Prediction of severe thunderstorm events with ensemble deep learning and radar data.

The problem of nowcasting extreme weather events can be addressed by applying either numerical methods for the solution of dynamic model equations or data-driven artificial intelligence algorithms. Within this latter framework, the most used techniques rely on video prediction deep learning methods which take in input time series of radar reflectivity images to predict the next future sequence of reflectivity images, from which the predicted rainfall quantities are extrapolated. Differently from the previous works, the present paper proposes a deep learning method, exploiting videos of radar reflectivity frames as input and lightning data to realize a warning machine able to sound timely alarms of possible severe thunderstorm events. The problem is recast in a classification one in which the extreme events to be predicted are characterized by a an high level of precipitation and lightning density. From a technical viewpoint, the computational core of this approach is an ensemble learning method based on the recently introduced value-weighted skill scores for both transforming the probabilistic outcomes of the neural network into binary predictions and assessing the forecasting performance. Such value-weighted skill scores are particularly suitable for binary predictions performed over time since they take into account the time evolution of events and predictions paying attention to the value of the prediction for the forecaster. The result of this study is a warning machine validated against weather radar data recorded in the Liguria region, in Italy.

Bad and Good Errors: Value-Weighted Skill Scores in Deep Ensemble Learning.

Forecast verification is a crucial task for assessing the predictive power of prognostic model forecasts and it is usually implemented by checking quality-based skill scores. In this article, we propose a novel approach to realize forecast verification focusing not just on the forecast quality but rather on its value. Specifically, we introduce a strategy for assessing the severity of forecast errors based on the evidence that, on the one hand, a false alarm just anticipating an occurring event is better than one in the middle of consecutive nonoccurring events, and that, on the other hand, a miss of an isolated event has a worse impact than a miss of a single event, which is part of several consecutive occurrences. Relying on this idea, we introduce a notion of value-weighted skill scores giving greater importance to the value of the prediction rather than to its quality. Then, we introduce an ensemble strategy to maximize quality-based and value-weighted skill scores independently of one another. We test it on the predictions provided by deep learning methods for binary classification in the case of four applications concerned with pollution, space weather, stock price, and IoT data stream forecasting. Our experimental studies show that using the ensemble strategy for maximizing the value-weighted skill scores generally improves both the value and quality of the forecast.

First Hard X-Ray Imaging Results by Solar Orbiter STIX.

The Spectrometer/Telescope for Imaging X-rays (STIX) is one of six remote sensing instruments on-board Solar Orbiter. The telescope applies an indirect imaging technique that uses the measurement of 30 visibilities, i.e., angular Fourier components of the solar flare X-ray source. Hence, the imaging problem for STIX consists of the Fourier inversion of the data measured by the instrument. In this work, we show that the visibility amplitude and phase calibration of 24 out of 30 STIX sub-collimators has reached a satisfactory level for scientific data exploitation and that a set of imaging methods is able to provide the first hard X-ray images of solar flares from Solar Orbiter. Four visibility-based image reconstruction methods and one count-based are applied to calibrated STIX observations of six events with GOES class between C4 and M4 that occurred in May 2021. The resulting reconstructions are compared to those provided by an optimization algorithm used for fitting the amplitudes of STIX visibilities. We show that the five imaging methods produce results morphologically consistent with the ones provided by the Atmospheric Imaging Assembly on board the Solar Dynamic Observatory (SDO/AIA) in UV wavelengths. The χ 2 values and the parameters of the reconstructed sources are comparable between methods, thus confirming their robustness.

Computational quantification of global effects induced by mutations and drugs in signaling networks of colorectal cancer cells.

Colorectal cancer (CRC) is one of the most deadly and commonly diagnosed tumors worldwide. Several genes are involved in its development and progression. The most frequent mutations concern APC, KRAS, SMAD4, and TP53 genes, suggesting that CRC relies on the concomitant alteration of the related pathways. However, with classic molecular approaches, it is not easy to simultaneously analyze the interconnections between these pathways. To overcome this limitation, recently these pathways have been included in a huge chemical reaction network (CRN) describing how information sensed from the environment by growth factors is processed by healthy colorectal cells. Starting from this CRN, we propose a computational model which simulates the effects induced by single or multiple concurrent mutations on the global signaling network. The model has been tested in three scenarios. First, we have quantified the changes induced on the concentration of the proteins of the network by a mutation in APC, KRAS, SMAD4, or TP53. Second, we have computed the changes in the concentration of p53 induced by up to two concurrent mutations affecting proteins upstreams in the network. Third, we have considered a mutated cell affected by a gain of function of KRAS, and we have simulated the action of Dabrafenib, showing that the proposed model can be used to determine the most effective amount of drug to be delivered to the cell. In general, the proposed approach displays several advantages, in that it allows to quantify the alteration in the concentration of the proteins resulting from a single or multiple given mutations. Moreover, simulations of the global signaling network of CRC may be used to identify new therapeutic targets, or to disclose unexpected interactions between the involved pathways.