Refine
Institute
Keywords
- Maschinelles Lernen (18)
- Machine learning (13)
- OA-Publikationsfonds2020 (10)
- machine learning (7)
- big data (6)
- Deep learning (5)
- OA-Publikationsfonds2018 (4)
- artificial intelligence (3)
- random forest (3)
- Biodiesel (2)
- Fluid (2)
- Fotovoltaik (2)
- Intelligente Stadt (2)
- Internet of things (2)
- Künstliche Intelligenz (2)
- Neuronales Netz (2)
- OA-Publikationsfonds2019 (2)
- Solar (2)
- artificial neural networks (2)
- clustering (2)
- data science (2)
- extreme learning machine (2)
- mathematical modeling (2)
- smart cities (2)
- support vector machine (2)
- urban morphology (2)
- wireless sensor networks (2)
- 3D printing (1)
- 3D-Druck (1)
- ANN modeling (1)
- Algorithmus (1)
- Artificial Intelligence (1)
- Artificial neural network (1)
- Bayes-Verfahren (1)
- Bodentemperatur (1)
- Bubble column reactor (1)
- CFD (1)
- ContikiMAC (1)
- Data Mining (1)
- Defect generation (1)
- ELM (1)
- Electric Energy Consumption (1)
- Erdbeben (1)
- Erneuerbare Energien (1)
- Fernerkung (1)
- Funktechnik (1)
- Fuzzy-Logik (1)
- Fuzzy-Regelung (1)
- Gaussian process regression (1)
- Geoinformatik (1)
- Gesundheitsinformationssystem (1)
- Gesundheitswesen (1)
- Grundwasser (1)
- Hydrological drought (1)
- IOT (1)
- Internet der Dinge (1)
- Internet der dinge (1)
- Internet of Things (1)
- K-nearest neighbors (1)
- KNN (1)
- Kühlkörper (1)
- Land surface temperature (1)
- M5 model tree (1)
- Machine Learning (1)
- Membrane contactors (1)
- Modeling (1)
- Molecular Liquids (1)
- Morphologie (1)
- Nachhaltigkeit (1)
- Nanofluid (1)
- Nanomaterials (1)
- Nanostrukturiertes Material (1)
- Nasskühlung (1)
- Naturkatastrophe (1)
- Nitratbelastung (1)
- OA-Publikationsfonds2021 (1)
- Oberflächentemperatur (1)
- Optimierung (1)
- Perovskite (1)
- Polymere (1)
- Prediction (1)
- RSSI (1)
- Renewable energy (1)
- Risikomanagement (1)
- Sensor (1)
- Simulation (1)
- Solar cells (1)
- Solarzelle (1)
- Sustainable production (1)
- Thermal conductivity (1)
- Time-dependent (1)
- Tsallis entropy (1)
- Vernetzung (1)
- Wärmeleitfähigkeit (1)
- adaptive neuro-fuzzy inference system (ANFIS) (1)
- ant colony optimization algorithm (ACO) (1)
- artificial neural networks (ANN) (1)
- back-pressure (1)
- battery (1)
- biodiesel (1)
- buildings (1)
- classification (1)
- classifier (1)
- clear channel assessments (1)
- cluster density (1)
- cluster shape (1)
- computation (1)
- computational fluid dynamics (CFD) (1)
- computational hydraulics (1)
- congestion control (1)
- coronary artery disease (1)
- deep learning neural network (1)
- demand response programs (1)
- diesel engines (1)
- duty-cycles (1)
- earthquake (1)
- earthquake safety assessment (1)
- energy consumption (1)
- energy efficiency (1)
- energy, exergy (1)
- ensemble model (1)
- estimation (1)
- extreme events (1)
- extreme pressure (1)
- firefly optimization algorithm (1)
- flow pattern (1)
- fog computing (1)
- food informatics (1)
- forecasting (1)
- forward contracts (1)
- fractional-order control (1)
- fused filament fabrication (1)
- fuzzy decision making (1)
- genetic programming (1)
- geoinformatics (1)
- ground water contamination (1)
- growth mode (1)
- gully erosion susceptibility (1)
- health (1)
- health informatics (1)
- heart disease diagnosis (1)
- heat sink (1)
- hybrid machine learning (1)
- hybrid machine learning model (1)
- hydraulic jump (1)
- hydrological model (1)
- hydrology (1)
- image processing (1)
- industry 4.0 (1)
- least square support vector machine (LSSVM) (1)
- longitudinal dispersion coefficient (1)
- mitigation (1)
- nanofluid (1)
- natural hazard (1)
- neural networks (NNs) (1)
- optimization (1)
- partical swarm optimization (1)
- photovoltaic (1)
- photovoltaic-thermal (PV/T) (1)
- physical activities (1)
- precipitation (1)
- prediction (1)
- predictive model (1)
- public health (1)
- public space (1)
- rapid visual screening (1)
- received signal strength indicator (1)
- reinforcement learning (1)
- remote sensing (1)
- residential buildings (1)
- response surface methodology (1)
- retailer (1)
- rice (1)
- risk management (1)
- rivers (1)
- seasonal precipitation (1)
- seismic assessment (1)
- signal processing (1)
- smart sensors (1)
- smooth rectangular channel (1)
- soil temperature (1)
- spatial analysis (1)
- spatiotemporal database (1)
- spearman correlation coefficient (1)
- square root cubature calman filter (1)
- standard deviation of pressure fluctuations (1)
- statistical analysis (1)
- statistical coeffcient of the probability distribution (1)
- stilling basin (1)
- stochastic programming (1)
- sugarcane (1)
- support vector machine (SVM) (1)
- support vector regression (1)
- sustainability (1)
- type-3 fuzzy systems (1)
- urban health (1)
- urban sustainability (1)
- wireless sensor network (1)
This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) and support vector machine (SVM) models in Shirahan watershed, Iran. For this purpose, 13 independent variables affecting GES in the study area, namely, altitude, slope, aspect, plan curvature, profile curvature, drainage density, distance from a river, land use, soil, lithology, rainfall, stream power index (SPI), and topographic wetness index (TWI), were prepared. A total of 132 gully erosion locations were identified during field visits. To implement the proposed model, the dataset was divided into the two categories of training (70%) and testing (30%). The results indicate that the area under the curve (AUC) value from receiver operating characteristic (ROC) considering the testing datasets of PSO-DLNN is 0.89, which indicates superb accuracy. The rest of the models are associated with optimal accuracy and have similar results to the PSO-DLNN model; the AUC values from ROC of DLNN, SVM, and ANN for the testing datasets are 0.87, 0.85, and 0.84, respectively. The efficiency of the proposed model in terms of prediction of GES was increased. Therefore, it can be concluded that the DLNN model and its ensemble with the PSO algorithm can be used as a novel and practical method to predict gully erosion susceptibility, which can help planners and managers to manage and reduce the risk of this phenomenon.