Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam

Journal of Water and Climate Change, Год журнала: 2022, Номер 14(1), С. 200 - 222

Опубликована: Дек. 19, 2022

Abstract The objective of this study was the development an approach based on machine learning and GIS, namely Adaptive Neuro-Fuzzy Inference System (ANFIS), Gradient-Based Optimizer (GBO), Chaos Game Optimization (CGO), Sine Cosine Algorithm (SCA), Grey Wolf (GWO), Differential Evolution (DE) to construct flood susceptibility maps in Ha Tinh province Vietnam. database includes 13 conditioning factors 1,843 locations, which were split by a ratio 70/30 between those used build validate model, respectively. Various statistical indices, root mean square error (RMSE), area under curve (AUC), absolute (MAE), accuracy, R1 score, applied models. results show that all proposed models performed well, with AUC value more than 0.95. Of models, ANFIS-GBO most accurate, 0.96. Analysis shows approximately 32–38% is located high very zone. successful performance over large-scale can help local authorities decision-makers develop policies strategies reduce threats related flooding future.

Язык: Английский

---

Applying a 1D Convolutional Neural Network in Flood Susceptibility Assessments—The Case of the Island of Euboea, Greece

Remote Sensing, Год журнала: 2023, Номер 15(14), С. 3471 - 3471

Опубликована: Июль 10, 2023

The main scope of the study is to evaluate prognostic accuracy a one-dimensional convolutional neural network model (1D-CNN), in flood susceptibility assessment, selected test site on island Euboea, Greece. Logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and deep learning (DLNN) are benchmark models used compare their performance with that 1D-CNN model. Remote sensing (RS) techniques collect necessary related data, whereas thirteen flash-flood-related variables were as predictive variables, such elevation, slope, plan curvature, profile topographic wetness index, lithology, silt content, sand clay distance faults, river network. Weight Evidence method was applied calculate correlation among flood-related assign weight value each variable class. Regression analysis multi-collinearity assess collinearity Shapley Additive explanations rank features by importance. evaluation process involved estimating ability all via classification accuracy, sensitivity, specificity, area under success rate curves (AUC). outcomes confirmed provided higher (0.924), followed LR (0.904) DLNN (0.899). Overall, 1D-CNNs can be useful tools for analyzing using remote high predictions.

Язык: Английский

---

Application of hybrid model-based deep learning and swarm‐based optimizers for flood susceptibility prediction in Binh Dinh province, Vietnam

Earth Science Informatics, Год журнала: 2023, Номер unknown

Опубликована: Фев. 11, 2023

Язык: Английский

---

Solving the spatial extrapolation problem in flood susceptibility using hybrid machine learning, remote sensing, and GIS

Environmental Science and Pollution Research, Год журнала: 2024, Номер 31(12), С. 18701 - 18722

Опубликована: Фев. 13, 2024

Язык: Английский

---

Flood susceptibility mapping leveraging open-source remote-sensing data and machine learning approaches in Nam Ngum River Basin (NNRB), Lao PDR

Geomatics Natural Hazards and Risk, Год журнала: 2024, Номер 15(1)

Опубликована: Май 28, 2024

Frequent floods caused by monsoons and rainstorms have significantly affected the resilience of human natural ecosystems in Nam Ngum River Basin, Lao PDR. A cost-efficient framework integrating advanced remote sensing machine learning techniques is proposed to address this issue enhancing flood susceptibility understanding informed decision-making. This study utilizes geo-datasets algorithms (Random Forest, Support Vector Machine, Artificial Neural Networks, Long Short-Term Memory) generate comprehensive maps. The results highlight Random Forest's superior performance, achieving highest train test Area Under Curve Receiver Operating Characteristic (AUROC) (1.00 0.993), accuracy (0.957), F1-score (0.962), kappa value (0.914), with lowest mean squared error (0.207) Root Mean Squared Error (0.043). Vulnerability particularly pronounced low-elevation low-slope southern downstream areas (Central part PDR). reveal that 36%–53% basin's total area highly susceptible flooding, emphasizing dire need for coordinated floodplain management strategies. research uses freely accessible data, addresses data scarcity studies, provides valuable insights disaster risk sustainable planning

Язык: Английский

---