AI and Open-data Driven Scalable Solar Power Profiling

• URL: http://arxiv.org/abs/2605.02738v1
• Date: Mon, 04 May 2026 15:37:52 GMT
• Title: AI and Open-data Driven Scalable Solar Power Profiling
• Abstract summary: This paper presents an open, scalable framework for detecting solar panels from open data and generating city-level solar power profiles.<n>We leverage foundation vision AI models to detect solar panel from open-source satellite imagery.<n>The framework reduces dependency on proprietary imagery, manual labeling, and closed-source models, and offers a transparent and scalable approach for solar planning and analysis.
• Score: 48.72868465736126
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Solar photovoltaic (PV) deployment is expanding rapidly, yet detailed, up-to-date information on the spatial distribution and capacity of rooftop PV remains limited. This paper presents an open, scalable framework for detecting solar panels from open data and generating city-level solar power profiles. We leverage foundation vision AI models to detect solar panel geometries from open-source satellite imagery. This avoids manual data labeling and case-specific model training while maintaining robustness across heterogeneous imagery. Detected solar panels are converted into georeferenced polygons, yielding spatially explicit and incrementally extensible inventories. By integrating open weather data, we translate panel footprints into regional solar power profiles. The framework reduces dependency on proprietary imagery, manual labeling, and closed-source models, and offers a transparent and scalable approach for solar planning and analysis. We released the data and an API resulted from this work. For any user-specified building location, our API retrieves aerial imagery, detects rooftop solar panels, and returns georeferenced polygons. This empowers researchers and developers to scan user-defined areas to build solar panel maps and associated solar production profiles, thus facilitating advanced analysis like distributed solar production integration, local power flow optimization, energy tariff design, and infrastructure planning.

Related papers

• SolarBench: A global solar energy nowcasting benchmark [10.905771157487608]
  We introduce SolarBench, an open global benchmark for image-based solar nowcasting.<n>SolarBench harmonizes more than six million sky and satellite images from 11 diverse sites spanning a decade.<n>We benchmark representative models and reveal a gap between average forecasting accuracy and the ability to capture rapid solar fluctuations.
  arXiv  Detail & Related papers  (2026-09-05T17:09:13Z)
• Solar Open 2 Technical Report [96.21161740206544]
  We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks.<n>To hold entire agent trajectories in a single context, Solar Open 2 reaches a 1M-token window.<n>We train twelve domain specialists across purpose-built scenarios, then consolidate them into a single model.
  arXiv  Detail & Related papers  (2026-07-22T12:08:41Z)
• Ultra-short-term solar power forecasting by deep learning and data reconstruction [60.200987006598524]
  We propose a deep-learning based ultra-short-term solar power prediction with data reconstruction.<n>We employ deep-learning models to capture long- and short-term dependencies towards the target prediction period.
  arXiv  Detail & Related papers  (2025-09-21T14:22:35Z)
• Solar Panel Mapping via Oriented Object Detection [0.0]
  We propose an end-to-end deep learning framework for detecting individual solar panels.<n>We evaluate our approach on a diverse dataset of solar power plants collected from across the United States.
  arXiv  Detail & Related papers  (2025-02-05T20:19:37Z)
• FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting [24.57911612111109]
  We propose a multi-modality fusion framework to integrate historical power data, numerical weather prediction, and satellite images. Our framework demonstrates strong zero-shot forecasting capability, which is especially useful for those newly installed plants. Our model not only operates with robustness but also boosts accuracy in both zero-shot forecasting and scenarios rich with training data, surpassing leading models.
  arXiv  Detail & Related papers  (2024-02-08T17:03:10Z)
• Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context [46.72071291175356]
  Solar power harbors immense potential in mitigating climate change by substantially reducing CO$_2$ emissions. However, the inherent variability of solar irradiance poses a significant challenge for seamlessly integrating solar power into the electrical grid. In this paper, we put forth a deep learning architecture designed to harnesstemporal context using satellite data.
  arXiv  Detail & Related papers  (2023-06-01T19:54:39Z)
• A Comparative Study on Generative Models for High Resolution Solar Observation Imaging [59.372588316558826]
  This work investigates capabilities of current state-of-the-art generative models to accurately capture the data distribution behind observed solar activity states. Using distributed training on supercomputers, we are able to train generative models for up to 1024x1024 resolution that produce high quality samples indistinguishable to human experts.
  arXiv  Detail & Related papers  (2023-04-14T14:40:32Z)
• Data-driven soiling detection in PV modules [58.6906336996604]
  We study the problem of estimating the soiling ratio in photo-voltaic (PV) modules. A key advantage of our algorithms is that they estimate soiling, without needing to train on labelled data. Our experimental evaluation shows that we significantly outperform current state-of-the-art methods for estimating soiling ratio.
  arXiv  Detail & Related papers  (2023-01-30T14:35:47Z)
• Computational Solar Energy -- Ensemble Learning Methods for Prediction of Solar Power Generation based on Meteorological Parameters in Eastern India [0.0]
  It is important to estimate the amount of solar photovoltaic (PV) power generation for a specific geographical location. In this paper, the impact of weather parameters on solar PV power generation is estimated by several Ensemble ML (EML) models like Bagging, Boosting, Stacking, and Voting. The results demonstrate greater prediction accuracy of around 96% for Stacking and Voting models.
  arXiv  Detail & Related papers  (2023-01-21T19:16:03Z)
• SKIPP'D: a SKy Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting [0.0]
  There are few publicly available standardized benchmark datasets for image-based solar forecasting. We introduce SKIPP'D -- a SKy Images and Photovoltaic Power Generation dataset. The dataset contains quality-controlled down-sampled sky images and PV power generation data ready-to-use for short-term solar forecasting using deep learning.
  arXiv  Detail & Related papers  (2022-07-02T21:52:50Z)
• HyperionSolarNet: Solar Panel Detection from Aerial Images [0.7157957528875099]
  We use deep learning methods for automated detection of solar panel locations and their surface area using aerial imagery. Our work provides an efficient and scalable method for detecting solar panels, achieving an accuracy of 0.96 for classification and an IoU score of 0.82 for segmentation performance.
  arXiv  Detail & Related papers  (2022-01-06T15:43:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.