Flood Forecasting by Using Machine Learning: A Study Leveraging Historic Climatic Records of Bangladesh

Water, Journal Year: 2023, Volume and Issue: 15(22), P. 3970 - 3970

Published: Nov. 15, 2023

Forecasting rainfall is crucial to the well-being of individuals and significant everywhere in world. It contributes reducing disastrous effects floods on agriculture, human life, socioeconomic systems. This study discusses challenges effectively forecasting necessity combining data with flood channel mathematical modelling forecast floodwater levels velocities. research focuses leveraging historical meteorological find trends using machine learning deep approaches estimate rainfall. The Bangladesh Meteorological Department provided for study, which also uses eight algorithms. performance models examined evaluation measures like R2 score, root mean squared error validation loss. According this research’s findings, polynomial regression, random forest long short-term memory (LSTM) had highest levels. Random regression have an value 0.76, while LSTM has a loss 0.09, respectively.

Language: Английский

---

Optimizing flood susceptibility assessment in semi-arid regions using ensemble algorithms: a case study of Moroccan High Atlas

Natural Hazards, Journal Year: 2024, Volume and Issue: 120(8), P. 7787 - 7816

Published: March 21, 2024

Abstract This study explores and compares the predictive capabilities of various ensemble algorithms, including SVM, KNN, RF, XGBoost, ANN, DT, LR, for assessing flood susceptibility (FS) in Houz plain Moroccan High Atlas. The inventory map past flooding was prepared using binary data from 2012 events, where “1” indicates a flood-prone area “0” non-flood-prone or extremely low area, with 762 indicating areas. 15 different categorical factors were determined selected based on importance multicollinearity tests, slope, elevation, Normalized Difference Vegetation Index, Terrain Ruggedness Stream Power Land Use Cover, curvature plane, profile, aspect, flow accumulation, Topographic Position soil type, Hydrologic Soil Group, distance river rainfall. Predicted FS maps Tensift watershed show that, only 10.75% mean surface predicted as very high risk, 19% 38% estimated respectively. Similarly, Haouz plain, exhibited an average 21.76% very-high-risk zones, 18.88% 18.18% low- very-low-risk zones applied algorithms met validation standards, under curve 0.93 0.91 learning stages, Model performance analysis identified XGBoost model best algorithm zone mapping. provides effective decision-support tools land-use planning risk reduction, across globe at semi-arid regions.

Language: Английский

---

FLOOD HAZARD ZONES PREDICTION USING MACHINE-LEARNING-BASED GEOSPATIAL APPROACH IN LOWER NIGER RIVER BASIN, NIGERIA

Natural Hazards Research, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

Machine learning models for prediction of rainfall over Nigeria

Scientific African, Journal Year: 2022, Volume and Issue: 16, P. e01246 - e01246

Published: June 26, 2022

Investigating climatology and predicting rainfall amounts are crucial for planning mitigating the risks caused by variable rainfall. This study utilized two multivariate polynomial regressions (MPR) twelve machine learning algorithms, namely three artificial neural networks (ANN), four adaptive neuro-fuzzy inference system (ANFIS) five support vector (SVM) to estimate monthly annual rainfalls in a tropical location. The ground measured data were collected from Nigerian Meteorological Agency (NIMET), Lagos spanning 31 years (1983–2013) spatially distributed across Nigeria. proposed models employed geoclimatic coordinates such as longitude, latitude, altitude input variables. Analyses based on general performance index (c) showed that model’s algorithms outscored MPR, ANN SVM ten months of year. Its generalized bell-shaped algorithm (ANFIS-GBELL) performed best January, April, May, July, October rainfalls, Gaussian (ANFIS-GAUSS) November December, subtractive clustered (ANFIS-SC) August September fuzzy c-means (ANFIS-FCM) June Also, regression second order (MPR-2) model February March rainfalls. These models’ have ranging 0.906 0.996 they thereby estimation over

Language: Английский

---

Machine Learning Research Trends in Africa: A 30 Years Overview with Bibliometric Analysis Review

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(7), P. 4177 - 4207

Published: April 29, 2023

The machine learning (ML) paradigm has gained much popularity today. Its algorithmic models are employed in every field, such as natural language processing, pattern recognition, object detection, image earth observation and many other research areas. In fact, technologies their inevitable impact suffice technological transformation agendas currently being propagated by nations, for which the already yielded benefits outstanding. From a regional perspective, several studies have shown that technology can help address some of Africa's most pervasive problems, poverty alleviation, improving education, delivering quality healthcare services, addressing sustainability challenges like food security climate change. this state-of-the-art paper, critical bibliometric analysis study is conducted, coupled with an extensive literature survey on recent developments associated applications perspective Africa. presented consists 2761 learning-related documents, 89% were articles at least 482 citations published 903 journals during past three decades. Furthermore, collated documents retrieved from Science Citation Index EXPANDED, comprising publications 54 African countries between 1993 2021. shows visualization current landscape future trends its application to facilitate collaborative knowledge exchange among authors different institutions scattered across continent.

Language: Английский

---

Flood susceptibility mapping leveraging open-source remote-sensing data and machine learning approaches in Nam Ngum River Basin (NNRB), Lao PDR

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 28, 2024

Frequent floods caused by monsoons and rainstorms have significantly affected the resilience of human natural ecosystems in Nam Ngum River Basin, Lao PDR. A cost-efficient framework integrating advanced remote sensing machine learning techniques is proposed to address this issue enhancing flood susceptibility understanding informed decision-making. This study utilizes geo-datasets algorithms (Random Forest, Support Vector Machine, Artificial Neural Networks, Long Short-Term Memory) generate comprehensive maps. The results highlight Random Forest's superior performance, achieving highest train test Area Under Curve Receiver Operating Characteristic (AUROC) (1.00 0.993), accuracy (0.957), F1-score (0.962), kappa value (0.914), with lowest mean squared error (0.207) Root Mean Squared Error (0.043). Vulnerability particularly pronounced low-elevation low-slope southern downstream areas (Central part PDR). reveal that 36%–53% basin's total area highly susceptible flooding, emphasizing dire need for coordinated floodplain management strategies. research uses freely accessible data, addresses data scarcity studies, provides valuable insights disaster risk sustainable planning

Language: Английский

---

Geospatial Mapping and Meteorological Flood Risk Assessment: A Global Research Trend Analysis

Environmental Management, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 12, 2024

Abstract Flooding is a global threat causing significant economic and environmental damage, necessitating policy response collaborative strategy. This study assessed research trends advances in geospatial meteorological flood risk assessment (G_MFRA), considering the ongoing debate on management adaptation strategies. A total of 1872 original articles were downloaded BibTex format using Web Science (WOS) Scopus databases to retrieve G_MFRA studies published from 1985 2023. The annual growth rate 15.48% implies that field has been increasing over time during period. analysis practice highlights key themes, methodologies, emerging directions. There exists notable gap data methodologies for between developed developing countries, particularly Africa South America, highlighting urgency coordinated efforts cohesive actions. challenges identified body extant literature include technical expertise, complex communication networks, resource constraints associated with application gaps methodologies. advocates holistic approach disaster through ecosystem-based underpins Sustainable Development Goals develop innovative techniques models potential influence decision-making domain. Addressing these requires networked partnership community, institutions, countries.

Language: Английский

---

A Smart Framework for Managing Natural Disasters Based on the IoT and ML

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(6), P. 3888 - 3888

Published: March 18, 2023

Natural disasters greatly threaten our lives in addition to adversely affecting all activities. Unfortunately, most solutions currently used flood management are suffering from many drawbacks related latency and accuracy. Moreover, the previous consider that whole city has same level of vulnerability damage, while each area may have different topologies conditions. This study presents a new framework collects data real-time about bad weather, which cause floods, where proposed classification algorithm process sensed determine danger city. In case threat, will send early alerts users rescue teams. The depends on Internet Things (IoT) fog computing coupled with multiple models machine learning (Rain Forest, Decision Tree, K-Nearest Neighbor, Support Vector Machine, Logistic Regression, Deep Learning) enhance performance reliability. addition, research suggests some assistant services. To prove efficiency framework, we applied real for Jeddah, Saudi Arabia, years 2009 2013 2018 2022. Then, depended standard metrics (accuracy, precision, recall, F1-score, ROC curve). Rain Forest Tree achieved highest accuracy, exceeding 99 percent, followed by Neighbor. provide detection systems can predict floods early, multi-level warning, reduce financial, human, infrastructural damage.

Language: Английский

---

Flood risk assessment in Kogi State Nigeria through the integration of hazard and vulnerability factors

Discover Geoscience, Journal Year: 2024, Volume and Issue: 2(1)

Published: July 9, 2024

Abstract Annually, Kogi State in Nigeria experiences significant flooding events, leading to serious fatalities, the destruction of livelihoods, and damage vital infrastructure. This study presents a multi-faceted approach methodology generate state-wide flood risk map by analyzing both vulnerability hazard factors. Seven factors (drainage length, distance river, elevation, slope, rainfall, from confluence/dam area, geomorphology) (population density, female population, land cover, road hospitals, literacy rate, employment rate) were ranked weighted based on their contributions within state using Fuzzy Analytical Hierarchy Process (FAHP). From these, Flood Hazard Index (FHI), Vulnerability (FVI), Risk (FRI) derived. Results showed that Kabba, Idah, Olamabor, Kotonkar, southern part Ajaokuta LGAs exhibit high due dense populations, remoteness roads critical infrastructure, considerable distances healthcare facilities. Likewise, exhibiting very FHI occur along geographic zones bounded confluence Niger Benue rivers, specifically Lokoja Kogi, Bassa, Ibaji LGAs. Five classes—very low, moderate, high, FRI classes—occupy 26.82, 31.12, 22.07, 15.26, 4.71% respectively. Out 295 villages, 65 villages are spread across zone. The safest include Ankpa, Omala, Dekina, Ijumu, Mopa-Muro

Language: Английский

---

Renewable Energy Potential Estimation Using Climatic-Weather-Forecasting Machine Learning Algorithms

Energies, Journal Year: 2023, Volume and Issue: 16(4), P. 1603 - 1603

Published: Feb. 5, 2023

The major challenge facing renewable energy systems in Nigeria is the lack of appropriate, affordable, and available meteorological stations that can accurately provide present future trends weather data solar PV performance. It crucial to find a solution this because information on performance important investors so they assess potential various locations across country. Although Nigerian provides favorable conditions for clean power generation, there little penetration region, since over 95% fossil-fuel-generated. This has been no detailed report showing generation due dysfunctional paper sought fill knowledge gap by providing machine-learning-inspired forecasting environmental parameters be used manufacturing companies evaluating profitability siting region. Crucial such as daily air temperature, relative humidity, atmospheric pressure, wind speed, rainfall were obtained from NASA period 19 years (viz. 2004–2022), resulting collection 6664 high-resolution points. These build diverse regressive neural networks with varying hyperparameters best network arrangement. In summary, low mean-squared error 7 × 10−3 high regression correlations 96% during training.

Language: Английский

---