Rapid impact assessment of severe cyclone storm Michaung along coastal zones of Andhra and Tamil Nadu, India: A geospatial analysis.

The coastal regions of India, particularly the Bay of Bengal, are highly vulnerable to the severe weather conditions induced by tropical cyclones. This study presents a comprehensive analysis of the changes in vegetation cover, shoreline dynamics, and meteorological variations resulting from Cyclone Michaung and subsequent post-monsoon events along the coastal zones of Andhra Pradesh and Tamil Nadu, India. A suite of vegetation indices, including the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Modified Vegetation Condition Index (mVCI), and Disaster Vegetation Damage Index (DVDI), were employed to assess changes in vegetation cover. The Digital Shoreline Assessment System (DSAS) was utilized to evaluate shoreline changes, and a range of meteorological variables were analyzed to assess the impacts of Cyclone Michaung and post-monsoon events. The findings reveal significant ecological impacts, with a notable decrease in Very Healthy Vegetation from 5.71% to 1.30%. The mean value of mVCI shifted from -0.2 to -0.16, indicating vegetation stress. DVDI analysis showed that 56.49% of the area experienced moderate damage, while 40.24% suffered severe vegetation damage. Additionally, erosion was observed along 79.46% of the shoreline transects in the study area. These insights are critical for assisting coastal managers in developing resilient coastal systems. Remarkably, a significant change in rainfall was recorded between the pre-cyclone period and the landfall day, with maximum rainfall intensifying from 13.93 mm/h on December 3rd to 164.26 mm/h on December 4th, and subsequently decreasing to 144.39 mm/h on December 5th.

Fine-tuning inflow prediction models: integrating optimization algorithms and TRMM data for enhanced accuracy.

This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m3/s RMSE (root mean square error) in training to 49.42 m3/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m3/s RMSE in training and 47.08 m3/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.

Morphostructural influence and neotectonic activity in the geomorphological configuration of southeast Paraíba and northeast Pernambuco, Brazil.

The current study provides critical insights into the field of geomorphology by examining the impact of lithological structures and tectonic activities on the geomorphological configuration of terrain and drainage networks in the southeast of Paraíba and northeast of Pernambuco, Brazil. This geographical region is characterized by phenomena of uplift and fluvial incision at various sites, yet remains inadequately explored with respect to its active deformation and the broader context of its recent geology. Therefore, the primary aim of this research is to elucidate the morphostructural and neotectonic influences on the geomorphological formations in these sectors of Brazil. The methodology encompasses morphostructural analysis, leveraging data derived from altimetry, slope, and geomorphology maps, categorized into taxonomic terrain units. Additionally, this research incorporates the use of morphometric indices, including the Stream Length-Gradient Index (SL), Valley Floor Width (VF), and Asymmetry Factor (AF) to quantify geomorphological anomalies. The analysis of the SL index indicates that a significant portion (87.5 %) of the drainage network exhibits anomalies. Furthermore, the VF index results reveal that 66 % of the profiles analyzed manifest anomalies of various magnitudes. Within the study region, the AF index elucidates the distribution of sub-basins into categories of low (0-30), medium (31-50), and high (>51) asymmetry, comprising 25 %, 31 %, and 44 % of the sub-basins, respectively. The sub-basins demonstrate channel disequilibrium, as evidenced by the SL index, attributed to numerous transient knickpoints along the drainage profiles. This observation is consistent with previous findings in the Koyna-Warna Shallow Seismic Region. The study's outcomes reveal both qualitatively and quantitatively anomalous patterns in the drainage network and terrain forms, which are likely indicative of recent tectonic events affecting the entire eastern edge of Northeast Brazil. Consequently, the findings highlight the significant role of post-Miocene tectonic events in shaping the relief of the study area.

Association of Child Growth Failure Indicators With Household Sanitation Practices in India (1998-2021): Spatiotemporal Observational Study.

BACKGROUND: Undernutrition among children younger than 5 years is a subtle indicator of a country's health and economic status. Despite substantial macroeconomic progress in India, undernutrition remains a significant burden with geographical variations, compounded by poor access to water, sanitation, and hygiene services. OBJECTIVE: This study aimed to explore the spatial trends of child growth failure (CGF) indicators and their association with household sanitation practices in India. METHODS: We used data from the Indian Demographic and Health Surveys spanning 1998-2021. District-level CGF indicators (stunting, wasting, and underweight) were cross-referenced with sanitation and sociodemographic characteristics. Global Moran I and Local Indicator of Spatial Association were used to detect spatial clustering of the indicators. Spatial regression models were used to evaluate the significant determinants of CGF indicators. RESULTS: Our study showed a decreasing trend in stunting (44.9%-38.4%) and underweight (46.7%-35.7%) but an increasing prevalence of wasting (15.7%-21.0%) over 15 years. The positive values of Moran I between 1998 and 2021 indicate the presence of spatial autocorrelation. Geographic clustering was consistently observed in the states of Madhya Pradesh, Jharkhand, Odisha, Uttar Pradesh, Chhattisgarh, West Bengal, Rajasthan, Bihar, and Gujarat. Improved sanitation facilities, a higher wealth index, and advanced maternal education status showed a significant association in reducing stunting. Relative risk maps identified hotspots of CGF health outcomes, which could be targeted for future interventions. CONCLUSIONS: Despite numerous policies and programs, malnutrition remains a concern. Its multifaceted causes demand coordinated and sustained interventions that go above and beyond the usual. Identifying hotspot locations will aid in developing control methods for achieving objectives in target areas.

Climate change and resilience, adaptation, and sustainability of agriculture in India: A bibliometric review.

Climate change (CC) is a global issue, with effects felt across nations, including India. The influences of CC, such as rising temperatures, irregular rainfall, and extreme weather events, have a direct impact on agricultural productivity, thereby affecting food security, income, livelihoods, and overall population health. This study aims to identify trends, patterns, and common themes in research on Climate Change and Resilience, Adaptation, and Sustainability of Agriculture in India (CCRASAI). It also seeks to illuminate potential future research directions to guide subsequent research and policy initiatives. The adverse impacts of CC could push farmers into poverty and undernourishment, underscoring the imperative to focus on the resilience, adaptation, and sustainability of agriculture in India. A bibliometric review was conducted using Biblioshiny and VoSviewer software to analyze 572 articles focused on CCRASAI from the Scopus and Web of Science databases, published between 1994 and 2022. There was an evident upward trend in CCRASAI publications during this period, with steady growth appearing after 2007. Among the States and Union Territories, Delhi, Tamil Nadu, West Bengal, Andhra Pradesh, and Karnataka have the highest number of published research articles. Research on CCRASAI is most concentrated in the southern plateau, the trans-Gangetic and middle Gangetic plains, and the Himalayan regions. The frequently used terms-'climate change impacts,' 'adaptation strategies,' and 'sustainable agriculture'-in CCRASAI research emphasize the focus on analyzing the effects of CC, creating adaptation strategies, and promoting sustainable agricultural practices.

Dynamic shoreline alterations and their impacts on Olive Ridley Turtle (Lepidochelys olivacea) nesting sites in Gahirmatha Marine Wildlife Sanctuary, Odisha (India).

Currently, sea turtle habitats are being altered by climate change and human activities, with habitat loss posing an urgent threat to Indian sea turtles. Thus, the objective of this study is to analyze the dynamic shoreline alterations and their impacts on Olive Ridley Sea Turtle (ORT) nesting sites in Gahirmatha Marine Wildlife Sanctuary from 1990 to 2022. Landsat satellite images served as input datasets to assess dynamic shoreline changes. This study assessed shoreline alterations and their rates across 929 transects divided into four zones using the Digital Shoreline Analysis System (DSAS) software. The results revealed a significant 14-km northward shift in the nesting site due to substantial coastal erosion, threatening the turtles' Arribada. This study underscores the need for conservation efforts to preserve nesting environments amidst changing coastal landscapes, offering novel insights into the interaction between coastal processes and marine turtle nesting behaviors.

Spatial analysis and machine learning prediction of forest fire susceptibility: a comprehensive approach for effective management and mitigation.

Forest fires (FF) in tropical seasonal forests impact ecosystem. Addressing FF in tropical ecosystems has become a priority to mitigate impacts on biodiversity loss and climate change. The escalating frequency and intensity of FF globally have become a mounting concern. Understanding their tendencies, patterns, and vulnerabilities is imperative for conserving ecosystems and facilitating the development of effective prevention and management strategies. This study investigates the trends, patterns, and spatiotemporal distribution of FF for the period of 2001-2022, and delineates the forest fire susceptibility zones in Odisha State, India. The study utilized: (a) MODIS imagery to examine active fire point data; (b) Kernel density tools; (c) FF risk prediction using two machine learning algorithms, namely Support Vector Machine (SVM) and Random Forest (RF); (d) Receiver Operating Characteristic and Area Under the Curve, along with various evaluation metrics; and (e) a total of 19 factors, including three topographical, seven climatic, four biophysical, and five anthropogenic, to create a map indicating areas vulnerable to FF. The validation results revealed that the RF model achieved a precision exceeding 94 % on the validation datasets, while the SVM model reached 89 %. The estimated forest fire susceptibility zones using RF and SVM techniques indicated that 20.14 % and 16.72 % of the area, respectively, fall under the "Very High Forest Fire" susceptibility class. Trend analysis reveals a general upward trend in forest fire occurrences (R2 = 0.59), with a notable increase after 2015, peaking in 2021. Notably, Angul district was identified as the most affected area, documenting the highest number of forest fire incidents over the past 22 years. Additionally, forest fire mitigation plans have been developed by drawing insights from forest fire management strategies implemented in various countries worldwide. Overall, this analysis provides valuable insights for policymakers and forest management authorities to develop effective strategies for forest fire prevention and mitigation.

Multi-datasets to monitor and assess meteorological and hydrological droughts in a typical basin of the Brazilian semiarid region.

This study analyzed the meteorological and hydrological droughts in a typical basin of the Brazilian semiarid region from 1994 to 2016. In recent decades, this region has faced prolonged and severe droughts, leading to marked reductions in agricultural productivity and significant challenges to food security and water availability. The datasets employed included a digital elevation model, land use and cover data, soil characteristics, climatic data (temperature, wind speed, solar radiation, humidity, and precipitation), runoff data, images from the MODIS/TERRA and AQUA sensors (MOD09A1 and MODY09A1 products), and soil water content. A variety of methods and products were used to study these droughts: the meteorological drought was analyzed using the Standardized Precipitation Index (SPI) derived from observed precipitation data, while the hydrological drought was assessed using the Standardized Soil Index (SSI), the Nonparametric Multivariate Standardized Drought Index (NMSDI), and the Parametric Multivariate Standardized Drought Index (PMSDI). These indices were determined using water balance components, including streamflow and soil water content, from the Soil Water Assessment Tool (SWAT) model, and evapotranspiration data from the Surface Energy Balance Algorithm for Land (SEBAL). The findings indicate that the methodology effectively identified variations in water dynamics and drought periods in a headwater basin within Brazil's semiarid region, suggesting potential applicability in other semiarid areas. This study provides essential insights for water resource management and resilience building in the face of adverse climatic events, offering a valuable guide for decision-making processes.

A multi-temporal analysis of shoreline dynamics influenced by natural and anthropogenic factors: Erosion and accretion along the Digha Coast, West Bengal, India.

This investigation analyzed shoreline evolution along India's Digha Coast from 1992 to 2022, using multispectral Landsat satellite images and the Digital Shoreline Analysis System (DSAS). Methods included identifying zones and transects, shoreline extraction, and applying spatial statistical techniques. The study area, divided into five zones with 587 transects, enabled both short- and long-term analysis. Key findings indicate that the mean long-term rate of shoreline change is -0.54 m per year, with 70.70 % of transects experiencing erosion and 29.30 % accretion. Notably, Zone V had the highest accretion rate (8.55 m/year), while Zone III faced the most erosion (-7.47 m/year). Short-term analysis from 1997 to 2017 indicated significant erosion, contrasting with accretion during 1992-1997 and 2017-2022. Particularly, Zones II, III, and IV underwent major erosion, especially from 1997 to 2002. The study underscores the need for continuous shoreline management strategies and demonstrates geospatial technology's effectiveness in capturing coastal landscape changes.

Current patterns and trends of microplastic pollution in the marine environment: A bibliometric analysis.

Microplastics are pervasive in the natural environment and pose a growing concern for global health. Plastic waste in marine environments has emerged as a global issue, threatening not only marine biota but also human health due to its implications for the food chain. This study aims to discern the patterns and trends of research, specifically on Marine Microplastic Pollution (MMP), based on a bibliometric analysis of scientific publications from 2011 to 2022. The methodology utilized in this study comprises three stages: (a) creating a bibliographical dataset from Scopus by Elsevier and the Web of Science Core Collection by Clarivate Analytics, (b) analyzing current research (trends and patterns) using bibliometric analysis through Biblioshiny tool, and (c) examining themes and subthemes in MMP research (wastewater treatment, plastic ingestion, the Mediterranean Sea, microplastics pollution, microplastics in freshwater, microplastic ingestion, plastic pollution, and microplastic pollution in the marine environment). The findings reveal that during the studied period, the number of MMP publications amounted to 1377 articles, with an average citation per publication of 59.23 and a total citation count of 81,553. The most cited article was published in 2011, and since then, the number of publications on this topic has been increasing steadily. The author count stood at 5478, with 22 trending topics identified from the 1377 published titles. Between 2019 and 2022, the countries contributing most to the publication of MMP articles were China, the United States of America (USA), and the United Kingdom (UK). However, a noticeable shift in the origin of author countries was observed in the 2019-2022 timeframe, transitioning from a dominance by the USA and the UK to a predominance by China. In 2019, there was a substantial increase in the volume of publications addressing the topic of microplastics. The results show that the most prevalent themes and subthemes pertained to MMP in the Mediterranean Sea. The journals with the highest number of MMP articles published were the Marine Pollution Bulletin (253 articles) and Science of the Total Environment (190 articles). The analysis concludes that research on MMP remains prominent and appears to be increasing each year.

Coastal evolution and future projections in Conde County, Brazil: A multi-decadal assessment via remote sensing and sea-level rise scenarios.

Global sea levels, having risen by approximately 20 cm since the mid-19th century, necessitate a critical examination of their impacts on shoreline dynamics. This research evaluates the historical (1985-2022) and future shoreline changes in Conde County, Paraíba State, Brazil, an area of significant touristic interest. Employing Landsat satellite imagery, the study utilized the Digital Shoreline Analysis System (DSAS) and a Kalman filter algorithm for cloud removal, while also assessing land use and land cover changes using data from the MapBiomas Project for 2000, 2010, and 2020. These analyses informed projections of potential inundation under various sea-level rise (SLR) scenarios: 1, 2, 5, and 10 m. Key findings revealed a negative average coastline change rate of -0.27 m/year from 1985 to 2022, indicative of erosive trends likely accelerated by human activities. Long-term projections for 2032 and 2042 anticipate continued erosion in areas identified as highly vulnerable. The SLR scenario analysis underscores the urgent need for adaptive climate measures; while a 1- or 2-meter SLR presents limited immediate effects, a 5-meter rise could lead to significant inundation across key sectors, including urban and agricultural landscapes. The projected severity of a 10-meter SLR necessitates immediate, comprehensive interventions to safeguard both natural and human systems.

Geo-ecological, shoreline dynamic, and flooding impacts of Cyclonic Storm Mocha: A geospatial analysis.

This research comprehensively assesses the aftermath of Cyclonic Storm Mocha, focusing on the coastal zones of Rakhine State and the Chittagong Division, spanning Myanmar and Bangladesh. The investigation emphasizes the impacts on coastal ecology, shoreline dynamics, flooding patterns, and meteorological variations. Employed were multiple vegetation indices-Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Modified Vegetation Condition Index (mVCI), Disaster Vegetation Damage Index (DVDI), and Fractional Vegetation Cover (FVC)-to evaluate ecological consequences. The Digital Shoreline Assessment System (DSAS) aided in determining shoreline alterations pre- and post-cyclone. Soil exposure and flood extents were scrutinized using the Bare Soil Index (BSI) and Modified Normalized Difference Water Index (MNDWI), respectively. Additionally, the study encompassed an analysis of microclimatic variables, comparing meteorological data across pre- and post-cyclone periods. Findings indicate significant ecological impacts: an estimated 8985.46 km2 of dense vegetation (NDVI >0.6) was adversely affected. Post-cyclone, there was a discernible reduction in EVI values. The mean mVCI shifted negatively from -0.18 to -0.33, and the mean FVC decreased from 0.39 to 0.33. The DVDI underscored considerable vegetation damage in various areas, underscoring the cyclone's extensive impact. Meteorological analysis revealed a 245 % increase in rainfall (20.22 mm on May 14, 2023 compared to the May average of 5.86 mm), and significant increases in relative humidity (14 %) and wind speed (205 %). Erosion was observed along 74.60 % of the studied shoreline. These insights are pivotal for developing comprehensive strategies aimed at the rehabilitation and conservation of critical coastal ecosystems. They provide vital data for emergency response initiatives and offer resources for entities engaged in enhancing coastal resilience and protecting local community livelihoods.

Remote sensing, GIS, and analytic hierarchy process-based delineation and sustainable management of potential groundwater zones: a case study of Jhargram district, West Bengal, India.

The present investigation delineates groundwater potential zones (GPZ) in the Jhargram district through an integrated approach employing analytical hierarchical process (AHP), remote sensing, and geographical information systems (GIS). Twelve parameters were utilized for GPZ analysis based on the Groundwater Potential Index, subsequent to multicollinearity testing. Classification of GPZ yielded five distinct categories: very poor, poor, moderate, good, and very good. Validation through receiver operating characteristics (ROC) and cross-validation with borewell yield data affirmed prediction accuracies of 78.4% and 84%, respectively. Spatial distribution analysis revealed that 30.39%, 30.86%, and 13.19% of the surveyed area fell within the poor, moderate, and good potentiality zones, respectively, whereas 15.86% and 9.69% were categorized as very poor and very good GPZs. Sensitivity analysis highlighted the significance of geology, elevation, geomorphology, slope, and lineament density as influencing parameters; elimination of any single parameter engendered significant alterations in the GPZ classification. The investigation culminated in the formulation of a block-wise sustainable groundwater management blueprint designed to inform policy initiatives.

Assessment of macrobenthos diversity and a zoning proposal for Seixas coral reefs (northeastern Brazil).

Coral reefs worldwide are under severe threat due to their inherent fragility and urgent need for conservation. The escalating tourism in coral reefs significantly impacts the marine ecosystem's biodiversity and conservation. This study analyzed the diversity and conservation status of macrobenthos in the Seixas coral reef, located in northeastern Brazil, and proposed a zoning plan. We employed monitoring protocols adapted from the Reef Check Program, the Rapid Assessment Protocol for Atlantic and Gulf Reefs, and the Protocol for Monitoring Coastal Benthic Habitats. Species identification was carried out by analyzing 25 transects, each divided into 1 m2 grids, with photos recorded for each grid, totaling 625 photos. Margalef, Shannon-Weaver, Simpson, and Pielou indices were used to analyze species distribution and diversity. The results indicated Dictyotaceae, Sargassaceae, and Corallinaceae as prevalent families. This research offers decision-makers a snapshot of species distribution in the Seixas coral reefs, providing a non-destructive, efficient methodology for assessing environmental impacts on coastal coral reefs.

Analysis of marine diversity and anthropogenic pressures on Seixas coral reef ecosystem (northeastern Brazil).

Coral reefs, vital and ecologically significant ecosystems, are among the most jeopardized marine environments in the Atlantic Ocean, particularly along the northeastern coast of Brazil. The persistent lack of effective management and conservation has led to fragmented information on reef use and pressures, hindering the understanding of these ecosystems' health. Major difficulties and challenges include inadequate data, diverse anthropogenic pressures, and the complex interaction between marine species. This study sought to bridge this knowledge gap by conducting a comprehensive analysis of marine diversity and anthropogenic pressures, specifically focusing on Seixas coral reef near João Pessoa city, an area notably impacted by tourism. Utilizing 25 monitoring transects, subdivided into 1 m2 quadrants, the marine diversity was meticulously evaluated through innovative procedures including (a) sedimentological and geochemical field surveys, (b) application of Shannon-Weaver diversity and Simpson dominance indices, (c) cluster analysis, (d) species identification of macroalgae, coral, and fish, and (e) an examination of anthropogenic interactions and pressures on the coral reef. The assessment encompassed three distinct zones: Back Reef, Reef Top, and Fore Reef, and identified a total of 25 species across 15 genera and 10 fish families. The findings revealed the prevalence of brown macroalgae, fish, and coral, with heightened abundance of red macroalgae in the Fore Reef, which also exhibited the greatest diversity (2.816) and dominance (0.894). Original achievements include the identification of specific spatial variations, recognition of the anthropogenic factors leading to ecological changes, and the formulation of evidence-based recommendations. The study concludes that escalating urbanization and burgeoning daily tourist visits to the reef have exacerbated negative impacts on Seixas coral reef's marine ecosystem. These insights underscore the urgent need for strategic planning and resource management to safeguard the reef's biodiversity and ecological integrity.

A method of Mapping Process for scientific production using the Smart Bibliometrics.

Big data launches a modern way of producing science and research around the world. Due to an explosion of data available in scientific databases, combined with recent advances in information technology, the researcher has at his disposal new methods and technologies that facilitate scientific development. Considering the challenges of producing science in a dynamic and complex scenario, the main objective of this article is to present a method aligned with tools recently developed to support scientific production, based on steps and technologies that will help researchers to materialize their objectives efficiently and effectively. Applying this method, the researcher can apply science mapping and bibliometric techniques with agility, taking advantage of an easy-to-use solution with cloud computing capabilities. From the application of the "Scientific Mapping Process", the researcher will be able to generate strategic information for a result-oriented scientific production, assertively going through the main steps of research and boosting scientific discovery in the most diverse fields of investigation. •The Scientific Mapping Process provides a method and a system to boost scientific development.•It automates Science Mapping and bibliometric analysis from scientific datasets.•It facilitates the researcher's work, increasing the assertiveness in scientific production.

Assessing coastal vulnerability and land use to sea level rise in Jeddah province, Kingdom of Saudi Arabia.

Sea level rise is one of the most serious outcomes of increasing temperatures, leading to coastal flooding, beach erosion, freshwater contamination, loss of coastal habitats, increased soil salinity, and risk of damage to coastal infrastructures. This study estimates the vulnerability to inundation for 2100 in coastal zones in Jeddah Province, Kingdom of Saudi Arabia, under various sea level rise (SLR) scenarios of 1, 2, 5, and 10 m. The predicted flooding was estimated using a combination of factors, including SLR, the bathtub model, digital elevation model, climate scenarios, and land use and land cover. The climate scenarios used were Representative Concentration Pathway (RCP) scenarios 1.9, 2.6, 4.5, and 8.5. The results of the SLR scenarios of 1, 2, 5, and 10 m revealed that 1.6, 4.7, 14.9, and 30.6% (or 88, 214, 679, 1398 km2) of the study area's coast could be classified as inundated areas. The various SLR scenarios can inundate 3.3 to 34% of the road area/length. The inundated built-up and road areas were estimated to range between 0.31 and 0.79 km2, accounting respectively for 1.18 to 3.01% of the total class areas for 1-meter and 2-meter SLR scenarios. In contrast, the inundated area will be significant in the situation of 5 and 10 m SLR scenarios. Regarding the case of a 10-meter SLR scenario, the inundation will negatively impact the built-up and road infrastructure areas, inundating 8.9 km2, with industrial infrastructures affected by inundation estimated at 0.21 km2, followed by green space infrastructures at 0.013 km2. The spatial information based on various SLR scenario impact mapping for Jeddah Province can be highly valuable for decision-makers to better plan future civil engineering structures within the framework of sustainable development.

Assessment of hybrid machine learning algorithms using TRMM rainfall data for daily inflow forecasting in Três Marias Reservoir, eastern Brazil.

This study investigates the application of the Gaussian Radial Basis Function Neural Network (GRNN), Gaussian Process Regression (GPR), and Multilayer Perceptron Optimized by Particle Swarm Optimization (MLP-PSO) models in analyzing the relationship between rainfall and runoff and in predicting runoff discharge. These models utilize autoregressive input vectors based on daily-observed TRMM rainfall and TMR inflow data. The performance evaluation of each model is conducted using statistical measures to compare their effectiveness in capturing the complex relationships between input and output variables. The results consistently demonstrate that the MLP-PSO model outperforms the GRNN and GPR models, achieving the lowest root mean square error (RMSE) across multiple input combinations. Furthermore, the study explores the application of the Empirical Mode Decomposition-Hilbert-Huang Transform (EMD-HHT) in conjunction with the GPR and MLP-PSO models. This combination yields promising results in streamflow prediction, with the MLP-PSO-EMD model exhibiting superior accuracy compared to the GPR-EMD model. The incorporation of different components into the MLP-PSO-EMD model significantly improves its accuracy. Among the presented scenarios, Model M4, which incorporates the simplest components, emerges as the most favorable choice due to its lowest RMSE values. Comparisons with other models reported in the literature further underscore the effectiveness of the MLP-PSO-EMD model in streamflow prediction. This study offers valuable insights into the selection and performance of different models for rainfall-runoff analysis and prediction.