We present a method to predict the global horizontal irradiance (GHI) one hour ahead in one-minute resolution using Artificial Neural Networks (ANNs). A feed-forward neural network with Levenberg–Marquardt Backpropagation (LM-BP) was used and was trained with four years of data from all-sky images and measured global irradiance as input. The pictures were recorded by a hemispheric sky imager at the Institute of Meteorology and Climatology (IMuK) of the Leibniz Universität Hannover, Hannover, Germany (52.23° N, 09.42° E, and 50 m above sea level). The time series of the global horizontal irradiance was measured using a thermopile pyranometer at the same site. The new method was validated with a test dataset from the same source. The irradiance is predicted for the first 10–30 min very well; after this time, the length of which is dependent on the weather conditions, the agreement between predicted and observed irradiance is reasonable. Considering the limited range that the camera and the ANN can “see”, this is not surprising. When comparing the results to the persistence model, we observed that the forecast accuracy of the new model reduced both the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) of the one-hour prediction by approximately 40% compared to the reference persistence model under various weather conditions, which demonstrates the high capability of the algorithm, especially within the first minutes.

Background: A previous study has demonstrated the feasibility of 3D phase‐resolved functional lung (PREFUL) MRI in healthy volunteers and patients with chronic pulmonary disease. Before clinical use, the repeatability of the ventilation parameters derived from 3D PREFUL MRI must be determined.Purpose: To evaluate repeatability of 3D PREFUL and to compare with pulmonary functional lung testing (PFT).Study Type: Prospective.Population: Fifty‐three healthy subjects and 13 patients with chronic obstructive pulmonary disease (COPD).Field Strength/Sequence: A prototype 3D stack‐of‐stars spoiled‐gradient‐echo sequence at 1.5 T.Assessment: Study participants underwent repeated MRI examination (median time interval between scans COPD/healthy subjects [interquartile range]: 7/0 days [6–8/0–0 days]) and one PFT carried out at the time of the baseline MRI. For 3D PREFUL, regional ventilation (RVent) and flow‐volume loops were computed and rated by cross‐correlation (CC). Also, ventilation time‐to‐peak (VTTP) was computed. Ventilation defect percentage (VDP) maps were obtained for RVent and CC.Statistical Tests: Repeatability of 3D PREFUL parameters was evaluated using Bland–Altman analysis, coefficient of variation (COV) and intraclass correlation coefficient (ICC). The relation between 3D PREFUL and PFT measures (forced expiratory volume in 1 second (FEV₁) and forced vital capacity (FVC) was assessed using the Pearson correlation coefficient (r).Results: In healthy subjects and COPD patients, no significant bias (all P range: 0.09–0.77) and a moderate to good repeatability of RVent, VTTP, and VDP_RVent were found (COV range: 0.1%–18.2%, ICC range: 0.51–0.88). For CC and VDP_CC moderate repeatability was found (COV range: 0.6%–43.6%, ICC: 0.38–0.60). CC, VDP_RVent, and VDP_CC showed a good correlation with FEV₁ (all |r| > 0.58, all P < 0.05) and FEV₁/FVC ratio (all |r| > 0.62, all P < 0.05).Data Conclusion: 3D PREFUL provided a good repeatability of RVent, VTTP, and VDP_RVent and moderate repeatability of CC and VDP_CC in healthy volunteers and COPD patients, and correlated well with FEV₁ and FEV₁/FVC.Level of Evidence: 2Technical Efficacy Stage: 2

Purpose: To improve automated lung segmentation on 2D lung MR images using balanced augmentation and artificially-generated consolidations for training of a convolutional neural network (CNN). Materials and methods: From 233 healthy volunteers and 100 patients, 1891 coronal MR images were acquired. Of these, 1666 images without consolidations were used to build a binary semantic CNN for lung segmentation and 225 images (187 without consolidations, 38 with consolidations) were used for testing. To increase CNN performance of segmenting lung parenchyma with consolidations, balanced augmentation was performed and artificially-generated consolidations were added to all training images. The proposed CNN (CNN_Bal/Cons) was compared to two other CNNs: CNN_Unbal/NoCons—without balanced augmentation and artificially-generated consolidations and CNN_Bal/NoCons—with balanced augmentation but without artificially-generated consolidations. Segmentation results were assessed using Sørensen-Dice coefficient (SDC) and Hausdorff distance coefficient. Results: Regarding the 187 MR test images without consolidations, the mean SDC of CNN_Unbal/NoCons (92.1 ± 6% (mean ± standard deviation)) was significantly lower compared to CNN_Bal/NoCons (94.0 ± 5.3%, P = 0.0013) and CNN_Bal/Cons (94.3 ± 4.1%, P = 0.0001). No significant difference was found between SDC of CNN_Bal/Cons and CNN_Bal/NoCons (P = 0.54). For the 38 MR test images with consolidations, SDC of CNN_Unbal/NoCons (89.0 ± 7.1%) was not significantly different compared to CNN_Bal/NoCons (90.2 ± 9.4%, P = 0.53). SDC of CNN_Bal/Cons (94.3 ± 3.7%) was significantly higher compared to CNN_Bal/NoCons (P = 0.0146) and CNN_Unbal/NoCons (P = 0.001). Conclusions: Expanding training datasets via balanced augmentation and artificially-generated consolidations improved the accuracy of CNN_Bal/Cons, especially in datasets with parenchymal consolidations. This is an important step towards a robust automated postprocessing of lung MRI datasets in clinical routine.

A novel high-resolution method for forecasting cloud motion from all-sky images using deep learning is presented. A convolutional neural network (CNN) was created and trained with more than two years of all-sky images, recorded by a hemispheric sky imager (HSI) at the Institute of Meteorology and Climatology (IMUK) of the Leibniz Universität Hannover, Hannover, Germany. Using the haze indexpostprocessing algorithm, cloud characteristics were found, and the deformation vector of each cloud was performed and used as ground truth. The CNN training process was built to predict cloud motion up to 10 min ahead, in a sequence of HSI images, tracking clouds frame by frame. The first two simulated minutes show a strong similarity between simulated and measured cloud motion, which allows photovoltaic (PV) companies to make accurate horizon time predictions and better marketing decisions for primary and secondary control reserves. This cloud motion algorithm principally targets global irradiance predictions as an application for electrical engineering and in PV output predictions. Comparisons between the results of the predicted region of interest of a cloud by the proposed method and real cloud position show a mean Sørensen–Dice similarity coefficient (SD) of 94 ± 2.6% (mean ± standard deviation) for the first minute, outperforming the persistence model (89 ± 3.8%). As the forecast time window increased the index decreased to 44.4 ± 12.3% for the CNN and 37.8 ± 16.4% for the persistence model for 10 min ahead forecast. In addition, up to 10 min global horizontal irradiance was also derived using a feed-forward artificial neural network technique for each CNN forecasted image. Therefore, the new algorithm presented here increases the SD approximately 15% compared to the reference persistence model.

We present here a new method to predict cloud concentration five minutes in advance from all-sky images using the Artificial Neural Networks (ANN). An autoregressive neural network with backpropagation (Ar-BP) was created and trained with four years of all-sky images as inputs. The pictures were taken with a hemispheric sky imager fixed on the roof at the Institute of Meteorology and Climatology (IMUK) of the Leibniz Universität Hannover, Hannover, Germany. Firstly, a statistical method is presented to obtain key information of the pictures. Secondly, a new image-processing algorithm is suggested to optimize the cloud detection process starting with the Haze Index. Finally, the cloud concentration five minutes in advance at the IMUK is forecasted using machine learning methods. A persistence model forecast to provide a reference for comparison was generated. The results are quantified in terms of the root mean square error (RMSE) and the mean absolute error (MAE). The new algorithm reduced both the RMSE and the MAE of the prediction by approximately 30% compared to the reference persistence model under diverse cloud conditions. The new algorithm could be used as a tool for the stable maintenance of the network for the transmission system operators, i.e., the primary control reserve (within 30 seconds) and the secondary control reserve (within 5 minutes).