Final Author Response DOI Creative Commons
Philipp Maier

Published: June 6, 2024

Abstract. Foehn has an impact on various climatological variables like temperature and humidity in the highly populated valleys of western Austria. With increasing global warming, question arises as to how well climate projections are able produce conditions for foehn their occurrence changes with change. This study uses six XGBoost models classify south EURO-CORDEX CMIP5 generation two spatial extents (localised widespread) three regions Vorarlberg, Tiroler Oberland Unterland Austria, located Eastern Alps. For each region, a model distinguishing from no one distinguish event's extent is trained. Several meteorological inputs  pressure levels ERA5 reanalysis combination training data derived semi-automated weather station Objective Classification used process. Weights individual by analysing performance ability considering independence other. The hereby evaluated biases annual occurrence, seasonal accuracy inter-annual variability comparison data.The confirm other studies showing that selected behave differently portion widespread events. Bias analysis shows pronounced negative bias driven general circulation ICHEC-EC-EARTH or MOHC-HadGEM2-ES. perform similar capturing foehn's seasonality, but vary reproducing historical period. A weighted trend future behaviour 21st century slight decrease frequency under warming Tirol increase events all regions, most Vorarlberg at strongest warming. Further, shift seasonality can be observed higher spring months lower July October, also depending change signal.

Language: Английский

A Systematic Literature Review on Classification Machine Learning for Urban Flood Hazard Mapping DOI
Maelaynayn El baida,

Mohamed Hosni,

Farid Boushaba

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(15), P. 5823 - 5864

Published: Aug. 3, 2024

Language: Английский

Citations

5
Classification machine learning models for urban flood hazard mapping: case study of Zaio, NE Morocco DOI
Maelaynayn El baida, Farid Boushaba, Mimoun Chourak

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: 120(11), P. 10013 - 10041

Published: April 16, 2024

Language: Английский

Citations

4
Analysing the future trends of foehn-enabling synoptic patterns over two valleys in the Eastern Alps in CMIP5 EURO-CORDEX models DOI Creative Commons
Philipp Maier, Tatiana Klisho, Herbert Formayer

et al.

Theoretical and Applied Climatology, Journal Year: 2025, Volume and Issue: 156(3)

Published: Feb. 14, 2025

Language: Английский

Citations

0
Advancing flood risk assessment: Multitemporal SAR-based flood inventory generation using transfer learning and hybrid fuzzy-AHP-machine learning for flood susceptibility mapping in the Mahananda River Basin DOI Creative Commons
Chiranjit Singha, Satiprasad Sahoo,

Alireza Bahrami Mahtaj

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 380, P. 124972 - 124972

Published: March 23, 2025

The Mahananda River basin, located in Eastern India, faces escalating flood risks due to its complex hydrology and geomorphology, threatening socioeconomic environmental stability. This study presents a novel approach susceptibility (FS) mapping updates the region's inventory. Multitemporal Sentinel-1 (S1) SAR images (2020-2022) were processed using U-Net transfer learning model generate water body frequency map, which was integrated with Global Flood Dataset (2000-2018) refined through grid-based classification create an updated Eleven geospatial layers, including elevation, slope, soil moisture, precipitation, type, NDVI, Land Use Cover (LULC), wind speed, drainage density, runoff, used as conditioning factors (FCFs) develop hybrid FS approach. integrates Fuzzy Analytic Hierarchy Process (FuzzyAHP) six machine (ML) algorithms models FuzzyAHP-RF, FuzzyAHP-XGB, FuzzyAHP-GBM, FuzzyAHP-avNNet, FuzzyAHP-AdaBoost, FuzzyAHP-PLS. Future trends (1990-2030) projected CMIP6 data under SSP2-4.5 SSP5-8.5 scenarios MIROC6 EC-Earth3 ensembles. SHAP algorithm identified LULC, type most influential FCFs, contributing over 60 % susceptibility. Results show that 31.10 of basin is highly susceptible flooding, western regions at greatest risk low elevation high density. projections indicate 30.69 area will remain vulnerable, slight increase SSP5-8.5. Among models, FuzzyAHP-XGB achieved highest accuracy (AUC = 0.970), outperforming FuzzyAHP-GBM 0.968) FuzzyAHP-RF 0.965). experimental results showed proposed can provide spatially well-distributed inventory derived from freely available remote sensing (RS) datasets robust framework for long-term assessment ML techniques. These findings offer critical insights improving management mitigation strategies basin.

Language: Английский

Citations

0
Prediction of Soil Pollution Risk Based on Machine Learning and SHAP Interpretable Models in the Nansi Lake, China DOI Creative Commons
Min Wang, Ruilin Zhang, Beibei Yan

et al.

Toxics, Journal Year: 2025, Volume and Issue: 13(4), P. 278 - 278

Published: April 5, 2025

To assess and predict the Nansi Lake soil pollution risk, we evaluate environmental quality in region using machine learning techniques, combined with SHapley Additive exPlanations (SHAP) model for interpretability. The primary objective was to level of caused by heavy metals, incorporating traditional Pollution Load Index (PLI) Potential Ecological Risk (PERI) methods. Through integration statistical characteristics, PLI, PERI evaluations, a new assessment method created, categorizing into “Class0—no risk”, “Class1—low “Class2—high risk”. Various models, including Support Vector Machine (SVM), Decision Tree Classifier (DT), Random Forest (RF), XGBoost, were employed based on these indices. XGBoost demonstrated highest accuracy, achieving prediction accuracy 93%. SHAP analysis further applied explain determined that accumulation key pollutants such as cadmium (Cd) mercury (Hg) may significantly produce targeted management needs be developed features.

Language: Английский

Citations

0
Flash Flood Prediction Modeling in the Hilly Regions of Southeastern Bangladesh: A Machine Learning attempt on Present and Future Climate Scenarios DOI Creative Commons

Arifur Rahman Rifath,

Md Golam Muktadir,

Mahmudul Hasan

et al.

Environmental Challenges, Journal Year: 2024, Volume and Issue: 17, P. 101029 - 101029

Published: Oct. 11, 2024

Language: Английский

Citations

3
Enhancing spatial prediction of groundwater-prone areas through optimization of a boosting algorithm with bio-inspired metaheuristic algorithms DOI Creative Commons
Seyed Vahid Razavi-Termeh, Abolghasem Sadeghi‐Niaraki, Sani I. Abba

et al.

Applied Water Science, Journal Year: 2024, Volume and Issue: 14(11)

Published: Oct. 30, 2024

Language: Английский

Citations

3
Assessment of the Susceptibility of Urban Flooding Using GIS with an Analytical Hierarchy Process in Hanoi, Vietnam DOI Open Access
Hong Ngoc Nguyen, Hiroatsu Fukuda,

Minh Nguyet Nguyen

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(10), P. 3934 - 3934

Published: May 8, 2024

The incidence of floods is rapidly increasing globally, causing significant property damage and human losses. Moreover, Vietnam ranks as one the top five countries most severely affected by climate change, with 1/3 residents facing flood risks. This study presents a model to identify susceptibility using analytic hierarchy process (AHP) in GIS environment for Hanoi, Vietnam. Nine flood-conditioning factors were selected used initial data. AHP analysis was utilized determine priority levels these concerning assess consistency obtained results develop flood-susceptibility map. performance found be based on AUC value receiver operating characteristic (ROC) curve. map has susceptibility: area very high flooding accounts less than 1% map, high- areas nearly 11%, moderate-susceptibility more 65%, low- about 22%, low-susceptibility 2%. Most Hanoi moderate level susceptibility, which expected increase urban expansion due impacts urbanization. Our findings will valuable future research involving planners, disaster management authorities enable them make informed decisions aimed at reducing impact enhancing resilience communities.

Language: Английский

Citations

2
Leveraging Sentinel-2 and Geographical Information Systems in Mapping Flooded Regions around the Sesia River, Piedmont, Italy DOI Creative Commons
George P. Petropoulos,

Athina Georgiadi,

Kleomenis Kalogeropoulos

et al.

GeoHazards, Journal Year: 2024, Volume and Issue: 5(2), P. 485 - 503

Published: May 28, 2024

Sentinel-2 data are crucial in mapping flooded areas as they provide high spatial and spectral resolution but under cloud-free weather conditions. In the present study, we aimed to devise a method for area using multispectral from optical sensors Geographical Information Systems (GISs). As case selected site located Northern Italy that was heavily affected by flooding events on 3 October 2020, when Sesia River Piedmont region hit severe disturbance, heavy rainfall, strong winds. The developed thresholding technique through water indices. More specifically, Normalized Difference Water Index (NDWI) Modified (MNDWI) were chosen among most widely used methods with applications across various environments, including urban, agricultural, natural landscapes. corresponding product Copernicus Emergency Management Service (EMS) evaluate predicted our method. results showed both indices captured satisfactory level of detail. NDWI demonstrated slightly higher accuracy, where it also appeared be more sensitive separation soil vegetation cover. study findings may useful disaster management linked flooded-area rehabilitation following flood event, can valuably assist decision policy making towards sustainable environment.

Language: Английский

Citations

2
Deep Learning Ensemble for Flood Probability Analysis DOI Open Access

Fred Sseguya,

Kyung Soo Jun

Water, Journal Year: 2024, Volume and Issue: 16(21), P. 3092 - 3092

Published: Oct. 29, 2024

Predicting flood events is complex due to uncertainties from limited gauge data, high data and computational demands of traditional physical models, challenges in spatial temporal scaling. This research innovatively uses only three remotely sensed computed factors: rainfall, runoff temperature. We also employ deep learning models—Feedforward Neural Network (FNN), Convolutional (CNN), Long Short-Term Memory (LSTM)—along with a neural network ensemble (DNNE) using synthetic predict future probabilities, utilizing the Savitzky–Golay filter for smoothing. Using hydrometeorological dataset 1993–2022 Nile River basin, six predictors were derived. The FNN LSTM models exhibited accuracy stable loss, indicating minimal overfitting, while CNN showed slight overfitting. Performance metrics revealed that achieved 99.63% 0.999886 ROC AUC, had 95.42% 0.893218 excelled 99.82% 0.999967 AUC. DNNE outperformed individual reliability consistency. Runoff rainfall most influential predictors, temperature impact.

Language: Английский

Citations

2