---
title: 'SunCastNet: Solar Irradiance Forecasting'
url: https://www.emergentmind.com/topics/suncastnet
type: topic
---

# SunCastNet: Solar Irradiance Forecasting

SunCastNet denotes a family of data-driven solar irradiance forecasting systems centered on gridded shortwave-radiation prediction rather than full numerical weather simulation. In the literature provided here, the name is associated with two technically distinct uses: a ConvLSTM-based continental nowcasting system that predicts GOES-16 downward shortwave radiation over North America up to 3 hours ahead, and a later four-stage sequential AI framework that predicts surface solar radiation downwards at \(0.05^\circ\), 10-minute resolution up to 7 days ahead and couples those forecasts to reinforcement-learning-based battery scheduling and long-horizon investment analysis [2201.06173] [2509.06925].

## 1. Nomenclature and problem scope

The term has a nontrivial naming history. The 2022 paper is titled **“SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data”**, but the supplied technical summary explicitly uses **“SunCast / SunCastNet”** and states that **SunCastNet** is the ConvLSTM-based spatiotemporal nowcasting model introduced there. The 2025 paper uses **SunCastNet** as the formal name of a broader, long-horizon forecasting system oriented toward industrial solar-plus-battery economics [2201.06173] [2509.06925].

| Aspect | 2022 usage | 2025 usage |
|---|---|---|
| Primary task | Solar irradiance nowcasting | High-resolution SSRD forecasting for economic decisions |
| Target field | DSR | SSRD |
| Geographic emphasis | North America | China |
| Resolution | Hourly, \(166 \times 394\) images | \(0.05^\circ\), 10-minute |
| Horizon | Up to 3 hours | Up to 7 days |

This dual usage matters because the two systems operate at different scales, use different targets, and answer different operational questions. The earlier system is explicitly positioned as **solar irradiance nowcasting**, not long-range weather forecasting; the later system is framed around **fast, cheap, high-resolution, long-horizon irradiance forecasts** for industrial decision-making [2201.06173] [2509.06925].

The target variables also differ. The 2022 system predicts **downward shortwave radiation at the surface (DSR)**, measured in \(W/m^2\), using GOES-16 DSR imagery. The 2025 system predicts **surface solar radiation downwards (SSRD)** and compares against GFS through the related **downward shortwave radiation flux (DSWRF)** field [2201.06173] [2509.06925].

## 2. ConvLSTM SunCastNet for continental nowcasting

In its 2022 form, SunCastNet treats solar nowcasting as a **spatiotemporal next-frame prediction problem** over North America. The operational data source is the GOES-16 **DSR product** from NOAA GOES open data on AWS. Each forecast uses three past hourly DSR images, \(X_{t-2}, X_{t-1}, X_t\), together with one-hot encodings of **month** and **hour of day**, which are embedded in the input images to account for solar geometry. The DSR frames have size \(166 \times 394\), so each frame contains \(65{,}404\) pixels [2201.06173].

The forecasting setup can be faithfully written as
\[
\hat{Y}_{t+k} = f_k(X_{t-2}, X_{t-1}, X_t, m_t, h_t), \quad k \in \{1,2,3\}.
\]
Although the paper states a 3-hour-ahead objective with inputs \(t-2,t-1,t\) and targets \(t+1,t+2,t+3\), the authors report that **separate horizon-specific models** performed better than a joint multi-horizon predictor. The 1-hour model outputs \(t-1,t,t+1\), the 2-hour model outputs \(t,t+1,t+2\), and the 3-hour model outputs \(t+1,t+2,t+3\), with the final frame taken as the effective forecast for that horizon [2201.06173].

The architecture is a stacked **Convolutional Long Short-Term Memory Network**. The reported network consists of a ConvLSTM layer with **128 kernels** of size \(5 \times 5\), **Batch Normalization**, a second ConvLSTM layer with **128 kernels** of size \(5 \times 5\), **Batch Normalization**, a third ConvLSTM layer with **64 kernels** of size \(5 \times 5\), and a **Conv3D** output layer with **same padding** and **sigmoid activation**. All ConvLSTM layers use **same padding** and **ReLU activation**. The output layer’s sigmoid implies that targets were squashed to \([0,1]\), although the exact normalization formula is not given [2201.06173].

The model family includes three recurrent-cell variants: **ConvLSTM**, **ConvLSTMPeephole**, and **ConvGRU**. The standard ConvLSTM formulation referenced in the summary is
\[
i_t = \sigma\left(W_{xi} * X_t + W_{hi} * H_{t-1} + W_{ci} \odot C_{t-1} + b_i\right),
\]
\[
f_t = \sigma\left(W_{xf} * X_t + W_{hf} * H_{t-1} + W_{cf} \odot C_{t-1} + b_f\right),
\]
\[
\tilde{C}_t = \tanh\left(W_{xc} * X_t + W_{hc} * H_{t-1} + b_c\right),
\]
\[
C_t = f_t \odot C_{t-1} + i_t \odot \tilde{C}_t,
\]
\[
o_t = \sigma\left(W_{xo} * X_t + W_{ho} * H_{t-1} + W_{co} \odot C_t + b_o\right),
\]
\[
H_t = o_t \odot \tanh(C_t).
\]
Training uses **mean squared error (MSE)** loss, but the paper does not specify the optimizer type, learning rate, batch size, epoch count, or full validation protocol [2201.06173].

## 3. Sequential SunCastNet for high-resolution SSRD forecasting

In its 2025 form, SunCastNet is a **four-stage sequential framework** implemented on the **NVIDIA Earth-2 platform**. It is designed to generate **\(0.05^\circ\), 10-minute resolution predictions of surface solar radiation downwards (SSRD) up to 7 days ahead**, with the stated goal of supporting distributed solar-plus-battery decision-making under peak–valley electricity pricing [2509.06925].

The system begins from coarse atmospheric forecasts based on **IFS/GFS**, using **73 atmospheric variables** at **\(0.25^\circ\)** and **6-hour intervals**. It then applies four learned stages that progressively refine atmospheric state information into local solar radiation forecasts:

1. **SFNO weather forecasting**: a **Spherical Fourier Neural Operator (SFNO)** predicts global circulation using **73 input variables** and produces **6-hourly fields at \(0.25^\circ\) resolution**.
2. **ModAFNO temporal interpolation**: a **Modulated Adaptive Fourier Neural Operator (ModAFNO)** takes **two consecutive atmospheric states**, hence **\(2 \times 73\)** variables, plus **9 auxiliary fields**, for **155 input channels \(\rightarrow 73\) output channels**, converting **6-hourly** fields to **1-hourly** at **\(0.25^\circ\)**.
3. **AFNO solar diagnostic**: an **AFNO-based diagnostic module** maps **31 key atmospheric fields** directly to **hourly SSRD** at **\(0.25^\circ\)**.
4. **CorrDiffSolar downscaling**: **CorrDiffSolar** takes **57-channel inputs** and outputs **\(0.05^\circ\), 10-minute SSRD fields**, calibrated against dense **East Asia–Pacific observations** and benchmarked to the **East Asia–Pacific Longwave/Shortwave Downward Radiation dataset (2016–2020)** [2509.06925].

The principal geographic domain for the economic study is China, explicitly given as **\(47\text{–}19.05^\circ \mathrm{N}\)** and **\(97\text{–}124.95^\circ \mathrm{E}\)**. Validation is performed against **2,164 meteorological stations across China** using **China Meteorological Administration ground-based solar radiation measurements**. The retrospective study uses **ERA5-driven forecasts spanning August 2000 to August 2025**, issued every **6 hours**, with each forecast extending **7 days** at **10-minute resolution** [2509.06925].

The paper does not provide a detailed preprocessing specification such as normalization formulas, missing-value handling, or exact loss definitions in the visible text. What is explicit is the structural progression from coarse atmospheric forecasts to hourly SSRD diagnosis and then to high-resolution spatial-temporal downscaling [2509.06925].

## 4. Forecast skill, baselines, and computational profile

The two SunCastNet usages are evaluated with different metrics and baselines, reflecting their different operational regimes. The 2022 nowcasting system reports **RMSE in \(W/m^2\)** on a **2-month test set**, while the 2025 system emphasizes **relative error (RE)**, **mutual information (MI)**, and **forecast consistency/inconsistency** against GFS [2201.06173] [2509.06925].

| System | Forecast-quality results | Deployment figures |
|---|---|---|
| 2022 ConvLSTM SunCastNet | Best overall RMSE: **60.2** at 1 hour, **85.7** at 2 hours, **120.6** at 3 hours; site-based HRRR comparison: **108.6** vs **124.9** overall RMSE, a **13.08% decrease in RMSE** | Predicts all North America up to 3 hours ahead in **under 60 seconds** on a **single machine without a GPU** |
| 2025 sequential SunCastNet | Median RE rises from about **13% at 2-day lead** to **~20% at 7 days**; GFS rises from about **22%** to **28%**; SunCastNet has **~5–10% lower error than GFS** and a mean MI ratio of **~1.2** | **About 25 minutes** per 7-day forecast on **one NVIDIA A100 GPU**, about **\$0.5 per continental-scale forecast** |

For the 2022 model, the detailed RMSE tables show that **ConvLSTMPeephole** is best overall at **1 hour** and **3 hours**, while standard **ConvLSTM** is slightly better at **2 hours**; **ConvGRU** performs markedly worse across all horizons. Error growth with horizon is substantial, progressing from **60.2** to **86.5** to **120.6 \(W/m^2\)** for the best overall models. Against a California subregion linear-regression baseline, ConvLSTM improves RMSE from **104.6 \(W/m^2\)** to **71.4 \(W/m^2\)**. Against **HRRR**, the comparison at **22 sites**—**17 large solar farm sites** and **5 urban centers**—during **10:00 AM to 3:00 PM PST** over **four weeks** shows lower RMSE for the learned model in every DSR bin, while the paper notes that HRRR requires **more than 10 TB of memory to run** [2201.06173].

For the 2025 system, the main baseline is **GFS**. The paper reports that SunCastNet’s median RE rises from about **13%** at 2-day lead to **~20%** at 7 days, whereas GFS rises from about **22%** to **28%**. SunCastNet also yields narrower interquartile ranges, achieves higher MI than GFS at **97%** of the **2,164 stations**, and maintains forecast inconsistency typically **<20 \(W\,m^{-2}\)**, rarely above **30 \(W\,m^{-2}\)**, whereas GFS inconsistency is broadly **30–50 \(W\,m^{-2}\)** with hotspots **>50 \(W\,m^{-2}\)** in the Yangtze basin and Sichuan. For the 25-year retrospective study, generating the full forecast archive required approximately **15,000 A100 GPU hours** and **43 TB of data** [2509.06925].

## 5. Coupling to control and investment decisions

A distinguishing feature of the 2025 SunCastNet is that it is not presented merely as a forecasting benchmark. Its explicit pipeline is
\[
\text{SunCastNet forecast} \rightarrow \text{RL battery scheduling} \rightarrow \text{25-year investment backtest}.
\]
The downstream controller uses solar forecasts, electricity demand, electricity prices, and PV/battery configurations to learn **optimal charge–discharge strategies**, and then propagates operational gains into investment calculations using a commercial-viability threshold of **\(12\%\) Internal Rate of Return (IRR)** [2509.06925].

The central operational comparison is against **robust decision making (RDM)**, described as uncertain-set-driven, defensive, and derived from **30-day historical scenarios**. Relative to RDM, **SunCastNet-informed RL** yields **76–93% regret reduction** across most of northern and eastern China; **GFS-informed RL** yields **43–66% regret reduction**. The text also notes an introduction-level statement of **72–93%** for the full retrospective study, so the safest interpretation is a consistent claim in the **mid-70s to low-90s percent** range, depending on region and experiment slice. Strong gains are especially reported in **northern China** and **eastern China** [2509.06925].

The economic effect is evaluated across **10 representative industrial sectors**—**automobile, electronics, food processing, textiles, pharmaceuticals, chemicals, steel, paper, cement,** and **glass**—and across **42 industrial cases** derived from real operational data via industrial collaborations. Under SunCastNet-informed RL, regions with high irradiation variability, including central provinces such as **Henan**, **Hubei**, and **Anhui**, shift from “infeasible” under RDM to “profitable.” The headline investment result is that SunCastNet enables **up to five out of ten sectors per region** to cross the **12% IRR** threshold, whereas under **GFS** typically only **two or three** sectors shift [2509.06925].

Horizon length is itself an economically salient design variable. The paper explicitly reports that **1–2 day** forecasts reduce regret by **less than 40%**, **3–5 day** horizons yield **40–60%**, and **7 day** horizons exceed **70%** in many regions. This supports the paper’s claim that the value of SunCastNet is not reducible to conventional forecast-error improvement alone; its long-horizon, high-resolution structure changes the feasible control space for battery scheduling [2509.06925].

## 6. Reproducibility, limitations, and relation to adjacent work

Both SunCastNet variants are only partially reproducible from the visible paper text. The 2022 system specifies the data source, input sequence length, image size, horizon-specific design, layer stack, activations, padding, and MSE loss, but omits the optimizer, learning rate, batch size, epoch count, exact normalization equation, exact treatment of night-time data, channel arrangement for month/hour embeddings, random seeds, and clear code-release status. The 2025 system is richer architecturally but likewise omits a detailed preprocessing pipeline, explicit uncertainty modeling, probabilistic calibration, and full Materials-and-Methods equations in the visible text. Geographic scope is also limited: the 2022 experiments are for **North America**, while the 2025 evaluation is confined to **China**, with the authors explicitly noting that transfer to other climates and sparse-observation regions requires further validation [2201.06173] [2509.06925].

A common misconception is to treat SunCastNet as interchangeable with other recent solar-forecasting models. The supplied literature does not support that equivalence. SunCastNet is distinct from the satellite-first self-supervised CNN-LSTM pipeline that predicts future GOES observations and then uses a site-specific SVR for PV output [2112.13974]; from the **Solar Multimodal Transformer (SMT)**, which fuses **single-frame public camera imagery** and normalized GHI history for **2-hour-ahead** daytime forecasting [2503.00250]; from **SolarCAST**, a causally informed graph-transformer that uses only target-site and nearby-station GHI histories and is explicitly stated not to be SunCastNet [2509.15481]; and from **Solarcast-ML**, which is a **per-node GraphCast extension** with a node-wise feedforward solar head rather than a graph-native solar forecasting architecture [2406.13559].

Taken together, the two SunCastNet usages define a technical arc from **ConvLSTM-based, public-satellite, continental nowcasting** to **multi-stage neural weather-to-radiation forecasting integrated with downstream control and finance**. A plausible implication is that the name now indexes not a single immutable architecture but a broader design philosophy: shortwave-radiation forecasting should be posed as a learned spatiotemporal prediction problem whose value is judged not only by forecast error, but also by computational efficiency, decision quality, and economic utility [2201.06173] [2509.06925].

Source: https://www.emergentmind.com/topics/suncastnet