An XGBoost-SHAP approach to quantifying morphological impact on urban flooding susceptibility

Ecological Indicators, Journal Year: 2023, Volume and Issue: 156, P. 111137 - 111137

Published: Oct. 29, 2023

Urban flooding risks, often overlooked by conventional methods, can be profoundly affected city configurations. However, explainable Artificial Intelligence could provide insights into how urban configurations flooding. This study, taking entered on Shenzhen City, deploys an XGBoost, integrating SHapley Additive exPlanation and Partial Dependency Plots, to assess morphology influences susceptibility. The models strategies presented in this study aimed adapt extreme storms from the perspective of spatial configuration planning. findings underscore varying impact disaster variables flooding, with morphological attributes becoming highly significant during severe inundations. In analysis, mean building volume emerged as a pivotal parameter, SHAP value 0.0107 m contribution ratio 9.70 %. indicates that should optimized minimize risks. It is recommended Mean Building Volume (MBV) maintained within range 1.25 km3 2.5 km3, Standard Deviation (SDBV) kept below 2.814 km3. By harnessing algorithms, offers intricate relationship between forms flood risk, thereby informing development effective adaptation strategies.

Language: Английский

---

Enhancing flood risk assessment through integration of ensemble learning approaches and physical-based hydrological modeling

Geomatics Natural Hazards and Risk, Journal Year: 2023, Volume and Issue: 14(1)

Published: May 4, 2023

This study aims to examine three machine learning (ML) techniques, namely random forest (RF), LightGBM, and CatBoost for flooding susceptibility maps (FSMs) in the Vietnamese Vu Gia-Thu Bon (VGTB). The results of ML are compared with those rainfall-runoff model, different training dataset sizes utilized performance assessment. Ten independent factors assessed. An inventory map approximately 850 sites is based on several post-flood surveys. randomly split between (70%) testing (30%). AUC-ROC 97.9%, 99.5%, 99.5% CatBoost, RF, respectively. FSMs developed by methods show good agreement terms an extension flood inundation using model. models' showed 10–13% total area be highly susceptible flooding, consistent RRI's map. that downstream areas (both urbanized agricultural) under high very levels susceptibility. Additionally, input datasets tested determine least number data points having acceptable reliability. demonstrate can realistically predict FSMs, regardless samples.

Language: Английский

---

AI-enabled strategies for climate change adaptation: protecting communities, infrastructure, and businesses from the impacts of climate change

Computational Urban Science, Journal Year: 2023, Volume and Issue: 3(1)

Published: July 17, 2023

Abstract Climate change is one of the most pressing global challenges we face today. The impacts rising temperatures, sea levels, and extreme weather events are already being felt around world only expected to worsen in coming years. To mitigate adapt these impacts, need innovative, data-driven solutions. Artificial intelligence (AI) has emerged as a promising tool for climate adaptation, offering range capabilities that can help identify vulnerable areas, simulate future scenarios, assess risks opportunities businesses infrastructure. With ability analyze large volumes data from models, satellite imagery, other sources, AI provide valuable insights inform decision-making us prepare change. However, use adaptation also raises important ethical considerations potential biases must be addressed. As continue develop deploy solutions, it crucial ensure they transparent, fair, equitable. In this context, article explores latest innovations directions AI-enabled strategies, highlighting both benefits considered. By harnessing power work towards more resilient, sustainable, equitable all.

Language: Английский

---

A hybrid of ensemble machine learning models with RFE and Boruta wrapper-based algorithms for flash flood susceptibility assessment

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 122, P. 103401 - 103401

Published: July 14, 2023

Flash floods are among the world most destructive natural disasters, and developing optimum hybrid Machine Learning (ML) models for flash flood susceptibility (FFS) modeling remains a challenge. This study proposed novel intelligence algorithms based on of several ensemble ML (i.e., Bagged Flexible Discriminant Analysis (BAFDA), Extreme Gradient Boosting (XBG), Rotation Forest (ROF) Boosted Generalized Additive Model (BGAM)) wrapper-based factor optimization Recursive Feature Elimination (RFE) Boruta) to improve accuracy FFS mapping at Neka-Haraz watershed in Iran. In addition, Random Search (RS) method is meta-optimization developed hyper-parameters. considers 20 conditioning factors (CgFs) 380 non-flood locations create geospatial database. The performance each model was evaluated by area under receiver operating characteristic (ROC) curve (AUC) validation methods, such as efficiency. demonstrated good performance, with BGAM-Boruta achieving highest (AUC = 0.953, Efficiency 0.910), followed ROF-Boruta 0.952), ROF-RFE 0.951), BAFDA-Boruta 0.950), BGAM-RFE ROF 0.949), BGAM 0.948), BAFDA-RFE 0.943), XGB-Boruta BAFDA 0.939), XGB-RFE 0.938) XGB 0.911). model, regional coverage about 46% high very areas. Moreover, revealed that distance river, slope, rainfall, altitude, road CgFs significant this region.

Language: Английский

---

Machine learning models for gully erosion susceptibility assessment in the Tensift catchment, Haouz Plain, Morocco for sustainable development

Journal of African Earth Sciences, Journal Year: 2024, Volume and Issue: 213, P. 105229 - 105229

Published: March 11, 2024

Gully erosion is a widespread environmental danger, threatening global socio-economic stability and sustainable development. This study comprehensively applied seven machine learning (ML) models including SVM, KNN, RF, XGBoost, ANN, DT, LR, evaluated gully susceptibility in the Tensift catchment predict it within Haouz plain, Morocco. To ensure reliability of findings, employed robust combination inventory, sentinel images, Digital Surface Model. Eighteen predictors, encompassing topographical, geomorphological, environmental, hydrological factors, were selected after multicollinearity analyses. The revealed that approximately 28.18% at very high risk erosion. Furthermore, 15.13% 31.28% are categorized as low respectively. These findings extend to where 7.84% surface area highly risking erosion, while 18.25% 55.18% characterized areas. gauge performance ML models, an array metrics specificity, precision, sensitivity, accuracy employed. highlights XGBoost KNN most promising achieving AUC ROC values 0.96 0.93 test phase. remaining namely RF (AUC = 0.89), LR 0.80), SVM 0.81), DT 0.86), ANN 0.78), also displayed commendable performance. novelty this research its innovative approach combat through cutting edge offering practical solutions for watershed conservation, management, prevention land degradation. insights invaluable addressing challenges posed by region, beyond geographical boundaries can be used defining appropriate mitigation strategies local national scale.

Language: Английский

---

Flood susceptibility mapping through geoinformatics and ensemble learning methods, with an emphasis on the AdaBoost-Decision Tree algorithm, in Mazandaran, Iran

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(2), P. 1433 - 1457

Published: Jan. 15, 2024

Language: Английский

---

Leveraging machine learning and open-source spatial datasets to enhance flood susceptibility mapping in transboundary river basin

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Feb. 9, 2024

Floods pose devastating effects on the resiliency of human and natural systems. flood risk management challenges are typically complicated in transboundary river basin due to conflicting objectives between multiple countries, lack systematic approaches data monitoring sharing, limited collaboration developing a unified system for hazard prediction communication. An open-source, low-cost modeling framework that integrates open-source models can help improve our understanding susceptibility inform design equitable strategies. This study datasets machine -learning techniques quantify across data-scare basin. The analysis focuses Gandak River Basin, spanning China, Nepal, India, where damaging recurring floods serious concern. is assessed using four widely used learning techniques: Long-Short-Term-Memory, Random Forest, Artificial Neural Network, Support Vector Machine. Our results exhibit improved performance Network Machine predicting maps, revealing higher vulnerability southern plains. demonstrates remote sensing prediction, mapping, environment.

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 susceptibility assessment using machine learning approach in the Mohana-Khutiya River of Nepal

Natural Hazards Research, Journal Year: 2024, Volume and Issue: 4(1), P. 32 - 45

Published: Jan. 4, 2024

Nepal, known for its challenging topography and fragile geology is confronted with the constant threat of floods leading to substantial socio-economic losses annually. However, country's efforts in planning managing flood risks remain insufficient, especially vulnerable Mohana-Khutiya River. Therefore, this study focused on River utilizes Maximum Entropy (MaxEnt) model comprehensively map susceptibility fill crucial gaps risk assessments. This employed a combination 10 geospatial environmental layers field-based past inventory implement MaxEnt machine learning modeling. The available data were divided into two sets, 75% allocated construction remaining 25% validation. demonstrated that proximity river had significant impact (33.1%) occurrence flood. Surprisingly, amount annual precipitation throughout year exhibited no detectable contribution event site. About 4.9% area came under high susceptible zone followed by 12.75 % moderate 82.34% low-risk zone. excellent performance an Area Under Curve (AUC) value 0.935 low standard deviation 0.018, indicating accurate predictions consistent precision. These results highlight model's reliability significance developing disaster management policy local government Future research should refine including more variables, validating against observed events, exploring integration other modeling approaches.

Language: Английский

---

Enhancing Flood Risk Analysis in Harris County: Integrating Flood Susceptibility and Social Vulnerability Mapping

Journal of Geovisualization and Spatial Analysis, Journal Year: 2024, Volume and Issue: 8(1)

Published: May 22, 2024

Language: Английский

---