Flood-Resilient Smart Cities: A Data-Driven Risk Assessment Approach Based on Geographical Risks and Emergency Response Infrastructure

Smart Cities, Journal Year: 2024, Volume and Issue: 7(1), P. 662 - 679

Published: Feb. 16, 2024

Flooding in urban areas is expected to become even more common due climatic changes, putting pressure on cities implement effective response measures. Practical mechanisms for assessing flood risk have highly desired, but existing solutions been devoted evaluating only specific and consider limited perspectives, constraining their general applicability. This article presents an innovative approach the of delimited by exploiting geospatial information from publicly available databases, providing a method that applicable any city world requiring minimum configurations. A set mathematical equations defined numerically levels based elevation, slope, proximity rivers, while existence emergency-related infrastructure considered as reduction factor. Then, computed are used classify areas, allowing easy visualisation city. smart not serves valuable tool different parameters also facilitates implementation cutting-edge strategies effectively mitigate critical situations, ultimately enhancing resilience flood-related disaster.

Language: Английский

---

A Critical Review of Emerging Technologies for Flash Flood Prediction: Examining Artificial Intelligence, Machine Learning, Internet of Things, Cloud Computing, and Robotics Techniques

Water, Journal Year: 2024, Volume and Issue: 16(14), P. 2069 - 2069

Published: July 22, 2024

There has been growing interest in the application of smart technologies for hazard management. However, very limited studies have reviewed trends such context flash floods. This study reviews innovative as artificial intelligence (AI)/machine learning (ML), Internet Things (IoT), cloud computing, and robotics used flood early warnings susceptibility predictions. Articles published between 2010 2023 were manually collected from scientific databases Google Scholar, Scopus, Web Science. Based on review, AI/ML applied to warning prediction 64% papers, followed by IoT (19%), computing (6%), (2%). Among most common methods predictions are random forests support vector machines. further optimization emerging technologies, computer vision, required improve these technologies. algorithms demonstrated accurate performance, with receiver operating characteristics (ROC) areas under curve (AUC) greater than 0.90. there is a need current models large test datasets. Through AI/ML, IoT, can be disseminated targeted communities real time via electronic media, SMS social media platforms. In spite this, systems issues internet connectivity, well data loss. Additionally, Al/ML number topographical variables (such slope), geological lithology), hydrological stream density) predict susceptibility, but selection lacks clear theoretical basis inconsistencies. To generate more reliable risk assessment maps, future should also consider sociodemographic, health, housing data. Considering climate change impacts, or may projected different scenarios help design long-term adaptation strategies.

Language: Английский

---

Flood Management Strategies in the Semarang Old Town Site: an Environmental Sustainability Perspective

Revista de Gestão Social e Ambiental, Journal Year: 2025, Volume and Issue: 19(2), P. e011181 - e011181

Published: Feb. 10, 2025

Objective: This study investigates the challenges and opportunities of managing urban flooding in Semarang Old Town, a historic heritage district, aiming to propose integrated solutions that enhance flood resilience while preserving cultural heritage. Theoretical Framework: Grounded theory, conservation frameworks, nature-based (NBS), this integrates risk management, community-centered planning, sustainable practices address interplay between infrastructure, community involvement, environmental sustainability. Method: A mixed-methods approach was employed, combining field surveys, semi-structured interviews with stakeholders residents, spatial analysis using hydrological modeling. Quantitative data on sedimentation rates (45–95 cm) drainage capacity provided critical insights, complemented by qualitative assessments stakeholder perspectives challenges. Results Discussion: The identified inadequate high levels, limited financial resources as primary barriers effective management. It also highlighted for implementing NBS, such rain gardens permeable pavements, water absorption reduce surface runoff. hybrid strategy traditional engineering ecological proposed improve resilience, aligning global best districts. Research Implications: findings provide actionable recommendations policymakers planners, emphasizing participatory approaches interventions. These strategies can serve replicable model other districts facing similar Originality/Value: contributes novel framework integrating conservation, offering dual benefits integrity have relevance, particularly culturally significant areas vulnerable hazards.

Language: Английский

---

Classifying chronic kidney disease using selected machine learning techniques

International Journal of ADVANCED AND APPLIED SCIENCES, Journal Year: 2025, Volume and Issue: 12(2), P. 72 - 79

Published: Feb. 1, 2025

Chronic kidney disease (CKD) is a serious global health problem with high mortality rates, often due to late diagnosis. Early detection and classification are essential improve treatment outcomes slow progression. This study evaluates the performance of four machine learning algorithms—linear discriminant analysis (LDA), Naïve Bayes, C4.5 decision tree, Random Forest—in classifying CKD using Kaggle dataset containing 1,659 instances 52 features, covering demographic, lifestyle, clinical data. After data pre-processing, accuracies algorithms were assessed. LDA showed highest accuracy at 92.8%, followed by Bayes (92.1%), (92.0%), Forest (91.9%) before hyperparameter tuning. tuning, achieved 92.5%, (92.2%), remaining 92.1%. However, even after remained most accurate, demonstrating superior performance. The key features contributing serum creatinine, glomerular filtration rate (GFR), muscle cramps, protein in urine, fasting blood sugar, itching, systolic pressure, urea nitrogen (BUN), HbA1c, edema, total cholesterol, body mass index (BMI), gender. These findings confirm that outperforms other without need for emphasizing value improving early diagnosis management CKD.

Language: Английский

---

A comprehensive review of flood monitoring and evaluation in Nigeria

International Journal of Energy and Water Resources, Journal Year: 2025, Volume and Issue: unknown

Published: April 8, 2025

Language: Английский

---

Development and Implementation of a Machine Learning‐Based Flood Forecasting System in Kasese District, Uganda

Journal of Flood Risk Management, Journal Year: 2025, Volume and Issue: 18(2)

Published: April 13, 2025

ABSTRACT This study aimed to develop a proof‐of‐concept prototype of machine learning system forecast and mitigate the effect floods in Kasese District. The researchers used participatory design science approach. conducted document reviews brainstorming obtain past climate data from representatives affected communities, Makerere University Department Meteorology, Uganda National Meteorological Authority. Qualitative were transcribed recordings sessions notes literature. then summarized tables analyzed using Visual Network Analysis (VNA) with Word Clouds Gephi Open Source Software. We employed combination C++ programming, sensors wired Arduino 2 3 Integrated Development Environment System build prototype. Two algorithms, including linear regression K‐nearest neighbours (KNN) learn collected hydrological make necessary predictions. Using sensors, we able read water levels, temperature, humidity. successfully demonstrated ability send early‐warning alerts users, contributing both theoretical advancements disaster risk reduction practical tools for mitigating flood‐related losses Uganda. recommend further validate use this evaluate its efficacy predictive accuracy averting areas.

Language: Английский

---

Multi-Hazard Susceptibility Mapping Using Machine Learning Approaches: A Case Study of South Korea

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(10), P. 1660 - 1660

Published: May 8, 2025

The frequency and magnitude of natural hazards have been steadily increasing, largely due to extreme weather events driven by climate change. These pose significant global challenges, underscoring the need for accurate prediction models systematic preparedness. This study aimed predict multiple in South Korea using various machine learning algorithms. area, (100,210 km2), was divided into a grid system with 0.01° resolution. Meteorological, climatic, topographical, remotely sensed data were interpolated each cell analysis. focused on three major hazards: drought, flood, wildfire. Predictive developed two algorithms: Random Forest (RF) Extreme Gradient Boosting (XGB). analysis showed that XGB performed exceptionally well predicting droughts floods, achieving ROC scores 0.9998 0.9999, respectively. For wildfire prediction, RF achieved high score 0.9583. results integrated generate multi-hazard susceptibility map. provides foundational development hazard management response strategies context Furthermore, it offers basis future research exploring interaction effects multi-hazards.

Language: Английский

---

A Review of the Application of Artificial Intelligence in Climate Change-Induced Flooding—Susceptibility and Management Techniques

CivilEng, Journal Year: 2024, Volume and Issue: 5(4), P. 1185 - 1198

Published: Dec. 18, 2024

A fresh paradigm for classifying current studies on flood management systems is proposed in this review. The literature has examined methods managing different activities from a variety of fields, such as machine learning, image processing, data analysis, and remote sensing. Prediction, detection, mapping, evacuation, relief efforts are all part management. This can be improved by adopting state-of-the-art tools technology. Preventing floods ensuring prompt response after crucial to the lowest number fatalities well minimizing environmental financial damages. following noteworthy research questions addressed framework: (1) What main used control? (2) Which stages majority currently existence focused on? (3) being suggested address issues with (4) In literature, what gaps regarding use technology management? To classify many technologies that have been studied, framework classification provided It was found there were few hybrid models control combined learning processing. Furthermore, it discovered little learning-based techniques aftermath disaster. provide efficient comprehensive disaster management, future must concentrate integrating processing methods, technologies, understanding across phases. study Generative Artificial Intelligence.

Language: Английский

---

An Efficient Flood Forecasting Model Using an Optimal Deep Belief Network

Global NEST Journal, Journal Year: 2024, Volume and Issue: 26(4), P. 1 - 8

Published: April 27, 2024

<p>Floods inflict significant damage globally each year, underscoring the importance of accurate and timely flood prediction to mitigate property loss life. Precise provides governments with crucial preemptive alerts regarding potential disasters, enabling evacuations life-saving measures. Although various ML (machine learning) models have demonstrated improved performance compared traditional statistical in prediction, they often overlook spatial features understanding generation floods. DL (deep is used enhance promptness efficiency levels predictions. This work presents an optimized model forecast floods using time series data. Initially, data set was cleaned normalized by linear interpolation. Then, ODBN (optimal deep belief network) utilized for forecasting prediction. integration DBN SCA (Sinh-Cosh algorithm). The experimental analysis carried out on real-time dataset achieved better MSE RMSE values 0.75 0.94 respectively. findings suggest that use effective method accurately floods.</p>

Language: Английский

---

Study on long short-term memory based on vector direction of flood process for flood forecasting

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 13, 2024

Accurate flood forecasting is crucial for prevention and mitigation, safeguarding the lives properties of residents, as well rational use water resources. The study proposes a model long short-term memory (LSTM) combined with vector direction (VD) process. Jingle Lushi basins were selected research objects, was trained validated using 50 49 measured rainfall-runoff data in 7:3 division ratio, respectively. results indicate that VD-LSTM has more advantages than LSTM model, increased NSE, reduced RMSE bias to varying degrees. flow simulation better match observed hydrographs, improving underestimation peak flows lag issue model. Under same task dataset, hyperparameter settings, can quickly reduce loss function value achieve fit compared LSTM. proposed couples vectorization process runoff neural network, which contributes exploring change characteristics rising receding processes, reducing training gradient error input-output effectively simulating

Language: Английский

---