Climatological Data Research Articles

Intensification mechanisms and moisture dynamics of super cyclonic storm ‘Amphan’ over the Bay of Bengal: Implications for aerosol re-distribution

The present research investigates the dynamics and underlying causes contributing to the exceptional intensity of Super Cyclonic Storm (SuCS) Amphan (16th to 21st May 2020) over the Bay of Bengal (BoB), as well as its impact on aerosol redistribution along the four cities of eastern coast and north-eastern India. Notably, the SuCS was formed during the first phase of the COVID-19 lockdown in India, giving it a unique aspect of study and analysis. Our analysis based on 30 years of climatology data from Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) reanalysis reveals ‘positive’ monthly anomalous winds (0.8 to 1.6 m/s) prevailed over the central BoB for May 2020. The present study further found the evolution of ‘barrier layer thickness’(BLT) leading up to landfall, noting a thickening trend from 8 to 3 days before landfall, contributing to maintaining warmer sea surface temperatures near the coast. Additionally, utilizing European Centre for Medium-Range Weather Forecasts (ECMWF), reanalysis version-5 (ERA-5) data, a mean positive sea surface temperature (SST) anomaly of 0.8 to 1 °C was observed ‘before’ cyclone period (10–15 May 2020) near the cyclogenesis point. A detailed examination of Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) vertical cross-section plots during the cyclone's intensification stage reveals the presence of high-altitude clouds composed primarily of ice crystals. Further, analysis also indicates that the cyclone transported Sea-salt PM2.5 aerosols from the ocean, dispersing them in the landfall region.The aerosol optical Depth (AOD) data obtained from the National Aeronautics and Space Administration's (NASA) ‘Clouds and the Earth's Radiant Energy System (CERES)’ mission and MERRA-2 were also analysed, revealing that the cyclone redistributed aerosols over the Bengal basin region (mainly over ‘Kolkata') and three other nearby cities along the track of the cyclone (i.e., Bhubaneswar (Odisha) Agartala (Tripura) and Shillong (Meghalaya) respectively).

The Nexus of Climate Change, Food Insecurity, and Conflict in Somalia: A Comprehensive Analysis of Multifaceted Challenges and Resilience Strategies

Climate change poses a significant threat to Somalia’s food security and stability. This review examines the complex interplay between climate change impacts, food insecurity, and conflict in Somalia. Recent climate data and forecasts paint a concerning picture: the rainfall probabilistic forecast for April- June 2024 indicates a high likelihood of above-normal rainfall across much of Somalia, thus increasing the flood risks. Concurrently, temperature forecasts project above-normal temperatures, potentially exacerbating drought conditions between the rainy seasons. Historical climatology data reveal Somalia’s vulnerability, with average temperatures ranging from 25°C to 30°C and significant seasonal variations affecting agriculture and water resources. These climate trends, combined with ongoing political instability and weak governance, have created a storm of challenges. This perspective explores how recurrent droughts and floods disrupt agricultural production, decimate livestock, and displace vulnerable populations, particularly those affecting rural and nomadic communities. It also examines how environmental stress exacerbates poverty and conflict, thereby creating a vicious cycle of vulnerability. This analysis draws on recent data on poverty rates, food expenditure patterns, and climate-related displacement, to illustrate the multifaceted nature of the crisis. Finally, this perspective proposed recommendations for building climate resilience, enhancing food security, and promoting sustainable development in Somalia, emphasizing the need for integrated approaches that combine immediate humanitarian assistance with long-term adaptation strategies.

The first outbreak of Lumpy Skin Disease in Indonesia.

This study describes the first outbreak of Lumpy Skin Disease (LSD) in cattle in the Bengkalis region, Indonesia, and vaccination to control the epidemic. Data on the outbreak and vaccination was obtained from the local veterinary authority of the Bengkalis region, Indonesia. Climatological data was provided by the Meteorological, Climatological, and Geophysical Agency of Riau Province. Over the 5.5 months, the outbreak caused 10.4% (94/906) morbidity and 0.6% (6/906) mortality of cattle on infected farms. Temporally, three epidemic waves occurred during the outbreak period. Villages with cattle populations of > 150 animals (n = 36) were 5.3 times more likely to be infected with LSD compared to villages with smaller cattle populations (n = 107) (CI: 2.56-10.90, P < 0.01). The vaccination campaign covered 43.8% of cattle in villages within a 10km radius of the cases. However, vaccination in villages with larger cattle populations (n = 29) was 0.63 less likely to cover 50% of the cattle populations compared to villages with smaller cattle populations (n = 41) (CI: 0.39-1.02, P = 0.05). By the time the first two and the major waves ceased, vaccination had covered only 0.0% (n = 6036), 27.8% (n = 6,036) and 9.7% (n = 5,697) of the cattle in the 10km radius of the respective spatial clusters. The outbreak was statistically associated with rainfall and its interaction with temperature (F(2, 13) = 5.822, R2 = 0.47, P = 0.016). This study indicates that the LSD outbreak had low morbidity and mortality. Despite the low vaccination rate, the outbreak ceased, possibly due to plummeting of the abundance of insect vectors.

The Use of Machine Learning to Predict Prevalence of Subclinical Mastitis in Dairy Sheep Farms.

The objective of the study was to develop a computational model with which predictions regarding the level of prevalence of mastitis in dairy sheep farms could be performed. Data for the construction of the model were obtained from a large Greece-wide field study with 111 farms. Unsupervised learning methodology was applied for clustering data into two clusters based on 18 variables (17 independent variables related to health management practices applied in farms, climatological data at the locations of the farms, and the level of prevalence of subclinical mastitis as the target value). The K-means tool showed the highest significance for the classification of farms into two clusters for the construction of the computational model: median (interquartile range) prevalence of subclinical mastitis among farms was 20.0% (interquartile range: 15.8%) and 30.0% (16.0%) (p = 0.002). Supervised learning tools were subsequently used to predict the level of prevalence of the infection: decision trees, k-NN, neural networks, and Support vector machines. For each of these, combinations of hyperparameters were employed; 83 models were produced, and 4150 assessments were made in total. A computational model obtained by means of Support vector machines (kernel: 'linear', regularization parameter C = 3) was selected. Thereafter, the model was assessed through the results of the prevalence of subclinical mastitis in 373 records from sheep flocks unrelated to the ones employed for the selection of the model; the model was used for evaluation of the correct classification of the data in each of 373 sets, each of which included a test (prediction) subset with one record that referred to the farm under assessment. The median prevalence of the infection in farms classified by the model in each of the two categories was 10.4% (5.5%) and 36.3% (9.7%) (p < 0.0001). The overall accuracy of the model for the results presented by the K-means tool was 94.1%; for the estimation of the level of prevalence (<25.0%/≥25.0%) in the farms, it was 96.3%. The findings of this study indicate that machine learning algorithms can be usefully employed in predicting the level of subclinical mastitis in dairy sheep farms. This can facilitate setting up appropriate health management measures for interventions in the farms.

Modeling and simulation for flashover location determination on 150 kV insulator string

The 150 kV Payakumbuh-Koto Panjang transmission line in West Sumatra is located in an area with high lightning activity. Based on Meteorological, Climatological, and Geophysical Agency (BMKG) data (2017-2023), the average number of lightning days per year (IKL: isokeraunic level) reaches 165-173 days/year, and 79% of the transmission towers are located in hilly and rocky areas. This causes contamination of the insulator, which can reduce its performance and cause flashovers in the insulator circuit. However, in the field, finding flash points in insulators is still a challenge. Therefore, simulation must be used as a tool to determine the location of flashover in an insulator circuit that is affected by temperature and humidity. Simulation by modeling flashover provides an effective solution for determining the location of flashover in insulator circuits, which is the novelty of this research. This research compares laboratory test results with manual calculations modeled using Visual Basic 6. The research results show that temperature and humidity have a significant influence on determining the flashover voltage value on the insulator. The flashover locations during the test are the same as the calculated flashover locations, as shown by these simulations and modeling.

Studies on Variation of Temperature and Rainfall using Climatological data for the Plain and Hill zones of Uttarakhand

The present study examines long-term annual, seasonal and monthly changes and short-term fluctuations in monsoonal rainfall and temperature over plain and hill zones of Uttarakhand. Both rainfall and temperature data for period of 1981-2020 were analyzed in this study. Statistical trend analysis techniques namely Mann–Kendall test and Sen’s slope estimator were used to examine and analyze the problems. The detailed analysis of the data for 40 years indicates that the annual range of temperature is increasing in the hill zone. In the context of agriculture, the observed trends in temperature and rainfall patterns pose significant implications for farming practices and crop yields in Uttarakhand. The increasing annual range of temperature, particularly in the hill zone, suggests a heightened risk of temperature extremes such as heat waves and cold spells. During the monsoon season, while rainfall levels may remain relatively stable or exhibit minor fluctuations, the variability highlighted by the box and whisker plots underscores the importance of preparedness for both excess and deficit rainfall scenarios.

Neural Hierarchical Interpolation for Standardized Precipitation Index Forecasting

In the context of climate change, studying changes in rainfall patterns is a crucial area of research, remarkably so in arid and semi-arid regions due to the susceptibility of human activities to extreme events such as droughts. Employing predictive models to calculate drought indices can be a useful method for the effective characterization of drought conditions. This study applies two type of machine learning methods—long short-term memory (LSTM) and Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS)—to develop and deploy artificial neural network models with the aim of predicting the regional standardized precipitation index (SPI) in four regions of Zacatecas, Mexico. The predictor variables were a set of climatological time series data spanning from 1964 to 2020. The results suggest that the N-HiTS model outperforms the LSTM model in the prediction and forecasting of SPI time series for all regions in terms of performance metrics: the Mean Squared Error, Mean Absolute Error, Coefficient of Determination and ξ correlation coefficient range from 0.0455 to 0.5472, from 0.1696 to 0.6661, from 0.9162 to 0.9684 and from 0.9222 to 0.9368, respectively, for the regions under study. Consequently, the outcomes revealed the successful performance of the N-HiTS models in accurately predicting the SPI across the four examined regions.

Auto-Machine-Learning Models for Standardized Precipitation Index Prediction in North–Central Mexico

Certain impacts of climate change could potentially be linked to alterations in rainfall patterns, including shifts in rainfall intensity or drought occurrences. Hence, predicting droughts can provide valuable assistance in mitigating the detrimental consequences associated with water scarcity, particularly in agricultural areas or densely populated urban regions. Employing predictive models to calculate drought indices can be a useful method for the effective characterization of drought conditions. This study applied an Auto-Machine-Learning approach to deploy Artificial Neural Network models, aiming to predict the Standardized Precipitation Index in four regions of Zacatecas, Mexico. Climatological time-series data spanning from 1979 to 2020 were utilized as predictive variables. The best models were found using performance metrics that yielded a Mean Squared Error, Mean Absolute Error, and Coefficient of Determination ranging from 0.0296 to 0.0388, 0.1214 to 0.1355, and 0.9342 to 0.9584, respectively, for the regions under study. As a result, the Auto-Machine-Learning approach successfully developed and tested Artificial Neural Network models that exhibited notable predictive capabilities when estimating the monthly Standardized Precipitation Index within the study region.

Ensemble hydrological predictions at an intraseasonal scale through a statistical–dynamical downscaling approach over southwestern Amazonia

ABSTRACT We developed and analyzed the performance of an ensemble forecasting system for the Madeira River basin, the largest sub-basin of the Amazon, with forecasts up to 30 days under different hydrometeorological conditions. We used outputs from the regional Eta model of precipitation and global climatological data as inputs to a large-scale hydrological model. Bias correction of precipitation through quantile mapping significantly improved the results, achieving a hit rate &amp;gt;70%. The system demonstrated the ability to discriminate between high, medium, and low flow conditions. Forecast performance is better for larger catchment areas. This system is expected to increase decision-making efficiency for flood and drought situations in the largest Amazon tributary.

Flood risk assessment of the Garita River in the urban zone of San Luis Potosí City, by hydrodynamic modeling

Rapid and uncontrolled urban growth and land use changes in watersheds worldwide have led to increased surface runoff within metropolitan areas, coupled with climate change, creating a risk for residents during the rainy season. The city of San Luis Potosí is no exception to this phenomenon. One affected watercourse is the Garita Stream, which flows inside the city near urbanization. It is essential to analyze the effects of urban sprawl on this stream based on historical precipitation data for the town. Hydrological and topographical information were required to conduct this research. The hydrological study of the basin involved analyzing the region’s geomorphology and historical climatological data. For the stream’s topography, aerial photogrammetry using an unmanned aerial Vehicle (UAV) and Global Navigation Satellite System (GNSS) equipment was employed to conduct topographic surveys in the area. To find out when the Garita stream would overflow and which areas are most likely to flood, numerical modeling was done using 1D, 2D, and 3D programs like SWMM5 (Storm Water Management Model), HEC-RAS (Hydrologic Engineering Center’s River Analysis System), and EDFC Explorer (Environmental Fluid Dynamics Code). These models simulated different return periods and their correlation with current flooding events recorded in the area, thereby further proposing solutions to mitigate overflow issues. By conducting these simulations and analyzing the results, solutions can be suggested to address the overflow problems in the area based on historical flood events at various return periods caused by the Garita Stream.

BULL Database – Spanish Basin attributes for Unravelling Learning in Large-sample hydrology

We present a novel basin dataset for large-sample hydrological studies in Spain. BULL comprises data for 484 basins, combining hydrometeorological time series with several attributes related to geology, soil, topography, land cover, anthropogenic influence and hydroclimatology. Thus, we followed recommendations in the CARAVAN initiative for generating a truly open global hydrological dataset to collect these attributes. Several climatological data sources were used, and their data were validated by hydrological modelling. One of the main novelties of BULL compared to other national-scale datasets is the analysis of the hydrological alteration of the basins included in this dataset. This aspect is critical in countries such as Spain, which are characterised by rivers suffering from the highest levels of anthropisation. The BULL dataset is freely available at https://zenodo.org/records/10605646.

A study on spatio-temporal trend of rubber leaf fall phenomenon using planetscope multi-index vegetation imagery in relations to climatological conditions

Background: Rubber plants are one of the most important plantation commodities in Indonesia. However, rubber production has declined due to leaf fall disease caused by the pathogen Pestalotiopsis sp. This study aims to analyze the spatial and temporal distribution of rubber plant leaf fall disease using multi-vegetation indices from PlanetScope imagery, as well as to analyze the influence of climatological conditions on the disease. Methods: The research was conducted at the Sembawa Rubber Research Center Garden, South Sumatra, using PlanetScope imagery data and climatological data in 2017 (before leaf fall) and 2023 (after leaf fall). Finding: Spatially, the 2023 leaf fall occurred in almost the entire garden area with poor to moderate levels. Blocks 2013D, 2012F, and 2009F experienced the most severe levels, with a total defoliated area reaching 396.76 ha. Analysis of monthly variations in vegetation index values revealed a decrease in values during leaf fall due to Pestalotiopsis sp., specifically in February, May, and September 2023. Statistical test results showed significant differences in vegetation index values between 2017 and 2023. Furthermore, based on Spearman's correlation analysis, there was a positive correlation between vegetation index values and humidity, but no significant correlation with rainfall and temperature. Conclusion: This research provides insights into mapping and monitoring rubber leaf fall disease using remote sensing data and climatological factors, which can be used for more effective rubber plantation management. However, the study has some limitations: monthly Planet data for 2017 is not fully available, several Planet image scenes from 2017 still have more than 50% cloud cover, and there may be biases as plants falling into the low health class are included in the high range of vegetation index values. Novelty/Originality of this Study: The study employs multi-vegetation indices derived from high-resolution PlanetScope imagery to detect and assess rubber leaf fall disease (LFD) within a plantation environment. By integrating spatial and temporal analyses with climatological data, the research provides a precise and comprehensive method for monitoring LFD and understanding its environmental determinants, thereby enhancing traditional rubber plantation management practices.

Meteorology Modulates the Impact of GCM Horizontal Resolution on Underestimation of Midlatitude Ocean Wind Speeds

AbstractWe utilize ocean 10‐m wind speed (U10m) from the microwave Multi‐sensor Advanced Climatology data set to examine the coupling between convective cloud and precipitation processes, synoptic state, and U10m and to evaluate the representation of U10m in global climate models (GCMs). We find that midlatitude U10m is underestimated by GCMs relative to observations. We examine two potential mechanisms to explain this model behavior: cold pool formation in cold air outbreaks (CAOs) associated with downdrafts that enhance U10m and sea surface temperature (SST) gradients affecting U10m through thermally forced surface winds at regional scales. When the effects of the CAO index (M) and SST gradients on U10m are accounted for, a relationship between GCM horizontal resolution and U10m appears. The strongest correlation between resolution and U10m is over the western boundary currents characterized by frequent CAOs atop strong SST gradients which drives the strongest surface fluxes on Earth.

Climate change impacts on the extreme power shortage events of wind-solar supply systems worldwide during 1980–2022

Economic productivity depends on reliable access to electricity, but the extreme shortage events of variable wind-solar systems may be strongly affected by climate change. Here, hourly reanalysis climatological data are leveraged to examine historical trends in defined extreme shortage events worldwide. We find uptrends in extreme shortage events regardless of their frequency, duration, and intensity since 1980. For instance, duration of extreme low-reliability events worldwide has increased by 4.1 hours (0.392 hours per year on average) between 1980–2000 and 2001–2022. However, such ascending trends are unevenly distributed worldwide, with a greater variability in low- and middle-latitude developing countries. This uptrend in extreme shortage events is driven by extremely low wind speed and solar radiation, particularly compound wind and solar drought, which however are strongly disproportionated. Only average 12.5% change in compound extremely low wind speed and solar radiation events may give rise to over 30% variability in extreme shortage events, despite a mere average 1.0% change in average wind speed and solar radiation. Our findings underline that wind-solar systems will probably suffer from weakened power security if such uptrends persist in a warmer future.

Assessing soil erosion and its drivers in agricultural landscapes: a case study in southern Bahia, Brazil

ABSTRACT Erosion is a worldwide threat to biodiversity conservation and agricultural yield, and it is linked to deforestation. In this study, we aim to assess soil loss in landscapes of Cachoeira River watershed, in southern Bahia, northeastern Brazil. We estimate the role of forests in diminishing soil erosion using the Revised Universal Soil Loss Equation (RUSLE). We compare real and simulated scenarios in which the forest was replaced by agricultural use, also comparing estimates of erosivity factor (R factor) derived from remote sensing and climatological station data. Real and simulated annual soil losses varied from 0 to 15.95 t/year and from 0 to 33.53 t/year along the watershed, respectively. However, only 0.04 and 1.67% of this area is highly and severely exposed to erosion, using data from climatological stations and remote sensing, respectively. Soil loss in the simulated deforested scenario was approximately two times higher than the real annual soil loss, indicating the importance of forest cover to mitigate soil erosion. Moreover, soil loss was 10.5 times greater when using precipitation data from remote sensing compared to climatological stations. Conclusively, the practice of agroforestry can be used as an alternative to avoid erosion.

Implementasi kebijakan pengawasan kearsipan internal pada Badan Meteorologi, Klimatologi, dan Geofisika(BMKG)

Archives are records of activities and events made and received by an agency that are useful as a monitoring tool and source of information. To protect the archives, archival supervision activities are carried out in accordance with PerANRI No. 6/2019 concerning Archival Supervision. BMKG is one of the LPNKs that has carried out internal archival supervision activities since 2019. The implementation of internal archival supervision at BMKG needs to be carried out to keep Meteorology, Climatology and Geophysics data and administrative data well managed and maintained. Using the policy implementation theory model from Van Horn, Van Meter, and Grindle which includes policy standards and objectives, resources, inter-organizational relationships, attitudes, characteristics of implementing agents, social and political conditions, and types of benefits. Using qualitative research with a descriptive approach. The results showed that the implementation of the internal archival supervision policy still has limited archival human resources and financial resources, and not all work units have carried out archival supervision so that MKG observation data has not been saved. Some of the inhibiting factors are inadequate human resources, limited funds, and a work culture that is less concerned about archives.

Modeling flood characteristics in the Krueng Keureuto river basin in North Aceh regency using the Jams/J2000 application

Abstract Significant land use changes in the Krueng Keureuto River basin exacerbate flooding annually. Despite intensive flood studies, there’s no mapped information on past and future flood inundation. Flood discharge parameters rely on empirical formulas, overlooking climate factors and flood event data, crucial in flood analysis due to climate change. To comprehensively understand flood characteristics, this research employs the JAMS/J2000 application on climatological data (2010-2020), land use, soil type, and geological maps. Using HRU-Web, Hydrologic Response Units (HRUs) are derived for J2000 modeling, producing four runoff components: overland flow, interflow, fast groundwater, and slow groundwater. Notably, the highest overland flow, or flood runoff, was 23.21 mm on December 26, 2014, with 40.69 mm/day rainfall. Interflow peaked at 6.72 mm on October 8, 2011, with 18.10 mm/day rainfall. Fast groundwater reached 1.28 mm on November 30, 2019, with 13.18 mm/day rainfall, and slow groundwater peaked at 1.04 mm on November 13, 2020, with 48.87 mm/day rainfall. This study provides comprehensive insights into the complex dynamics of flood characteristics in the Krueng Keureuto River basin.

The Impact of Climatological Factors on the Incidence of Cutaneous Leishmaniasis (CL) in Colombian Municipalities from 2017 to 2019.

Cutaneous leishmaniasis (CL) is a zoonotic disease caused by protozoa of the Leishmania genus, transmitted by vectors from the Phlebotominae subfamily. The interaction between the vector, reservoir, and parasite is susceptible to climate change. This study explores how temperature and rainfall influenced the incidence of CL in 15 Colombian municipalities between 2017 and 2019. Epidemiological data were obtained from Colombia's Instituto Nacional de Salud, while climatological data came from the Instituto de Hidrología, Meteorología y Estudios Ambientales. Using Spearman's rank correlation coefficient, we examined the relationships between monthly climatic variables and the cumulative incidence of CL, considering various lag times. The data were further analyzed using Locally Weighted Scatterplot Smoothing (LOWESS). Our findings reveal both significant positive and negative correlations, depending on locality and climate variables. LOWESS analysis indicates that while rainfall-related incidence remains stable, temperature impacts incidence in a parabolic trend. This study underscores the significant yet complex influence of climatic factors on CL incidence. The insights gained could aid public health efforts by improving predictive models and crafting targeted interventions to mitigate the disease's impact, particularly in regions vulnerable to climate variability.

Climate Change and Flood Vulnerability Analysis in the Narayani River of Nepal

Flood disasters annually devastate livelihoods, particularly during the monsoon season, with no apparent reduction in impacts in low-lying regions of developing countries like Nepal. Given the increasing effects of climate change globally, this study aims to assess climate change effects and biophysical vulnerability of riverine communities to floods in the Narayani River of Nepal, elucidating the interrelationship between these phenomena. This paper presents an analysis of trends and extreme events of climatological variables, such as temperature, precipitation, and daily river discharge and hazard mapping and risk assessments in the river stretch of two Village Development Committees (VDCs) in the country’s inner Terai region of Nawalparasi district for different return-period floods, with the aid of the HEC-RAS (Hydrologic Engineering Centre’s River Analysis System) and HEC-GeoRAS. A long-term climatological data was collected from the Department of Hydrology and Meteorology, Kathmandu, and the analysis was performed using statistical softwares, SigmaStat, and SigmaPlot. In addition, flood conditions representing 2, and 100-year periods were determined using Gumbel’s distribution. The study revealed a narrowing temperature range, with increasing minimum temperatures and decreasing maximum temperatures, precipitation, and river discharge. However, there was a notable increase in extreme events. The hazard mapping indicated the people’s vulnerability to inundation and soil erosion along the low-lying riverbanks. The findings underscore the necessity for reliable technological and socio-economic vulnerability mapping to provide early warnings to at-risk populations. This paper argues that unplanned and mismanaged settlements in riverine areas may lead to population displacements, creating environmental refugees.

Evaluating the efficiency of NDVI and climatic data in maize harvest prediction using machine learning

ABSTRACT Accurate anticipation of the maize harvest date is important in the agricultural market, as it ensures the sustainability of food production in response to the increasing global demand for food. This paper proposes a predictive model to determine the optimal harvest time in maize plots using the Normalised Difference Vegetation Index (NDVI) and climatological data. These variables were oversampled and used to train various models, including Random Forest (RF), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting Machine (XGBoost), CatBoost and Support Vector Machine (SVM). Bayesian optimisation has been used to find the best hyperparameters and Shapley values to identify the variables that exert the most significant influence on the prediction in each model instance. As a result of this approach, a model with an accuracy of 92.1% and an Area Under the Curve (AUC) of 0.935 was developed. The variables that determined these results were atmospheric pressure, mean temperature, precipitation, NDVI, and precipitation.