Solar energy decision support is fragmented across dashboards that provide data without explanation, research papers are slow to parse, and general-purpose language models are not solar domain specific and answer without evidence. This paper introduces Solar Intelligence, a hybrid retrieval-augmented framework that unifies structured solar analytics, evidence-grounded scientific question answering, and machine learning forecasting in one system. The platform integrates daily NASA POWER solar and meteorological data, Biosphere 2 ground-sensor readings, and a curated corpus of research papers and institutional reports. Structured queries use DuckDB SQL; scientific questions are answered by a hybrid retriever that fuses BM25 and ChromaDB dense embeddings via Reciprocal Rank Fusion, with responses grounded through a language model (llama3.2:3b). An Extreme Gradient Boosting (XGBoost) model produces daily forecasts of irradiance, temperature, and wind speed. The system is exposed via FastAPI, Streamlit, and an MCP server, so it can be used as an application, an API service, or an agent tool - by students, researchers, and energy analysts.
Figures & tables
S. No.
Data Details
Data Period
Data Sources
1
Research papers and Reports
1994–2006
arXiv, NREL, IEA-PVPS,
IRENA, and Sandia
2
Irradiance, Temperature, Humidity,
2012–2026
NASA POWER
Wind Speed, Precipitation
3
Air Temperature, Irradiance, and
Aug 2012 –
University of Arizona
Wind Speed
July 2013
Biosphere 2
Table 1: Data sources used in Solar Intelligence
Category
Topic Query
Max Results
1
Forecasting & ML
solar irradiance forecasting machine learning
20
solar power generation neural network
15
2
Irradiance components
global horizontal irradiance GHI estimation
15
direct normal irradiance DNI clear sky
10
solar radiation satellite measurement validation
15
solar resource assessment NASA POWER
10
Table 2: Eighteen topic queries used to construct the arXiv subset of the corpus via the official arXiv API
S. No.
Features
Types
1
Day-of-year (1–366)
Calendar features
2
Month (1–12)
3
sin(2π⋅doy/365.25)
Cyclic seasonality
4
cos(2π⋅doy/365.25)
5
Target value at lag 1 day
Lag features
6
Target value at lag 7 days
Table 3: Features used in forecasting
Component
Technology
Backend
FastAPI
Storage
DuckDB
Sparse retrieval
BM25
Dense retrieval
BGE-small
Fusion
Reciprocal Rank Fusion
Chunking
PyMuPDF
Table 4: System component and technology stack of Solar Intelligence
Figure 1: NASA POWER vs Biosphere 2 (B2) (32.578 ∘ N, 110.848 ∘ W) (Aug 2012 – July 2013).
Figure 2: Seven-day forecasts from the Solar Intelligence Streamlit dashboard for temperature (top), temperature (middle), and irradiance(bottom) at Biosphere 2 location. Each panel shows the last observed NASA POWER value at the top and the XGBoost roll-forward prediction as a continuous line (32.578 ∘ N, 110.848 ∘ W).
Solar power forecasting predicts photovoltaic generation and irradiance from weather, imagery, plant data, and recent output to support reliable grid and energy decisions.
Solar panels are increasingly deployed in cities on rooftops, walls, and urban infrastructure. Although the panel costs have fallen in recent years, the soft costs of installing them have not. These soft costs include assessing the illumination (irradiance) of a panel, which is typically performed using a 3D model that fails to capture small nearby structures that impact the irradiance. Our approach uses a single image taken at the panel's location to forecast its irradiance at any time in the future. We use visual cues in the image to find the camera's orientation and the portion of the sky visible to the panel in order to forecast the irradiance due to the sun and the sky. In addition, we show that the irradiance due to reflections from nearby buildings varies smoothly over time and can be forecasted from the image. This approach enables assessing the solar energy potential of any surface and forecasting the temporal variation of a panel's irradiance. We validate our approach using real irradiance measurements in urban canyons. We show that our approach often yields more accurate irradiance forecasts compared to conventional irradiance-based transposition methods and 3D model-based simulations. We also show that a single spherical image can be used to find the best fixed orientation of a panel. Finally, we present Solaris, a device to capture the image seen by a panel in a variety of urban settings.
Jeremy Klotz, Shree K. Nayar
Computer Science Department, Columbia University, 500 West 120th St., New York, 10027, NY, USA
Reliable short horizon forecasting of solar and wind generation is a structural prerequisite of any modern power system yet most published forecasters are tuned and evaluated on a single climatic regime and most algorithmic novelty has been concentrated either on classical recurrent networks or on monolithic foundation models that combine forecasting and explanation We develop a four stage hybrid framework that separates these concerns The first stage acquires hourly generation irradiance and surface weather records through public application programming interfaces The second stage trains three classical baselines autoregressive integrated moving average gradient boosted regression trees and a two layer long short term memory network and produces a strong point forecast together with a residual error series The third stage corrects the residual through a quantum inspired variational kernel built on a six qubit hardware efficient ansatz with three repeated entangling layers The fourth stage uses generative artificial intelligence strictly as an explainability layer that reads the measured benchmark numbers and produces a structured natural language interpretation Across three regions drawn from open public archives Iberian solar North Sea wind and a mixed Texas trace the proposed configuration stays within one percentage point of the strongest classical baseline on the in domain forecasting task and the quantum inspired kernel separates calm and stormy weather regimes with a Fisher discriminant ratio approximately fifteen fold higher than a tuned radial basis kernel
Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids. All-sky imagers (ASI) provide high-resolution observations of clouds, making them well suited for intra-hour forecasting. Recent deep learning approaches have substantially improved forecast accuracy but are often limited by deterministic predictions and a reduced capability to anticipate ramp events. This work proposes FarSky, a generative forecasting framework that leverages latent-space coupling to learn task-aware representations of sky images. A multi-task autoencoder first learns a shared latent representation for image reconstruction and irradiance estimation. A latent diffusion model then generates future latent states conditioned on recent observations, from which irradiance forecasts are directly decoded. Probabilistic forecasts are inherently obtained through stochastic sampling. The framework is developed using a multi-year ASI dataset acquired at the Plataforma Solar de Almería, Spain, and evaluated on two independent test datasets against persistence, state-of-the-art end-to-end, and generative forecasting approaches. FarSky achieves the best overall deterministic and probabilistic forecasting performance, improving forecast skill by up to 11 percentage points. Furthermore, it substantially improves ramp event detection over existing methods, achieving F1-scores above 60%. These results demonstrate the potential of combining generative models with task-aware latent-space coupling for solar forecasting.
Yann Fabel, Bijan Nouri, Milon Miah +4
1DLR, Institute of Solar Research · 2RWTH Aachen University · 3CIEMAT, Energy Department, Renewable Energy Division