A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions

Remote Sensing, Год журнала: 2022, Номер 14(3), С. 672 - 672

Опубликована: Янв. 30, 2022

The effects of the spatial resolution remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate coarse (Landsat 8 and SRTM) medium (Sentinel-2 ALOS) using random forest (RF) support vector machine (SVM) models. addition, investigate fusion predictions from different resolutions Dempster–Shafer theory (DST) 14 conditioning factors. Seven factors derived separately datasets for whole area Guilan Province, Iran. All conditional used to train test SVM RF models in Google Earth Engine (GEE) software environment, along with an inventory dataset comprehensive global positioning system (GPS)-based field survey points locations. These locations evaluated combined satellite data, namely thermal anomalies product moderate imaging spectroradiometer (MODIS) period 2009 2019. We assess performance four-fold cross-validation by receiver operating characteristic (ROC) curve method. under (AUC) achieved ROC yields 92.15% 91.98% accuracy respective RS data. comparison, AUC is 92.5% 93.37%, respectively. Remarkably, highest value 94.71% model where through DST.

Язык: Английский

---

Flash Flood Susceptibility Assessment and Zonation by Integrating Analytic Hierarchy Process and Frequency Ratio Model with Diverse Spatial Data

Water, Год журнала: 2022, Номер 14(19), С. 3069 - 3069

Опубликована: Сен. 29, 2022

Flash floods are the most dangerous kinds of because they combine destructive power a flood with incredible speed. They occur when heavy rainfall exceeds ability ground to absorb it. The main aim this study is generate flash maps using Analytical Hierarchy Process (AHP) and Frequency Ratio (FR) models in river’s floodplain between Jhelum River Chenab rivers. A total eight flood-causative physical parameters considered for study. Six based on remote sensing images Advanced Land Observation Satellite (ALOS), Digital Elevation Model (DEM), Sentinel-2 Satellite, which include slope, elevation, distance from stream, drainage density, flow accumulation, land use/land cover (LULC), respectively. other two soil geology, consist different rock formations, In case AHP, each criteria allotted an estimated weight according its significant importance occurrence floods. end, all were integrated weighted overlay analysis influence value density was given highest weight. shows that 2500 m river has values FR ranging 0.54, 0.56, 1.21, 1.26, 0.48, output zones categorized into very low, moderate, high, high risk, covering 7354, 5147, 3665, 2592, 1343 km2, Finally, results show areas or 6.68% area. Mangla, Marala, Trimmu valleys identified as high-risk area, have been damaged drastically many times by It provides policy guidelines risk managers, emergency disaster response services, urban infrastructure planners, hydrologists, climate scientists.

Язык: Английский

---

Comparison of Machine Learning Algorithms for Flood Susceptibility Mapping

Remote Sensing, Год журнала: 2022, Номер 15(1), С. 192 - 192

Опубликована: Дек. 29, 2022

Floods are one of the most destructive natural disasters, causing financial and human losses every year. As a result, reliable Flood Susceptibility Mapping (FSM) is required for effective flood management reducing its harmful effects. In this study, new machine learning model based on Cascade Forest Model (CFM) was developed FSM. Satellite imagery, historical reports, field data were used to determine flood-inundated areas. The database included 21 flood-conditioning factors obtained from different sources. performance proposed CFM evaluated over two study areas, results compared with those other six methods, including Support Vector Machine (SVM), Decision Tree (DT), Random (RF), Deep Neural Network (DNN), Light Gradient Boosting (LightGBM), Extreme (XGBoost), Categorical (CatBoost). result showed produced highest accuracy models both Overall Accuracy (AC), Kappa Coefficient (KC), Area Under Receiver Operating Characteristic Curve (AUC) more than 95%, 0.8, 0.95, respectively. Most these recognized southwestern part Karun basin, northern northwestern regions Gorganrud basin as susceptible

Язык: Английский

---

A novel flood risk mapping approach with machine learning considering geomorphic and socio-economic vulnerability dimensions

The Science of The Total Environment, Год журнала: 2022, Номер 851, С. 158002 - 158002

Опубликована: Авг. 17, 2022

Язык: Английский

---

A Review of Hydrodynamic and Machine Learning Approaches for Flood Inundation Modeling

Water, Год журнала: 2023, Номер 15(3), С. 566 - 566

Опубликована: Фев. 1, 2023

Machine learning (also called data-driven) methods have become popular in modeling flood inundations across river basins. Among data-driven methods, traditional machine (ML) approaches are widely used to model events, and recently deep (DL) gained more attention the world. In this paper, we reviewed published literature on ML DL applications for various hydrologic catchment characteristics. Our extensive review shows that models produce better accuracy compared approaches. Unlike physically based models, ML/DL suffer from lack of using expert knowledge events. Apart challenges implementing a uniform approach basins, benchmark data evaluate performance is limiting factor developing efficient inundation modeling.

Язык: Английский

---

Flood susceptibility mapping using machine learning boosting algorithms techniques in Idukki district of Kerala India

Urban Climate, Год журнала: 2023, Номер 49, С. 101503 - 101503

Опубликована: Март 18, 2023

Язык: Английский

---

Flood susceptible prediction through the use of geospatial variables and machine learning methods

Journal of Hydrology, Год журнала: 2023, Номер 617, С. 129121 - 129121

Опубликована: Янв. 13, 2023

Язык: Английский

---

Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data

Heliyon, Год журнала: 2023, Номер 9(2), С. e13212 - e13212

Опубликована: Янв. 26, 2023

The present study is designed to monitor the spatio-temporal changes in forest cover using Remote Sensing (RS) and Geographic Information system (GIS) techniques from 1990 2017. Landsat data (Thematic mapper [TM]), 2000 2010 (Enhanced Thematic Mapper [ETM+]), 2013 2017 (Operational Land Imager/Thermal Infrared Sensor [OLI/TIRS]) were classified into classes termed snow, water, barren land, built-up area, forest, vegetation. method was built multitemporal images machine learning Support Vector Machine (SVM), Naive Bayes Tree (NBT) Kernel Logistic Regression (KLR). According results, area decreased 19,360 km2 (26.0%) 18,784 (25.2%) 2010, while increased 18,640 (25.0%) 26,765 (35.9%) due "One billion tree Project". our findings, SVM performed better than KLR NBT on all three accuracy metrics (recall, precision, accuracy) F1 score >0.89. demonstrated that concurrent reforestation land areas improved methods of sustaining RS GIS everyday forestry organization practices Khyber Pakhtun Khwa (KPK), Pakistan. results beneficial, especially at decision-making level for local or provincial government KPK understanding global scenario regional planning.

Язык: Английский

---

Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany

Geomatics Natural Hazards and Risk, Год журнала: 2022, Номер 13(1), С. 1640 - 1662

Опубликована: Июль 12, 2022

Identifying urban pluvial flood-prone areas is necessary but the application of two-dimensional hydrodynamic models limited to small areas. Data-driven have been showing their ability map flood susceptibility in flooding still rare. A inventory (4333 flooded locations) and 11 factors which potentially indicate an increased hazard for were used implement convolutional neural network (CNN), artificial (ANN), random forest (RF) support vector machine (SVM) to: (1) Map Berlin at 30, 10, 5, 2 m spatial resolutions. (2) Evaluate trained models' transferability space. (3) Estimate most useful mapping. The performance was validated using Kappa, area under receiver operating characteristic curve (AUC). results indicated that all perform very well (minimum AUC = 0.87 testing dataset). RF outperformed other resolutions model resolution superior present predictor variables. majority had a moderate predictions outside training based on Kappa evaluation 0.8). Aspect altitude influencing image-based point-based respectively. can be reliable tool mapping wherever available.

Язык: Английский

---

Climate transition risk and bank performance:Evidence from China

Journal of Environmental Management, Год журнала: 2022, Номер 323, С. 116275 - 116275

Опубликована: Сен. 22, 2022

Язык: Английский

---