Journal of Atmospheric Science Research

Machine Learning Based Drought Prediction Using the Standardized Precipitation Evapotranspiration Index (SPEI) in Kebbi State, Nigeria

Precious Eguagie-suyi — 2025-04-25

Drought represents a major threat to livelihoods and economic stability in regions prone to its occurrence. This paper aims to address the gap in applying machine learning techniques for enhanced meteorological drought prediction to support resilience and preparedness. The study focuses on Kebbi State, located in northwest Nigeria, which experiences droughts with devastating agricultural, ecological and humanitarian impacts. The Standardized Precipitation Evapotranspiration Index (SPEI) was used to calculate different drought severity based on rainfall deficit, over varying accumulation periods (3-month, 6-month) over four decades (1980–2022). Different time series meteorological parameters such as mean temperature, maximum temperature, minimum temperature, radiation, wind speed, precipitation were used in training machine learning models to predict and forecast future drought risk across Kebbi’s regions. Four candidate models were evaluated Random Forest (RF), Extreme Gradient Boosting (XGB), 1D Convolutional Neural Networks (CNN), and Long Short-Term Memory Networks (LSTM). Results indicate RF models consistently achieved the highest prediction accuracy (R2: 47–67%) for both short and long-term SPEI forecasts across different regions over the other models, while LSTM was not able to make good prediction for drought in Kebbi state. Optimized XGB models also performed reasonably well for specific locations. One-year lead SPEI projections exhibit XGB potential for advancing early warning given forecast reliabilities. This pioneering study provides robust evidence for integrating machine learning for drought prediction in Kebbi state, Nigeria, which is located in the sub-Saharan region.

Deep Learning-based Flood Risk Prediction for Climate Resilience Planning in Malawi

Isaac Kadono Mwalwimba — 2025-04-07

Climate change resilience in Malawi faces an institutional gap because most institutions often fail to prioritize risk data when dealing with climate extremes such as floods. This unfortunate gap forces many Malawians to fend for themselves during times of climate extremes. This situation is also heightened by a few studies that utilize Time Series Analysis (TSA) and Deep Learning Models (DLM) to predict climate extremes for decision-making processes. Therefore, this study focused on flood risk prediction and assessment in six selected districts of Malawi: Chikwawa, Blantyre, Phalombe, Zomba, Rumphi, and Karonga. Traditional Time Series Models (ARIMA) and Semantic Convolution Deep Learning Analysis were used for this purpose. Data were retrieved from the database of the US National Aeronautics and Space Administration (NASA). The results revealed frequent and significant precipitation peaks in Blantyre and Chikwawa, particularly during the rainy season, suggesting that the areas are at a higher risk of flooding, with a high probability of infrastructural damage and economic losses. Karonga and Phalombe revealed cyclical trends with prominent spikes in rainfall. In contrast, Rumphi and Zomba exhibit less pronounced trends, though there are still significant fluctuations in rainfall patterns, suggesting an increasing likelihood of flood risk in future climate extremes. This study situates its policy implications by emphasizing that residents, institutions, government, partners, and NGOs need to take a problem-focused approach towards climate resilience planning, including updating flood risk maps, designing flood protection infrastructure, and preparing emergency response plans tailored to the specific needs of each district in Malawi.

Warm Fog Artificial Dispersion, Preliminary Results

Alexandra Alekseeva — 2025-04-16

We describe the results of laboratory and field experiments aimed at dispersing warm fog. The laboratory experiments were conducted inside the Large Aerosol Chamber (volume: 3500 m³) RPA Typhoon (Obninsk, Russia) while the field experiments were carried out in the Caucasus foothills (Nalchik, Russia) and foothills close to Usui-Karuizawa (Japan). The results of experiments in the Large Aerosol Chamber demonstrated that the ion wind generated by the corona discharge lifted the fog cloud from a height of 3 m to 12 m. In the installation area, the fog dissipated and the visibility range increased dramatically. Field experiments in the North Caucasus revealed that the method for fog displacement from a controlled area with air stream electrically cleared from fog droplets could only be recommended to disperse fog in the area located downwind of the object. At the same time, the fog flow velocity should also be no more than 5 m/s. Statistics of field experiments at foothills close to Usui-Karuizawa (Japan) indicated that the effect of corona discharge on warm fog manifested itself in a noticeable change in fog density and range of visibility. The methods of fog displacement with air mechanically purified from water droplets are also considered from the point of view of its potential technical solutions.

Trends and Temporal of Rainfall Erosion due Variability Rainfall in Nakambè Watershed, Burkina Faso

Joseph Yaméogo — 2025-04-18

Understanding how rain erosion evolves and what determines it can contribute to the better management of soil resources. This study analyses the evolution of rain erosion in the Nakambè catchment in Burkina Faso between 1992 and 2022. Monthly rainfall data for this period were extracted from NASA POWER. Erodibility indices were then employed to evaluate the extent of erosion. Precipitation variability was assessed using the coefficients of variation and the standardized precipitation index. The study shows that precipitation varied within the catchment area during this period. This variation is seasonal, as it fluctuates before, during and after the rainy season, with a coefficient of variation ranging from 18 during the rainy season to 556.18 after the rainy season. The catchment also exhibits multi-year fluctuations, long-term fluctuations or perennial variations (1992–2004 and 2004–2022). The study also shows that rain erosion varies annually and seasonally. The Fournier, Arnoldus and rainfall concentration indices indicate variability in erosivity, with a significant increase in August. It also appears that rainfall trends and variability have an impact on erosion in the catchment. For example, erosion increases with precipitation concentration and the standardized rainfall anomaly over the period 1992-2022. The cumulative effect of precipitation concentration—reflected in increased rainfall during July and August—along with the wet phase of the 1992–2022 period, are the main determining factors for rain erosion in the catchment. It is therefore important to limit the construction of dams in the basin, as they may contribute to the continued degradation of the catchment.

The Influence of Atmospheric Microplastics on Global Climate Dynamics: An Interdisciplinary Review

Estefan M. da Fonseca — 2025-04-20

This article examines the growing concern over microplastics in the atmosphere and their potential effects on climate systems and atmospheric circulation. It explores the role of natural aerosols in atmospheric processes, highlighting how these particles influence cloud formation, radiative forcing, and global circulation patterns. It contrasts these natural aerosols with microplastics, which, because of their unique physical and chemical properties, behave differently in the atmosphere. Microplastics, unlike natural aerosols, are resistant to degradation, leading to their cumulative accumulation in the atmosphere. Their persistence and transport in the atmospheric column are influenced by diffusion dynamics, allowing them to travel over long distances, potentially impacting weather patterns and climate systems far from their original sources. Microparticles may also alter cloud properties, influencing precipitation, radiation balance, and atmospheric chemistry. The diffusion behavior of microplastics, their interaction with other airborne pollutants, and their potential to influence advanced climate models are discussed. The cumulative effect of these persistent pollutants, coupled with their resistance to biological degradation, may have serious long-term implications for atmospheric composition and global climate patterns. There is a growing need for further interdisciplinary research into the interaction between microplastics and natural aerosols in order to fully understand their diverse impacts on climate systems and atmospheric dynamics.