Solar ultraviolet radiation (UVR) is a highly energetic component of the solar spectrum that needs to be monitored because of the effects on human health and on the ecosystems. In Brazil, few cities monitor UVR, especially in the Amazon region which is particularly poor in observation. This work is the first to address the short-term (2-year) time variability of UVR in Santarém (2°25′ S, 54°44′ W, 51 m) using ground-based measurements. The irradiance in the wavelength range of 250–400 nm was investigated on different time scales. Furthermore, to understand how the UVR varies without the influence of clouds, the hours corresponding to the clear sky condition were analyzed as well as the hours in all sky conditions. Regarding the averages, there is a slight variation over the year. In all sky and clear sky conditions, the dry season had a higher average than the rainy season, despite the slight difference. Also, both in all-sky and clear-sky conditions the maximums occurred around local solar noon, and reached a maximum of 87 $\mathrm{W}/{\mathrm{m}}^2$ in the dry season under the clear sky condition. Further understanding of the radiative effects of the clouds in UVR time variability is considered essential for future research. This study can serve as a reference for UVR levels in this region where no other ground-based UVR measurements are made.

Different algorithms for forecasting and tracking meteorological systems have been developed over the years. Many of them are used to study cloud propagation, precipitation and lightning for nowcasting. Therefore, it is necessary to define carefully the parameters (e.g., intensity thresholds and minimum size) that impact tracking of these variables. In order to represent the physical aspects of rain propagation over the Amazon region, several methods of correction and displacement detection were studied. Different parameters were used to validate the methods based on the extrapolated rain cell. A probability detection of 78.4% and 68.6% was achieved for 20 dBZ thresholds during the wet and dry season, respectively. However, the POD decreases for higher reflectivity thresholds. The results for corrections by Inner Nuclei showed that embedded convection can dictate the propagation of rain cells. Split and merge corrections performed well; however, they applied only to a few cases. Corrections performed better for precipitating systems with larger areas and longer duration. The correction methods showed similar skills for both seasons. Which shows that they are able to monitor rain cells throughout the year. The automated combination of different methods for the 20 dBZ threshold proved to be the best choice for tracking rainfall in the Amazon region.

This study evaluates the performance of two deep learning architectures, U-Net and convolutional long short-term memory (ConvLSTM), for predicting cloud-to-ground (CG) lightning probability in the central Amazon basin. Utilizing data from S-band weather radar and very low-frequency (VLF) lightning detection networks, we explored nowcasting capabilities at 12- and 6-min intervals. Various data configurations were tested, specifically examining the integration of volumetric radar reflectivity (dB Z ) and echo-top 35-dBZ (ET35). The evaluation encompassed objective skill metrics and spatial error analyses, accounting for sensor uncertainties. Results reveal a critical divergence in multimodal data assimilation. While the U-Net struggled with volumetric inputs, the ConvLSTM architecture successfully leveraged dB Z data, achieving the highest critical success index (CSI) of 0.546 and an effective spatial scale of 6 km, notably outperforming persistence baselines. Conversely, U-Net performed best using only quality-controlled lightning data or lightweight ET35 inputs. Furthermore, 6-min experiments demonstrated that extending the temporal lookback window notably enhances the skill of recurrent models. Spatial error analyses indicated well-collocated clusters with average centroid errors below 6 km at optimal probability thresholds. These findings suggest that while U-Net provides a robust baseline, ConvLSTM is superior for integrating high-dimensional radar variables in very short-term lightning nowcasting. Significance Statement: This exploratory study evaluates and compares emerging computational approaches for meteorological forecasting, specifically examining the effectiveness of U-Net and convolutional long short-term memory (ConvLSTM) architectures in predicting cloud-to-ground lightning probabilities in the central Amazon basin. By integrating data from weather radar and lightning detection networks, the research investigates methodological solutions for very short-term lightning prediction (6–12 min) in one of Earth’s most climatically complex regions. The comparative analysis reveals a critical distinction in data assimilation capabilities. While the ConvLSTM successfully leverages volumetric radar reflectivity to achieve effective spatial scales of 6 km, the U-Net performs optimally with simplified inputs like echo tops. This work identifies robust configurations that surpass traditional persistence baselines, laying the foundation for next-generation early warning systems capable of mitigating the socioeconomic impacts and risks of human fatalities caused by lightning.

In this work, machine learning techniques were applied to detect clusters present in satellite and weather radar images. The technique used was the unsupervised clustering algorithm DBSCAN. This algorithm was used to extract the morphological characteristics of atmospheric systems that occurred between February 1 and March 30, 2014 (rainy season) and September 15 to October 15, 2014 (dry season). The morphological characteristics are extracted from different thresholds (235K, 220K and 210K) of cloud top brightness temperature observed in the infrared channel of GOES-13 satellite, and also the precipitation estimated at the reflectivity thresholds (20dBZ, 30dBZ and 40dBZ) of the SIPAM meteorological radar in the city of Manaus. The results present the number of clusters identified by the algorithm and described the characteristics of the clusters during the diurnal cycle and in both seasons.

Brazil is one of countries highest incidence of lightning in the world and the characterization of thus event can help in the development of public polices and decision-making by authorities to mitigate the socio-economic damage that may be caused. This work presents some analysis of spatio-temporal patterns of lightnings in Brazil in 2020, generated from Self-Organizing Map (SOM) technique. This analysis considers the activity of the lightning in the hourly, daily and monthly periods accumulated in the different Brazilian states. The seasonal variation of lightning was also evaluated, considering the four seasons of 2020. The results showed that the self-organizing maps were efficient in identifying spatio-temporal patterns of lightning, which are highly variability events. Thus, theses results can support the development of new tools or analysis in which the spatio-temporal information lightning is important, for example, in warning and forecasting systems.

Precipitating systems (PSs) are key components of atmospheric dynamics, shaping both regional and global hydrological cycles. Accurate identification, tracking, and forecasting of these systems are essential for improving weather and climate predictions and mitigating the socio-economic impacts of extreme events. This study presents a global climatology of PSs based on the pyForTraCC (Python Forecasting and Tracking the Evolution of Configurable Clusters) algorithm, developed to identify and track PSs using satellite-based precipitation datasets. The algorithm applies multi-threshold segmentation, clustering, and vectorization techniques to extract features from GSMaP/MVK version 8 data, covering the period from 2015 to 2024 and spanning latitudes from 60°N to 60°S. This decade was selected specifically because it relies exclusively on data from the Global Precipitation Measurement (GPM) mission, ensuring the highest consistency and quality in satellite-derived precipitation estimates. The latest version of GSMaP includes significant improvements from the GPM era, such as enhanced inter-sensor calibration and the Microwave Rainfall Normalization module, which standardizes estimates across different sensors. In this study, pyForTraCC tracks PSs using four precipitation thresholds (0.1, 1, 5, and 10 mm/h), classifies clusters into six evolutionary types, and applies a 10% spatial overlap criterion to ensure continuity across time steps. To reduce uncertainties associated with displacement vectors, multiple correction methods were tested and validated using persistence-based forecasting and minimization of the False Alarm Rate (FAR). Only systems with a minimum duration of three hours and a spatial extent larger than 10 km² were included to ensure robustness. The resulting global climatology reveals spatial and seasonal distributions of PSs aligned with major atmospheric features such as convergence zones, monsoon regions, and storm tracks. Additionally, a high variability in the response to climate change can be observed. For example, in some regions, such as the Amazon Basin, precipitating systems are becoming more intense, and certain convergence zones are persisting for longer periods. Most importantly, this work provides the scientific community with both a flexible, open-source tool for PS tracking and a publicly available, curated database of all tracked systems over a full decade of high-quality GPM observations. This dataset includes detailed information on size, duration, intensity, and displacement, supporting future research on precipitation regimes, climate variability, and extreme weather. By making both the algorithm and database openly accessible, this study contributes to advancing satellite precipitation validation, nowcasting applications using AI, and data-driven meteorological research.