What question did this study set out to answer?

This research aims to enhance the accuracy of photovoltaic power forecasts by integrating numerical weather prediction with physics-informed neural networks.

June 14, 2026Geoscientific model developmentOpen Access

MIPV-NWP-PINNs V1.0: development of a multi-scale photovoltaic power forecasting framework integrating numerical weather prediction with physics-informed neural networks

View Full Paper

Ask AI

Bookmark

Authors

FZFei ZhangChinese Academy of Sciences XLXingcai LiNingxia University ZWZi WangHarbin University of Science and Technology

Discussion

Member takes

Implication

Randomized trial integrates numerical weather prediction with deep learning to enhance photovoltaic power forecasts, suggesting improved grid integration reliability.

Key Points

This research aims to enhance the accuracy of photovoltaic power forecasts by integrating numerical weather prediction with physics-informed neural networks.
Developed a regional high-resolution NWP system using the Weather Research and Forecasting model for multi-scale meteorological forecasts with lead times of 6 h, 1, 3, and 5 d.
Proposed a hybrid correction model combining Quantile Mapping with a Temporal Pattern Attention-based Long Short-Term Memory network to improve Global Horizontal Irradiance forecasts.
Created a Physics-Informed Neural Networks-iTransformer model for photovoltaic power prediction using corrected meteorological data.
The novel correction approach reduced Mean Absolute Error by over 23% compared to raw NWP outputs.
The Physics-Informed Neural Networks-iTransformer model achieved a 15.5% reduction in RMSE and 12.4% reduction in MAE across all forecasting horizons.
The framework significantly improved reliability in photovoltaic power forecasting, aiding secure grid integration.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a2e4608b1cc60ccdea8adf7 https://doi.org/10.5194/gmd-19-4999-2026

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial integrates numerical weather prediction with deep learning to enhance photovoltaic power forecasts, suggesting improved grid integration reliability.

MIPV-NWP-PINNs V1.0: development of a multi-scale photovoltaic power forecasting framework integrating numerical weather prediction with physics-informed neural networks

Discussion

Member takes

Implication

Key Points

Cite This Study

MIPV-NWP-PINNs V1.0: development of a multi-scale photovoltaic power forecasting framework integrating numerical weather prediction with physics-informed neural networks

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider