0）发布。然而，从第三方数据集衍生的组件仍保留其原始输入数据集的许可协议。部分用于生成阵列边界的上游数据集包含非商业（NC）许可条款。因此，计划将GM-SEUS用于商业用途的用户需确保遵守这些上游数据源的许可条件。GM-SEUS未纳入非商业数据集的元数据或属性信息，但部分几何形状或推导得到的边界可能构成这些源数据的衍生作品。为保障透明度，GM-SEUS在Source属性列中保留了原始空间数据源的信息，完整的上游许可信息详见随附的sourceDataLicenses.csv文件。