Flood Susceptibility Assessment in Urban Areas via Deep Neural Network Approach

Sustainability, Journal Year: 2024, Volume and Issue: 16(17), P. 7489 - 7489

Published: Aug. 29, 2024

Floods, caused by intense rainfall or typhoons, overwhelming urban drainage systems, pose significant threats to areas, leading substantial economic losses and endangering human lives. This study proposes a methodology for flood assessment in areas using multiclass classification approach with Deep Neural Network (DNN) optimized through hyperparameter tuning genetic algorithms (GAs) leveraging remote sensing data of dataset the Ibadan metropolis, Nigeria Metro Manila, Philippines. The results show that DNN model significantly improves risk accuracy (Ibadan-0.98) compared datasets containing only location precipitation (Manila-0.38). By incorporating soil into model, as well reducing number classes, it is able predict risks more accurately, providing insights proactive mitigation strategies planning.

Language: Английский

---

On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis

Water Resources Research, Journal Year: 2025, Volume and Issue: 61(3)

Published: March 1, 2025

Abstract Machine learning (ML) is increasingly considered the solution to environmental problems where limited or no physico‐chemical process understanding exists. But in supporting high‐stakes decisions, ability explain possible solutions key their acceptability and legitimacy, ML can fall short. Here, we develop a method, rooted formal sensitivity analysis , uncover primary drivers behind predictions. Unlike many methods for explainable artificial intelligence (XAI), this method (a) accounts complex multi‐variate distributional properties of data, common systems, (b) offers global assessment input‐output response surface formed by ML, rather than focusing solely on local regions around existing data points, (c) scalable data‐size independent, ensuring computational efficiency with large sets. We apply suite models predicting various water quality variables pilot‐scale experimental pit lake. A critical finding that subtle alterations design some (such as variations random seed, functional class, hyperparameters, splitting) lead different interpretations how outputs depend inputs. Further, from families (decision trees, connectionists, kernels) may focus aspects information provided despite displaying similar predictive power. Overall, our results underscore need assess explanatory robustness advocate using model ensembles gain deeper insights into system improve prediction reliability.

Language: Английский

---

Geospatial SHAP interpretability for urban road collapse susceptibility assessment: a case study in Hangzhou, China

Geomatics Natural Hazards and Risk, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 15, 2025

Language: Английский

---

Using Explainable Artificial Intelligence (Xai) to Understand Compound Flooding Arising from Rainstorms and Tides

Published: Jan. 1, 2025

Language: Английский

---

Advancing device-based computing by simplifying circuit complexity

Device, Journal Year: 2025, Volume and Issue: unknown, P. 100720 - 100720

Published: March 1, 2025

Language: Английский

---

Uncovering water conservation patterns in semi-arid regions through hydrological simulation and deep learning

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(3), P. e0319540 - e0319540

Published: March 20, 2025

Under the increasing pressure of global climate change, water conservation (WC) in semi-arid regions is experiencing unprecedented levels stress. WC involves complex, nonlinear interactions among ecosystem components like vegetation, soil structure, and topography, complicating research. This study introduces a novel approach combining InVEST modeling, spatiotemporal transfer Water Conservation Reserves (WCR), deep learning to uncover regional patterns driving mechanisms. The model evaluates Xiong’an New Area’s characteristics from 2000 2020, showing 74% average increase depth with an inverted “V” spatial distribution. Spatiotemporal analysis identifies temporal changes, WCR land use, key protection areas, revealing that Area primarily shifts lowest areas lower areas. potential enhancement are concentrated northern region. Deep quantifies data complexity, highlighting critical factors precipitation, drought influencing WC. detailed enables development personalized zones strategies, offering new insights into managing complex data.

Language: Английский

---

Quantifying the nonlinear and interactive effects of urban form on resilience to extreme precipitation: Evidence from 192 cities of Southern China

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106366 - 106366

Published: April 1, 2025

Language: Английский

---

A review of the transition from Shapley values and SHAP values to RGE

Statistics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 23

Published: April 14, 2025

Language: Английский

---

Assessing the influence of green space morphological spatial pattern on urban waterlogging: A case study of a highly-urbanized city

Environmental Research, Journal Year: 2024, Volume and Issue: unknown, P. 120561 - 120561

Published: Dec. 1, 2024

Language: Английский

---

City scale urban flooding risk assessment using multi-source data and machine learning approach

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132626 - 132626

Published: Dec. 1, 2024

Language: Английский

---