Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Published: March 2, 2022

Abstract. Deep Learning techniques have been increasingly used in flood management to overcome the limitations of accurate, yet slow, numerical models, and improve results traditional methods for mapping. In this paper, we review 58 recent publications outline state-of-the-art field, identify knowledge gaps, propose future research directions. The focuses on type deep learning models various mapping applications, types considered, spatial scale studied events, data model development. show that based convolutional layers are usually more accurate as they leverage inductive biases better process characteristics flooding events. Models fully-connected layers, instead, provide when coupled with other statistical models. showed increased accuracy compared approaches speed methods. While there exist several applications susceptibility, inundation, hazard mapping, work is needed understand how can assist real-time warning during an emergency, it be employed estimate risk. A major challenge lies developing generalize unseen case studies. Furthermore, all reviewed their outputs, deterministic, limited considerations uncertainties outcomes probabilistic predictions. authors argue these identified gaps addressed by exploiting fundamental advancements or taking inspiration from developments applied areas. graph neural networks operators arbitrarily structured thus should capable generalizing across different studies could account complex interactions natural built environment. Physics-based preserve underlying physical equations resulting reliable speed-up alternatives Similarly, resorting Gaussian Processes Bayesian networks.

Language: Английский

---

Estimating potential illegal land development in conservation areas based on a presence-only model

Journal of Environmental Management, Journal Year: 2022, Volume and Issue: 321, P. 115994 - 115994

Published: Aug. 18, 2022

Language: Английский

---

Spatial Mapping of Flood Susceptibility Using Decision Tree–Based Machine Learning Models for the Vembanad Lake System in Kerala, India

Journal of Water Resources Planning and Management, Journal Year: 2023, Volume and Issue: 149(10)

Published: Aug. 4, 2023

Floods have claimed the lives of countless people and caused significant property damage in many countries, putting their livelihoods jeopardy. The Vembanad lake system (VLS) Kerala, India, has faced adverse mishappening during 2018, 2019, 2021 floods state due to torrential rainfall. goal this research is construct effective decision tree–based machine learning models such as adaptive boosting (AdaBoost), random forest (RF), gradient machines (GBMs), extreme (XGBoost) for integrating data, processing, generating flood susceptibility maps. There are 18 conditioning parameters considered, which include seven categories 11 numerical data. These categorical data were converted bringing total amount input 61. recursive feature elimination (RFE) was utilized selection technique, a 22 layers chosen feed into generate efficiencies evaluated using receiver operating characteristic (ROC)–area under ROC curve (AUC), F1 score, accuracy, kappa. According results, performance all four demonstrated practical application; however, XGBoost fared well terms model's metrics. For testing set, ROC-AUC values XGBoost, GBM, AdaBoost 0.90, whereas it 0.89 RF. accuracy varied significantly among models, with scoring 0.92, followed by GBM (0.88), RF (0.87), (0.87). As result, map may be early mitigation actions future floods, land-use planners emergency managers, assisting reduction risk regions prone hazard.

Language: Английский

---

Flood susceptibility mapping with ensemble machine learning: a case of Eastern Mediterranean basin, Türkiye

Stochastic Environmental Research and Risk Assessment, Journal Year: 2023, Volume and Issue: 37(11), P. 4273 - 4290

Published: July 1, 2023

Language: Английский

---

Modeling flood susceptibility on the onset of the Kerala floods of 2018

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 83(4)

Published: Feb. 1, 2024

Language: Английский

---