The focus of nowcasting development is transitioning from physically motivated advection methods to purely data-driven Machine Learning (ML) approaches. Nevertheless, recent work indicates that incorporating advection into the ML value chain has improved skill for radar-based precipitation nowcasts. However, the generality of this approach and the underlying causes remain unexplored. This study investigates the generality by probing the approach on satellite-based thunderstorm nowcasts for the first time. Resorting to a scale argument, we then put forth an explanation when and why skill improvements can be expected. In essence, advection guarantees that thunderstorm patterns relevant for nowcasting are contained in the receptive field at long forecast times. To test our hypotheses, we train ResU-Nets solving segmentation tasks with lightning observations as ground truth. The input of the Baseline Neural Network (BNN) are short time series of multispectral satellite imagery and lightning observations, whereas the Advection-Informed Neural Network (AINN) additionally receives the Lagrangian persistence nowcast of all input channels at the desired forecast time. Overall, we find only a minor skill improvement of the AINN over the BNN when considering fully averaged scores. However, assessing skill conditioned on forecast time and advection speed, we demonstrate that our scale argument correctly predicts the onset of skill improvement of the AINN over the BNN after 2h forecast time. We confirm that, generally, advection becomes gradually more important with longer forecast times and higher advection speeds. Our work accentuates the importance of considering and incorporating the underlying physical scales when designing ML-based forecasting models.

This paper presents a convolutional neural network model for precipitation nowcasting that combines data-driven learning with physics-informed domain knowledge. We propose LUPIN, a Lagrangian Double U-Net for Physics-Informed Nowcasting, that draws from existing extrapolation-based nowcasting methods and implements the Lagrangian coordinate system transformation of the data in a fully differentiable and GPU-accelerated manner to allow for real-time end-to-end training and inference. Based on our evaluation, LUPIN matches and exceeds the performance of the chosen benchmark, opening the door for other Lagrangian machine learning models.

This study presents the application of generative deep learning techniques to evaluate marine fog visibility nowcasting using the FATIMA (Fog and turbulence interactions in the marine atmosphere) campaign observations collected during July 2022 in the North Atlantic in the Grand Banks area and vicinity of Sable Island (SI), northeast of Canada. The measurements were collected using the Vaisala Forward Scatter Sensor model FD70 and Weather Transmitter model WXT50, and Gill R3A ultrasonic anemometer mounted on the Research Vessel Atlantic Condor. To perform nowcasting, the time series of fog visibility (Vis), wind speed, dew point depression, and relative humidity with respect to water were preprocessed to have lagged time step features. Generative nowcasting of Vis time series for lead times of 30 and 60 minutes were performed using conditional generative adversarial networks (cGAN) regression at visibility thresholds of Vis < 1 km and < 10 km. Extreme gradient boosting (XGBoost) was used as a baseline method for comparison against cGAN. At the 30 min lead time, Vis was best predicted with cGAN at Vis < 1 km (RMSE = 0.151 km) and with XGBoost at Vis < 10 km (RMSE = 2.821 km). At the 60 min lead time, Vis was best predicted with XGBoost at Vis < 1 km (RMSE = 0.167 km) and Vis < 10 km (RMSE = 3.508 km), but the cGAN RMSE was similar to XGBoost. Despite nowcasting Vis at 30 min being quite difficult, the ability of the cGAN model to track the variation in Vis at 1 km suggests that there is potential for generative analysis of marine fog visibility using observational meteorological parameters.

We investigate the predictive power of different machine learning algorithms to nowcast Madagascar's gross domestic product (GDP). We trained popular regression models, including linear regularized regression (Ridge, Lasso, Elastic-net), dimensionality reduction model (principal component regression), k-nearest neighbors algorithm (k-NN regression), support vector regression (linear SVR), and tree-based ensemble models (Random forest and XGBoost regressions), on 10 Malagasy quarterly macroeconomic leading indicators over the period 2007Q1--2022Q4, and we used simple econometric models as a benchmark. We measured the nowcast accuracy of each model by calculating the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Our findings reveal that the Ensemble Model, formed by aggregating individual predictions, consistently outperforms traditional econometric models. We conclude that machine learning models can deliver more accurate and timely nowcasts of Malagasy economic performance and provide policymakers with additional guidance for data-driven decision making.

Nowcasting can play a key role in giving policymakers timelier insight to data published with a significant time lag, such as final GDP figures. Currently, there are a plethora of methodologies and approaches for practitioners to choose from. However, there lacks a comprehensive comparison of these disparate approaches in terms of predictive performance and characteristics. This paper addresses that deficiency by examining the performance of 12 different methodologies in nowcasting US quarterly GDP growth, including all the methods most commonly employed in nowcasting, as well as some of the most popular traditional machine learning approaches. Performance was assessed on three different tumultuous periods in US economic history: the early 1980s recession, the 2008 financial crisis, and the COVID crisis. The two best performing methodologies in the analysis were long short-term memory artificial neural networks (LSTM) and Bayesian vector autoregression (BVAR).

The COVID-19 pandemic has demonstrated the increasing need of policymakers for timely estimates of macroeconomic variables. A prior UNCTAD research paper examined the suitability of long short-term memory artificial neural networks (LSTM) for performing economic nowcasting of this nature. Here, the LSTM's performance during the COVID-19 pandemic is compared and contrasted with that of the dynamic factor model (DFM), a commonly used methodology in the field. Three separate variables, global merchandise export values and volumes and global services exports, were nowcast with actual data vintages and performance evaluated for the second, third, and fourth quarters of 2020 and the first and second quarters of 2021. In terms of both mean absolute error and root mean square error, the LSTM obtained better performance in two-thirds of variable/quarter combinations, as well as displayed more gradual forecast evolutions with more consistent narratives and smaller revisions. Additionally, a methodology to introduce interpretability to LSTMs is introduced and made available in the accompanying nowcast_lstm Python library, which is now also available in R, MATLAB, and Julia.

Weather plays an important role in our everyday lives. Among other weather conditions, rain influences our day-to-day decisions significantly. Weather forecasting has always been important to our communities and countries throughout history. Machine learning has found applications in almost every field, and weather forecasting is no longer an exception. DeepMind's recent study presents a cutting-edge model that forecasts rain (and other precipitation phenomena) within the next 1-2 hours.

Updating observations of a signal due to the delays in the measurement process is a common problem in signal processing, with prominent examples in a wide range of fields. An important example of this problem is the nowcasting of COVID-19 mortality: given a stream of reported counts of daily deaths, can we correct for the delays in reporting to paint an accurate picture of the present, with uncertainty? Without this correction, raw data will often mislead by suggesting an improving situation. We present a flexible approach using a latent Gaussian process that is capable of describing the changing auto-correlation structure present in the reporting time-delay surface. This approach also yields robust estimates of uncertainty for the estimated nowcasted numbers of deaths. We test assumptions in model specification such as the choice of kernel or hyper priors, and evaluate model performance on a challenging real dataset from Brazil. Our experiments show that Gaussian process nowcasting performs favourably against both comparable methods, and a small sample of expert human predictions. Our approach has substantial practical utility in disease modelling -- by applying our approach to COVID-19 mortality data from Brazil, where reporting delays are large, we can make informative predictions on important epidemiological quantities such as the current effective reproduction number.

Heavy rainfall events can cause major disruption to human activities. It is desirable to predict these events ahead of time so that decision makers can take action to protect life, property and prosperity. Nowcasting, or short-term forecasting from observations, remains an important tool in predicting these events. The essential goals of nowcasting are identical to those of all weather forecasting, with the only difference being the spatial and temporal scales involved. The World Meteorological Organization (WMO, 2016) distinguishes among the various forecasting time horizons as: "Usually forecasts for the next 0-2 hours are called nowcasting, from 2-12 hours very short-range forecasting (VSRF), and short-range forecasting beyond that; but the capabilities of the different ranges can vary upon variables and weather situations." Radar-based nowcasting emerged in an era of mainly synoptic and mesoscale weather prediction. Predicting rainfall during that time was a challenge for numerical weather prediction (NWP) models, since computational restrictions limited the resolution at which NWP models could operate. As a result, NWP models were able to capture mesoscale weather patterns such as fronts, but not the smaller-scale convective patterns that occur within mesoscale systems. Thus, these models had limited utility in predicting rainfall in the early hours of the forecast because of its dependence on the unrepresented small scales.