Hybrid XGboost model with various Bayesian hyperparameter optimization algorithms for flood hazard susceptibility modeling

2021 ◽  
pp. 1-14
Author(s):  
Saeid Janizadeh ◽  
Mehdi Vafakhah ◽  
Zoran Kapelan ◽  
Naghmeh Mobarghaee Dinan
Keyword(s):  
Flood Hazard ◽  
Optimization Algorithms ◽  
Hyperparameter Optimization ◽  
Susceptibility Modeling

Comparison of statistical and analytical hierarchy process methods on flood susceptibility mapping: In a case study of the Lake Tana sub-basin in northwestern Ethiopia

2021 ◽  
Vol 13 (1) ◽  
pp. 1668-1688
Author(s):  
Azemeraw Wubalem ◽  
Gashaw Tesfaw ◽  
Zerihun Dawit ◽  
Belete Getahun ◽  
Tamrat Mekuria ◽  
...  
Keyword(s):  
Land Use Planning ◽  
Analytical Hierarchy Process ◽  
Flood Hazard ◽  
Google Earth ◽  
Information Value ◽  
Lake Tana ◽  
Ahp Model ◽  
Flood Susceptibility ◽  
Susceptibility Modeling ◽  
Hierarchy Process

Abstract The flood is one of the frequently occurring natural hazards within the sub-basin of Lake Tana. The flood hazard within the sub-basin of Lake Tana causes damage to cropland, properties, and a fatality every season. Therefore, flood susceptibility modeling in this area is significant for hazard reduction and management purposes. Thus, the analytical hierarchy process (AHP), bivariate (information value [IV] and frequency ratio [FR]), and multivariate (logistic regression [LR]) statistical methods were applied. Using an intensive field survey, historical document, and Google Earth Imagery, 1,404-flood locations were determined, classified into 70% training datasets and 30% testing flood datasets using a subset within the geographic information system (GIS) environment. The statistical relationship between the probability of flood occurrence and 11 flood-driving factors was performed using the GIS tool. The flood susceptibility maps of the study area were developed by summing all weighted aspects using a raster calculator. It is classified into very low, low, moderate, high, and very high susceptibility classes using the natural breaks method. The accuracy and performance of the models were evaluated using the area under the curve (AUC). As the result indicated, the FR model has better performance (AUC = 99.1%) compared to the AHP model (AUC = 86.9%), LR model (AUC = 81.4%), and IV model (AUC = 78.2%). This research finds out that the applied methods are quite worthy for flood susceptibility modeling within the study area. In flood susceptibility modeling, method selection is not a serious challenge; the care should tend to the input parameter quality. Based on the AUC values, the FR model is comparatively better, followed by the AHP model for regional land use planning, flood hazard mitigation, and prevention purposes.

scholarly journals Flash Flood Susceptibility Modeling Using New Approaches of Hybrid and Ensemble Tree-Based Machine Learning Algorithms

2020 ◽  
Vol 12 (21) ◽  
pp. 3568
Author(s):  
Shahab S. Band ◽  
Saeid Janizadeh ◽  
Subodh Chandra Pal ◽  
Asish Saha ◽  
Rabin Chakrabortty ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Flash Flood ◽  
Flood Hazard ◽  
Machine Learning Algorithms ◽  
Mitigation Strategies ◽  
Boosted Regression Tree ◽  
Flash Flooding ◽  
Flood Susceptibility ◽  
Susceptibility Modeling

Flash flooding is considered one of the most dynamic natural disasters for which measures need to be taken to minimize economic damages, adverse effects, and consequences by mapping flood susceptibility. Identifying areas prone to flash flooding is a crucial step in flash flood hazard management. In the present study, the Kalvan watershed in Markazi Province, Iran, was chosen to evaluate the flash flood susceptibility modeling. Thus, to detect flash flood-prone zones in this study area, five machine learning (ML) algorithms were tested. These included boosted regression tree (BRT), random forest (RF), parallel random forest (PRF), regularized random forest (RRF), and extremely randomized trees (ERT). Fifteen climatic and geo-environmental variables were used as inputs of the flash flood susceptibility models. The results showed that ERT was the most optimal model with an area under curve (AUC) value of 0.82. The rest of the models’ AUC values, i.e., RRF, PRF, RF, and BRT, were 0.80, 0.79, 0.78, and 0.75, respectively. In the ERT model, the areal coverage for very high to moderate flash flood susceptible area was 582.56 km2 (28.33%), and the rest of the portion was associated with very low to low susceptibility zones. It is concluded that topographical and hydrological parameters, e.g., altitude, slope, rainfall, and the river’s distance, were the most effective parameters. The results of this study will play a vital role in the planning and implementation of flood mitigation strategies in the region.

scholarly journals Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks

2018 ◽  
Vol 17 (02) ◽  
pp. 1850008 ◽  
Author(s):  
Tobias Hinz ◽  
Nicolás Navarro-Guerrero ◽  
Sven Magg ◽  
Stefan Wermter
Keyword(s):  
Random Search ◽  
Standard Procedure ◽  
Optimization Algorithms ◽  
Optimization Procedure ◽  
Search Space ◽  
Original Data ◽  
Optimization Process ◽  
Deep Convolutional Neural Networks ◽  
Hyperparameter Optimization ◽  
Lower Dimensional

Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms.

scholarly journals DeepQGHO: Quantized Greedy Hyperparameter Optimization in Deep Neural Networks for on-the-fly Learning

2021 ◽  
Author(s):  
Anjir Ahmed Chowdhury ◽  
Md Abir Hossen ◽  
Md Ali Azam ◽  
Md. Hafizur Rahman
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Energy Consumption ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Optimization Algorithms ◽  
Computation Time ◽  
Hyperparameter Optimization ◽  
Computationally Expensive ◽  
Time And Energy

Abstract Hyperparameter optimization or tuning plays a significant role in the performance and reliability of deep learning (DL). Many hyperparameter optimization algorithms have been developed for obtaining better validation accuracy in DL training. Most state-of-the-art hyperparameters are computationally expensive due to a focus on validation accuracy. Therefore, they are unsuitable for online or on-the-fly training applications which require computational efficiency. In this paper, we develop a novel greedy approach-based hyperparameter optimization (GHO) algorithm for faster training applications, e.g., on-the-fly training. We perform an empirical study to compute the performance such as computation time and energy consumption of the GHO and compare it with two state-of-the-art hyperparameter optimization algorithms. We also deploy the GHO algorithm in an edge device to validate the performance of our algorithm. We perform post-training quantization to the GHO algorithm to reduce inference time and latency.

Comparison of Meta-heuristic Algorithms on Benchmark Functions

2019 ◽  
Vol 2 (3) ◽  
pp. 508-517
Author(s):  
FerdaNur Arıcı ◽  
Ersin Kaya
Keyword(s):  
Heuristic Algorithms ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Optimization Algorithms ◽  
Gravitational Search Algorithm ◽  
Differential Evolution Algorithm ◽  
Population Based ◽  
Time Interval ◽  
Bee Colony ◽  
Different Characteristics

Optimization is a process to search the most suitable solution for a problem within an acceptable time interval. The algorithms that solve the optimization problems are called as optimization algorithms. In the literature, there are many optimization algorithms with different characteristics. The optimization algorithms can exhibit different behaviors depending on the size, characteristics and complexity of the optimization problem. In this study, six well-known population based optimization algorithms (artificial algae algorithm - AAA, artificial bee colony algorithm - ABC, differential evolution algorithm - DE, genetic algorithm - GA, gravitational search algorithm - GSA and particle swarm optimization - PSO) were used. These six algorithms were performed on the CEC’17 test functions. According to the experimental results, the algorithms were compared and performances of the algorithms were evaluated.

Sign in / Sign up

Export Citation Format

Share Document