eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 1 19 10.30493/das.2025.514366 article Abdullah Mahmoud Alkaddour Mirna Ahmad Shadoud Masoumeh Hashemi Fares Mahmoud Muhannad Hammad Youssef M. Youssef Laszlo Mucsi Flooding is a natural hazard that becomes increasingly devastating in urban areas when it endangers human life. Determining areas most susceptible to flooding is the initial phase of hydrological management. Integrating multiple criteria into the spatial flood assessment process enhances dependability. This study sought to evaluate flood susceptibility in the Quwaiq River Basin located in northeastern Syria through the Analytical Hierarchy Process (AHP). For that purpose, ten factors were employed to assess flood risk. Remote sensing (RS) and geographic information systems (GIS) data were utilized to ascertain the spatial distribution of flood criteria. Flood susceptibility was categorized into five classes: very low, low, moderate, high, and very high. These categories were found to represent 12.36%, 25.43%, 28.36%, 23.30%, and 10.55% of the study area, respectively. Out of the 103 neighborhoods within the urban area of Aleppo City, 18, 22, 37, 19, and 7 neighborhoods were located at very low, low, moderate, high, and very high flood susceptibility areas, respectively. The flood hazard susceptibility map of the Quwaiq River Basin in Aleppo City serves as a dependable instrument for hydrological management, facilitating sustainable planning and environmental preservation. The flood hazard susceptibility map allows decision-makers and planners to implement preventive steps to reduce flood risk. https://applied.dysona.org/article_225768_d5f4cb14bf97cc3b7d1be2cd9d6ad7a9.pdf Flood susceptibility mapping AHP GIS Urban flood Aleppo eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 20 27 10.30493/das.2025.530918 article Mesbahuddin Ahadi Rongfang Guo This study investigated the efficiency of anther culture and callus induction in three cauliflower genotypes (Graffiti, Sicilian, and Cheddar) using three basal media (MS, NLN, and B5) supplemented with varying concentrations of plant growth regulators. The highest callus induction rate (26.98%) was observed in the Graffiti genotype, followed by Cheddar (11.58%) and Sicilian (9.60%). Morphological analysis revealed that Graffiti produced friable, embryogenic calli, while Sicilian and Cheddar formed compact structures, suggesting divergent regeneration potential. Among the media compositions, MS medium supplemented with 0.3 mg/L 2,4-D and 2.0 mg/L BAP (MS2) showed superior performance. Additionally, callus proliferation was most effective with 1 mg/L BAP and 3 mg/L 2,4-D (88.60%). These findings highlight the genotype-specific and media-dependent responses in cauliflower anther culture, providing valuable insights for the development of double haploids. Therefore, the optimized protocol can accelerate breeding programs, particularly for stress-responsive genotypes like Graffiti. https://applied.dysona.org/article_225916_1ac95eba0f147a8a05c2823bde5a8cca.pdf Anther culture Cauliflower Callus induction Genotype eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 28 40 10.30493/das.2025.527660 article Mozakkir Azad Mahmud Afroz Rajib Saha Rojbe Rowshan Mofassir Azad This research evaluates changes in land use and land cover, as well as vegetation dynamics in Rupganj, using Google Earth Engine and ArcGIS. For that purpose, land cover categories were classified utilizing supervised algorithms applied to multi-temporal Landsat TM and OLI imagery from the years 1994 and 2024. The classification accuracy attained was 86.75% for the 1994 imagery and 87.20% for the 2024 imagery. The analysis of land use and land cover change between 1994 and 2024 revealed significant increases in agricultural, vegetation, and urban areas (262.51%, 60.08%, and 12.96%, respectively). On the other hand, a notable decrease in barren lands and water bodies was observed (-46.12% and -42.11%, respectively). A substantial increase in NDVI values was recorded in 2024 relative to 1994, underscoring the enhanced vegetation health. The results highlight the patterns of urban growth, increased agricultural practices, reforestation initiatives, and changes in hydrological dynamics within the region. It is imperative to implement stringent measures aimed at safeguarding water resources, directing sustainable urban development, encouraging agro-ecological practices, and establishing green infrastructure as a standard practice. In this context, the integration of cloud-enabled monitoring facilitates adaptive and sustainable land management in the face of rapid peri-urban transformation. https://applied.dysona.org/article_226575_93567a5a77e3c8f7116c9f3816767079.pdf Land use land cover NDVI Remote sensing Vegetation dynamics Rupganj eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 41 49 10.30493/das.2025.531444 article Darina Štyriaková Timea Hajnal-Jafari Vladimira Žunić Jaroslav Šuba Marta Prekopová Ali Kaan Yetik Iveta Štyriaková This study aimed to assess the effects of biostimulant applications on both vegetative and generative growth, fruit characteristics, and yield of strawberry (Fragaria × ananassa Duch.) A total of ten treatments were implemented, comprising various combinations of Microfertile® plant (MP) and Ekofertile® plant (EP) biostimulants, with both full and 50% reduced NPK applications, alongside a control group that received solely NPK. The findings demonstrate that the application of biostimulants led to notable enhancements in plant height, leaf count, and flower yield, especially when utilized in conjunction with full NPK fertilization. The EP10% treatment exhibited the most significant vegetative growth parameters, resulting in the tallest plants and the greatest number of leaves, whereas the MP5% treatment achieved the highest flower count. The examination of fruit attributes revealed that the application of full NPK in conjunction with biostimulants resulted in fruits that exhibited increased size and weight, although the differences compared to other treatments were not statistically significant. The yield of strawberries exhibited significant variation among the treatments, with EP10% achieving the highest yield of 38.70 t ha-1, representing a 60.02% increase compared to the control group (24.18 t ha-1). Despite the observed decrease in yields associated with treatments featuring reduced NPK, the utilization of biostimulants successfully maintained productivity levels akin to those of the control group. The findings indicate that although optimal NPK levels are crucial for maintaining baseline growth and yield, the application of biostimulants markedly improves nutrient uptake efficiency and optimizes both vegetative growth and fruit yield. Further investigation is necessary to determine the mechanism through which the use of biostimulants may mitigate nutritional stress in strawberries. https://applied.dysona.org/article_227677_d92d4b33777b6314db2247839d0e6dc2.pdf Strawberry Biostimulants Yield Vegetative Fertilization eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 50 60 10.30493/das.2025.520833 article Lalit Pathak High-resolution gridded population data are fundamental for disaster risk planning, emissions inventories, and urban service delivery, as they provide sub-administrative spatial detail that informs resource allocation and vulnerability assessments. In Nepal, ward-level census counts are spatially aggregated and lack the granularity required for sub-kilometer analyses, limiting their utility for fine-scale applications. This study presents an open-source QGIS workflow using the QuickOSM plugin to extract OpenStreetMap building footprints and generate a 500 m × 500 m gridded population surface for the Kathmandu Valley. Residential buildings were isolated via OSM tags, and the number of buildings within each grid cell was calculated using spatial join functions in QGIS. The population was then allocated by applying a uniform occupancy factor of 9.6 persons per building, based on existing research. Grid-level estimates were aggregated into wards and validated against Central Bureau of Statistics (CBS) 2021 census figures using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), bias, Bland–Altman analysis, and Moran’s I to assess accuracy and spatial error patterns. The model estimated 3,256,317 inhabitants, 7.8% above the census total, and achieved an MAE of 3,607.5, RMSE of 4,618.8, and MAPE of 48.0%, with a positive mean error of 1,274, indicating a systematic overestimation. Bland–Altman analysis showed most ward-level differences fell within the 95% limits of agreement, while Moran’s I (Queen contiguity = 0.312, Z=8.05, p<0.001) revealed significant clustering of estimation errors in contiguous wards. This reproducible, cost-effective methodology offers a robust tool for sub-kilometer population mapping in data-scarce contexts, supporting enhanced disaster management and urban planning across Nepal and similar regions. https://applied.dysona.org/article_227900_fe3b2c057d04d2ed053832c83bc1b918.pdf QGIS Gridded population OpenStreetMap Kathmandu Valley eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 61 72 10.30493/das.2025.530500 article Rumpa Jana Narayan C. Jana Coastal West Bengal, a heavily populated agricultural center dependent on fertile deltaic plains, confronts increasing cyclone hazards that jeopardize livelihoods and food security. This research assesses agricultural susceptibility to cyclones in Purba Medinipur district through a multi-dimensional framework that incorporates exposure, sensitivity, and adaptive capacity. Analysis of 31 years (1991–2022) of cyclone track data from the Joint Typhoon Warning Centre involved assessing cyclone frequency using the Cox-Stuart test and evaluating intensity through Accumulated Cyclone Energy (ACE) and Power Dissipation Index (PDI). Although the frequency of yearly cyclones has diminished, the intensity during the pre-monsoon period has exhibited an upward tendency, in contrast to the decreased severity observed in the post-monsoon phase. Vulnerability was assessed using 12 factors, such as elevation, slope, cropping system, literacy rates, and population density. Principal Component Analysis (PCA) identified literacy rate, slope, and coastline proximity as the most significant determinants. The results indicated that Nandigram-I, Khejuri-II, and Ramnagar-I are significantly vulnerable due to their low elevation, susceptibility to storm surges, and reliance on monocropping during the cyclone season (July–November), exacerbated by low literacy rates. In contrast, Contai-III and Ramnagar-II shown resilience due to elevated literacy rates and diverse agriculture. This study demonstrates that agricultural vulnerability arises not only from hazard exposure but also from socio-agricultural characteristics, notably single crop dependency and educational deficiencies. Consequently, it is advisable to implement policy integration of literacy initiatives, crop diversification (such as triple-cropping systems), and elevation-based land-use planning to alleviate cyclone effects on coastal agriculture. https://applied.dysona.org/article_228721_2ec72232a2104fa630560a1e4b883a96.pdf Agricultural vulnerability Cyclones Principal component analysis West Bengal eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 73 81 10.30493/das.2025.539371 article Nauaf Mansur Mohsen Abbod Soil color is a straightforward yet insightful indication of soil properties. This work employed machine learning (ML) to predict soil organic matter (SOM) content utilizing 50 soil samples from Homs province, based on RGB color values. The concentration of SOM was determined using the wet oxidation method, and predictive models were built utilizing Support Vector Machine (SVM), Gaussian Process Regression (GPR), Least Squares Kernel (LSK), Ensemble Tree, Artificial Neural Network (ANN), and Multiple Linear Regression (MLR). Among these, GPR, SVM, and Ensemble Tree demonstrated robust training performance (R²=0.91, 0.89, and 0.89, respectively); however, SVM displayed decreased robustness with external data. Subsequent validation using external testing and multicriteria decision-making (MCDM) analysis demonstrated that the ANN model attained the highest predictive accuracy and generalization ability, followed by GPR. The findings indicate that machine learning models can reliably forecast soil organic matter from RGB values, providing a faster and more cost-effective substitute for laboratory analyses. This facilitates effective large-scale soil monitoring in Homs and comparable regions for improved agricultural and environmental decision-making. https://applied.dysona.org/article_229116_37b88344c702df3ad50e6a0bf40ee1c5.pdf Soil organic matter RGB Machine learning Wet oxidation eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 82 87 10.30493/das.2025.539377 article Huda Jamal Jumaah Maha Adnan Dawood Takwaa abd Alreza Maha Adnan Meteab Iraq is ranked among the nations most adversely affected by increased air pollution. This research utilized Sentinel-5P imagery and Geographic Information Systems (GIS) to monitor and assess gaseous pollutants, as well as to delineate the spatial distributions of these pollutants across Iraq. The methodology involved the systematic mapping of sulphur dioxide (SO₂), nitrogen dioxide (NO₂), and aerosol index (AI). The research findings demonstrated robust monitoring capabilities and precise outcomes, juxtaposed with historical data and prior investigations. The observed concentration values ranged between 0 and 240.2 μg/m² for SO₂, from 0 to 4.6 μg/m² for NO₂, and from -1 to 2.75 for AI. A few provinces, such as Baghdad in the center, Basra in the south, in addition to Kirkuk and Nineveh in the north, were recognized as the most severely impacted by air pollution. The current study emphasizes the importance of air pollution monitoring in Iraq, particularly in the highlighted hotspots. Such observations are crucial in formulating pollution-mitigating strategies and improving air quality in affected areas. https://applied.dysona.org/data/pdf/Air-pollution-landscape-in-Iraq-A-Sentinel-5P-based-assessment-of-key-atmospheric-pollutants.pdf Sentinel-5P Sulfur dioxide Nitrogen dioxide Aerosol Index Iraq eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 88 97 10.30493/das.2025.525949 article Sahar Richi Roula Maya Mounir Ghribi Annual wildfires present a growing threat to the endangered forests of the Eastern Mediterranean. In this research, high-resolution forest fire susceptibility maps in Tartous Governorate were developed by employing four distinct machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and k-Nearest Neighbor (KNN), to evaluate and contrast their predictive efficacy in Tartous Governorate of western Syria. A comprehensive dataset comprising 1,500 historical fire events, along with 15 environmental variables, was utilized for the analysis. This analysis utilized a range of data sources, encompassing remote sensing data as well as datasets from official governmental sources. Among the models assessed, RF demonstrated the highest predictive accuracy at 94.33%. Random forest classifier map indicated that 38.78% of the study area is categorized as being at high and very high risk of forest fire. The geographical characteristics of these areas, which are predominantly situated in mountainous and hard-to-reach regions, underscore the inherent sensitivity and the necessity of formulating a thorough fire management strategy for the region. Among the studied parameters, precipitation, altitude, and NDVI were identified as the primary determinants affecting fire vulnerability. The findings detailed in this study offer substantial insights into the various factors influencing forest fires in the examined area. Coupled with the generated susceptibility map, these results can aid in formulating effective fire management strategies applicable to this region and comparable Eastern Mediterranean forest ecosystems. https://applied.dysona.org/article_231654_c7244c259137d2ce2effd6078c6433c5.pdf Forest fire susceptibility Machine learning Random forest Eastern Mediterranean eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 98 109 10.30493/das.2025.545963 article Seemal Naeem Syed Amer Mehmood Anthropogenic activities have significantly changed land use and land cover (LULC), especially in areas with significant population expansion. In this study, the spatiotemporal dynamics of LULC and Land Surface Temperature (LST) of Multan were monitored. The research was carried out for the years 2001, 2011, and 2020 using Landsat-5 TM and Landsat-8 OLI images. While the dataset concludes in 2020, the observed patterns offer a critical long-term baseline for assessing ongoing urbanization and food security risks in the region. The urban area has expanded by 3.23%, whereas forest and vegetation areas have decreased by 4.31% and 9.8%, respectively. Additionally, a weak relationship with between LST and NDVI was observed, whereas a more significant relationship was noted with NDBI. Standardized Precipitation Index (SPI) and Reconnaissance Drought Index (RDI) indices were computed using climatological data to observe the drought status. A consistent drying trend was evident in both indices, highlighting a progressive increase in drought severity over the study period. The study findings highlight the influence of rapid population increase as the primary factor driving urban food insecurity and climate change in the study area. https://applied.dysona.org/article_232873_1fb54538660d938ea52cdebc31467bdd.pdf LULC Land surface temperature Drought Urbanization Multan eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 110 118 10.30493/das.2025.548892 article Ammar Mostafa Questan Ameen The application of food by-products in poultry production has emerged as a compelling area of investigation in recent years. This research assessed the efficacy of pomegranate peel as a nutritional additive in broiler feed. To achieve this objective, a total of 120 unsexed one-day-old Ross 308 chicks, with an average initial body weight of 41.40 g, were randomly allocated into four experimental groups, each consisting of three replicates (10 birds per replicate). The T1 group, serving as the control, was administered a basal diet devoid of any supplementation. In contrast, groups T2, T3, and T4 were given the basal diet enhanced with pomegranate peel powder at concentrations of 0.1%, 0.3%, and 0.6%, respectively. Notable improvements in overall weight, weight gain, feed conversion efficiency, as well as protein, albumin, and globulin concentrations were recorded in T3 and T4 relative to the control group. Conversely, T3 and T4 treatments led to notable decreases in blood glucose levels, total cholesterol, and the activities of aspartate aminotransferase (AST) and alanine aminotransferase (ALT). The addition of pomegranate peel exhibited a more pronounced effect at the 0.6% level (T4). Consequently, pomegranate peel can be effectively employed at the specified level as a cost-effective functional feed additive in broiler diets. https://applied.dysona.org/article_232875_f3d593d84afa7f86c57c6e2d248b6d87.pdf Pomegranate peel Broiler Growth performance Feed efficiency Cholesterol eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 119 133 10.30493/das.2025.011311 article Arman Niknam Mehrnoosh Taherizadeh Javid Hojabri Khushemehr Thong Nguyen-Huy Reza Sarli This study investigates the effectiveness of integrating meteorological and remotely sensed indicators for drought monitoring and zoning in four provinces of Iran. Specifically, the standardized precipitation index (SPI) derived from the existing meteorological stations was utilized to identify changes in precipitation during the crop growing season (April, May, and June). P-value statistics were applied to establish the significance of any precipitation trend changes and classify climate divisions. In addition, the vegetation health index (VHI), vegetation condition index (VCI), and temperature condition index (TCI) obtained from MODIS satellite images were employed to detect drought conditions from 2000 to 2019. The studied indices reveal a pronounced dryness trend in the eastern part of the examined provinces. Correlation analysis also indicates a robust correlation between TCI and SPI compared to other indices. This study contributes to the body of knowledge on drought monitoring and zoning by providing valuable insights into the usefulness of combining meteorological and remotely sensed indicators, as well as by identifying the areas most susceptible to drought and the indicators most suitable for assessing drought conditions in the studied provinces. https://applied.dysona.org/data/pdf/Assessing%20the%20concordance%20between%20meteorological%20and%20agricultural%20drought%20indices%20in%20arid%20and%20semi-arid%20regions.pdf Agricultural drought Drought monitoring Remote sensing Climate change Arid eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 134 141 10.30493/das.2025.012411 article Moeassar A. Abdullah Asmaa H. Allawi Taha S. Ahmed Mineral nutrition is one of the most effective means of improving the quantitative and qualitative characteristics of onion production systems. In semi-arid regions where alkaline soils are the most widespread type, iron deficiency chlorosis and potassium insufficiency severely limit onion yield. This experiment assessed the interactive effects of chelated iron foliar application and potassium sulfate soil application on yield parameters and the accumulation of bioactive compounds in onions under field conditions. A two-factor factorial randomized complete block design was employed, with three concentrations of chelated iron foliar spray (0, 2.25, and 4.5 g/L) and three rates of potassium sulfate (0, 150, and 300 kg K₂SO₄/ha). Standard methods were used to analyze bulb characteristics and bioactive compound content. Maximal improvements were observed with the highest treatment combination (F3K3: 4.5 g/L Fe-EDTHA + 300 kg/ha K₂SO₄), which increased fresh and dry bulb weights by 80.9% and 102% compared to control, respectively. A notable increase in phenols, flavonoids, glycosides, and terpenoids content was observed under the F3K3 treatment compared to the control. The synergistic effects of Fe and K were most pronounced in fresh and dry bulb weights. Therefore, the application of chelated iron and potassium sulfate proved to be an effective strategy for enhancing both the yield and nutritional value of onions under alkaline soil cultivation conditions. https://applied.dysona.org/data/pdf/Chelated%20iron%20and%20potassium%20sulfate%20synergistically%20improve%20bulb%20yield%20and%20levels%20of%20bioactive%20phytochemicals%20in%20onion%20grown%20on%20alkaline%20soils.pdf Onion Chelated iron Potassium Foliar Yield Bioactive eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 142 151 10.30493/das.2025.012911 article Pragadeeshwaran Kannan Gurugnanam Balasubramaniyan Suresh Mani Bairavi Swaminathan Bagyaraj Murugesan Groundwater is primarily used for drinking and irrigation in hard rock regions like Jambuduraikottai, Tamil Nadu. This study aimed to evaluate the suitability of groundwater sampled from the region for drinking and irrigation purposes. Twenty groundwater samples were collected, analyzed, and mapped using interpolation methods. Total hardness (TH), K+, Cl–, and F– exceed the not permissible limits in various locations. Piper and Gibbs plots indicated that water type is Ca2+-Mg2+-Cl–, which reveals rock dominance as a major factor affecting groundwater chemistry. Wilcox plot indicates that the majority of samples were suitable for irrigation purposes. The groundwater quality index showed that 90% of the samples are drinkable. Moreover, irrigation indices such the Kelly ratio and Sodium adsorption ratio indicate suitability for irrigation, whereas the Na% causes notable risk in 10% of the locations. Thus, proper measures such as regular monitoring and controlled usage of fertilizers must be taken to prevent further contamination and also for long-term usage. https://applied.dysona.org/data/pdf/Hydrogeochemical%20assessment%20and%20suitability%20evaluation%20of%20groundwater%20in%20a%20hard%20rock%20region%20A%20case%20study%20of%20Jambuduraikottai%2C%20Tamil%20Nadu.pdf Groundwater quality Water quality index Irrigation suitability Sodium percentage eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 152 175 10.30493/das.2025.011212 article Shrinwantu Raha Sayan Deb Precise demarcation of ecotourism-suitable zones is essential for achieving sustainable development and guiding infrastructure investment across regions. This research presents a machine learning approach to assess and demarcate ecotourism suitability zones (ESZs) in Odisha using two machine learning ensembles: CatBoost and Model Averaged Neural Network (MA-NNET). The classification framework divided the state’s landscape into four tourism potential categories (Very High, High, Moderate, and Low) based on several physical and social criteria. Both models achieved comparable accuracy, precision, recall, F1-score and AUC-ROC values with the training and test sets; however, CatBoost scored a marginally better consistency between training and testing performance. CatBoost spatial output revealed that more than half the area of the state has a high and very high potential as ecotourism zones. Approximately 31.44% of the total area was categorized under the moderate ecotourism potential class, and the remaining 13.31% of area was classified under the low ecotourism potentials. SHAP analysis revealed that relief and relative relief are the most influential features driving model decisions in both MA-NNET and CatBoost. The study highlights the usefulness of machine learning algorithms in regional tourism planning and provides practical results to the development of data-driven policies and sustainable sectoral development (specifically SDG 8 and SDG 11) in Odisha. https://applied.dysona.org/data/pdf/Delineation%20of%20ecotourism%20suitability%20zone%20using%20machine%20learning%20based%20ensemble%20models.pdf Ecotourism Suitability zone Model averaged neural network CatBoost SDG eng E-NAMTILA DYSONA – Applied Science 2708-6283 2026-01-01 7 1 176 188 10.30493/das.2025.012612 article Khder Alakkari Okan Mert Katipoğlu This paper proposes a hybrid deep learning framework for predicting monthly rainfall in Latakia, Syria, using historic data from 1993 to 2023 and utilizing three deep learning architectures: Convolutional Neural Network (CNN), Convolutional Long Short-Term Memory network (ConvLSTM), and CNN–Fourier. For that purpose, the rainfall data was preprocessed and normalization techniques were applied to ensure model convergence. Each model was then trained on a partitioned dataset (training, validation, and testing) and optimized through early stopping and regularization. It was noted that CNN model captured underlying rainfall patterns but was less robust in predicting extreme rainfall events. On the other hand, the ConvLSTM model accurately predicted upper-bound variability during periods of heavy rainfall. The CNN-Fourier model incorporated frequency domain features to reduce noise and enhance forecast stability. A statistical comparison of the models showed that CNN-Fourier demonstrates the effectiveness of combining Fourier noise removal and deep learning to address rainfall variability through hybridization. To inform environmental planning, the forecasts were extended to 2027 using three scenarios: minimum, average, and maximum. These scenarios may offer valuable insight for stakeholders in preparing for evolving climatic conditions by incorporating spectral filtering and hybridizing spatio-temporal modeling within a robust statistical framework. https://applied.dysona.org/data/pdf/Hybrid%20deep%20learning%20for%20probabilistic%20rainfall%20forecasting%20in%20a%20changing%20climate.pdf Rainfall forecasting Deep learning CNN Fourier LSTM Climate